From cc09f45d3a61d4012ee3d69a63ea911c603a670b Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Thu, 18 Apr 2024 18:36:58 -0600 Subject: [PATCH 01/15] fix a bug for HPC HNMFk when checkpointing would not save if using custom callback --- CITATION.cff | 2 +- README.md | 2 +- TELF/factorization/HNMFk.py | 3 +++ TELF/version.py | 2 +- docs/source/conf.py | 2 +- docs/source/index.rst | 2 +- setup.py | 2 +- 7 files changed, 9 insertions(+), 6 deletions(-) diff --git a/CITATION.cff b/CITATION.cff index 3938144a..16d33b97 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -20,7 +20,7 @@ authors: - family-names: Alexandrov given-names: Boian title: "Tensor Extraction of Latent Features (T-ELF)" -version: 0.0.15 +version: 0.0.16 url: https://github.com/lanl/T-ELF doi: 10.5281/zenodo.10257897 date-released: 2023-12-04 diff --git a/README.md b/README.md index 91400c6c..5b6b5223 100644 --- a/README.md +++ b/README.md @@ -156,7 +156,7 @@ If you use T-ELF please cite. **APA:** ```latex -Eren, M., Solovyev, N., Barron, R., Bhattarai, M., Truong, D., Boureima, I., Skau, E., Rasmussen, K., & Alexandrov, B. (2023). Tensor Extraction of Latent Features (T-ELF) (Version 0.0.15) [Computer software]. https://doi.org/10.5281/zenodo.10257897 +Eren, M., Solovyev, N., Barron, R., Bhattarai, M., Truong, D., Boureima, I., Skau, E., Rasmussen, K., & Alexandrov, B. (2023). Tensor Extraction of Latent Features (T-ELF) (Version 0.0.16) [Computer software]. https://doi.org/10.5281/zenodo.10257897 ``` **BibTeX:** diff --git a/TELF/factorization/HNMFk.py b/TELF/factorization/HNMFk.py index 0cc9a5c1..0a0270bd 100644 --- a/TELF/factorization/HNMFk.py +++ b/TELF/factorization/HNMFk.py @@ -741,5 +741,8 @@ def _set_params(self, class_parameters): def _save_checkpoint(self): class_params = vars(self).copy() del class_params["X"] + if self.generate_X_callback is not None: + del class_params["generate_X_callback"] + pickle.dump(class_params, open(os.path.join( self.experiment_save_path, "checkpoint.p"), "wb")) diff --git a/TELF/version.py b/TELF/version.py index 1216ef05..caa86770 100644 --- a/TELF/version.py +++ b/TELF/version.py @@ -1 +1 @@ -__version__ = '0.0.15' \ No newline at end of file +__version__ = '0.0.16' \ No newline at end of file diff --git a/docs/source/conf.py b/docs/source/conf.py index 605f4018..a27ce607 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -9,7 +9,7 @@ project = 'TELF' copyright = '2022, LANL' author = 'Maksim E. Eren, Nicholas Solovyev, Ryan Barron, Manish Bhattarai, Ismael Boureima, Erik Skau, Kim Rasmussen, Boian S. Alexandrov' -release = '0.0.15' +release = '0.0.16' # -- General configuration --------------------------------------------------- # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration diff --git a/docs/source/index.rst b/docs/source/index.rst index f6b7a994..06560cba 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -104,7 +104,7 @@ How to Cite T-ELF? .. code-block:: console - Eren, M., Solovyev, N., Barron, R., Bhattarai, M., Truong, D., Boureima, I., Skau, E., Rasmussen, K., & Alexandrov, B. (2023). Tensor Extraction of Latent Features (T-ELF) (Version 0.0.15) [Computer software]. https://doi.org/10.5281/zenodo.10257897 + Eren, M., Solovyev, N., Barron, R., Bhattarai, M., Truong, D., Boureima, I., Skau, E., Rasmussen, K., & Alexandrov, B. (2023). Tensor Extraction of Latent Features (T-ELF) (Version 0.0.16) [Computer software]. https://doi.org/10.5281/zenodo.10257897 **BibTeX:** diff --git a/setup.py b/setup.py index 32be9a93..67db7d3d 100644 --- a/setup.py +++ b/setup.py @@ -1,6 +1,6 @@ from setuptools import setup, find_packages from glob import glob -__version__ = "0.0.15" +__version__ = "0.0.16" # add readme with open('README.md', 'r') as f: From 74dc705c3f6d5f80607e3e172f1b523279b54500 Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Thu, 18 Apr 2024 18:56:56 -0600 Subject: [PATCH 02/15] Added checks for X shape and Ks for making sure it can be decomposed --- TELF/factorization/HNMFk.py | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/TELF/factorization/HNMFk.py b/TELF/factorization/HNMFk.py index 0a0270bd..dae15669 100644 --- a/TELF/factorization/HNMFk.py +++ b/TELF/factorization/HNMFk.py @@ -420,6 +420,14 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name curr_X, save_at_node = self.generate_X_callback(current_node.original_indices) current_node.user_node_data = save_at_node.copy() + # + # Based on number of features or samples, no seperation possible + # + if min(curr_X.shape) <= 1: + current_node.leaf = True + pickle_path = f'{node_save_path}/node_{current_node.node_name}.p' + pickle.dump(current_node, open(pickle_path, "wb")) + return {"name":node_name, "target_jobs":[], "node_save_path":pickle_path} # # prepare the current nmfk parameters @@ -431,6 +439,16 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name curr_nmfk_params = self.nmfk_params[select_params % len(self.nmfk_params)] curr_nmfk_params["save_path"] = node_save_path + # + # check for K range + # + Ks = self._adjust_curr_Ks(curr_X.shape, Ks) + if len(Ks) == 0 or (len(Ks) == 1 and Ks[0] < 2): + current_node.leaf = True + pickle_path = f'{node_save_path}/node_{current_node.node_name}.p' + pickle.dump(current_node, open(pickle_path, "wb")) + return {"name":node_name, "target_jobs":[], "node_save_path":pickle_path} + # # apply nmfk # @@ -517,6 +535,11 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name return {"name":node_name, "target_jobs":target_jobs, "node_save_path":pickle_path} + def _adjust_curr_Ks(self, X_shape, Ks): + if min(X_shape) >= max(Ks): + Ks = range(1, min(X_shape), self.Ks_deep_step) + return Ks + def _get_curr_Ks(self, node_k, num_samples): if not self.K2: if self.Ks_deep_max is None: @@ -743,6 +766,6 @@ def _save_checkpoint(self): del class_params["X"] if self.generate_X_callback is not None: del class_params["generate_X_callback"] - + pickle.dump(class_params, open(os.path.join( self.experiment_save_path, "checkpoint.p"), "wb")) From 060ba35b828c01246b0e5a311464c2964a3dd589 Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Thu, 18 Apr 2024 18:59:39 -0600 Subject: [PATCH 03/15] Added checks for X shape and Ks for making sure it can be decomposed --- TELF/factorization/HNMFk.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/TELF/factorization/HNMFk.py b/TELF/factorization/HNMFk.py index dae15669..13158fae 100644 --- a/TELF/factorization/HNMFk.py +++ b/TELF/factorization/HNMFk.py @@ -536,8 +536,13 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name return {"name":node_name, "target_jobs":target_jobs, "node_save_path":pickle_path} def _adjust_curr_Ks(self, X_shape, Ks): - if min(X_shape) >= max(Ks): - Ks = range(1, min(X_shape), self.Ks_deep_step) + if max(Ks) >= min(X_shape): + try: + Ks = range(1, min(X_shape), self.Ks_deep_step) + except Exception as e: + print(e) + return [] + return Ks def _get_curr_Ks(self, node_k, num_samples): From 206caf63697532612cb9b75afbf1edab03e3f9dd Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Thu, 18 Apr 2024 19:03:11 -0600 Subject: [PATCH 04/15] update documentation --- docs/Beaver.html | 6 +-- docs/Cheetah.html | 6 +-- docs/HNMFk.html | 6 +-- docs/NMFk.html | 6 +-- docs/RESCALk.html | 6 +-- docs/SymNMFk.html | 6 +-- docs/TELF.factorization.decompositions.html | 6 +-- ...actorization.decompositions.utilities.html | 6 +-- docs/TELF.factorization.html | 6 +-- docs/TELF.factorization.utilities.html | 6 +-- docs/TELF.html | 6 +-- docs/TELF.pre_processing.Beaver.html | 6 +-- docs/TELF.pre_processing.Vulture.html | 8 ++-- ...re_processing.Vulture.tokens_analysis.html | 6 +-- docs/TELF.pre_processing.html | 6 +-- docs/TriNMFk.html | 6 +-- docs/Vulture.html | 8 ++-- .../TELF/applications/Cheetah/cheetah.html | 6 +-- docs/_modules/TELF/factorization/HNMFk.html | 37 ++++++++++++++++-- docs/_modules/TELF/factorization/NMFk.html | 6 +-- docs/_modules/TELF/factorization/RESCALk.html | 6 +-- docs/_modules/TELF/factorization/SymNMFk.html | 6 +-- docs/_modules/TELF/factorization/TriNMFk.html | 6 +-- .../decompositions/nmf_fro_admm.html | 6 +-- .../decompositions/nmf_fro_mu.html | 6 +-- .../decompositions/nmf_kl_admm.html | 6 +-- .../decompositions/nmf_kl_mu.html | 6 +-- .../decompositions/nmf_mc_fro_mu.html | 6 +-- .../decompositions/rescal_fro_mu.html | 6 +-- .../decompositions/tri_nmf_fro_mu.html | 6 +-- .../utilities/bool_clustering.html | 6 +-- .../decompositions/utilities/bool_noise.html | 6 +-- .../decompositions/utilities/clustering.html | 6 +-- .../utilities/concensus_matrix.html | 6 +-- .../utilities/data_reshaping.html | 6 +-- .../utilities/generic_utils.html | 6 +-- .../decompositions/utilities/math_utils.html | 6 +-- .../decompositions/utilities/nnsvd.html | 6 +-- .../decompositions/utilities/resample.html | 6 +-- .../decompositions/utilities/silhouettes.html | 6 +-- .../factorization/utilities/clustering.html | 6 +-- .../utilities/co_occurance_matrix.html | 6 +-- .../utilities/organize_n_jobs.html | 6 +-- .../factorization/utilities/plot_NMFk.html | 6 +-- .../utilities/pvalue_analysis.html | 6 +-- .../factorization/utilities/sppmi_matrix.html | 6 +-- .../factorization/utilities/take_note.html | 6 +-- .../factorization/utilities/vectorize.html | 6 +-- .../TELF/pre_processing/Beaver/beaver.html | 6 +-- .../pre_processing/Beaver/cooccurrence.html | 6 +-- .../TELF/pre_processing/Beaver/sppmi.html | 6 +-- .../TELF/pre_processing/Beaver/tenmat.html | 6 +-- .../TELF/pre_processing/Beaver/vectorize.html | 6 +-- .../Vulture/tokens_analysis/top_words.html | 6 +-- .../TELF/pre_processing/Vulture/vulture.html | 6 +-- docs/_modules/index.html | 6 +-- docs/_sources/index.rst | 2 +- docs/_static/documentation_options.js | 2 +- .../TELF.pre_processing.Vulture.doctree | Bin 44272 -> 44272 bytes docs/doctrees/Vulture.doctree | Bin 52684 -> 52684 bytes docs/doctrees/environment.pickle | Bin 3089703 -> 3090938 bytes docs/doctrees/index.doctree | Bin 35064 -> 35064 bytes docs/genindex.html | 6 +-- docs/index.html | 8 ++-- docs/modules.html | 6 +-- docs/py-modindex.html | 6 +-- docs/search.html | 6 +-- docs/searchindex.js | 2 +- examples/HNMFk/00-HNMFk.ipynb | 24 ++++++------ 69 files changed, 232 insertions(+), 201 deletions(-) diff --git a/docs/Beaver.html b/docs/Beaver.html index 353b61ee..88bbb016 100644 --- a/docs/Beaver.html +++ b/docs/Beaver.html @@ -8,7 +8,7 @@ - TELF.pre_processing.Beaver: Fast matrix and tensor building tool — TELF 0.0.15 documentation + TELF.pre_processing.Beaver: Fast matrix and tensor building tool — TELF 0.0.16 documentation @@ -37,7 +37,7 @@ - + @@ -127,7 +127,7 @@ -

TELF 0.0.15 documentation

+

TELF 0.0.16 documentation

" ], "text/plain": [ - " word tf df df_fraction tf_fraction\n", - "0 scada system 452 113 1.0 3.074830\n", - "1 tensor decomposition 339 113 1.0 2.306122\n", - "2 grid system 226 113 1.0 1.537415\n", - "3 anomaly scada 226 113 1.0 1.537415\n", - "4 expect behavior 226 113 1.0 1.537415" + " word tf df df_fraction tf_fraction\n", + "0 anomaly scada system 226 113 1.0 1.439490\n", + "1 supervisory control acquisition 113 113 1.0 0.719745\n", + "2 control acquisition system 113 113 1.0 0.719745\n", + "3 acquisition system often 113 113 1.0 0.719745\n", + "4 system often serve 113 113 1.0 0.719745" ] }, - "execution_count": 36, + "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "leaf_nodes[5][\"top_2grams\"].head(5)" + "leaf_nodes[5][\"top_3grams\"].head(5)" ] }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 48, "metadata": {}, "outputs": [ { @@ -1496,69 +1498,69 @@ " \n", " \n", " 0\n", - " sub topic\n", - " 500\n", + " text document matrix\n", + " 200\n", " 100\n", " 1.0\n", - " 3.311258\n", + " 1.197605\n", " \n", " \n", " 1\n", - " topic model\n", - " 300\n", + " matrix word context\n", + " 200\n", " 100\n", " 1.0\n", - " 1.986755\n", + " 1.197605\n", " \n", " \n", " 2\n", - " hierarchical senmfk\n", - " 300\n", + " word context matrix\n", + " 200\n", " 100\n", " 1.0\n", - " 1.986755\n", + " 1.197605\n", " \n", " \n", " 3\n", - " text document\n", + " hierarchical senmfk extract\n", " 200\n", " 100\n", " 1.0\n", - " 1.324503\n", + " 1.197605\n", " \n", " \n", " 4\n", - " document matrix\n", + " topic semantic sub\n", " 200\n", " 100\n", " 1.0\n", - " 1.324503\n", + " 1.197605\n", " \n", " \n", "\n", "" ], "text/plain": [ - " word tf df df_fraction tf_fraction\n", - "0 sub topic 500 100 1.0 3.311258\n", - "1 topic model 300 100 1.0 1.986755\n", - "2 hierarchical senmfk 300 100 1.0 1.986755\n", - "3 text document 200 100 1.0 1.324503\n", - "4 document matrix 200 100 1.0 1.324503" + " word tf df df_fraction tf_fraction\n", + "0 text document matrix 200 100 1.0 1.197605\n", + "1 matrix word context 200 100 1.0 1.197605\n", + "2 word context matrix 200 100 1.0 1.197605\n", + "3 hierarchical senmfk extract 200 100 1.0 1.197605\n", + "4 topic semantic sub 200 100 1.0 1.197605" ] }, - "execution_count": 37, + "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "leaf_nodes[6][\"top_2grams\"].head(5)" + "leaf_nodes[6][\"top_3grams\"].head(5)" ] }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 49, "metadata": {}, "outputs": [ { @@ -1592,69 +1594,69 @@ " \n", " \n", " 0\n", - " sparse matrix\n", - " 232\n", + " propose efficient distribute\n", + " 116\n", " 116\n", " 1.0\n", - " 2.148148\n", + " 1.035714\n", " \n", " \n", " 1\n", - " matrix operation\n", - " 232\n", + " efficient distribute memory\n", + " 116\n", " 116\n", " 1.0\n", - " 2.148148\n", + " 1.035714\n", " \n", " \n", " 2\n", - " multi gpu\n", - " 232\n", + " distribute memory implementation\n", + " 116\n", " 116\n", " 1.0\n", - " 2.148148\n", + " 1.035714\n", " \n", " \n", " 3\n", - " latency associate\n", - " 232\n", + " memory implementation negative\n", + " 116\n", " 116\n", " 1.0\n", - " 2.148148\n", + " 1.035714\n", " \n", " \n", " 4\n", - " collective communication\n", - " 232\n", + " implementation negative matrix\n", + " 116\n", " 116\n", " 1.0\n", - " 2.148148\n", + " 1.035714\n", " \n", " \n", "\n", "" ], "text/plain": [ - " word tf df df_fraction tf_fraction\n", - "0 sparse matrix 232 116 1.0 2.148148\n", - "1 matrix operation 232 116 1.0 2.148148\n", - "2 multi gpu 232 116 1.0 2.148148\n", - "3 latency associate 232 116 1.0 2.148148\n", - "4 collective communication 232 116 1.0 2.148148" + " word tf df df_fraction tf_fraction\n", + "0 propose efficient distribute 116 116 1.0 1.035714\n", + "1 efficient distribute memory 116 116 1.0 1.035714\n", + "2 distribute memory implementation 116 116 1.0 1.035714\n", + "3 memory implementation negative 116 116 1.0 1.035714\n", + "4 implementation negative matrix 116 116 1.0 1.035714" ] }, - "execution_count": 38, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "leaf_nodes[7][\"top_2grams\"].head(5)" + "leaf_nodes[7][\"top_3grams\"].head(5)" ] }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 50, "metadata": {}, "outputs": [ { @@ -1688,109 +1690,109 @@ " \n", " \n", " 0\n", - " malware family\n", - " 490\n", + " identification family malware\n", + " 98\n", " 98\n", " 1.0\n", - " 4.298246\n", + " 0.809917\n", " \n", " \n", " 1\n", - " semi supervise\n", - " 294\n", + " family malware specimen\n", + " 98\n", " 98\n", " 1.0\n", - " 2.578947\n", + " 0.809917\n", " \n", " \n", " 2\n", - " class imbalance\n", - " 196\n", + " malware specimen belong\n", + " 98\n", " 98\n", " 1.0\n", - " 1.719298\n", + " 0.809917\n", " \n", " \n", " 3\n", - " hnmfk classify\n", - " 196\n", + " specimen belong essential\n", + " 98\n", " 98\n", " 1.0\n", - " 1.719298\n", + " 0.809917\n", " \n", " \n", " 4\n", - " identification family\n", + " belong essential understand\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", " 5\n", - " family malware\n", + " essential understand behavior\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", " 6\n", - " malware specimen\n", + " understand behavior malware\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", " 7\n", - " specimen belong\n", + " behavior malware develop\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", " 8\n", - " belong essential\n", + " malware develop mitigation\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", " 9\n", - " essential understand\n", + " develop mitigation strategy\n", " 98\n", " 98\n", " 1.0\n", - " 0.859649\n", + " 0.809917\n", " \n", " \n", "\n", "" ], "text/plain": [ - " word tf df df_fraction tf_fraction\n", - "0 malware family 490 98 1.0 4.298246\n", - "1 semi supervise 294 98 1.0 2.578947\n", - "2 class imbalance 196 98 1.0 1.719298\n", - "3 hnmfk classify 196 98 1.0 1.719298\n", - "4 identification family 98 98 1.0 0.859649\n", - "5 family malware 98 98 1.0 0.859649\n", - "6 malware specimen 98 98 1.0 0.859649\n", - "7 specimen belong 98 98 1.0 0.859649\n", - "8 belong essential 98 98 1.0 0.859649\n", - "9 essential understand 98 98 1.0 0.859649" + " word tf df df_fraction tf_fraction\n", + "0 identification family malware 98 98 1.0 0.809917\n", + "1 family malware specimen 98 98 1.0 0.809917\n", + "2 malware specimen belong 98 98 1.0 0.809917\n", + "3 specimen belong essential 98 98 1.0 0.809917\n", + "4 belong essential understand 98 98 1.0 0.809917\n", + "5 essential understand behavior 98 98 1.0 0.809917\n", + "6 understand behavior malware 98 98 1.0 0.809917\n", + "7 behavior malware develop 98 98 1.0 0.809917\n", + "8 malware develop mitigation 98 98 1.0 0.809917\n", + "9 develop mitigation strategy 98 98 1.0 0.809917" ] }, - "execution_count": 39, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "leaf_nodes[8][\"top_2grams\"].head(10)" + "leaf_nodes[8][\"top_3grams\"].head(10)" ] }, { From 617c7f1362eba9d89728102ecae975b3cb69cd0b Mon Sep 17 00:00:00 2001 From: Ryan Barron Date: Fri, 19 Apr 2024 12:03:51 -0600 Subject: [PATCH 06/15] fix iterable check in exclude hyphen optionion of stop word clean --- TELF/pre_processing/Vulture/modules/simple_clean.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/TELF/pre_processing/Vulture/modules/simple_clean.py b/TELF/pre_processing/Vulture/modules/simple_clean.py index 16afee3c..d5b7f373 100644 --- a/TELF/pre_processing/Vulture/modules/simple_clean.py +++ b/TELF/pre_processing/Vulture/modules/simple_clean.py @@ -244,7 +244,7 @@ def _remove_stop_words(self, text ): if self.exclude_hyphenated_stopwords: cleaned_words = [t for t in tokens if t in self.frozen or # entire term in frozen - not any(t.lower() in self.effective_stop_words)] + not t.lower() in self.effective_stop_words] return ' '.join(cleaned_words) else: cleaned_words = [t for t in tokens if From 2176e9d40be8391e5b311851b8d1d46f6a0a2100 Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 13:19:55 -0600 Subject: [PATCH 07/15] Update acronym.py closes #142 --- TELF/pre_processing/Vulture/modules/acronym.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/TELF/pre_processing/Vulture/modules/acronym.py b/TELF/pre_processing/Vulture/modules/acronym.py index 4171f39a..d1da0832 100644 --- a/TELF/pre_processing/Vulture/modules/acronym.py +++ b/TELF/pre_processing/Vulture/modules/acronym.py @@ -23,7 +23,7 @@ def flatten_acronym_dict(acronym_dict): a list of dict that contain the acronyms. """ acronym_dict_list = [] - for id, data in acronym_dict: + for id, data in acronym_dict.items(): acronym_dict_list.append(data['Acronyms']) return acronym_dict_list @@ -161,4 +161,4 @@ def _detect_acronym_helper(self, df): warnings.warn(warning_sring) acronyms[words_composing_acronym] = acronym - return acronyms \ No newline at end of file + return acronyms From 69e71ff43b8654ef8227134650608df40273b0ff Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 13:31:37 -0600 Subject: [PATCH 08/15] Update levenstein.py time indication on Levenshtein consolidation of terms -- tqdm --- TELF/pre_processing/Vulture/tokens_analysis/levenstein.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py b/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py index aee24afb..ab1ef325 100644 --- a/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py +++ b/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py @@ -1,4 +1,5 @@ import pandas as pd +from tqdm import tqdm def levenshtein_distance(s1, s2): """ @@ -78,7 +79,7 @@ def replace_similar_keys_levenshtein(dict_list, changes_made_save_path=None, sim changes = [] sorted_keys = sorted(all_keys) - for key1 in sorted_keys: + for key1 in tqdm(sorted_keys): for key2 in sorted_keys: if key1 != key2: similar_bool, similar_score = is_levenshtein_similar(key1, key2, similarity_threshold) @@ -102,4 +103,4 @@ def replace_similar_keys_levenshtein(dict_list, changes_made_save_path=None, sim if changes_made_save_path: changes_df.to_csv(changes_made_save_path, index=False) - return dict_list, changes_df \ No newline at end of file + return dict_list, changes_df From b22aef2670c3e7902014dc5aa670ef7e4adbaf9d Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 13:45:18 -0600 Subject: [PATCH 09/15] Update materials.py --- TELF/pre_processing/Vulture/tokens_analysis/materials.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/TELF/pre_processing/Vulture/tokens_analysis/materials.py b/TELF/pre_processing/Vulture/tokens_analysis/materials.py index d484b450..4dfe1a27 100644 --- a/TELF/pre_processing/Vulture/tokens_analysis/materials.py +++ b/TELF/pre_processing/Vulture/tokens_analysis/materials.py @@ -1,4 +1,4 @@ -import permutations +from itertools import permutations import re def expand_materials_regex(material:str): @@ -53,4 +53,4 @@ def permute_material_list(materials:list, save_path:str ,sort=True,): for permuted_material in permuted_materials: f.write(permuted_material + '\n') else: - return permuted_materials \ No newline at end of file + return permuted_materials From ba421b8109bbfbe6b9249deaa9d6391278e708d0 Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 13:54:16 -0600 Subject: [PATCH 10/15] Update materials.py closes #144 --- TELF/pre_processing/Vulture/tokens_analysis/materials.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/TELF/pre_processing/Vulture/tokens_analysis/materials.py b/TELF/pre_processing/Vulture/tokens_analysis/materials.py index 4dfe1a27..ae6f963e 100644 --- a/TELF/pre_processing/Vulture/tokens_analysis/materials.py +++ b/TELF/pre_processing/Vulture/tokens_analysis/materials.py @@ -1,7 +1,7 @@ from itertools import permutations import re -def expand_materials_regex(material:str): +def expand_materials_regex(material:str, include_lower_case=True): """ Expand a given material string by finding all the elements that match the regex pattern and generating all possible permutations of those elements. @@ -9,6 +9,8 @@ def expand_materials_regex(material:str): ---------- material : str The material string to be expanded. + include_lower_case : bool + if the permutations should be duplicated, lowercased, then added back to the permutations Returns ------- @@ -20,6 +22,10 @@ def expand_materials_regex(material:str): permuted_elements = permutations(elements) permuted_materials = [''.join(perm) for perm in permuted_elements] + + if include_lower_case: + lower_case_materials = [material.lower() for material in permuted_materials] + permuted_materials += lower_case_materials return list(set(permuted_materials)) # Remove duplicates and return From c9be345db5228f0e5a758919b670c3528659f3a4 Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 14:01:26 -0600 Subject: [PATCH 11/15] Update materials.py bug in saving material permutations. no standard save path defined --- TELF/pre_processing/Vulture/tokens_analysis/materials.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/TELF/pre_processing/Vulture/tokens_analysis/materials.py b/TELF/pre_processing/Vulture/tokens_analysis/materials.py index ae6f963e..59a9b0fa 100644 --- a/TELF/pre_processing/Vulture/tokens_analysis/materials.py +++ b/TELF/pre_processing/Vulture/tokens_analysis/materials.py @@ -29,7 +29,7 @@ def expand_materials_regex(material:str, include_lower_case=True): return list(set(permuted_materials)) # Remove duplicates and return -def permute_material_list(materials:list, save_path:str ,sort=True,): +def permute_material_list(materials:list, save_path:str=None, sort:bool=True,): """ Generates a list of permuted materials based on the given list of materials. @@ -47,13 +47,14 @@ def permute_material_list(materials:list, save_path:str ,sort=True,): list A list of permuted materials. """ - if sort: - materials.sort() permuted_materials = [] for material in materials: permuted_materials += expand_materials_regex(material) + if sort: + permuted_materials.sort(key=str.lower) + if save_path: with open(save_path, 'w') as f: for permuted_material in permuted_materials: From f0dcb2e33b38bdec7cb806f65a76151605b3eeaf Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Fri, 19 Apr 2024 14:26:25 -0600 Subject: [PATCH 12/15] move leaf node termination based on sample threshold to after factorization --- TELF/factorization/HNMFk.py | 13 +++-- examples/HNMFk/01-Semantic-HNMFk.ipynb | 72 +++++++++++++------------- 2 files changed, 46 insertions(+), 39 deletions(-) diff --git a/TELF/factorization/HNMFk.py b/TELF/factorization/HNMFk.py index 13158fae..7d78304a 100644 --- a/TELF/factorization/HNMFk.py +++ b/TELF/factorization/HNMFk.py @@ -396,9 +396,9 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name ) # - # check if leaf node status + # check if leaf node status based on number of samples # - if (current_node.num_samples == 1) or (self.sample_thresh > 0 and (current_node.num_samples <= self.sample_thresh)): + if (current_node.num_samples == 1): current_node.leaf = True pickle_path = f'{node_save_path}/node_{current_node.node_name}.p' pickle.dump(current_node, open(pickle_path, "wb")) @@ -479,6 +479,13 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name current_node.W = factors_data["W"] current_node.H = factors_data["H"] current_node.k = predict_k + + # sample threshold check for leaf node determination + if self.sample_thresh > 0 and (current_node.num_samples <= self.sample_thresh): + current_node.leaf = True + pickle_path = f'{node_save_path}/node_{current_node.node_name}.p' + pickle.dump(current_node, open(pickle_path, "wb")) + return {"name":node_name, "target_jobs":[], "node_save_path":pickle_path} # # apply clustering @@ -494,7 +501,7 @@ def _process_node(self, Ks, depth, original_indices, node_name, parent_node_name # obtain the unique number of clusters that samples falls to n_clusters = len(set(cluster_labels)) - # leaf node or single cluster or all samples in same cluster + # leaf node based on depth limit or single cluster or all samples in same cluster if ((current_node.depth >= self.depth) and self.depth > 0) or current_node.k == 1 or n_clusters == 1: current_node.leaf = True pickle_path = f'{node_save_path}/node_{current_node.node_name}.p' diff --git a/examples/HNMFk/01-Semantic-HNMFk.ipynb b/examples/HNMFk/01-Semantic-HNMFk.ipynb index e8fb7eff..22759eba 100644 --- a/examples/HNMFk/01-Semantic-HNMFk.ipynb +++ b/examples/HNMFk/01-Semantic-HNMFk.ipynb @@ -396,7 +396,7 @@ { "data": { "text/plain": [ - "{'time': 6.1265130043029785}" + "{'time': 6.327818155288696}" ] }, "execution_count": 16, @@ -446,7 +446,7 @@ { "data": { "text/plain": [ - "'f9feb3b8-fde8-11ee-bfd1-ea13c6004852'" + "'fc079682-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 17, @@ -502,7 +502,7 @@ { "data": { "text/plain": [ - "'f9feb3b8-fde8-11ee-bfd1-ea13c6004852'" + "'fc079682-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 19, @@ -529,15 +529,15 @@ { "data": { "text/plain": [ - "['faac4c76-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4d98-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4e2e-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4e7e-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4ec4-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4f0a-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4f5a-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac4fd2-fde8-11ee-bfd1-ea13c6004852',\n", - " 'faac5022-fde8-11ee-bfd1-ea13c6004852']" + "['fcb98fa4-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb990c6-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb99152-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb991a2-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb991de-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb99224-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb99274-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb992ec-fe8a-11ee-8382-ea13c6004852',\n", + " 'fcb9933c-fe8a-11ee-8382-ea13c6004852']" ] }, "execution_count": 20, @@ -564,7 +564,7 @@ { "data": { "text/plain": [ - "'faac4d98-fde8-11ee-bfd1-ea13c6004852'" + "'fcb990c6-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 21, @@ -612,7 +612,7 @@ { "data": { "text/plain": [ - "'f9feb3b8-fde8-11ee-bfd1-ea13c6004852'" + "'fc079682-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 23, @@ -639,7 +639,7 @@ { "data": { "text/plain": [ - "'faac4d98-fde8-11ee-bfd1-ea13c6004852'" + "'fcb990c6-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 24, @@ -667,7 +667,7 @@ { "data": { "text/plain": [ - "'f9feb3b8-fde8-11ee-bfd1-ea13c6004852'" + "'fc079682-fe8a-11ee-8382-ea13c6004852'" ] }, "execution_count": 25, @@ -791,7 +791,7 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 30, "metadata": {}, "outputs": [ { @@ -800,7 +800,7 @@ "9" ] }, - "execution_count": 41, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -843,7 +843,7 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 31, "metadata": {}, "outputs": [ { @@ -973,7 +973,7 @@ "9 national security crucial 90 90 1.0 0.338346" ] }, - "execution_count": 42, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } @@ -984,7 +984,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 32, "metadata": {}, "outputs": [ { @@ -1069,7 +1069,7 @@ "4 implementation truncate singular 101 101 1.0 0.893805" ] }, - "execution_count": 43, + "execution_count": 32, "metadata": {}, "output_type": "execute_result" } @@ -1080,7 +1080,7 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 33, "metadata": {}, "outputs": [ { @@ -1165,7 +1165,7 @@ "4 malware family classification 236 118 1.0 4.214286" ] }, - "execution_count": 44, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -1176,7 +1176,7 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 34, "metadata": {}, "outputs": [ { @@ -1261,7 +1261,7 @@ "4 literature research education 99 99 1.0 1.137931" ] }, - "execution_count": 45, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" } @@ -1272,7 +1272,7 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 35, "metadata": {}, "outputs": [ { @@ -1357,7 +1357,7 @@ "4 value completion well 105 105 1.0 1.25" ] }, - "execution_count": 46, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } @@ -1368,7 +1368,7 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 36, "metadata": {}, "outputs": [ { @@ -1453,7 +1453,7 @@ "4 system often serve 113 113 1.0 0.719745" ] }, - "execution_count": 47, + "execution_count": 36, "metadata": {}, "output_type": "execute_result" } @@ -1464,7 +1464,7 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 37, "metadata": {}, "outputs": [ { @@ -1549,7 +1549,7 @@ "4 topic semantic sub 200 100 1.0 1.197605" ] }, - "execution_count": 48, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } @@ -1560,7 +1560,7 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 38, "metadata": {}, "outputs": [ { @@ -1645,7 +1645,7 @@ "4 implementation negative matrix 116 116 1.0 1.035714" ] }, - "execution_count": 49, + "execution_count": 38, "metadata": {}, "output_type": "execute_result" } @@ -1656,7 +1656,7 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 39, "metadata": {}, "outputs": [ { @@ -1786,7 +1786,7 @@ "9 develop mitigation strategy 98 98 1.0 0.809917" ] }, - "execution_count": 50, + "execution_count": 39, "metadata": {}, "output_type": "execute_result" } From 4ca19e6325a4c472d3304a77de2ae7e47cabe966 Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 18:00:46 -0600 Subject: [PATCH 13/15] Update levenstein.py multithreaded levenshtein, grouping by first letter to reduce number of computations -- optional. --- .../Vulture/tokens_analysis/levenstein.py | 153 ++++++++++++++---- 1 file changed, 119 insertions(+), 34 deletions(-) diff --git a/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py b/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py index aee24afb..5493210c 100644 --- a/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py +++ b/TELF/pre_processing/Vulture/tokens_analysis/levenstein.py @@ -1,4 +1,9 @@ import pandas as pd +from tqdm import tqdm +from collections import Counter +from concurrent.futures import ThreadPoolExecutor, as_completed +from itertools import combinations +import os def levenshtein_distance(s1, s2): """ @@ -15,7 +20,6 @@ def levenshtein_distance(s1, s2): ------- int The Levenshtein distance between s1 and s2. - """ if len(s1) < len(s2): return levenshtein_distance(s2, s1) @@ -32,74 +36,155 @@ def levenshtein_distance(s1, s2): previous_row = current_row return previous_row[-1] -def is_levenshtein_similar(s1, s2, threshold=0.95): +def compare_keys(key1, key2, threshold=0.95, use_indel=False): """ - Check if two strings are Levenshtein similar based on a given threshold. + Check if two strings are Levenshtein similar based on a given threshold. This function can optionally consider + insertion and deletion costs in the similarity calculation, which is controlled by the 'use_indel' parameter. Parameters ---------- - s1 : str - The first string. - s2 : str - The second string. + key1 : str + The first string to compare. + key2 : str + The second string to compare. threshold : float, optional - The minimum similarity threshold (default is 0.95). + The minimum similarity threshold for considering the strings as similar (default is 0.95). + use_indel : bool, optional + Whether to include insertion and deletion costs in the similarity calculation (default is False). Returns ------- tuple A tuple containing a boolean indicating if the strings are similar and the similarity score. """ - max_len = max(len(s1), len(s2)) - dist = levenshtein_distance(s1, s2) - similarity = (max_len - dist) / max_len - return similarity >= threshold, similarity + if use_indel: + raise ValueError("use_indel is not implemented yet -- pending dependency approval") + else: + max_len = max(len(key1), len(key2)) + dist = levenshtein_distance(key1, key2) + similarity = (max_len - dist) / max_len + return similarity > threshold, similarity + +def process_chunk(pairs, key_frequency, threshold=0.95, use_indel=False): + """ + Process a chunk of key pairs to determine if they are similar and decide the preferred key based on frequency. + + Parameters + ---------- + pairs : list of tuple + A list of tuples each containing two keys to be compared. + key_frequency : dict + A dictionary with keys and their corresponding frequency count. + threshold : float, optional + The minimum similarity threshold for considering keys as similar (default is 0.95). + use_indel : bool, optional + Whether to include insertion and deletion costs in the similarity calculation (default is False). + + Returns + ------- + list + A list of tuples, each containing the less preferred key, the preferred key, and the similarity score. + """ + results = [] + for key1, key2 in pairs: + similar_bool, similar_score = compare_keys(key1, key2, threshold, use_indel) + if similar_bool: + preferred_key = key1 if key_frequency[key1] > key_frequency[key2] else key2 + less_preferred_key = key2 if preferred_key == key1 else key1 + results.append((less_preferred_key, preferred_key, similar_score)) + return results -def replace_similar_keys_levenshtein(dict_list, changes_made_save_path=None, similarity_threshold=0.95): +def replace_similar_keys_levenshtein(dict_list, + group_by_first_letter=True, + changes_made_save_path=None, + similarity_threshold=0.95, + use_indel=False, + n_jobs=-1): """ - Replace similar keys in a list of dictionaries based on Levenshtein similarity. + Replace similar keys in a list of dictionaries based on similarity, + preferring the key that occurs more often. Optionally uses an alternative similarity calculation method. + + This function can group keys by their first letter before comparing them to reduce computational load, which is + controlled by the 'group_by_first_letter' parameter. It supports parallel processing through the 'n_jobs' parameter. Parameters ---------- dict_list : list A list of dictionaries. + group_by_first_letter : bool, optional + Whether to group keys by the first letter before comparison (default is True). changes_made_save_path : str, optional The path to save the changes made (default is None). similarity_threshold : float, optional The minimum similarity threshold for considering keys as similar (default is 0.95). + use_indel : bool, optional + Whether to use an alternative method for similarity comparison, such as including insertions and deletions in the cost (default is False). + n_jobs : int, optional + The number of jobs to run in parallel (default is -1, which uses all processors). Returns ------- tuple A tuple containing the updated list of dictionaries and a DataFrame of changes made. """ - all_keys = set(key for d in dict_list for key in d.keys()) + + all_keys = [key for d in dict_list for key in d.keys()] + key_frequency = Counter(all_keys) similar_keys = {} changes = [] - sorted_keys = sorted(all_keys) - for key1 in sorted_keys: - for key2 in sorted_keys: - if key1 != key2: - similar_bool, similar_score = is_levenshtein_similar(key1, key2, similarity_threshold) - if similar_bool: - smaller, larger = sorted([key1, key2], key=len) - similar_keys[larger] = (smaller, similar_score) - - for dict_index, dict_ in enumerate(dict_list): - keys_to_replace = {k: v for k, v in similar_keys.items() if k in dict_} - for longer_key, (shorter_key, score) in keys_to_replace.items(): - if longer_key in dict_: - dict_[shorter_key] = dict_.pop(longer_key) + sorted_keys = sorted(set(all_keys)) + + # Group keys by the first character + if group_by_first_letter: + grouped_keys = {} + for key in sorted_keys: + first_char = key[0] + if first_char not in grouped_keys: + grouped_keys[first_char] = [] + grouped_keys[first_char].append(key) + + # Generate all pairs where the first character matches + all_pairs = [pair for key_list in grouped_keys.values() for pair in combinations(key_list, 2)] + else: + all_pairs = list(combinations(sorted_keys, 2)) + + num_cpus = os.cpu_count() + if n_jobs == -1: + num_cpus = os.cpu_count() # Get the number of CPUs available + else: + # Make sure the thread count passed in is not greater than the number available + num_cpus = min(n_jobs, num_cpus) + + chunk_size = int(len(all_pairs) / num_cpus) + 1 + print(f"chunk_size = {chunk_size}, num_cpus = {num_cpus}, len all_pairs = {len(all_pairs)}") + chunks = [all_pairs[i:i + chunk_size] for i in range(0, len(all_pairs), chunk_size)] + progress = tqdm(total=len(chunks), desc="Processing Chunks") + + with ThreadPoolExecutor(max_workers=min(num_cpus,len(chunks))) as executor: + results = list(executor.map(process_chunk, chunks, [key_frequency]*len(chunks), [similarity_threshold]*len(chunks), [use_indel]*len(chunks))) + for chunk_result in results: + for less_preferred_key, preferred_key, similar_score in chunk_result: + similar_keys[less_preferred_key] = (preferred_key, similar_score) + progress.update(1) + + progress.close() + + for dict_ in dict_list: + for less_preferred_key, (preferred_key, score) in similar_keys.items(): + if less_preferred_key in dict_: + if isinstance(dict_[less_preferred_key], int): + dict_[preferred_key] = dict_.get(preferred_key, 0) + dict_.pop(less_preferred_key) + elif isinstance(dict_[less_preferred_key], str): + dict_[preferred_key] = dict_.get(preferred_key, '') + dict_.pop(less_preferred_key) changes.append({ - 'Index': dict_index, - 'Previous Word': longer_key, - 'New Word': shorter_key, + 'Previous Key': less_preferred_key, + 'New Key': preferred_key, 'Similarity Score': score }) changes_df = pd.DataFrame(changes) + if changes_made_save_path: changes_df.to_csv(changes_made_save_path, index=False) - - return dict_list, changes_df \ No newline at end of file + return dict_list, changes_df From f02343e99dd1e4efeb7ccbf99668a7fbe5114ec4 Mon Sep 17 00:00:00 2001 From: Ryan Barron <64450632+ryancb4@users.noreply.github.com> Date: Fri, 19 Apr 2024 19:11:25 -0600 Subject: [PATCH 14/15] Update acronym.py --- .../pre_processing/Vulture/modules/acronym.py | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/TELF/pre_processing/Vulture/modules/acronym.py b/TELF/pre_processing/Vulture/modules/acronym.py index d1da0832..71af92eb 100644 --- a/TELF/pre_processing/Vulture/modules/acronym.py +++ b/TELF/pre_processing/Vulture/modules/acronym.py @@ -8,6 +8,27 @@ FIRST_LETTER = 0 LAST_PART_INDEX = -1 +def transform_acronyms_to_substitutions(old_list): + """ + TODO: Document this + """ + new_list = [] + for dictionary in old_list: + if dictionary: + index_dictionary = {} + for key, value in dictionary.items(): + new_key = '_'.join(key.split()) + + index_dictionary[key] = new_key + index_dictionary[value] = new_key + + new_list.append(index_dictionary) + else: + new_list.append({}) + + return new_list + + def flatten_acronym_dict(acronym_dict): """ Transform the acronym operator data into the format that will work for consolidation and substitution operators. From 861080746222e1aabbeb71030598a8129d6bb78b Mon Sep 17 00:00:00 2001 From: MaksimEkin Date: Mon, 22 Apr 2024 12:27:31 -0600 Subject: [PATCH 15/15] update documentation --- docs/TELF.pre_processing.Vulture.html | 2 +- docs/Vulture.html | 2 +- docs/_modules/TELF/factorization/HNMFk.html | 13 ++++++++++--- .../TELF.pre_processing.Vulture.doctree | Bin 44272 -> 44272 bytes docs/doctrees/Vulture.doctree | Bin 52684 -> 52684 bytes docs/doctrees/environment.pickle | Bin 3090938 -> 3091319 bytes docs/searchindex.js | 2 +- 7 files changed, 13 insertions(+), 6 deletions(-) diff --git a/docs/TELF.pre_processing.Vulture.html b/docs/TELF.pre_processing.Vulture.html index cfe57b47..258c0562 100644 --- a/docs/TELF.pre_processing.Vulture.html +++ b/docs/TELF.pre_processing.Vulture.html @@ -410,7 +410,7 @@

Submodules
-DEFAULT_PIPELINE = [SimpleCleaner(module_type='CLEANER', effective_stop_words=['characteristics', 'acknowledgment', 'characteristic', 'substantially', 'significantly', 'unfortunately', 'predominantly', 'automatically', 'approximately', 'corresponding', 'investigation', 'successfully', 'representing', 'demonstrated', 'respectively', 'sufficiently', 'applications', 'specifically', 'introduction', 'particularly', 'consequently', 'demonstrates', 'nevertheless', 'application', 'investigate', ... (+1359 more)], patterns={'standardize_hyphens': (re.compile('[\\u002D\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015\\u2212\\u2E3A\\u2E3B]'), '-'), 'remove_copyright_statement': None, 'remove_stop_phrases': None, 'make_lower_case': None, 'normalize': None, 'remove_trailing_dash': ('(?<!\\w)-|-(?!\\w)', ''), 'make_hyphens_words': ('([a-z])\\-([a-z])', ''), 'remove_next_line': ('\\n+', ' '), 'remove_email': ('\\S*@\\S*\\s?', ''), 'remove_formulas': ('\\b\\w*[\\=\\≈\\/\\\\\\±]\\w*\\b', ''), 'remove_dash': ('-', ''), 'remove_between_[]': ('\\[.*?\\]', ' '), 'remove_between_()': ('\\(.*?\\)', ' '), 'remove_[]': ('[\\[\\]]', ' '), 'remove_()': ('[()]', ' '), 'remove_\\': ('\\\\', ' '), 'remove_numbers': ('\\d+', ''), 'remove_standalone_numbers': ('\\b\\d+\\b', ''), 'remove_nonASCII_boundary': ('\\b[^\\x00-\\x7F]+\\b', ''), 'remove_nonASCII': ('[^\\x00-\\x7F]+', ''), 'remove_tags': ('&lt;/?.*?&gt;', ''), 'remove_special_characters': ('[!|"|#|$|%|&|\\|\\\'|(|)|*|+|,|.|/|:|;|<|=|>|?|@|[|\\|]|^|_|`|{|\\||}|~]', ''), 'isolate_frozen': None, 'remove_extra_whitespace': ('\\s+', ' '), 'remove_stop_words': None, 'min_characters': None}, exclude_hyphenated_stopwords=False, sw_pattern=re.compile('\\b[\\w-]+\\b'))]#
+DEFAULT_PIPELINE = [SimpleCleaner(module_type='CLEANER', effective_stop_words=['characteristics', 'characteristic', 'acknowledgment', 'significantly', 'automatically', 'predominantly', 'investigation', 'approximately', 'unfortunately', 'corresponding', 'substantially', 'nevertheless', 'demonstrates', 'specifically', 'applications', 'introduction', 'sufficiently', 'demonstrated', 'particularly', 'consequently', 'representing', 'respectively', 'successfully', 'background:', 'application', ... (+1359 more)], patterns={'standardize_hyphens': (re.compile('[\\u002D\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015\\u2212\\u2E3A\\u2E3B]'), '-'), 'remove_copyright_statement': None, 'remove_stop_phrases': None, 'make_lower_case': None, 'normalize': None, 'remove_trailing_dash': ('(?<!\\w)-|-(?!\\w)', ''), 'make_hyphens_words': ('([a-z])\\-([a-z])', ''), 'remove_next_line': ('\\n+', ' '), 'remove_email': ('\\S*@\\S*\\s?', ''), 'remove_formulas': ('\\b\\w*[\\=\\≈\\/\\\\\\±]\\w*\\b', ''), 'remove_dash': ('-', ''), 'remove_between_[]': ('\\[.*?\\]', ' '), 'remove_between_()': ('\\(.*?\\)', ' '), 'remove_[]': ('[\\[\\]]', ' '), 'remove_()': ('[()]', ' '), 'remove_\\': ('\\\\', ' '), 'remove_numbers': ('\\d+', ''), 'remove_standalone_numbers': ('\\b\\d+\\b', ''), 'remove_nonASCII_boundary': ('\\b[^\\x00-\\x7F]+\\b', ''), 'remove_nonASCII': ('[^\\x00-\\x7F]+', ''), 'remove_tags': ('&lt;/?.*?&gt;', ''), 'remove_special_characters': ('[!|"|#|$|%|&|\\|\\\'|(|)|*|+|,|.|/|:|;|<|=|>|?|@|[|\\|]|^|_|`|{|\\||}|~]', ''), 'isolate_frozen': None, 'remove_extra_whitespace': ('\\s+', ' '), 'remove_stop_words': None, 'min_characters': None}, exclude_hyphenated_stopwords=False, sw_pattern=re.compile('\\b[\\w-]+\\b'))]#
diff --git a/docs/Vulture.html b/docs/Vulture.html index c1f96bad..3fd191c7 100644 --- a/docs/Vulture.html +++ b/docs/Vulture.html @@ -482,7 +482,7 @@

Available Functions
-DEFAULT_PIPELINE = [SimpleCleaner(module_type='CLEANER', effective_stop_words=['characteristics', 'acknowledgment', 'characteristic', 'substantially', 'significantly', 'unfortunately', 'predominantly', 'automatically', 'approximately', 'corresponding', 'investigation', 'successfully', 'representing', 'demonstrated', 'respectively', 'sufficiently', 'applications', 'specifically', 'introduction', 'particularly', 'consequently', 'demonstrates', 'nevertheless', 'application', 'investigate', ... (+1359 more)], patterns={'standardize_hyphens': (re.compile('[\\u002D\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015\\u2212\\u2E3A\\u2E3B]'), '-'), 'remove_copyright_statement': None, 'remove_stop_phrases': None, 'make_lower_case': None, 'normalize': None, 'remove_trailing_dash': ('(?<!\\w)-|-(?!\\w)', ''), 'make_hyphens_words': ('([a-z])\\-([a-z])', ''), 'remove_next_line': ('\\n+', ' '), 'remove_email': ('\\S*@\\S*\\s?', ''), 'remove_formulas': ('\\b\\w*[\\=\\≈\\/\\\\\\±]\\w*\\b', ''), 'remove_dash': ('-', ''), 'remove_between_[]': ('\\[.*?\\]', ' '), 'remove_between_()': ('\\(.*?\\)', ' '), 'remove_[]': ('[\\[\\]]', ' '), 'remove_()': ('[()]', ' '), 'remove_\\': ('\\\\', ' '), 'remove_numbers': ('\\d+', ''), 'remove_standalone_numbers': ('\\b\\d+\\b', ''), 'remove_nonASCII_boundary': ('\\b[^\\x00-\\x7F]+\\b', ''), 'remove_nonASCII': ('[^\\x00-\\x7F]+', ''), 'remove_tags': ('&lt;/?.*?&gt;', ''), 'remove_special_characters': ('[!|"|#|$|%|&|\\|\\\'|(|)|*|+|,|.|/|:|;|<|=|>|?|@|[|\\|]|^|_|`|{|\\||}|~]', ''), 'isolate_frozen': None, 'remove_extra_whitespace': ('\\s+', ' '), 'remove_stop_words': None, 'min_characters': None}, exclude_hyphenated_stopwords=False, sw_pattern=re.compile('\\b[\\w-]+\\b'))]#
+DEFAULT_PIPELINE = [SimpleCleaner(module_type='CLEANER', effective_stop_words=['characteristics', 'characteristic', 'acknowledgment', 'significantly', 'automatically', 'predominantly', 'investigation', 'approximately', 'unfortunately', 'corresponding', 'substantially', 'nevertheless', 'demonstrates', 'specifically', 'applications', 'introduction', 'sufficiently', 'demonstrated', 'particularly', 'consequently', 'representing', 'respectively', 'successfully', 'background:', 'application', ... (+1359 more)], patterns={'standardize_hyphens': (re.compile('[\\u002D\\u2010\\u2011\\u2012\\u2013\\u2014\\u2015\\u2212\\u2E3A\\u2E3B]'), '-'), 'remove_copyright_statement': None, 'remove_stop_phrases': None, 'make_lower_case': None, 'normalize': None, 'remove_trailing_dash': ('(?<!\\w)-|-(?!\\w)', ''), 'make_hyphens_words': ('([a-z])\\-([a-z])', ''), 'remove_next_line': ('\\n+', ' '), 'remove_email': ('\\S*@\\S*\\s?', ''), 'remove_formulas': ('\\b\\w*[\\=\\≈\\/\\\\\\±]\\w*\\b', ''), 'remove_dash': ('-', ''), 'remove_between_[]': ('\\[.*?\\]', ' '), 'remove_between_()': ('\\(.*?\\)', ' '), 'remove_[]': ('[\\[\\]]', ' '), 'remove_()': ('[()]', ' '), 'remove_\\': ('\\\\', ' '), 'remove_numbers': ('\\d+', ''), 'remove_standalone_numbers': ('\\b\\d+\\b', ''), 'remove_nonASCII_boundary': ('\\b[^\\x00-\\x7F]+\\b', ''), 'remove_nonASCII': ('[^\\x00-\\x7F]+', ''), 'remove_tags': ('&lt;/?.*?&gt;', ''), 'remove_special_characters': ('[!|"|#|$|%|&|\\|\\\'|(|)|*|+|,|.|/|:|;|<|=|>|?|@|[|\\|]|^|_|`|{|\\||}|~]', ''), 'isolate_frozen': None, 'remove_extra_whitespace': ('\\s+', ' '), 'remove_stop_words': None, 'min_characters': None}, exclude_hyphenated_stopwords=False, sw_pattern=re.compile('\\b[\\w-]+\\b'))]#

diff --git a/docs/_modules/TELF/factorization/HNMFk.html b/docs/_modules/TELF/factorization/HNMFk.html index f11d41bc..c9dc5b3c 100644 --- a/docs/_modules/TELF/factorization/HNMFk.html +++ b/docs/_modules/TELF/factorization/HNMFk.html @@ -686,9 +686,9 @@

Source code for TELF.factorization.HNMFk

         )
 
         #
-        # check if leaf node status
+        # check if leaf node status based on number of samples
         #
-        if (current_node.num_samples == 1) or (self.sample_thresh > 0 and (current_node.num_samples <= self.sample_thresh)):
+        if (current_node.num_samples == 1):
             current_node.leaf = True
             pickle_path = f'{node_save_path}/node_{current_node.node_name}.p'
             pickle.dump(current_node, open(pickle_path, "wb"))
@@ -769,6 +769,13 @@ 
Source code for TELF.factorization.HNMFk
             current_node.W = factors_data["W"]
             current_node.H = factors_data["H"]
             current_node.k = predict_k
+
+        # sample threshold check for leaf node determination
+        if self.sample_thresh > 0 and (current_node.num_samples <= self.sample_thresh):
+            current_node.leaf = True
+            pickle_path = f'{node_save_path}/node_{current_node.node_name}.p'
+            pickle.dump(current_node, open(pickle_path, "wb"))
+            return {"name":node_name, "target_jobs":[], "node_save_path":pickle_path}
         
         #
         # apply clustering
@@ -784,7 +791,7 @@ 
Source code for TELF.factorization.HNMFk
         # obtain the unique number of clusters that samples falls to
         n_clusters = len(set(cluster_labels))
 
-        # leaf node or single cluster or all samples in same cluster
+        # leaf node based on depth limit or single cluster or all samples in same cluster
         if ((current_node.depth >= self.depth) and self.depth > 0) or current_node.k == 1 or n_clusters == 1:
             current_node.leaf = True
             pickle_path = f'{node_save_path}/node_{current_node.node_name}.p'
diff --git a/docs/doctrees/TELF.pre_processing.Vulture.doctree b/docs/doctrees/TELF.pre_processing.Vulture.doctree
index 752088eb5fa53696cc07313e1c37eefe943cb222..21d7c214a11004ae22c97e895c622844fde4d460 100644
GIT binary patch
delta 506
zcmd^)F-inM5Jhn@*AZ0MKn#QhS=vN)U~l0O+U}a!!k+4(yL!aX3z*ay49tYRgGPes
zW*V695$xVcyo2HA|N5`~b~D*-Ca;f5L>*1Fxg&q?z_uL_&*tZ|h%I4*M!wYatPfy)
zhop(!LvfJ?h>Wdf^dz5)V|iDV{46SYR@EiJ0D)KFAjXom(0Pg+G{a8E9!%-hPHyUx
zIT8nNlPO(0bZWAR`H>O!=iJK6)rFkahsyw^g>ir}6q7L-*CaRU+dQcaK9OCPPTlt|
V0}EpPUBB(GKdztl{^Rt6^b0?*yx#x-

delta 486
zcmexxlj*}vrVWjHlPBv5$tPzd79}Q^q!wismt-cZ>nNxfmnIdLB<7W5Cg$W+PF|=d
zI{Av3;N;_af|Iua@nInQshOa3W?oq;P)B-VNoIZ?L|bxlYH@K|Y0l({=3-hYsk!-i
z#U(|FC8;SO>7vx)g4E=a%(B#+N{I5bw9Mqp)Vz|(hUQ{2AjwRi0LV^|bY@;jQGQA(
zP(yy+b_hzBfa2TFnSvpF3nZbQ_>`Nd4HB`rk@OyKuCzoB7Oa<_*%pe2K}~dHLlzsVV8Xsd*)nKSqhk6qhCymn7zuWG3e1RI2MJs269Z
z=Vhj4CIiJL_XUe{6cnYVLIC*KXpmb(lS!!`fW_n^tW_})6S7~x`
zYH@K|Y0l)p5HYQk)ZF~M;*z4olGGHCbWv(?L27bIW?3rKlF~Gw6`5d11Opublmy!e
zbwg%eNl|`EDNsXx-elew6)Pn3ib3Y(rIw`@m1Lym0PO_v6AKD*fKGd`W_%`z+Peam_?P0LL4bxW3?Rvy%r8n*xWcgn+;%
z*CA!aGsMs@5jP#)Z0MQ85_2)YQq7
z8Oxz~CvotqU|27#`xv1Tw_KalKrVDLD|u{6*h*mxAFGb)#WO#tG$RmXq5J1`k?XIC(uU*eU#7#4bEOlA2cp|nNuu2X-M{o^g$!B
zPofVRfW4ePsOR>{^pX13z%C(9^|N12X?-ie)lNNc)Wp4-$}sAEqh_s7I>TrLjha7N
zGZ;prXw(#r%VZdhq*3Gln}kv0jha-~p^Qi4Xw-~p9L6vjX``lF@Cb&{Xd5+e)(g1|
zrGYkTf>TE`jE2*wd1JnW(a;+;Ays*dN5gN_m`9Ca7)?Q=CT)>~(TE#0PA>V3N26}k
zxXq9-8hN9p|3(Q*WmwTxCq%`u-A9VsigLt0gOkL41rcIPPfxM;m;}+gx3@TNOaPec
z)$Zbg^#0OYs8oP^%3Jo>%=*udWs>vLc}HcaT=P-=2k&W
zC|D_)dPitzHYxsIibZ_BcbfQfN~C)Ws|!kP&rB3=56%!TrbLPldq+XShG4yTVL-BY
zH#JzyO6(+F=^q6x-ZF@qT$FbowL~3S1Y>Y
znXsF$^UTVr6IbT-7F}}(Yv`C!Tk}U-B>nUHgos5GJS4qT)x`mW#h(Y|qN@I~+6-~x
zKoj_$^VNvw2PBH-BwtkBO`MT5NNn%l2Lqr(&jRR^iK3jCHX)Izan7?ydcW$?7xk@B
zrHL;O=_Z~X93U=APj_g)mHUE2Vb_5@oLcPJVs3JhhE|P|Etfnw^ppv>BG9l)2MXfS
z)KcaS$z_p3<-!1+I5U$*)QOq6I4DQFp4Lt5m6*uTXz-`9nl#{-Nk}DZ&hoD
z;u_#Ky}GQVwx+m3w2d69N~ReF?fO8S7&Uy2>ctL{S>l4MX7N^TChG1Zp3e598Bh&k
z9U4{`J;m#TZFHE_O&dG(>M6$BB2@c=Kt0)qhSoS|nWxgS{|e2{^DvHU%4Q0vyIv}w~4HpND^+rdQ|9@En=rTp)pH?zN95TMQs;79Q
zGzP36M0kpCj!zYHOOsTIlq7B*uN6=ANMh6CaA`MnQxYTJ7^hS9W>8wGuZW&w6v5)T
zac=PNqXWl
z<3txp#ZT%+Zt2?pmkaTWZk8^+S*pVSYW(kn|DDOrQkSH!;LC>rq44OmS1g&HfWH4=>`-cN0YS=;dBH2RAA@|{aj0%@OR4j!4!@ZZxFa65>XIE7w
zthizcVfljLL6HG%V>uV{`f2wsLsgli{;suh)^;m%R=+OJMRf
zucJAz^Mc+$IwgCTs3q#kRPPm@5d4MCKoUoK|E5u8Q^(Rt%^2_QYE?GbTHyVzmnusl
zzE+>HoT=Y#zN|$j1^>ZA`wJCb0{BXXWDQ_63
z9}}!d{xM5`)}h0vUT^5Ea1wXuzjttK?fSwVG6(jY)@$L!AO0qC<%0gS!_K42`n`!t
z?_&{ue>r;J7yLH#Q8?`-et$YR=O_DJ9ini4+UXbW;Pijfk9qy?PyCqI`;PnFaHQm&
z%YOL|M`H~BO_+LVP>v7rw>da*l^r-=yySnyOA-5GyML&!jO^R*-`8JZWPRp;%z?z8
z_g~vZ;ryUAJgrj@YlPtwUO|MR1~+#cHJqDg6$vnmHE7|;c!NCL!^;da9hrJK*^m*h
z^e$L!co{ha%cumCM2f#Lyy1|ves7rI$m#q30fmnIb@NHYv9w
z^nssxDM)-+;1PEj0bU5yLZLp;MB<_YztSr*0sR7}L@F}T;}n@Ag@GqcDjQibC-APf
zBD-N(;94IA$%4SA9mv5gfxcRWb8c^7Uq_#W4+5JM1itwU^_vd|y2A}ikdE9t8ThGjgZz;zx9V!Ii*(}DQh4_vRPSVe;5D6Y5%)hNM{8o!__Pq{O!4ndi73xi}U=CGjf
zAVu-$-a#RXE*R5aQT9ekkQk`Qj2RoW*CCTWS&^~XgZevCyJ1FAa8zGqlqk!H;z+ApFA3A
zJQu2%zFlS9AFh}_)r1{3E>o0USz(+O1n<3rEAoiV5w7ssJ&PHJKML@MX0HfWa%P9|
z7ccOv2{n*^5u+)RfslC$b=)|GI;!6_=}5QJ#y@#UXrPm6SE3}eIMJkq5l$u(iS1{a
zqLcVLZKe?h3DlOD3c@6C{z8+Vy9923-jwRWKg#^9Y&0L0oqI73oEwwDC=43Ttk^}$+bUl=SK
z44EIiEdff(y)%gC8^M`sxNi6MArsyTE_74nN;|3h!Qd+f_~VMJfw=!8*sg}S5w1G2
z_^aTQJc)WHHe}p72^{fh$iZzAXs!tzzL*hqZ_4Rxl7?kQuY|D9jzQ?uF>c+QH^At0W!w_bAN@O
z35V`Q9tJWiB%(qM&)&sT&z(*YD}7<%ktn@Samkd*s+kpKrIV(XRo24GN1_by?U5)Q
zd`usk_ebeGi>s?^s%A}|T3lNO?MI>l;V;T+rH`@$QCi5Q4+DL;(1(RS?(D}$pTr1H
zIJZB_1$rKcGQ&rd_VfNIJ&^rTKBft1dQweQU1ez>KGw{mm5RwF#kG^GDoOK!s7KDk
zt7pWIs{d^-k2=G_qfy=@y??~s5Gl>N{D?Na1Rku2SZI>K?4=PSW$J+!Bf_*2_3En;
zmqJv@(zu1at8;~|hp@6A9g7Ge){i4L2SD`iI3CewBJkAqd4xNJsUqUQqBL!6lt&xK@5*U;n`B^X3Fln>8+YpH-L?%78Dbi9R
z)1l#Vq!yYpB2DDW>ycLmDddSUIB1M~FCi+Khp&%D$geO<^P*miP+3X%Gf{V)Rn~36
z^P^l44OtR(%&f9X#{Sw8RiQ@Wr0r3g{>KaMyzBpZsSzx-_d}G_ia$lQ=@n$a?@`a2
z6y&VdGSb0GiL``i70#^gmV<%d5)>H*C%e13kUXnpX0vJ(Ir*Jsm@|xR!s3ei!7@@U
zfz9VFHW|G7ljRkSDwW`?$^sR(epf9!UEu6rmQZMUXfeWWffFF~mgQSG`-i0$_{?@Q
zl9byPtqS_xRbTn^oNS%02Ma}5+9(c&vOJlTvc%e(zW-h
zSJm>h_ihTYYwu$eV%Oe3QHWi8KcEo1r4HPI5WDP-q7b_Z?@A$d6+VDM>;l|MA$G-`
zMpTsQ8x%o+F*ry=$p-0w1;upaT*y|_PQygnH5hD6RuO+C|-
z^?f+C1OgL1(2x5~5+&~r;2LF?)(?9X4W>@6s^Jz&HM=F53sOPcOiqsPdX#r1$jf{D>iv&L{%6|1LEOAH^elIuw#rgBpm&O?@~mllLp^z@rbu0a+uALli2
zdKK55?5yT4tDt04hZxza0JtjnkU`TqjS9|PRQ#AyOYI^qkJhhs)Go!zz?s}8nZ<@E
zA=BFzglDi?qGwaPtP{0Mj?dvj)UbU5Uq#m&6I9RRGN8Irsrc{baRDld>tWqyE({{;
zF<;r_yLws;jC}nSz7u(M0d$p$|
zwGzm$&ru_Y%SO5`LnB$_(lTmV59KmkH*2LLm9EUN1++EH+C*wGlJ;+DR
z+$^kqR7-FiFds}6%Lg3?g5!V{g~VaRr%e$BOkD`f->P*Z2Ul~?N}ULH`bh4N)jN<(
zSj!!hSvcpm%T|8f$jw$k<4c%JT%vn}`zsjcl(l>mse6S+h@cMEZstzWTOvY+#=!@l+~XO+8FyvGq)e!xdu7ijUtcPq57BlAAs
z+GVB4xh)HISx1lfzvMbojyw72bGp>9y#1}C?+omC?!*%v33kNGK1tjQ6}9(K>}+WE*AxG*=xWB&
zdiQJ2ph!OH(I>C@`;ek(qi$M>~v(T@#XC3jfLO@Oc
z*?#UxB8$KOY{8A}`H}lT*5>QSxsjF&T$bz{W-b;s-V5*{oqypL$U;T0^KP*11Wr)x
z7(*brdr7GVaB#?tU%6AVIF7RgPR3kO`QU^LiOH^Pec~!%Q$sCmL1snSXdcyjNI7K^q@H1p{*d6;MAZK0IKwomtlgA>Y
z*2qb39$!KkXw&lF%G6$ZK1NoGpcSso$C3WjUvWqBVIw_t40<6@OKt`5QL+-j$iFWe
zE$o3t2Zi#!Bq^BxSSD8I^IZrMWlPX5mlV$=;p9R=Ln_1gNLk&caQ>*=bAzYg1}|Co
zo@8Gn|5*njK_U(%i(v=PyULC$@=1_&JJ6N5#W);OIK7B5mj7JV#8RZa6X*j)O9U@6
zDBh89me%=UL7s3i9Mk$i0zX~ugURaxSqVX&WI;DY5y7zW;6uHEUq4#y4>K6z1``u~Rpbk`*_B#Y>5hbqw7oOyy5VeFzpvSx%ziRX#)?$8~3f_Gg_cP_Cq875=$GT*v;k_k1
zPB_H%!1m|6rThd5CsQZ#`(zd#XARKuy3wDEFQ;|MHM|k-*5EOu
z`!qT|DW@%&HxOj>kpxLd9sicBk{!w~&ET)gIG&d^1oyq0G9LdOXJ~uR5|2fU{Ibvgh&dN?dAHVQOJ_i^-Q1*Yg1#oJFpY99qCHd!mC89M1b5Cz_HW@UWRB@eK2)5))teM;<8c#W9nG)uerg87p-Y&CGd>(%1iVJ)
zJmoux7IDyu0GRVHJjlKNI**4E#>LmH;pFq(G?Ns^D$qcZfy*Q}-}ny=QR4hvfpFDR
z@F3oM=p<$uu;w&SZR7@#uzj?csuMXQ1p0ANFyekEUpNqq2d1R`bP$VrDV(=Mxgaw5
zZGMlegN@&YFs?tb9;E9ZRZPr>c;CMT76p%5&A#9jh3w@=6iGnI&Xi+-l$%(4d*0`l
z$Q^NB%c(rqIoz8(^AV3HZss=Dga)ea@xCjMYDmJzyhZ9kCLQCqDGnUxd&qho4~cm}
zxSKS0Hhr#)3o)PIFUg&7i15QL3!v0N!Hg&UI`NM1&)c1_!o~y
z9D9LWD|qg)c*3|p!#U})WZG#y1I`sHWpm~<)*Z#=_m8MExO!!f(`R^m|6pXczU}yd
z$MXlnheZl_5PFENzxV@Ax4iRw;bYDKqWOuhlyMIWzAhZSz^|9_yPPnFoVZAxrkYrR
zL`MsmJM;j;9C*yp#zq8z&BfwI
zD*vEcn8W9PC85t7?(%q~XI<#{6CD4$e^)_T9`Ja={hQwTg2hY@J>o}5A(Ak)fEyGQ
zB6-fj^C}n;Ds*^j#EYn8Smi2YfHoR;ezyInGy+a`#O3WL)lI;Y1LFSVGj{BU4EWwlSp@44rvwAB(9Xyp)>xpL
zQE7P*EH9k+Ockvxz{(m)Hgy(o31LK9UIfbv_caAiCHuPwcphRnEiZ!Qh36rLKUqO=u21(l&*Z^HtUomQ5XA*4sY
z|Dp!#t1C$v@L%lHA_FWk9T_!9z~c?GkCm1|ejOr|s9=sS767|j#p}yH@Oui@*9|{q
z1SX^k{Ztg!llC-WtPFO_5OAt9YICMgCWEe42X*E!T3bxu7n=iodIU8{sqk5ra27A2
zUmHn1W|W$2;oorbJ3MCL936=MIwk;iHUM9@lFB
zy|?PAVrG%@@BOBF%KiW!Wy~z{i!0Q~ALRtYPvZr1Dm3K@o$ILu{2?i-#^0c^h+3Fx
ziqXJYn2pC6H9|3ZRoudiP>fy;w=ipuF=~!tH0Tz4)OHD@_rNW7yvAX?QS}TJ6qI2x
zPhhc6VDV322~S|%p1^uMfepbcZ|V$9Z%bX1_oRxd35B&)C1mdyAqIa62j>cefvTZk
z9xL=2OE1o83P&Em6j##6)e|(&^ctPgdwqkXZ2Gu(k(Sv7;U1R)2T
zD^fG4L>P@2ln8m)+$a%pyx13msz|*4ua1ZMb+{xC`pGFAUMLk@QDjxAkd4jdQo)K%
z&oW^cHVeyyG1z=x##DEm$gt-p3Y~DYc1#pfvAHo3caU@#Fo`uylY}h9&P+lr=@4Cx
zI@4iZx$rbLUzamt_+(U_4waLI(Po-3`PNq7%-lpAzgt;lgCx
z7KTEYT^NAPcsp)MLt&F$$i(K~b|D>`9#hbdp)h9(BYrqVNJ8x46jn+DDunL%YrC2X
zArYI`DsWNBf=d-bFKoi5qRuQBKUEll&C64fmgpt_1Ej3;>n7tGjQzK-0vrk3#EL>yI
zGkAHP5QASt^j>gsuHFN#*Wj>Xjn@dHu*sZ`!;=Cq9aEM9KTO9_N`Zu0)-0&SaY=#C
zrN&q%jPYWcm)TMC_fsKZhLFTA72!yo;DM6IQ3M;y3>?-Jm^TB#&SELB&BnS-fz7j-Pd8>`;iW+8
z9M-Iv!(zEQhozv;GeR!%TBPQp)byLnw6x3>=nuZWn2R3TfSV^&daGRV^8^iwT$+c69~%sPRw$Pw8@HmQ_clpVn-J&^51tj=G)zmcZE$U#(8qBF
zrj>)RL3usyfViU6LHjNAIZ%Fm@Y!xIieN
zy%!2a*eqCx>9xTR3o%+7^jw4+uMJj7&7DQUSV{BVH&JuWTd;AFkj`$X{N&p$neihBQD+gp*{ND^63nj*ih>8r1p1>Y&jyzC
zsSQFoVyC2LU?an}H{ud!1E1%arOD3=HYxWpA47b#kO1d+qf$Gls0j<%hM%=r+V?gw
zw*r=9DcHciT$qT>m&>v8ZD4!>SCAYS_X2jvfn6_PQggt$Sr`V_O9U6lZN?G6U-dTQ
z%*%m0&8RO2hPU8ikOM1Pa0=zX4=q@IIS{)73p@wrt`Ks)+2`5HA27_DKd>+@Z8Lda
z$g1acZt^hXKRZo{
z?FBgZa-kMbYc3FAd(?dp1|imeHJ<8oVX@R4UyaLVE~sC`wK@Za(8dZ2U&Mj3!ly4{
zZCD|84Gw`7maM@cwZg?Ug3XhC&mR3EuB@Bj#u}kFYzF%}y@UVjddg#!f=*U&!c*ujo
zCXU<5j$DrpTrj_a#&ckR)QpvyIa0G4n*yf5_;W`E$sH6>NlJ@i~VTNG2<%VeHVJiV;cTvchVteZNatj1h5(LB9)YIQ{!4F00CKYV^5
zCIU9?i`T=AcVq4n>pL-DdSrT-<$sZ~thu(lrfhn7RYj?}q`a(Tig{vHjk%(%c%r$o
zsQMhD96uHlN|KJoTv7Qu{3-EZR@-{3mxAv+_aG1Z+vn9!*^<<@OlY|pV@|iK
zZ6no7Tbs1fUnfth!k4YWnyM=NYhosut+o|WzK_f=t1YBH%iIZSTP5Y{p?D?+(H~Bx;UCh(UyE^dUZA!CBwmZ*onKVjwnE9Z7|waS+O`vxUyJGNyi09shlAH*
zqMhGV+unuC*J8RjA6DBwhmh;YJ)yS!2-fQ{5zZIXwwo~RI%>J4w%voZNaG%;Z7L_U
zrjr~joQ@t=7uOU|oi6+6#!Qw
zpChl|u0Z*(DbS{!3Uu#v1-iLQfqvPoK)2czX!c$isUJq
z3f0-wN1l4BwiTv1d4-but2)0^DM`Hki$lWWdqu*4zlU=pzdFa3=X5Ax3t3&i*3R8PNKiB|S2k>V6&6<*J23iM*F0(~-5f%LN#=r;%C_KZSXHCKV+>DvU;
zJZpgheZN?NmM)Q@I{TaCvoUeC#t;X4?m@IYKAoteq>r!N5v
zig;ay>g-NP#6b-IEHIvay7nRe`ZUf-V_;&c-Aac$3?etbj7u?gXS^JG?q|>m2lOmG
z?K4{39t8@f2YVYSzY@1Pwx029MBzPfKo1Wnv=whFP~$raR74N*tnYUYsPSEe=66Ja
z3f@zoSKe2k6CWs$@R5%KT8~nQEDwqg!FMpSBP`zL8o&&^b6l3Gv*&**WyTZ~57o81@8*o+b7JCCd_CE2yXzk)oiJj4c&$0d|rp15ejQ!Tmh!1jhqnzpX+6(Z87$3>LHImD7;x`3_u`W^cXw9Iv
zE-6skuT0GjG5#l4$+1P(8D;gF_(M@D+`A6PYn`zz{~-RDrzhJH!zbd&BbW3$5ufKG
zQD#kMlnr0SzcREt+mokHLkfdV)F@C}tpaVWQ=ps~6e4wDUFtlv^rxWH?VaYRv99Xs
HCdB_Ai?h&!

delta 16903
zcmd6Od0bRg`*<@f!_LgWFwC$obMFNaaR*nF9UMTxR8Ro{g;5b%+|p266v99+@{}o>
zxu<5O9yKf5G_z7$v~n-C%-7V+%>DPAbMFQ0eLtVyzu!N&=h@D)o#!m~+~LlN{i=K4
z?pN)&5b30Ox^_xUZB;3#S_PxHaH0>aQH5&Y^|^vYT-v3Z(LU3fJh`ROJ~wGta!aEo
zXZBP^fTj0BqIHc9$s=B7dmPH9pw3mdZ
zQruP6Es?SrN%l@6rBjjxigIM<$RYe%Q5-V+JJ~QOsNPjCRORq^J|km*htp
z#a-pFCDI5+k~1%n5-7=;rBfmdV={7HC6ZN~7Hz4c>9LKW51JQS9(~Y^*z)OvCc-wB
zK4|>5arBW)ALHqRhHNXK4;rhjkUnUXwj%nV@!2NOM-qJ$(+3UCRze>%E?cQx6h3K4
zwu$sXBe6}Q4;p~2j6SI6wsQKgzB{;^zg^wpsQmS1K8`l(d4on(K8|73`v%SOpT;wc
zM$n-7d2%7cXcP?^|9(XbqmeXdu6!k7)Odp?=A4AlI2trRj3{Q3G|~pmg_ubUqtP~K
zrq-RA%upI=gXW{s3Wm{e8Z?KuNEi*hLG#oXm5fKjN7vR*XBbUEgQoI?gwco_G~-8A
zF&>S&L8JLn!f50Tnv(kxW@VUBi80eizTC1i6@5i7q|3wb8cp7Yibe11MwrpUkkg7uk>;g&3!{v
zS>jtok*W}JL5fM-k>Dbh^-Z>GwxuF9Q`9DUi+5sU#Tm(i#4|&Nh`;w6Dt^|hzc?ky
zP3)5#FFqf?RJ@#S7Gnm)irLAY_A@J{P88i^t>U^-J;Z$pJy0M*434uGx20&sgK6Ex
zXA*nDd_P}zmzHK$W7MJ7`@Phzv_oN__)%&<@r_YE#p@|%@I3FS5m%3jfaagfZep+G
zp-*UYLv3_)QCnjV3`EdW&z@R9eF;kJBAysEM?9M2jj2d|!p^|_INA9?(J&-U)W@c_
z`%Q!E?5{mqNE1gU#A#@yP_GN)BHJUooZgWlDII~G5_&s1Obkyn!}-lx7jaJlCmtK>
zL4y(pC04Rzh__??;n)PTt9W*#muN`k#a*#I;aq>Ci?~02jQC|z4^hnMFNP)hNqIQX
zE1r$O^YH_j(^8@=N^XYWVABewUQSQnhJ)8veAk*Jo*X=simQ6k3^^4PlvkA36cmX2
zQwNL7G6smBrS(wtMOGAKhw5BuN@?NKlqS#);*9|=plvhi>{=Qd#03NTiOo44VpMLN
zTXki5MQL?(XordbzWxm^aK*m8fVFACGW=OpVbUH7@TYmLz_e
z>7t5P#Grnu$yMy094mTS-D%~j7IzZvCk`5^5qHKWV0b-Iqo-Jv)zp!{?bdWv%M(tm
zvigW8GFNs~#i%rlqMu_?O>tRiwOAL=k|h3;^BPw8VAp20uqlOQf&**)Ormx>(ULmS+9PgLt#I3
z{q5pVc=Q=k`{z50q&)4?8ttIJBn96ce7;C%@P&_KF1_xz19@K+tRe*t*COF#El0Zv|3|995|uQ9!0|m{03i&Vg(@<$OECI}Q>EkDXT*!VjB64J5VD1+6fF
zy%St6{{;`mAa&;`*Tlh4T;?th#Sn0P(GQvjdFsdy@3>xdkihTuxJISJuz0Njp8m>J
z3&*~7b#66a<_6oj#i=EkdIz`G*CF6T4+H77(QSJ#RXTH%;0TwyL){0?Ix_o;+g^JK
zO!&j?U@lB9bT*K{1ovXKL|vBTzSI@Y_#icQxci?PRT|ZiLaN5N_f)IW$cB9P_ub%=
z9e%0g%`*2yH8i&I&g37P`jBd2V=JCT<*d-m_4K;UBXWM|G`-nYl6
zm*t>JhKDN+u_U3FZeCZ3{(X_IcL#lv?olM8Lu$QF3(X63SdxQuIx>Hmu9v;i{aUMT
zyAPCI!7c$>-9
zi~3XTb{=2R?~0Xr9uD=o*WUAi;I+D+MBh>D^-nwfLb=zqp%VR
ziJ1MR_hA`~zTmyGn?yaQHH^|pU`D9nb6x_4bOSCZZ19tE3|~kBU>IxA!h!Jyd0aC~
z4Kv$Q@~GU98ZGt6f5q@R(g~JJv6Kzi`!V)pd0c(cP~F}s$m|KR(?jUm6+m^|L>D
zq0t#`SbTNl{xRcA21)+4%f?kM5@@|?+$w_}4~%V6*X6`lcKE8ZZQ4e
z$>ZTBoNdhfU(-x`LL@^c8c}r3VnxZ-rKah=svK4|khLz<5#GFS35LwaKJL)u7V1dO
zY%%@nh5~G9|B;x?VKM?~Cs5Ok6R4^3eY1}AIA!{WR|E&!nYYI(g3rgAwUA|JHj}6U
z=E*umW~kZ>tg&$r$LDs;DBHiv4=~D|)#)KP~K7
z=qKCupYOLZ2L3YYQikI$=8znHfDj@TD27>8}0L)uJpqXs@JD_cb#4ns0=sQ^g
zm;4a8CrbkJgrGBvByiY{Al*_10>lSnwjKvLL-u`t9a%Xfc+7H1$mL{ko=pO04+&Y;
zlYtw9YePaLV(-?FcU&a!!J3f4-V&I-Dee?ms9RY~N<
zdm(2+R7p~~%<>PNLW!3GL)Uu3!UN%YkK(eTs-ohW(yH?6n(|^;vnSjDEeFDNFsW~-
z4t7&$JwBX@Dl4m|%_^S?HxGoHA&D|e_l9dBi9QVUF>-IX9yEKyJ>b$FM8Btx+w@`C
z8y*bz`i8o~u|44qunTEsR5zu(xTvOlS_K~!%$HZpC`J2|ifT$p)86pM_Qb7s=+CPE
z!!91Qhy4e`-AT&8&|UsYesy`Ft$GF7KP7ab8Ihus1_Q}m6q?=6+52i}kX8}9wmI}S
ze^rJw;e+1SIl_hyu&y5;4)rA&heFr+K*ZlTCJ|>s@dWl&s51nq!gM71Z0N~2=#^m!
zf^nn6BMBaQ-MYZD7c4q5IUy|FNdgaMgbmS1pl?ptmwi+tq&m1;ABN{kCOx$=%u+1V
zq5evk7MfDS%;fm>u&eP3d154vA|v0A2~XhR`-7qK*?7_D@K-}s2_)p1@VoY^gpGdl
z!yORye8DaziPtsDRtH%3z!Ct>k1Qs5OW*_uxMleP*8gqk
z10J)TOeFCyi&h1(4;7iVXWV_s+S?X873{q$5xYY0yRI5&o5Xp5{T<6saQhbaUTw!Y
z!ds6l9<6`5X-Kz!Ebc1Ey^TGx=W)R>`>rJ(j1MefaQd#L49?y`hIY7}BYm@&2_OEc
zp!tt|`a_eW;0QzSV~+uMvB%(3ydwk@^HFe;(h~0>t=|KS4Hn)NDfkQbKopB@Kvs$hifV>
zU%Jj-zF93_XTL=ucAb5gLhL&G7YecK?1vO$x6j5c2(e4-a0;<2?(P&~SKNar#4ffo
zD8#O=M^lJhahFnvU2#`!i9(Rwao15IyUuQ;5WCLaKp}RWeSkt%a!bwiv%veW^8s+)
z#1CWROmLi?RFM5KuY=%moEJG2!6h?X5640Tp5%4m5+t0w6~%3lSy?%p24+lm3@5G8
zT$@b1@dvLV))?+qCmayBK=52gC-Pzs?ug78{28YqwqD%dG9J^0`0PI19T~6lL%cqg
zvr|*g^rWpHr0aF
ze2B~O6(-a8C{A{zaI0l-Vj8zkmKwH#Gr;)?&Tb?pg9gAvW31FyrX_DA7XpYz((T1;>8sJV3xEnf+MKRRw4N
z;B^E?$;v=IsT-WHiIjtYutp5;~QeDxoY@*^X{n5L!4LIa$HgON`(n
zyarA!=X#Q@mE08-xFq24Jh3PME(#tbzM9jhAUH$uV{#20EX3u(`n{G0NO3ZFCbyP>
zJjA5AdxG!`MjbI5ElTp#BsnsN^H+l{ALE_BmKy;DcP(b9oX4fY`2xkp>3N)wisE`$
zwT=sdusTdv8u_V?76T(+e}fMsn-@@55cei_&vBC^7Mc4zH(3P@ukq99+9klVFQV?r
zEBSEp`-@a9f;w2ajthqFi@DwOD#wM~T+Fq~oIl>+g9vHhM#%WoB21CBk+aFTUoqF6
z++D)GDB+~JiQA@TN=fE2?hRRLO$FDN#I?}SnZ2MRyc5A}zbT2rpqVuO4O%C%{}t}p
zj!r%h?~AuUql|)%EL_1g$s8w>5KktoDI<=mW^In!_85_@+v8x$D!*?C5yFh
z&~OoFS^OSf;j7ov1TqRs;LwdURTL*5ZsPXJte{*z9Cm!IbAsStojuvNg-$Wn=}8XG
zFr5oH@4~YBc`Ns(tZ4OiZkSrq`EUnEjoHA(
zLjyNv@gA@vOdm*G2$R8LBO7_NkGm(!BNzjo+x2+AK|RTRU-1Ok+UNTrmmv3_
z`VpOU%m^-a(a`Maujo=k)e#i8my`e%A}FMil^*-HJ;;0CbKWvF
z_y_KR+&B6s1q5cb?i+6pGWRt1g=`fS^nf+zIeTcDh5oEO%N>w8Y{;}0gAdts{z>AF
z)!rU3aJJw?cK*zLB8#*2y7?lPEqjXL;^pFf9}m*yS8jpq%?H1=dxKyPXnGm%kXZJ8
zuX5XEO*k&$aBPlXAi8UG#`5|jwMRp7_+X)rtaRq>cBL$u
zn46p@vE8AoJsT(713h589q&(8-Q~t3QBc;Fj?>AT_i+)3@1aZ$;{(oHMR7f_iID%0
znN$$JySUJp*)E)|F`~;&LbQy;oc@N$oyO62nPs%Rz
z)$5UNnGg)YjtDu3`EPQXWJBhxKk&psShzl@n6YAmND&ZqX!heAh?nEXg*k0#Iig;
z$k!DvhhVZkiQ%hdYnV$%*-?xW&nYbA-?I2PSUtekiR|jbACyHgWEYvwqMdK@H9-9$
z!IfO=$K$kMJsIcxRNr9YIFQHr&xkk^!=ZVuuRk#kenOIHhwx`5q1_3JBf#RwjzMp;
z5BqwMf+YT^>;jG#9s!t61c$=))4uNHgEanY*$@)r;IzF77vw*&=d}zT7i20|}B9ALGW8wO1faYx`Z!*4&mLVhJf*=v0@_UmPOew?BUT&k~CiS__
z`NIx7b0E1og?~ZrgZVJPj$5Wc*#D==1Ll5)eZH%pqrv*%-h^M;tFW@~R^ch7=X5$l
zDF;(xAjs$^2@?NW{#{um+faU+!C#kgx>XU}s&2|SuF{6qkIb%6xXA1QQPXH!{(Xr{ttw0{ywz;>Bt><+PbX)QYa$;k;1@s9!32+1nRW2t0@SwY
zIa=w|7TNy-j~f~@%XTsCr{(~%V-c^F6=G0$k0lB&aH$DY=p={Z{Q2CG91O~B(IzIx7v$_nMR>hM}xkcjIEZUWCpAh6wJ+>cm1G0vQc
z>{-uGkvZn$e1JHAgF7kQ$m1@@ItFj%z0?c@+zK^t#)C^DOW&mPi}Krv7BPOQ56t-y
z&zjq|@whoNF7CFORNIl4;!~90Yfg^k`Sx?6x1TP42k|xXAuauD>!AJSuYfFCJ@lQXAiIUy*&
z9)zF4RVj&_I>Y0knUUGM!IpFUcp1+K6F4~b2t9oD98ROr7x;n>&S0YXg|CotXA2(S
z4_@TkWc(ja$RkHDQ{R~8HE;7q&_;zukh8zheV!33^YEqN>)&}iHZolMA?E}YU4=m;
z;u^n87E*`;ta&!v9yW9n^rZK7x=FD$;`Ix$h`9h
z=4$o*a1F`6MR!Hkt?N(7!P@eKHMOC^Wc+QqJ^YJK~BZGH2!Kh|b+;21_B0|6!&s5>2
zuK_Hz;bd(W0oM*j#Qm-tY3(ZD4yNEqWKTB%Ym4FRH3n-7-%=QkJA|gAoB+#7M=tgh
zuu>UYS+As;0<0+=`Lnk`{)^pSSb&A4BkEWIrwLU-z25j^92NspsH`bNNv{F_Lk-qe
zcak{hf7qu523TM^G9q3WBx?&&3#sJyp+d0==6GTOuPxN
zQk5h82kzg)?GLXv^PrF(>1l~W#z&5SPWVl$&VyVcC_XIGjTcI-YAF?yMqVPF@T*pJ>~W@y+IW`-BL
zzszv4(O;uxsA?PG;3#3hNP34lu0^mV{)Io&O~ywlvqnk%ZX;;`K1!M8aV@sL`>LKQ
zViqa?{-3I+Y!C5K%FH6aXo?#7!|WjQ6yE<@p>ed(rH)#_pEIIr`~?_`sF|sz7!9nM
z+33Ki5sJ~9+-7EkV)W*=nOW<=s5y$!pqp*snB{U1*>DIpr8zkd;*Jl0*ihE
zi+KX;@dVcE32Z3dNKl3JkwilO7C+LNjda!`7))`a-j6j|AVAU^l|x5N>@hjRXTbHq|t-j
zW6@AD{5@7UhQF{lG)}mMABEo=FEn`2B;qi2y+wyH7jg=O2K>@?wm_JG-`Iu}3P${>
zHKtIYA5vx%3ZtE9DpB4FCkln^N%U9S^{ia$S+&+Pck7vR^~{xeHlX!v=oYg&t!HIg
z&xWs_6=^*iu6kCY^{hhcS%KEG`m9G|ONwwB=EAKaArYI{3BovRS|DiWV^9D{b^x%L0=gSb*pemj{n6j1YRx?98q|AiI9WMl@cKXo8G0u
zFl-i<3S+Q2UCOj~pUAM6CJKQ#U|S~QEFB3qCgKh<5(Z6TP2(gX8?iH!P|HY&C_|ki
zVP2Uq3Y+iC7%`+ARgZ*OMM&B31`($3AQY_SdQC5
z76jRZLD-D9;g*yIYi&XrHvh2+DcJOyjDBRnoXL#%>0}`eu}70xH4T~~^u*tmRZS6M
zv3YX}u5g*~+Z3S>HbGNSXC{oFDh$Qu^{GfqhaV_09gG!7OozM*K?r4^QC^`H>}49PtH919;8X>69s%ZQLW(>4LUQpXO!lN^HSCxz_~D1M@IZ|e*a+A@O^8Ob
zXQm11Sd2m?CMp@`O3krKArrBn=|U*zA)Uw<^qDGK{Gb(%jj{99uRnGw2z-
zK2M0mZx(ttI5t=B0@tf>Sh38jgb~=JRpam^15{(mlHpu6j#4tj)Uakj4US7Pd?hue
zT49VE)4bS*nom!Km>EJGyY_Njkmfqt46)5VAz*0(gICloOH+cW1E_SZ8DDCd0bf%%>Z(vG9^1X%1^v
z%we%yo5NDj?-^kv@|vaQveXQi%d|Al6$T>j>$&J*3UKp;3ODw>Yxg=de_%bRs?mJ2
z$>qovqG69*{}g6-8V{-+8C64_^jZhVOsiZgg@p9{o3!lv~mzB
zP*#UKATBC(!f0%Q=L^%ZS%!_IG;Av>{bws&s2A`aO}@#}wfCO70Ao*qPZtRJwD&@x
z5Ss-HF}*2pZXrgS0==KZjW-3BOU>=)gt3z5UGJdg+;?Hkb3zKcfAW%xlQ~@SE^_U5
zQf{KIs=TD2bVkvX7DWQ|F9=1F8r3coe14Y{^?bd_2M)Y|WrPvEzyjl5WUeiIQOHB$
znHQOdgBCFlS4z#jMOXkSkh@qI=gy2D*pE63@kLJ6jFVt~g>N`KTr9YwjB7nh`qX-%
z46zeZGq{0an;LMHO979Un5FWU1gn($$U_iaDa6prAEkCsQ6m;|3VwTLY2Vez-11q1
zrH}%)CBj5(jxWK=PXW`*xPs)sxRuJR~jPd3<7NezgChrN^b-d0=&TtNN
zStg`vnB-^Y;eHbqU;GBMC%xp*%cGwIUo8`oByHdSg4*bmX3GY>^tWhDoGZej6Rmb0KMq=qcV
z^)d%;EEl?|5+S%1bCwGwt=J(KcDD)x*stO
z%>@E%k9q(?JYoZ1!6SVxJTEmzUcogp7u2ufLY)LdX_Ej8U&T>MfG=Lf!bpIq6*vS5
z@WKil&jh%=BtXq7*5y;F@ovL9Nr2Kep)WeQstq^34A|d>
zb1(z^SEH{PP_i0%xv+Az5P-YdKH6l#57^|hukO#|0kJHvEKl0ozQ=9N_U?JQw=wSD
zT2&|R*$yuIihl@CG97(??cky4jhV)xk{!?K(7`3(-jg4keZ-k4_1`Aq_f5n}yHaL*t{&rK(9eMi6h;3LlF@qgQJ|K=3iL;c0;Ojv&^x0Q
zNK>Lf_0uRsMxBTlzcqrL8Yj#{3WGK-R3Q7M3bd1+DM!NDg^_}jTlrH@g@%T@fU3qR
zmLxwHSxUyP_(^k7OQS*hx7&iE5?gI`O+j&ORaHSob&GA^1@%)_v)UR8hyI8R
zbPQKpW7LblbDp!Wi^S`pwhjgN>yg3siE3*)biW?yZ$C_J9RtI!N1E;P)z(Qc?RsRO
zeYx5?3znjs=Nz@QnVR&IOu~ZGk@!2*<|vK*GPQLzoWCB)*}tx~t_PPJkzMRJs;!$L
z?nY#U{hMm*ZkTu@vYY)Lwe=vpO1Yn_t*7Ag8F@ABZGEhUqMMN+bt*fnlO5WZ|5@2)##3-c8l%bIp(;pLSw-u?SgN5|JOosJa>ulIBXdbLJ@KA)*T`q>KfXFKHdj6z#JSAnAG@tSF#
zwLpPRKd(TGUXY<$+dB@EF~$}+e$vo`%+K#S&?M#KLA@e;WJ$ZQ|00@?8_fd#)B8f7
z0ODEOHG`An=d>#FMJp62v5i7x_G?|kT~sNgZGG2^cCKvEUq=tsDP+m!u8BH{60(I+
zPVeg)s53B`f%J^bpwMlM=lNyVbdAJQy`}JOGl*1t+cnYDlS${&6EK60wnNX-b1$QH
z-Kju+^oW~6F8!zLD^YcfXC(^nVLS9_uR>e8Pk|cVQ=me6q-A}7YKI!$S7=@b6e#~A
z1$yIS1v>hP0tugaC}74x3K17`w7&*Z#)m{(9i;@lcZ6~3_-OnumK1WQOLU^AE8AtZ
ze}kMHlH5Pq8-IpR@`ptiI$*nhc=V)@2qsZ|ib~KuXVX~)T1-!>jOKTq^&eIp{iQwj
zGtG+jwRfVNYFo`kh+ZBY#y+KyiF2dZ`UbHs;q*w!pm%>$pw{1+8h&~7FOCMrd+xf-
ztF;})y{-njw+dZI`pW3~aCf>9RNJN(swe|mg$B?Dg|n-QJ@XA
o3Y0rThH7n7E10#yv!Su1cSyG$E?W9C$7);P97?aPoe=&108EFf^Z)<=

diff --git a/docs/searchindex.js b/docs/searchindex.js
index 22c98ed8..1ad909db 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["Beaver", "Cheetah", "HNMFk", "NMFk", "RESCALk", "SymNMFk", "TELF", "TELF.factorization", "TELF.factorization.decompositions", "TELF.factorization.decompositions.utilities", "TELF.factorization.utilities", "TELF.pre_processing", "TELF.pre_processing.Beaver", "TELF.pre_processing.Vulture", "TELF.pre_processing.Vulture.tokens_analysis", "TriNMFk", "Vulture", "index", "modules"], "filenames": ["Beaver.rst", "Cheetah.rst", "HNMFk.rst", "NMFk.rst", "RESCALk.rst", "SymNMFk.rst", "TELF.rst", "TELF.factorization.rst", "TELF.factorization.decompositions.rst", "TELF.factorization.decompositions.utilities.rst", "TELF.factorization.utilities.rst", "TELF.pre_processing.rst", "TELF.pre_processing.Beaver.rst", "TELF.pre_processing.Vulture.rst", "TELF.pre_processing.Vulture.tokens_analysis.rst", "TriNMFk.rst", "Vulture.rst", "index.rst", "modules.rst"], "titles": ["TELF.pre_processing.Beaver: Fast matrix and tensor building tool", "TELF.applications.Cheetah: Advanced search by keywords and phrases", "TELF.factorization.HNMFk: Hierarchical Non-negative Matrix Factorization with Automatic Model Determination", "TELF.factorization.NMFk: Non-negative Matrix Factorization with Automatic Model Determination", "TELF.factorization.RESCALk: RESCAL with Automatic Model Determination", "TELF.factorization.SymNMFk: Symmetric Non-negative Matrix Factorization with Automatic Model Determination", "TELF package", "TELF.factorization package", "TELF.factorization.decompositions package", "TELF.factorization.decompositions.utilities package", "TELF.factorization.utilities package", "TELF.pre_processing package", "TELF.pre_processing.Beaver package", "TELF.pre_processing.Vulture package", "TELF.pre_processing.Vulture.tokens_analysis package", "TELF.factorization.TriNMFk: NMFk with Automatic Determination of Latent Clusters and Patterns", "TELF.pre_processing.Vulture: Advanced text pre-processing and cleaning tool for NLP and text-mining", "Tensor Extraction of Latent Features (T-ELF)", "TELF"], "terms": {"i": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17], "sever": 0, "can": [0, 1, 2, 3, 4, 7, 15, 16, 17], "found": [0, 1, 3, 4, 16], "here": [0, 2, 3, 4, 5, 12, 15, 16, 17], "we": [0, 2, 3, 4, 15, 16], "show": [0, 3, 4, 7, 10, 15], "usag": [0, 5], "creat": [0, 1, 3, 4, 7, 9, 10, 12, 13, 16, 17], "document": [0, 1, 7, 10, 12, 13, 14, 15, 16, 17], "word": [0, 1, 10, 12, 14], "first": [0, 2, 3, 4, 7, 9, 10, 12, 15, 16], "let": [0, 16], "": [0, 1, 2, 3, 4, 5, 7, 8, 9, 12, 13, 15, 16, 17], "load": [0, 2, 16, 17], "dataset": [0, 1, 12, 16, 17], "import": [0, 3, 4, 10, 15, 16], "panda": [0, 1, 16], "pd": [0, 1, 12, 14, 16], "df": [0, 10, 13, 14, 16], "read_csv": 0, "data": [0, 1, 2, 3, 4, 7, 10, 12, 15, 16, 17], "sampl": [0, 1, 2, 3, 4, 7], "csv": [0, 1, 12], "info": 0, "next": [0, 15], "vocabulari": [0, 10, 12], "from": [0, 2, 3, 4, 7, 9, 10, 12, 15, 16, 17], "set": [0, 1, 2, 3, 4, 7, 9, 12, 13, 15, 16, 17], "target_column": [0, 12], "clean_abstract": 0, "min_df": [0, 12], "10": [0, 2, 3, 4, 7, 12, 14, 15, 16, 17], "max_df": [0, 12], "0": [0, 3, 4, 5, 7, 8, 9, 10, 12, 15, 16, 17], "5": [0, 1, 12, 15, 17], "get_vocabulari": [0, 11, 12], "option": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15, 17], "matrix_typ": [0, 12], "tfidf": [0, 7, 10, 11, 12], "highlight": [0, 12], "aberr": 0, "abil": 0, "ablat": 0, "abl": 0, "weight": [0, 3, 7, 12], "2": [0, 2, 4, 8, 12, 17], "save_path": [0, 1, 3, 4, 5, 7, 11, 12, 13, 15, 16], "documents_word": [0, 11, 12], "cam": 0, "scipi": [0, 2, 3, 4, 7, 9, 10, 12, 15], "spars": [0, 2, 3, 4, 7, 8, 9, 10, 12, 15], "ss": 0, "save": [0, 1, 2, 3, 4, 7, 10, 12, 14, 15], "file": [0, 1, 10, 17], "which": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "coo": 0, "format": [0, 2, 8, 10], "x_csr_spars": 0, "load_npz": 0, "npz": 0, "2022": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "triad": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nation": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "secur": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "llc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "all": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "right": [0, 3, 4, 5, 7, 8, 9, 10, 12, 13, 15, 16, 17], "reserv": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "thi": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 15, 16, 17], "program": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "wa": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "produc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "under": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "u": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "govern": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "contract": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "89233218cna000001": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "lo": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "alamo": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "laboratori": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "lanl": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "oper": [0, 2, 3, 4, 5, 7, 10, 11, 12, 13, 15, 16, 17], "depart": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "energi": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nuclear": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "administr": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "ar": [0, 1, 3, 4, 5, 7, 9, 10, 12, 13, 14, 15, 16, 17], "The": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 14, 15, 16, 17], "grant": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "itself": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "other": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "act": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "its": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "behalf": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nonexclus": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "paid": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "up": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "irrevoc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "worldwid": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "licens": [0, 3, 4, 5, 7, 12, 13, 15, 16], "materi": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "reproduc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "prepar": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "deriv": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "work": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "distribut": [0, 3, 4, 5, 7, 9, 12, 13, 15, 16, 17], "copi": [0, 3, 4, 5, 7, 9, 12, 13, 15, 16, 17], "public": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "perform": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "publicli": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "displai": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "permit": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "do": [0, 2, 3, 4, 5, 7, 10, 12, 13, 15, 16, 17], "so": [0, 2, 3, 4, 5, 7, 8, 12, 13, 15, 16, 17], "class": [0, 1, 2, 3, 4, 5, 7, 10, 12, 13, 15, 16], "n_node": [0, 2, 3, 4, 5, 7, 11, 12, 13, 16], "1": [0, 1, 2, 3, 4, 5, 7, 8, 9, 12, 13, 14, 15, 16, 17], "n_job": [0, 3, 4, 5, 7, 10, 11, 12, 13, 15, 16], "sourc": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17], "base": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "object": [0, 1, 2, 3, 4, 5, 7, 8, 12, 13, 15, 16], "supported_output_format": [0, 11, 12], "pydata": [0, 12], "citation_tensor": [0, 11, 12], "datafram": [0, 1, 12, 14], "tupl": [0, 7, 10, 12, 13, 15, 16], "author_id": [0, 1, 12], "paper_id": [0, 12], "refer": [0, 12], "year": [0, 1, 12, 17], "dimension_ord": [0, 12], "list": [0, 1, 2, 3, 4, 7, 8, 10, 12, 13, 14, 15, 16, 17], "split_authors_with": [0, 12], "str": [0, 1, 2, 3, 4, 7, 10, 12, 14, 15], "split_references_with": [0, 12], "none": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16], "int": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 13, 14, 15, 16], "joblib_backend": [0, 12], "loki": [0, 12, 13, 16], "verbos": [0, 1, 2, 3, 4, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16], "bool": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15], "fals": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16], "return_object": [0, 12], "true": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 14, 15], "output_mod": [0, 12], "an": [0, 1, 3, 4, 7, 9, 12, 15, 17], "author": [0, 1, 10, 12], "paper": [0, 1, 12], "time": [0, 1, 2, 3, 4, 7, 8, 9, 12, 14, 15], "non": [0, 7, 9, 12, 15, 17], "zero": [0, 8, 9, 12], "entri": [0, 1, 10, 12], "x": [0, 2, 3, 4, 5, 7, 8, 9, 10, 12, 15], "j": [0, 8, 9, 12], "k": [0, 2, 3, 4, 5, 7, 8, 9, 10, 12, 15, 17], "mean": [0, 9, 12], "cite": [0, 12], "paramet": [0, 2, 3, 4, 7, 8, 9, 12, 13, 14, 15, 16], "contain": [0, 1, 9, 10, 12, 13, 16], "target": [0, 9, 12], "column": [0, 1, 2, 3, 4, 7, 9, 12, 13, 14, 15, 16], "name": [0, 1, 3, 4, 5, 7, 10, 12, 15, 17], "default": [0, 1, 2, 3, 4, 7, 9, 10, 12, 14, 15], "when": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15, 17], "assign": [0, 9, 12], "type": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15], "order": [0, 1, 9, 10, 12, 16], "should": [0, 1, 2, 3, 7, 12, 15], "preserv": [0, 1, 12], "e": [0, 12, 17], "g": [0, 12], "come": [0, 12], "last": [0, 1, 12], "dimens": [0, 9, 12], "appear": [0, 1, 12], "For": [0, 1, 2, 12], "what": [0, 3, 4, 7, 12], "symbol": [0, 12], "us": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 15, 17], "get": [0, 1, 12, 17], "individu": [0, 12], "element": [0, 9, 10, 12], "string": [0, 1, 10, 12], "If": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15], "output": [0, 3, 4, 7, 8, 9, 10, 12, 16], "number": [0, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15, 17], "node": [0, 1, 2, 3, 4, 7, 10, 12, 13, 16, 17], "job": [0, 2, 3, 4, 7, 12, 15], "joblib": [0, 12], "parallel": [0, 3, 4, 7, 12, 13, 15, 16], "backend": [0, 12, 13, 16], "multiprocess": [0, 12, 13, 16], "vebos": [0, 1, 12], "flag": [0, 1, 9, 12, 14], "determin": [0, 1, 7, 12, 17], "whether": [0, 9, 12, 17], "gener": [0, 1, 2, 3, 4, 7, 9, 12, 15], "return": [0, 2, 3, 4, 7, 8, 9, 12, 14, 15], "In": [0, 10, 12], "case": [0, 10, 12], "larg": [0, 12, 17], "mai": [0, 10, 12, 17], "better": [0, 12], "disk": [0, 12], "without": [0, 12, 17], "see": [0, 1, 5, 7, 12, 15, 17], "support": [0, 1, 12], "coauthor_tensor": [0, 11, 12], "authorid": [0, 12], "authors_idx_map": [0, 12], "dict": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15], "time_idx_map": [0, 12], "co": [0, 9, 10, 12], "second": [0, 1, 12], "index": [0, 1, 2, 10, 12, 17], "map": [0, 1, 12], "pass": [0, 1, 3, 4, 7, 12, 16], "cocitation_tensor": [0, 11, 12], "note": [0, 1, 3, 4, 5, 7, 10, 12, 15], "normal": [0, 12, 13, 16], "two": [0, 1, 12], "b": [0, 1, 9, 12, 13, 16, 17], "where": [0, 1, 2, 9, 10, 12], "n": [0, 1, 8, 9, 12, 13, 14, 16, 17], "singl": [0, 1, 2, 9, 10, 12], "receiv": [0, 12], "citat": [0, 12], "each": [0, 2, 3, 4, 7, 9, 10, 12, 15], "cooccurrence_matrix": [0, 11, 12], "abstract": [0, 1, 12], "cooccurrence_set": [0, 12], "sppmi_set": [0, 12], "occur": [0, 10, 12, 14], "sppmi": [0, 6, 7, 10, 11], "text": [0, 1, 8, 10, 12, 14, 17], "token": [0, 1, 12, 14], "retriv": [0, 12], "via": [0, 12, 17], "empti": [0, 1, 3, 7, 12], "space": [0, 10, 12], "window_s": [0, 1, 10, 12], "20": [0, 3, 4, 5, 7, 10, 12, 15], "dens": [0, 3, 4, 9, 10, 12, 15], "sentenc": [0, 10, 12], "shift": [0, 10, 12], "4": [0, 1, 3, 4, 7, 10, 12, 15, 17], "vector": [0, 6, 7, 9, 11], "tf": [0, 10, 12, 14], "idf": [0, 10, 12], "count": [0, 7, 10, 11, 12], "float": [0, 1, 3, 4, 7, 9, 12], "get_ngram": [0, 11, 12], "limit": [0, 12, 17], "gram": [0, 1, 12, 14], "restrict": [0, 12], "top": [0, 8, 12, 14], "ngram": [0, 1, 12], "max_featur": [0, 12], "kwarg": [0, 9, 10, 12], "ignor": [0, 1, 12], "term": [0, 1, 12, 14], "have": [0, 12], "frequenc": [0, 12, 14], "strictli": [0, 12], "higher": [0, 12], "than": [0, 1, 12], "given": [0, 1, 2, 3, 4, 7, 9, 12, 13, 14, 15, 16], "threshold": [0, 3, 7, 12], "corpu": [0, 12], "specif": [0, 12, 13, 16, 17], "stop": [0, 2, 3, 7, 12, 15], "rang": [0, 2, 3, 4, 7, 12, 15], "repres": [0, 12, 13, 16], "proport": [0, 12], "integ": [0, 12], "absolut": [0, 12], "lower": [0, 12], "valu": [0, 1, 2, 3, 4, 7, 10, 12, 13, 14, 15, 16], "also": [0, 10, 12], "call": [0, 1, 8, 10, 12], "cut": [0, 12, 17], "off": [0, 9, 12], "literatur": [0, 12], "onli": [0, 1, 2, 3, 4, 7, 12, 15, 17], "consid": [0, 12], "across": [0, 12, 17], "properti": [0, 1, 12, 13, 16], "participation_tensor": [0, 11, 12], "boolean": [0, 9, 12], "publish": [0, 1, 12], "something_word": [0, 11, 12], "split_something_with": [0, 12], "someth": [0, 12], "specifi": [0, 1, 2, 3, 4, 7, 12, 15], "variabl": [0, 2, 12], "evel": [0, 12], "seper": [0, 2, 12], "autho1": [0, 12], "author2": [0, 12], "inform": [0, 2, 10, 12, 17], "something_words_tim": [0, 11, 12], "tfidf_transform": [0, 12], "unfold_at": [0, 12], "unfold": [0, 8, 9, 11, 12], "over": [0, 3, 4, 7, 12], "tool": [1, 13, 17], "custom": [1, 2, 3, 7, 9], "fast": [1, 12, 13, 16, 17], "tue": 1, "feb": 1, "15": 1, "17": 1, "05": 1, "54": 1, "maksimekineren": [1, 10, 12], "init": [1, 3, 4, 7, 15], "affili": 1, "titl": [1, 17], "retriev": 1, "A": [1, 8, 9, 10, 17], "dictionari": [1, 2, 8, 10, 14], "kei": [1, 10, 13, 14, 16], "classmethod": 1, "find_ngram": 1, "queri": 1, "within": 1, "slide": 1, "window": [1, 10, 12], "algorithm": [1, 8, 9, 12], "need": [1, 8], "maintain": 1, "posit": [1, 10, 12, 17], "match": 1, "multipl": [1, 3, 7, 8, 10], "separ": [1, 10], "whitespac": 1, "check": 1, "duplic": 1, "allow": 1, "size": [1, 2, 10, 12], "len": [1, 14], "ever": 1, "cannot": [1, 2], "fit": [1, 2, 3, 4, 5, 6, 7, 15, 17], "otherwis": [1, 17], "index_fil": 1, "reindex": 1, "indic": [1, 2, 8, 9, 10, 12], "select": [1, 2, 7, 15], "expect": 1, "respect": [1, 13, 16], "slic": 1, "structur": [1, 17], "exampl": [1, 2, 5, 7, 12, 17], "notebook": 1, "pre": [1, 3, 4, 13, 15, 17], "process": [1, 2, 3, 4, 7, 10, 13, 17], "vultur": [1, 6, 11, 17], "simpl": [1, 3, 4, 7, 13, 16], "clean": [1, 11, 13, 17], "lowercas": 1, "special": [1, 17], "charact": [1, 10], "remov": [1, 3, 4, 7, 9, 15], "delimit": 1, "categori": 1, "correspond": [1, 9, 13, 16], "current": [1, 2, 10], "path": [1, 3, 4, 10, 15, 16], "previous": 1, "one": [1, 2, 14, 17], "doe": 1, "exist": 1, "them": 1, "futur": 1, "new": 1, "overwrit": 1, "ngram_ord": 1, "statu": 1, "ngram_window_s": 1, "numer": 1, "either": [1, 3, 4, 15], "union": 1, "and_search": 1, "in_titl": 1, "in_abstract": 1, "author_filt": 1, "affiliation_filt": 1, "country_filt": 1, "year_filt": 1, "do_results_t": 1, "link_search": 1, "filter": [1, 3, 7], "both": [1, 7, 15, 17], "result": [1, 2, 3, 4, 7, 15, 16, 17], "intersect": 1, "try": [1, 2, 16], "never": 1, "error": [1, 3, 4, 7, 9, 15, 17], "nonetyp": 1, "lookup": 1, "split": [1, 13, 16], "convert": 1, "lowecas": 1, "strip": 1, "extra": 1, "laser": 1, "neg": [1, 7, 15, 17], "angl": [1, 9], "deflect": 1, "bigram": 1, "blue": 1, "green": 1, "unigram": 1, "appli": [1, 7, 15, 17], "being": [1, 9, 10], "look": 1, "simulten": 1, "between": [1, 10], "subset": 1, "defin": [1, 2], "id": [1, 14], "countri": 1, "more": [1, 3, 7, 13, 16], "how": [1, 2, 13, 14, 16], "mani": [1, 13, 14, 16], "examin": 1, "aa": 1, "bb": 1, "cc": 1, "dd": 1, "greater": 1, "length": 1, "while": [1, 10], "tabl": [1, 14], "provid": [1, 3, 4, 15, 17], "explain": 1, "why": 1, "certain": 1, "were": 1, "argument": [1, 8, 9], "control": 1, "link": [1, 17], "inclus": 1, "step": [1, 2, 13, 16, 17], "take": [1, 10], "howev": [1, 17], "partner": 1, "overrid": 1, "sinc": 1, "anoth": 1, "had": 1, "alreadi": [1, 9], "topic": [1, 2], "henc": 1, "return_data": 1, "results_t": 1, "add_with_union_of_oth": [1, 17], "d": [1, 8, 13, 16, 17], "comput": [1, 3, 4, 7, 9, 10, 12, 15, 16, 17], "addit": [1, 2], "associ": 1, "ad": 1, "whose": [1, 10], "modifi": 1, "valueerror": 1, "includ": [2, 3, 4, 7, 15, 17], "miss": [2, 3, 7], "predict": [2, 3, 4, 7, 15], "ha": [2, 3, 4, 7, 9, 15, 16], "hpc": [2, 3, 4, 7, 17], "schedul": 2, "200": [2, 3], "complet": [2, 3, 7], "300": 2, "signal": 2, "exit": 2, "400": 2, "nmfk_param": [2, 7, 15], "cluster_on": 2, "h": [2, 3, 7, 8, 9, 10, 15], "depth": 2, "sample_thresh": 2, "ks_deep_min": 2, "ks_deep_max": 2, "ks_deep_step": 2, "k2": 2, "experiment_nam": [2, 7, 15], "hnmfk_output": 2, "generate_x_callback": 2, "comm_buff_s": 2, "10000000": 2, "capabl": [2, 3, 4, 5, 7, 15, 16], "nmfk": [2, 6, 17, 18], "same": [2, 8], "item": 2, "hmmfk": 2, "append": [2, 3, 4, 8, 15], "nmfk_params0": 2, "nmfk_params1": 2, "nmfk_params2": 2, "requir": 2, "param": [2, 3, 4, 9, 12], "collect_output": [2, 3, 4, 5, 7, 15], "save_output": [2, 3, 4, 5, 7], "predict_k": [2, 3, 7, 15], "cluster": [2, 6, 7, 8, 17], "w": [2, 3, 7, 8, 9, 12, 13, 15, 16], "ff": 2, "row": [2, 3, 4, 7, 8, 9, 15], "deep": 2, "go": 2, "after": [2, 3, 7, 15], "root": 2, "goe": 2, "until": 2, "further": 2, "criteria": [2, 3, 7, 15], "num": [2, 9], "search": [2, 17], "minimum": 2, "start": 2, "optin": 2, "maximum": [2, 3, 4, 7, 9], "parent": 2, "decomposit": [2, 3, 6, 7], "done": [2, 3, 4, 7, 15], "instead": 2, "find": [2, 9], "stabl": [2, 9], "latent": [2, 3, 4, 7], "featur": 2, "re": [2, 13, 16], "befor": [2, 3, 7, 15], "slice": [2, 9], "origin": [2, 3, 4, 7], "taken": 2, "equal": 2, "serial": 2, "def": 2, "__call__": 2, "original_indic": 2, "new_x": 2, "save_at_nod": 2, "hyper": 2, "user_node_data": 2, "print": [2, 10, 12], "progress": [2, 3, 4, 7, 10, 12, 15], "from_checkpoint": 2, "save_checkpoint": 2, "input": [2, 3, 4, 7, 8, 9, 10, 12, 15], "np": [2, 3, 4, 7, 9, 10, 12, 15], "ndarrai": [2, 3, 4, 7, 8, 9, 10, 12, 15], "_csr": [2, 3, 4, 7, 9, 15], "csr_matrix": [2, 3, 4, 7, 9, 10, 15], "continu": 2, "checkpoint": 2, "get_nod": 2, "graph": 2, "iter": [2, 3, 4, 7, 8, 9, 15], "onlin": 2, "kept": 2, "memori": 2, "go_to_children": 2, "idx": 2, "child": 2, "go_to_par": 2, "go_to_root": 2, "traverse_nod": 2, "persist": 2, "node_nam": 2, "parent_top": 2, "parent_node_nam": 2, "child_node_nam": 2, "num_sampl": 2, "leaf": 2, "onlinenod": [2, 17], "node_path": 2, "parent_nod": 2, "child_nod": 2, "synthet": [3, 4, 15], "It": [3, 4, 13, 15, 16], "script": [3, 4, 15], "locat": [3, 4, 7, 10, 14, 15, 17], "sy": [3, 4, 15], "generate_x": [3, 4, 15], "gen_data": [3, 4], "gen_data_spars": 3, "xsp": 3, "shape": [3, 4, 7, 9, 12, 15], "100": [3, 4, 7, 8, 9, 15, 17], "densiti": 3, "01": [3, 15], "r": [3, 4, 8, 9, 17], "now": [3, 4, 16], "n_perturb": [3, 4, 5, 7, 15], "36": 3, "n_iter": [3, 4, 5, 7, 15], "epsilon": [3, 4, 5, 7, 9, 15], "015": [3, 4, 5, 7], "nnsvd": [3, 4, 7, 8, 15], "use_gpu": [3, 4, 5, 7, 8, 9, 10, 15], "predict_k_method": [3, 7, 15], "sill": [3, 7, 15], "nmf_verbos": [3, 5, 7, 8, 15], "transpos": [3, 4, 5, 7, 15], "sill_thresh": [3, 7, 15], "9": [3, 10, 16], "prune": [3, 4, 7, 8, 9, 15], "nmf_method": [3, 5, 7, 15], "nmf_kl_mu": [3, 6, 7], "calculate_error": [3, 4, 7, 10, 15], "use_consensus_stop": [3, 5, 7, 8, 15], "calculate_pac": [3, 5, 7, 15], "perturb_typ": [3, 4, 5, 7, 15], "uniform": [3, 4, 5, 7, 9, 15], "11": [3, 17], "example_nmfk": 3, "run": [3, 4, 16], "plot": [3, 4, 7, 9, 10, 15], "estim": [3, 4, 7, 15, 17], "rank": [3, 4, 7, 9, 17], "perturb_verbos": [3, 4, 5, 7], "8": [3, 4, 7, 15], "nmf_func": [3, 7], "nmf_fro_mu": [3, 6, 7, 15], "nmf_obj_param": [3, 5, 7], "perturb_multiprocess": [3, 4, 5, 7], "consensus_mat": [3, 7, 15], "mask": [3, 5, 7, 8, 9, 15], "get_plot_data": [3, 4, 5, 7, 15], "simple_plot": [3, 4, 7, 10, 15], "bootstrap": [3, 4, 7, 15], "random": [3, 4, 5, 7, 9], "matric": [3, 4, 7, 8, 9, 12, 15], "around": [3, 4, 7], "nmf": [3, 7, 8, 9, 10, 15], "amount": [3, 4, 7, 9], "poisson": [3, 4, 7, 8, 9], "poission": [3, 4, 7], "resourc": [3, 4, 7, 15], "initil": [3, 4, 7, 8, 15], "procedur": [3, 4, 7], "gpu": [3, 4, 7, 9, 15, 17], "collect": [3, 4, 7, 14], "even": [3, 7, 17], "figur": [3, 7], "method": [3, 7, 8, 9, 15], "pvalu": [3, 7], "l": [3, 7, 13, 16], "statist": [3, 4, 7, 14, 17], "wise": [3, 7], "silhouett": [3, 4, 7, 8, 15], "score": [3, 4, 7, 9, 15], "significantli": [3, 7, 13, 16], "longer": [3, 4, 7], "altough": [3, 7], "accur": [3, 7], "hand": [3, 7], "much": [3, 7], "faster": [3, 7], "perturb": [3, 4, 7, 9], "func": [3, 4, 7], "frobeni": [3, 4, 7], "norm": [3, 4, 7, 8, 9], "updat": [3, 7, 8], "rule": [3, 7], "kl": [3, 7, 8], "diverg": [3, 7, 8], "nmf_recommend": [3, 7], "recommend": [3, 7], "collabor": [3, 7], "wnmf": [3, 7], "possibl": [3, 7, 17], "left": [3, 7, 8, 9, 10], "min": [3, 7], "calcul": [3, 4, 7, 9], "rel": [3, 4, 7, 9], "reconstruct": [3, 4, 7], "make": [3, 4, 7, 17], "consensu": [3, 7, 9, 15], "earli": [3, 7, 15], "numpi": [3, 7, 9, 10, 15], "arrai": [3, 7, 8, 9, 10, 12, 15, 17], "point": [3, 7, 9, 15], "out": [3, 7, 10, 15, 17], "dure": [3, 7, 15], "pac": [3, 7, 9, 15], "stabil": [3, 7], "intermidi": [3, 4, 7], "hide": [3, 4, 7], "averag": [3, 4, 7], "experi": [3, 4, 7, 10, 15], "log": [3, 4, 7, 8, 10, 15], "took": [3, 4, 7, 15], "depend": [3, 4, 7, 15, 17], "field": [3, 4, 7, 15, 17], "plot_data": [3, 4, 7, 15], "k_predict": [3, 7, 10, 15], "intig": [3, 7, 15], "alwai": [3, 4, 7, 15], "give": [3, 4, 7, 15], "total": [3, 4, 7, 14, 15], "recalk": 4, "matrix": [4, 7, 8, 9, 10, 12, 15, 17], "1000": [4, 5, 8, 9], "gen": 4, "rescal_verbos": [4, 7, 8], "rescal_method": [4, 7], "rescal_fro_mu": [4, 6, 7], "7": [4, 5], "rescal_func": [4, 7], "rescal_obj_param": [4, 7], "implement": [4, 7], "yet": [4, 7], "symmetr": [4, 7, 17], "init_typ": 5, "newton": 5, "graph_typ": 5, "full": 5, "similarity_typ": 5, "gaussian": 5, "nearest_neighbor": 5, "pac_thresh": 5, "factor": [6, 12, 17, 18], "nmf_fro_admm": [6, 7], "nmf_kl_admm": [6, 7], "nmf_mc_fro_mu": [6, 7], "tri_nmf_fro_mu": [6, 7], "util": [6, 7, 8], "co_occurance_matrix": [6, 7], "organize_n_job": [6, 7], "plot_nmfk": [6, 7], "pvalue_analysi": [6, 7], "sppmi_matrix": [6, 7, 12], "take_not": [6, 7], "rescalk": [6, 17, 18], "trinmfk": [6, 17, 18], "fit_nmfk": [6, 7, 15], "fit_tri_nmfk": [6, 7, 15], "pre_process": [6, 17, 18], "beaver": [6, 11, 17], "cooccurr": [6, 10, 11], "tenmat": [6, 11], "bool_clust": [7, 8], "bool_nois": [7, 8], "concensus_matrix": [7, 8], "data_reshap": [7, 8], "generic_util": [7, 8], "math_util": [7, 8], "resampl": [7, 8], "h_updat": [7, 8], "w_updat": [7, 8], "h_update_admm": [7, 8], "h_update_mu": [7, 8], "w_update_admm": [7, 8], "w_update_mu": [7, 8], "coord_desc_thresh": [7, 8], "coord_desc_thresh_onefactor": [7, 8], "find_thres_wh": [7, 8], "nmf_with_admm": [7, 8], "old_find_thres_wh": [7, 8], "old_nmf": [7, 8], "roc_w_h": [7, 8], "thres_norm": [7, 8], "a_upd": [7, 8], "r_updat": [7, 8], "rescal": [7, 8, 17], "s_updat": [7, 8], "trinmf": [7, 8], "h_cluster": [7, 10], "plot_h_clust": [7, 10], "co_occurr": [7, 10, 11, 12], "plot_bnmfk": [7, 10], "plot_symnmfk": [7, 10], "plot_consensus_mat": [7, 10], "plot_cophenetic_coeff": [7, 10], "append_to_not": [7, 10], "format_not": [7, 10], "take_note_fmat": [7, 10], "automat": [7, 13, 16, 17], "model": [7, 15, 17], "avail": [7, 17], "function": [7, 8, 10, 12, 17], "alpha": [7, 8, 15], "n_init": [7, 15], "pattern": [7, 13, 16, 17], "wk": [7, 15], "hk": [7, 15], "rate": [7, 15], "k1k2": [7, 15], "3": [7, 12, 15, 17], "mix": [7, 15], "along": [7, 12, 15], "custom_bool_clust": [8, 9], "add_bool_nois": [8, 9], "add_bool_posneg_nois": [8, 9], "custom_k_mean": [8, 9], "compute_connectivity_mat": [8, 9], "compute_consensus_matrix": [8, 9], "reorder_con_mat": [8, 9], "fold": [8, 9, 11, 12], "move_axi": [8, 9], "bary_proj": [8, 9], "get_cupyx": [8, 9], "get_np": [8, 9], "get_scipi": [8, 9], "grid_ev": [8, 9], "update_opt": [8, 9], "bary_coord": [8, 9], "fro_norm": [8, 9], "get_pac": [8, 9], "kl_diverg": [8, 9], "masked_nmf": [8, 9], "nan_to_num": [8, 9], "norm_x": [8, 9], "nz_indic": [8, 9], "relative_error": [8, 9], "relative_error_resc": [8, 9], "relative_trinmf_error": [8, 9], "sparse_divide_product": [8, 9], "sparse_dot_product": [8, 9], "unprun": [8, 9], "uniform_product": [8, 9], "custom_silhouett": [8, 9], "opt": 8, "dual": 8, "admm": 8, "nonneg": [8, 9, 12], "optim": [8, 17], "frobeniu": 8, "loss": [8, 17], "underset": 8, "operatornam": 8, "minim": 8, "frac": 8, "vert": 8, "vert_f": 8, "subject": 8, "quad": 8, "geq": 8, "m": [8, 9, 10, 12, 17], "decompos": 8, "initi": [8, 9], "hist": 8, "niter": 8, "rho": 8, "doubl": [8, 9], "converg": 8, "w_opt": 8, "h_opt": 8, "kullback": 8, "leibler": 8, "_": [8, 13, 16], "sum_": 8, "x_": [8, 9], "wh": [8, 9], "nz_row": [8, 9], "1d": [8, 9], "csr": [8, 10, 12], "nz_col": [8, 9], "col": [8, 9], "csc": 8, "_f": [8, 9], "wt": 8, "ht": 8, "max_it": [8, 9], "wn": 8, "hn": 8, "best": 8, "npoint": 8, "lowerthr": 8, "upperthr": 8, "penal": 8, "adapt": [8, 17], "grid_search": 8, "sum": 8, "x_i": 8, "r_i": 8, "pair": [8, 10], "a_opt": 8, "r_opt": 8, "alpha_h": 8, "alpha_w": 8, "tri": 8, "With": 8, "orthogon": 8, "constraint": 8, "kw": [8, 9], "kx": 8, "kh": [8, 9], "middl": [8, 9], "w_all": 9, "centroid": [9, 10], "distanc": 9, "ham": 9, "noiseperc": 9, "greedi": 9, "approxim": [9, 13, 16], "quadrat": 9, "problem": [9, 17], "p": [9, 16], "group": 9, "construct": [9, 17], "three": 9, "tensor": [9, 12], "ambient": 9, "been": 9, "reach": 9, "warn": 9, "organ": 9, "dimension": 9, "ith": 9, "cosin": 9, "sil": [9, 10], "measur": 9, "h_all": 9, "perturb_col": 9, "c": [9, 10, 12, 17], "return_index": 9, "hc": 9, "axi": [9, 12], "num_var": 9, "barycentr": 9, "coordin": 9, "activ": [9, 17], "extrem": 9, "rai": 9, "theta": 9, "arg": 9, "fn": 9, "grid": 9, "num_cpu": 9, "y": 9, "3d": 9, "cdf": 9, "itr": 9, "replac": 9, "nan": 9, "els": 9, "normx": 9, "you": [9, 17], "know": 9, "rel_err": 9, "kk": 9, "wsh": 9, "effici": [9, 12], "svd": 9, "gilli": 9, "et": 9, "al": 9, "http": [9, 12, 17], "arxiv": 9, "org": [9, 12, 17], "pdf": 9, "1807": 9, "04020": 9, "desir": 9, "random_st": [9, 15], "y_": 9, "multipli": 9, "gather": 10, "clusters_inform": 10, "centroid_similar": 10, "carri": 10, "filenam": [10, 14], "matplotlib": [10, 15], "mon": [10, 12], "nov": [10, 12], "22": [10, 12], "18": [10, 12], "38": [10, 12], "26": [10, 12], "2021": [10, 12], "form": [10, 12, 17], "consecut": [10, 12], "analysi": [10, 12, 17], "unqiu": [10, 12], "present": [10, 12, 17], "build": [10, 12, 17], "bool_err": 10, "plot_predict": 10, "plot_fin": 10, "descript": 10, "fignam": 10, "coeff": 10, "errregr": 10, "sill_min": 10, "sill_thr": 10, "cooc": [10, 12], "pointwis": [10, 12], "mutual": [10, 12], "cooccur": [10, 12], "erik": [10, 12, 17], "skau": [10, 12, 17], "lock": 10, "write": 10, "newlin": 10, "safe": 10, "thread": [10, 13, 16], "applic": [10, 12, 13, 16, 17], "protect": 10, "ensur": [10, 17], "simultan": 10, "enter": 10, "directori": [10, 16, 17], "rtype": 10, "16": [10, 17], "align": 10, "rest": 10, "accord": 10, "tab": 10, "follow": [10, 17], "written": [10, 17], "sort_index": 10, "record": 10, "some": [10, 17], "stat": 10, "manner": 10, "These": 10, "store": 10, "signifi": 10, "care": 10, "sort": 10, "batch": 10, "caus": [10, 17], "sklearn": [10, 12], "librari": [10, 12, 16, 17], "bag": [10, 12], "submodul": [11, 18], "tokens_analysi": [11, 13], "top_word": [11, 13], "default_operator_pipelin": [11, 13, 16], "default_pipelin": [11, 13, 16], "parallel_backend_opt": [11, 13, 16], "cach": [11, 13, 16], "clean_datafram": [11, 13, 16], "parallel_backend": [11, 12, 13, 16], "use_mpi": [11, 13, 16], "chunk_tuple_list": [11, 13, 16, 17], "py": [12, 17], "softwar": [12, 17], "latest": 12, "releas": 12, "brett": 12, "bader": 12, "tamara": 12, "kolda": 12, "toolbox": [12, 17], "matlab": 12, "version": [12, 17, 18], "www": 12, "tensortoolbox": 12, "april": 12, "t": 12, "862": 12, "prototyp": 12, "acm": 12, "tran": 12, "mathemat": [12, 17], "32": 12, "635": 12, "653": 12, "2006": 12, "dx": 12, "doi": [12, 17], "1145": 12, "1186785": 12, "1186794": 12, "kruskal": 12, "tucker": 12, "siam": 12, "scientif": 12, "30": 12, "205": 12, "231": 12, "2007": 12, "1137": 12, "060676489": 12, "chi": 12, "2012": 12, "On": [12, 17], "sparsiti": 12, "journal": 12, "33": 12, "pp": 12, "1272": 12, "1299": 12, "maksim": [12, 17], "ekin": 12, "eren": [12, 17], "mode": 12, "dim": 12, "unfol": 12, "get_top_word": [13, 14], "tmp": [13, 16], "multi": [13, 16, 17], "design": [13, 16], "natur": [13, 16, 17], "cleaner": [13, 16], "nedetector": [13, 16], "module_typ": [13, 16], "simpleclean": [13, 16], "effective_stop_word": [13, 16], "characterist": [13, 16], "acknowledg": [13, 16], "substanti": [13, 16], "unfortun": [13, 16], "predominantli": [13, 16], "investig": [13, 16], "successfulli": [13, 16], "demonstr": [13, 16], "suffici": [13, 16], "introduct": [13, 16], "particularli": [13, 16], "consequ": [13, 16], "nevertheless": [13, 16], "1359": [13, 16], "standardize_hyphen": [13, 16], "compil": [13, 16], "u002d": [13, 16], "u2010": [13, 16], "u2011": [13, 16], "u2012": [13, 16], "u2013": [13, 16], "u2014": [13, 16], "u2015": [13, 16], "u2212": [13, 16], "u2e3a": [13, 16], "u2e3b": [13, 16], "remove_copyright_stat": [13, 16], "remove_stop_phras": [13, 16], "make_lower_cas": [13, 16], "remove_trailing_dash": [13, 16], "make_hyphens_word": [13, 16], "z": [13, 16], "remove_next_lin": [13, 16], "remove_email": [13, 16], "remove_formula": [13, 16], "remove_dash": [13, 16], "remove_between_": [13, 16], "remove_": [13, 16], "remove_numb": [13, 16], "remove_standalone_numb": [13, 16], "remove_nonascii_boundari": [13, 16], "x00": [13, 16], "x7f": [13, 16], "remove_nonascii": [13, 16], "remove_tag": [13, 16], "lt": [13, 16], "gt": [13, 16], "remove_special_charact": [13, 16], "isolate_frozen": [13, 16], "remove_extra_whitespac": [13, 16], "remove_stop_word": [13, 16], "min_charact": [13, 16], "exclude_hyphenated_stopword": [13, 16], "sw_pattern": [13, 16], "substitut": [13, 16, 17], "append_to_original_df": [13, 16], "concat_cleaned_col": [13, 16], "file_nam": [13, 16], "n_chunk": [13, 16], "sub": [13, 16], "yield": [13, 16], "top_n": 14, "n_gram": 14, "df_fraction": 14, "tf_fraction": 14, "uniqu": 14, "report": 14, "gen_trinmf_data": 15, "pyplot": 15, "plt": 15, "kwkh": 15, "factor_wh": 15, "factor_": 15, "wtrue": 15, "strue": 15, "htrue": 15, "64": 15, "2000": 15, "tri_nmfk_param": 15, "portion": 15, "trinfmk": 15, "tri_nmfk_result": 15, "pickl": 16, "data_dir": 16, "o": 16, "join": 16, "pathlib": 16, "resolv": [16, 17], "data_fil": 16, "open": [16, 17], "rb": 16, "lemmatizeclean": 16, "substitutionclean": 16, "removenonenglishclean": 16, "default_stop_word": 16, "stop_word": 16, "default_stop_phras": 16, "stop_phras": 16, "results_dir": 16, "results_fil": 16, "clean_docu": 16, "mkdir": 16, "except": 16, "fileexistserror": 16, "pipelin": 16, "disabl": 16, "ascii_ratio": 16, "stopwords_ratio": 16, "25": 16, "spaci": [16, 17], "cleaned_docu": 16, "machin": 17, "learn": 17, "packag": [17, 18], "part": 17, "win": 17, "smarttensor": 17, "ai": 17, "project": 17, "customiz": 17, "solut": 17, "craft": 17, "comprehens": 17, "facilit": 17, "decis": 17, "leverag": 17, "high": 17, "edg": 17, "architectur": 17, "our": 17, "analyz": 17, "divers": 17, "central": 17, "core": 17, "lie": 17, "discov": 17, "facet": 17, "hidden": 17, "detail": 17, "autom": 17, "pivot": 17, "precis": 17, "conceal": 17, "addition": 17, "incorpor": 17, "modul": [17, 18], "post": 17, "tailor": 17, "task": 17, "mine": 17, "languag": 17, "robust": 17, "span": 17, "multitud": 17, "disciplin": 17, "analyt": 17, "Its": 17, "proven": 17, "efficaci": 17, "extend": 17, "variou": 17, "scale": 17, "dynam": 17, "network": 17, "biologi": 17, "scienc": 17, "medicin": 17, "chemistri": 17, "compress": 17, "climat": 17, "studi": 17, "relat": 17, "databas": 17, "privaci": 17, "economi": 17, "agricultur": 17, "websit": 17, "code": 17, "pip": 17, "conda": 17, "telf": 17, "python": 17, "git": 17, "github": 17, "com": 17, "clone": 17, "cd": 17, "setup": 17, "env": 17, "environment_gpu": 17, "yml": 17, "environment_cpu": 17, "cpu": 17, "telf_conda": 17, "nlp": 17, "nltk": 17, "download": 17, "en_core_web_lg": 17, "en_core_web_trf": 17, "wordnet": 17, "omw": 17, "cupi": 17, "skip": 17, "forg": 17, "mpi": 17, "openmpi": 17, "mpi4pi": 17, "system": 17, "tutori": 17, "jupyt": 17, "consider": 17, "linux": 17, "devic": 17, "cuda": 17, "configur": 17, "cudatoolkit": 17, "cudnn": 17, "pleas": 17, "apa": 17, "solovyev": 17, "barron": 17, "bhattarai": 17, "truong": 17, "boureima": 17, "rasmussen": 17, "alexandrov": 17, "2023": 17, "5281": 17, "zenodo": 17, "10257897": 17, "bibtex": 17, "nick": 17, "ryan": 17, "manish": 17, "duc": 17, "ismael": 17, "kim": 17, "boian": 17, "month": 17, "oct": 17, "url": 17, "advanc": 17, "research": 17, "cyber": 17, "nichola": 17, "theoret": 17, "divis": 17, "c22048": 17, "bsd": 17, "redistribut": 17, "binari": 17, "modif": 17, "condit": 17, "met": 17, "must": 17, "retain": 17, "abov": 17, "disclaim": 17, "neither": 17, "holder": 17, "nor": 17, "contributor": 17, "endors": 17, "promot": 17, "product": 17, "prior": 17, "permiss": 17, "BY": 17, "THE": 17, "AND": 17, "AS": 17, "ani": 17, "express": 17, "OR": 17, "impli": 17, "warranti": 17, "BUT": 17, "NOT": 17, "TO": 17, "OF": 17, "merchant": 17, "FOR": 17, "particular": 17, "purpos": 17, "IN": 17, "NO": 17, "event": 17, "shall": 17, "BE": 17, "liabl": 17, "direct": 17, "indirect": 17, "incident": 17, "exemplari": 17, "consequenti": 17, "damag": 17, "procur": 17, "good": 17, "servic": 17, "profit": 17, "busi": 17, "interrupt": 17, "ON": 17, "theori": 17, "liabil": 17, "strict": 17, "tort": 17, "neglig": 17, "aris": 17, "wai": 17, "IF": 17, "advis": 17, "SUCH": 17, "ran": 17, "folder": 17, "pytest": 17, "hnmfk": 17, "hierarch": 17, "symnmfk": 17, "cheetah": 17, "keyword": 17, "phrase": 17, "page": 17, "subpackag": 18, "content": 18}, "objects": {"": [[6, 0, 0, "-", "TELF"]], "TELF.applications.Cheetah": [[1, 0, 0, "-", "cheetah"]], "TELF.applications.Cheetah.cheetah": [[1, 1, 1, "", "Cheetah"], [1, 5, 1, "", "add_with_union_of_others"]], "TELF.applications.Cheetah.cheetah.Cheetah": [[1, 2, 1, "", "COLUMNS"], [1, 3, 1, "", "columns"], [1, 4, 1, "", "find_ngram"], [1, 4, 1, "", "index"], [1, 3, 1, "", "ngram_ordered"], [1, 3, 1, "", "ngram_window_size"], [1, 3, 1, "", "query"], [1, 4, 1, "", "search"]], "TELF": [[7, 0, 0, "-", "factorization"], [11, 0, 0, "-", "pre_processing"], [6, 0, 0, "-", "version"]], "TELF.factorization": [[2, 0, 0, "-", "HNMFk"], [7, 0, 0, "-", "NMFk"], [7, 0, 0, "-", "RESCALk"], [5, 0, 0, "-", "SymNMFk"], [15, 0, 0, "-", "TriNMFk"], [8, 0, 0, "-", "decompositions"], [10, 0, 0, "-", "utilities"]], "TELF.factorization.HNMFk": [[2, 1, 1, "", "HNMFk"], [2, 1, 1, "", "Node"], [2, 1, 1, "", "OnlineNode"]], "TELF.factorization.HNMFk.HNMFk": [[2, 4, 1, "", "fit"], [2, 4, 1, "", "get_node"], [2, 4, 1, "", "go_to_children"], [2, 4, 1, "", "go_to_parent"], [2, 4, 1, "", "go_to_root"], [2, 4, 1, "", "traverse_nodes"]], "TELF.factorization.NMFk": [[7, 1, 1, "", "NMFk"]], "TELF.factorization.NMFk.NMFk": [[7, 4, 1, "", "fit"]], "TELF.factorization.RESCALk": [[7, 1, 1, "", "RESCALk"]], "TELF.factorization.RESCALk.RESCALk": [[7, 4, 1, "", "fit"]], "TELF.factorization.SymNMFk": [[5, 1, 1, "", "SymNMFk"]], "TELF.factorization.SymNMFk.SymNMFk": [[5, 4, 1, "", "fit"]], "TELF.factorization.TriNMFk": [[15, 1, 1, "", "TriNMFk"]], "TELF.factorization.TriNMFk.TriNMFk": [[15, 4, 1, "", "fit_nmfk"], [15, 4, 1, "", "fit_tri_nmfk"]], "TELF.factorization.decompositions": [[8, 0, 0, "-", "nmf_fro_admm"], [8, 0, 0, "-", "nmf_fro_mu"], [8, 0, 0, "-", "nmf_kl_admm"], [8, 0, 0, "-", "nmf_kl_mu"], [8, 0, 0, "-", "nmf_mc_fro_mu"], [8, 0, 0, "-", "rescal_fro_mu"], [8, 0, 0, "-", "tri_nmf_fro_mu"], [9, 0, 0, "-", "utilities"]], "TELF.factorization.decompositions.nmf_fro_admm": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_fro_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_kl_admm": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_kl_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_mc_fro_mu": [[8, 5, 1, "", "H_update_ADMM"], [8, 5, 1, "", "H_update_MU"], [8, 5, 1, "", "W_update_ADMM"], [8, 5, 1, "", "W_update_MU"], [8, 5, 1, "", "coord_desc_thresh"], [8, 5, 1, "", "coord_desc_thresh_onefactor"], [8, 5, 1, "", "find_thres_WH"], [8, 5, 1, "", "nmf"], [8, 5, 1, "", "nmf_with_ADMM"], [8, 5, 1, "", "old_find_thres_WH"], [8, 5, 1, "", "old_nmf"], [8, 5, 1, "", "roc_W_H"], [8, 5, 1, "", "thres_norm"]], "TELF.factorization.decompositions.rescal_fro_mu": [[8, 5, 1, "", "A_update"], [8, 5, 1, "", "R_update"], [8, 5, 1, "", "rescal"]], "TELF.factorization.decompositions.tri_nmf_fro_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "S_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "trinmf"]], "TELF.factorization.decompositions.utilities": [[9, 0, 0, "-", "bool_clustering"], [9, 0, 0, "-", "bool_noise"], [9, 0, 0, "-", "clustering"], [9, 0, 0, "-", "concensus_matrix"], [9, 0, 0, "-", "data_reshaping"], [9, 0, 0, "-", "generic_utils"], [9, 0, 0, "-", "math_utils"], [9, 0, 0, "-", "nnsvd"], [9, 0, 0, "-", "resample"], [9, 0, 0, "-", "silhouettes"]], "TELF.factorization.decompositions.utilities.bool_clustering": [[9, 5, 1, "", "custom_bool_clustering"]], "TELF.factorization.decompositions.utilities.bool_noise": [[9, 5, 1, "", "add_Bool_noise"], [9, 5, 1, "", "add_Bool_posneg_noise"]], "TELF.factorization.decompositions.utilities.clustering": [[9, 5, 1, "", "custom_k_means"], [9, 5, 1, "", "silhouettes"]], "TELF.factorization.decompositions.utilities.concensus_matrix": [[9, 5, 1, "", "compute_connectivity_mat"], [9, 5, 1, "", "compute_consensus_matrix"], [9, 5, 1, "", "reorder_con_mat"]], "TELF.factorization.decompositions.utilities.data_reshaping": [[9, 5, 1, "", "fold"], [9, 5, 1, "", "move_axis"], [9, 5, 1, "", "unfold"]], "TELF.factorization.decompositions.utilities.generic_utils": [[9, 5, 1, "", "bary_proj"], [9, 5, 1, "", "get_cupyx"], [9, 5, 1, "", "get_np"], [9, 5, 1, "", "get_scipy"], [9, 5, 1, "", "grid_eval"], [9, 5, 1, "", "update_opts"]], "TELF.factorization.decompositions.utilities.math_utils": [[9, 5, 1, "", "bary_coords"], [9, 5, 1, "", "fro_norm"], [9, 5, 1, "", "get_pac"], [9, 5, 1, "", "kl_divergence"], [9, 5, 1, "", "masked_nmf"], [9, 5, 1, "", "nan_to_num"], [9, 5, 1, "", "norm_X"], [9, 5, 1, "", "nz_indices"], [9, 5, 1, "", "prune"], [9, 5, 1, "", "relative_error"], [9, 5, 1, "", "relative_error_rescal"], [9, 5, 1, "", "relative_trinmf_error"], [9, 5, 1, "", "sparse_divide_product"], [9, 5, 1, "", "sparse_dot_product"], [9, 5, 1, "", "unprune"]], "TELF.factorization.decompositions.utilities.nnsvd": [[9, 5, 1, "", "nnsvd"]], "TELF.factorization.decompositions.utilities.resample": [[9, 5, 1, "", "poisson"], [9, 5, 1, "", "uniform_product"]], "TELF.factorization.decompositions.utilities.silhouettes": [[9, 5, 1, "", "custom_silhouettes"]], "TELF.factorization.utilities": [[10, 0, 0, "-", "clustering"], [10, 0, 0, "-", "co_occurance_matrix"], [10, 0, 0, "-", "organize_n_jobs"], [10, 0, 0, "-", "plot_NMFk"], [10, 0, 0, "-", "pvalue_analysis"], [10, 0, 0, "-", "sppmi_matrix"], [10, 0, 0, "-", "take_note"], [10, 0, 0, "-", "vectorize"]], "TELF.factorization.utilities.clustering": [[10, 5, 1, "", "H_clustering"], [10, 5, 1, "", "plot_H_clustering"]], "TELF.factorization.utilities.co_occurance_matrix": [[10, 5, 1, "", "co_occurrence"]], "TELF.factorization.utilities.organize_n_jobs": [[10, 5, 1, "", "organize_n_jobs"]], "TELF.factorization.utilities.plot_NMFk": [[10, 5, 1, "", "plot_BNMFk"], [10, 5, 1, "", "plot_NMFk"], [10, 5, 1, "", "plot_SymNMFk"], [10, 5, 1, "", "plot_consensus_mat"], [10, 5, 1, "", "plot_cophenetic_coeff"]], "TELF.factorization.utilities.pvalue_analysis": [[10, 5, 1, "", "pvalue_analysis"]], "TELF.factorization.utilities.sppmi_matrix": [[10, 5, 1, "", "sppmi"]], "TELF.factorization.utilities.take_note": [[10, 5, 1, "", "append_to_note"], [10, 5, 1, "", "format_note"], [10, 5, 1, "", "take_note"], [10, 5, 1, "", "take_note_fmat"]], "TELF.factorization.utilities.vectorize": [[10, 5, 1, "", "count"], [10, 5, 1, "", "tfidf"]], "TELF.pre_processing": [[12, 0, 0, "-", "Beaver"], [13, 0, 0, "-", "Vulture"]], "TELF.pre_processing.Beaver": [[12, 0, 0, "-", "beaver"], [12, 0, 0, "-", "cooccurrence"], [12, 0, 0, "-", "sppmi"], [12, 0, 0, "-", "tenmat"], [12, 0, 0, "-", "vectorize"]], "TELF.pre_processing.Beaver.beaver": [[12, 1, 1, "", "Beaver"]], "TELF.pre_processing.Beaver.beaver.Beaver": [[12, 2, 1, "", "SUPPORTED_OUTPUT_FORMATS"], [12, 4, 1, "", "citation_tensor"], [12, 4, 1, "", "coauthor_tensor"], [12, 4, 1, "", "cocitation_tensor"], [12, 4, 1, "", "cooccurrence_matrix"], [12, 4, 1, "", "documents_words"], [12, 4, 1, "", "get_ngrams"], [12, 4, 1, "", "get_vocabulary"], [12, 3, 1, "", "n_jobs"], [12, 3, 1, "", "n_nodes"], [12, 4, 1, "", "participation_tensor"], [12, 4, 1, "", "something_words"], [12, 4, 1, "", "something_words_time"]], "TELF.pre_processing.Beaver.cooccurrence": [[12, 5, 1, "", "co_occurrence"]], "TELF.pre_processing.Beaver.sppmi": [[12, 5, 1, "", "sppmi"]], "TELF.pre_processing.Beaver.tenmat": [[12, 5, 1, "", "fold"], [12, 5, 1, "", "unfold"]], "TELF.pre_processing.Beaver.vectorize": [[12, 5, 1, "", "count"], [12, 5, 1, "", "tfidf"]], "TELF.pre_processing.Vulture": [[13, 0, 0, "-", "modules"], [14, 0, 0, "-", "tokens_analysis"], [16, 0, 0, "-", "vulture"]], "TELF.pre_processing.Vulture.tokens_analysis": [[14, 0, 0, "-", "top_words"]], "TELF.pre_processing.Vulture.tokens_analysis.top_words": [[14, 5, 1, "", "get_top_words"]], "TELF.pre_processing.Vulture.vulture": [[16, 1, 1, "", "Vulture"], [16, 5, 1, "", "chunk_tuple_list"]], "TELF.pre_processing.Vulture.vulture.Vulture": [[16, 2, 1, "", "DEFAULT_OPERATOR_PIPELINE"], [16, 2, 1, "", "DEFAULT_PIPELINE"], [16, 2, 1, "", "PARALLEL_BACKEND_OPTIONS"], [16, 3, 1, "", "cache"], [16, 4, 1, "", "clean"], [16, 4, 1, "", "clean_dataframe"], [16, 3, 1, "", "n_jobs"], [16, 3, 1, "", "n_nodes"], [16, 4, 1, "", "operate"], [16, 3, 1, "", "parallel_backend"], [16, 3, 1, "", "save_path"], [16, 4, 1, "", "use_mpi"], [16, 3, 1, "", "verbose"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:property", "4": "py:method", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "property", "Python property"], "4": ["py", "method", "Python method"], "5": ["py", "function", "Python function"]}, "titleterms": {"telf": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18], "pre_process": [0, 11, 12, 13, 14, 16], "beaver": [0, 12], "fast": 0, "matrix": [0, 2, 3, 5], "tensor": [0, 17], "build": 0, "tool": [0, 16], "exampl": [0, 3, 4, 15, 16], "avail": [0, 1, 2, 3, 4, 5, 15, 16], "function": [0, 1, 2, 3, 4, 5, 15, 16], "modul": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16], "content": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], "applic": 1, "cheetah": 1, "advanc": [1, 16], "search": 1, "keyword": 1, "phrase": 1, "paramet": [1, 10], "return": [1, 10], "rais": 1, "factor": [2, 3, 4, 5, 7, 8, 9, 10, 15], "hnmfk": 2, "hierarch": 2, "non": [2, 3, 5], "neg": [2, 3, 5], "automat": [2, 3, 4, 5, 15], "model": [2, 3, 4, 5], "determin": [2, 3, 4, 5, 15], "nmfk": [3, 7, 15], "rescalk": [4, 7], "rescal": 4, "symnmfk": 5, "symmetr": 5, "packag": [6, 7, 8, 9, 10, 11, 12, 13, 14], "subpackag": [6, 7, 8, 11, 13], "submodul": [6, 7, 8, 9, 10, 12, 13, 14], "version": 6, "trinmfk": [7, 15], "decomposit": [8, 9], "nmf_fro_admm": 8, "nmf_fro_mu": 8, "nmf_kl_admm": 8, "nmf_kl_mu": 8, "nmf_mc_fro_mu": 8, "rescal_fro_mu": 8, "tri_nmf_fro_mu": 8, "util": [9, 10], "bool_clust": 9, "bool_nois": 9, "cluster": [9, 10, 15], "concensus_matrix": 9, "data_reshap": 9, "generic_util": 9, "math_util": 9, "nnsvd": 9, "resampl": 9, "silhouett": 9, "co_occurance_matrix": 10, "organize_n_job": 10, "plot_nmfk": 10, "pvalue_analysi": 10, "sppmi_matrix": 10, "take_not": 10, "vector": [10, 12], "cooccurr": 12, "sppmi": 12, "tenmat": 12, "vultur": [13, 14, 16], "tokens_analysi": 14, "top_word": 14, "latent": [15, 17], "pattern": 15, "text": 16, "pre": 16, "process": 16, "clean": 16, "nlp": 16, "mine": 16, "extract": 17, "featur": 17, "t": 17, "elf": 17, "resourc": 17, "instal": 17, "capabl": 17, "how": 17, "cite": 17, "author": 17, "copyright": 17, "notic": 17, "licens": 17, "develop": 17, "test": 17, "suit": 17, "indic": 17, "tabl": 17}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinxcontrib.bibtex": 9, "sphinx": 60}, "alltitles": {"TELF.pre_processing.Beaver: Fast matrix and tensor building tool": [[0, "telf-pre-processing-beaver-fast-matrix-and-tensor-building-tool"]], "Example": [[0, "example"], [3, "example"], [4, "example"], [15, "example"], [16, "example"]], "Available Functions": [[0, "available-functions"], [1, "available-functions"], [2, "available-functions"], [3, "available-functions"], [4, "available-functions"], [5, "available-functions"], [15, "available-functions"], [16, "available-functions"]], "Module Contents": [[0, "module-TELF.pre_processing.Beaver.beaver"], [1, "module-TELF.applications.Cheetah.cheetah"], [2, "module-TELF.factorization.HNMFk"], [3, "module-TELF.factorization.NMFk"], [4, "module-TELF.factorization.RESCALk"], [5, "module-TELF.factorization.SymNMFk"], [15, "module-TELF.factorization.TriNMFk"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "TELF.applications.Cheetah: Advanced search by keywords and phrases": [[1, "telf-applications-cheetah-advanced-search-by-keywords-and-phrases"]], "Parameters:": [[1, "parameters"], [10, "parameters"], [10, "id1"], [10, "id2"], [10, "id3"]], "Returns:": [[1, "returns"], [10, "returns"]], "Raises:": [[1, "raises"]], "TELF.factorization.HNMFk: Hierarchical Non-negative Matrix Factorization with Automatic Model Determination": [[2, "telf-factorization-hnmfk-hierarchical-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF.factorization.NMFk: Non-negative Matrix Factorization with Automatic Model Determination": [[3, "telf-factorization-nmfk-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF.factorization.RESCALk: RESCAL with Automatic Model Determination": [[4, "telf-factorization-rescalk-rescal-with-automatic-model-determination"]], "TELF.factorization.SymNMFk: Symmetric Non-negative Matrix Factorization with Automatic Model Determination": [[5, "telf-factorization-symnmfk-symmetric-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF package": [[6, "telf-package"]], "Subpackages": [[6, "subpackages"], [7, "subpackages"], [8, "subpackages"], [11, "subpackages"], [13, "subpackages"]], "Submodules": [[6, "submodules"], [7, "submodules"], [8, "submodules"], [9, "submodules"], [10, "submodules"], [12, "submodules"], [13, "submodules"], [14, "submodules"]], "TELF.version module": [[6, "module-TELF.version"]], "Module contents": [[6, "module-TELF"], [7, "module-TELF.factorization"], [8, "module-TELF.factorization.decompositions"], [9, "module-TELF.factorization.decompositions.utilities"], [10, "module-TELF.factorization.utilities"], [11, "module-TELF.pre_processing"], [12, "module-TELF.pre_processing.Beaver"], [13, "module-TELF.pre_processing.Vulture"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis"]], "TELF.factorization package": [[7, "telf-factorization-package"]], "TELF.factorization.NMFk module": [[7, "module-TELF.factorization.NMFk"]], "TELF.factorization.RESCALk module": [[7, "module-TELF.factorization.RESCALk"]], "TELF.factorization.TriNMFk module": [[7, "module-TELF.factorization.TriNMFk"]], "TELF.factorization.decompositions package": [[8, "telf-factorization-decompositions-package"]], "TELF.factorization.decompositions.nmf_fro_admm module": [[8, "module-TELF.factorization.decompositions.nmf_fro_admm"]], "TELF.factorization.decompositions.nmf_fro_mu module": [[8, "module-TELF.factorization.decompositions.nmf_fro_mu"]], "TELF.factorization.decompositions.nmf_kl_admm module": [[8, "module-TELF.factorization.decompositions.nmf_kl_admm"]], "TELF.factorization.decompositions.nmf_kl_mu module": [[8, "module-TELF.factorization.decompositions.nmf_kl_mu"]], "TELF.factorization.decompositions.nmf_mc_fro_mu module": [[8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"]], "TELF.factorization.decompositions.rescal_fro_mu module": [[8, "module-TELF.factorization.decompositions.rescal_fro_mu"]], "TELF.factorization.decompositions.tri_nmf_fro_mu module": [[8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"]], "TELF.factorization.decompositions.utilities package": [[9, "telf-factorization-decompositions-utilities-package"]], "TELF.factorization.decompositions.utilities.bool_clustering module": [[9, "module-TELF.factorization.decompositions.utilities.bool_clustering"]], "TELF.factorization.decompositions.utilities.bool_noise module": [[9, "module-TELF.factorization.decompositions.utilities.bool_noise"]], "TELF.factorization.decompositions.utilities.clustering module": [[9, "module-TELF.factorization.decompositions.utilities.clustering"]], "TELF.factorization.decompositions.utilities.concensus_matrix module": [[9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"]], "TELF.factorization.decompositions.utilities.data_reshaping module": [[9, "module-TELF.factorization.decompositions.utilities.data_reshaping"]], "TELF.factorization.decompositions.utilities.generic_utils module": [[9, "module-TELF.factorization.decompositions.utilities.generic_utils"]], "TELF.factorization.decompositions.utilities.math_utils module": [[9, "module-TELF.factorization.decompositions.utilities.math_utils"]], "TELF.factorization.decompositions.utilities.nnsvd module": [[9, "module-TELF.factorization.decompositions.utilities.nnsvd"]], "TELF.factorization.decompositions.utilities.resample module": [[9, "module-TELF.factorization.decompositions.utilities.resample"]], "TELF.factorization.decompositions.utilities.silhouettes module": [[9, "module-TELF.factorization.decompositions.utilities.silhouettes"]], "TELF.factorization.utilities package": [[10, "telf-factorization-utilities-package"]], "TELF.factorization.utilities.clustering module": [[10, "module-TELF.factorization.utilities.clustering"]], "TELF.factorization.utilities.co_occurance_matrix module": [[10, "module-TELF.factorization.utilities.co_occurance_matrix"]], "TELF.factorization.utilities.organize_n_jobs module": [[10, "module-TELF.factorization.utilities.organize_n_jobs"]], "TELF.factorization.utilities.plot_NMFk module": [[10, "module-TELF.factorization.utilities.plot_NMFk"]], "TELF.factorization.utilities.pvalue_analysis module": [[10, "module-TELF.factorization.utilities.pvalue_analysis"]], "TELF.factorization.utilities.sppmi_matrix module": [[10, "module-TELF.factorization.utilities.sppmi_matrix"]], "TELF.factorization.utilities.take_note module": [[10, "module-TELF.factorization.utilities.take_note"]], "TELF.factorization.utilities.vectorize module": [[10, "module-TELF.factorization.utilities.vectorize"]], "TELF.pre_processing package": [[11, "telf-pre-processing-package"]], "TELF.pre_processing.Beaver package": [[12, "telf-pre-processing-beaver-package"]], "TELF.pre_processing.Beaver.beaver module": [[12, "module-TELF.pre_processing.Beaver.beaver"]], "TELF.pre_processing.Beaver.cooccurrence module": [[12, "module-TELF.pre_processing.Beaver.cooccurrence"]], "TELF.pre_processing.Beaver.sppmi module": [[12, "module-TELF.pre_processing.Beaver.sppmi"]], "TELF.pre_processing.Beaver.tenmat module": [[12, "module-TELF.pre_processing.Beaver.tenmat"]], "TELF.pre_processing.Beaver.vectorize module": [[12, "module-TELF.pre_processing.Beaver.vectorize"]], "TELF.pre_processing.Vulture package": [[13, "telf-pre-processing-vulture-package"]], "TELF.pre_processing.Vulture.modules module": [[13, "module-TELF.pre_processing.Vulture.modules"]], "TELF.pre_processing.Vulture.vulture module": [[13, "module-TELF.pre_processing.Vulture.vulture"]], "TELF.pre_processing.Vulture.tokens_analysis package": [[14, "telf-pre-processing-vulture-tokens-analysis-package"]], "TELF.pre_processing.Vulture.tokens_analysis.top_words module": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"]], "TELF.factorization.TriNMFk: NMFk with Automatic Determination of Latent Clusters and Patterns": [[15, "telf-factorization-trinmfk-nmfk-with-automatic-determination-of-latent-clusters-and-patterns"]], "TELF.pre_processing.Vulture: Advanced text pre-processing and cleaning tool for NLP and text-mining": [[16, "telf-pre-processing-vulture-advanced-text-pre-processing-and-cleaning-tool-for-nlp-and-text-mining"]], "Tensor Extraction of Latent Features (T-ELF)": [[17, "tensor-extraction-of-latent-features-t-elf"]], "Resources": [[17, "resources"]], "Installation": [[17, "installation"]], "Capabilities": [[17, "capabilities"]], "How to Cite T-ELF?": [[17, "how-to-cite-t-elf"]], "Authors": [[17, "authors"]], "Copyright Notice": [[17, "copyright-notice"]], "License": [[17, "license"]], "Developer Test Suite": [[17, "developer-test-suite"]], "Contents:": [[17, null]], "Indices and tables": [[17, "indices-and-tables"]], "TELF": [[18, "telf"]]}, "indexentries": {"beaver (class in telf.pre_processing.beaver.beaver)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver"], [12, "TELF.pre_processing.Beaver.beaver.Beaver"]], "supported_output_formats (telf.pre_processing.beaver.beaver.beaver attribute)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.SUPPORTED_OUTPUT_FORMATS"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.SUPPORTED_OUTPUT_FORMATS"]], "telf.pre_processing.beaver.beaver": [[0, "module-TELF.pre_processing.Beaver.beaver"], [12, "module-TELF.pre_processing.Beaver.beaver"]], "citation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.citation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.citation_tensor"]], "coauthor_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.coauthor_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.coauthor_tensor"]], "cocitation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.cocitation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.cocitation_tensor"]], "cooccurrence_matrix() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.cooccurrence_matrix"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.cooccurrence_matrix"]], "documents_words() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.documents_words"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.documents_words"]], "get_ngrams() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.get_ngrams"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.get_ngrams"]], "get_vocabulary() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.get_vocabulary"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.get_vocabulary"]], "module": [[0, "module-TELF.pre_processing.Beaver.beaver"], [1, "module-TELF.applications.Cheetah.cheetah"], [2, "module-TELF.factorization.HNMFk"], [3, "module-TELF.factorization.NMFk"], [4, "module-TELF.factorization.RESCALk"], [5, "module-TELF.factorization.SymNMFk"], [6, "module-TELF"], [6, "module-TELF.version"], [7, "module-TELF.factorization"], [7, "module-TELF.factorization.NMFk"], [7, "module-TELF.factorization.RESCALk"], [7, "module-TELF.factorization.TriNMFk"], [8, "module-TELF.factorization.decompositions"], [8, "module-TELF.factorization.decompositions.nmf_fro_admm"], [8, "module-TELF.factorization.decompositions.nmf_fro_mu"], [8, "module-TELF.factorization.decompositions.nmf_kl_admm"], [8, "module-TELF.factorization.decompositions.nmf_kl_mu"], [8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"], [8, "module-TELF.factorization.decompositions.rescal_fro_mu"], [8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"], [9, "module-TELF.factorization.decompositions.utilities"], [9, "module-TELF.factorization.decompositions.utilities.bool_clustering"], [9, "module-TELF.factorization.decompositions.utilities.bool_noise"], [9, "module-TELF.factorization.decompositions.utilities.clustering"], [9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"], [9, "module-TELF.factorization.decompositions.utilities.data_reshaping"], [9, "module-TELF.factorization.decompositions.utilities.generic_utils"], [9, "module-TELF.factorization.decompositions.utilities.math_utils"], [9, "module-TELF.factorization.decompositions.utilities.nnsvd"], [9, "module-TELF.factorization.decompositions.utilities.resample"], [9, "module-TELF.factorization.decompositions.utilities.silhouettes"], [10, "module-TELF.factorization.utilities"], [10, "module-TELF.factorization.utilities.clustering"], [10, "module-TELF.factorization.utilities.co_occurance_matrix"], [10, "module-TELF.factorization.utilities.organize_n_jobs"], [10, "module-TELF.factorization.utilities.plot_NMFk"], [10, "module-TELF.factorization.utilities.pvalue_analysis"], [10, "module-TELF.factorization.utilities.sppmi_matrix"], [10, "module-TELF.factorization.utilities.take_note"], [10, "module-TELF.factorization.utilities.vectorize"], [11, "module-TELF.pre_processing"], [12, "module-TELF.pre_processing.Beaver"], [12, "module-TELF.pre_processing.Beaver.beaver"], [12, "module-TELF.pre_processing.Beaver.cooccurrence"], [12, "module-TELF.pre_processing.Beaver.sppmi"], [12, "module-TELF.pre_processing.Beaver.tenmat"], [12, "module-TELF.pre_processing.Beaver.vectorize"], [13, "module-TELF.pre_processing.Vulture"], [13, "module-TELF.pre_processing.Vulture.modules"], [13, "module-TELF.pre_processing.Vulture.vulture"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"], [15, "module-TELF.factorization.TriNMFk"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "n_jobs (telf.pre_processing.beaver.beaver.beaver property)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.n_jobs"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.n_jobs"]], "n_nodes (telf.pre_processing.beaver.beaver.beaver property)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.n_nodes"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.n_nodes"]], "participation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.participation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.participation_tensor"]], "something_words() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.something_words"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.something_words"]], "something_words_time() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.something_words_time"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.something_words_time"]], "columns (telf.applications.cheetah.cheetah.cheetah attribute)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.COLUMNS"]], "cheetah (class in telf.applications.cheetah.cheetah)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah"]], "telf.applications.cheetah.cheetah": [[1, "module-TELF.applications.Cheetah.cheetah"]], "add_with_union_of_others() (in module telf.applications.cheetah.cheetah)": [[1, "TELF.applications.Cheetah.cheetah.add_with_union_of_others"]], "columns (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.columns"]], "find_ngram() (telf.applications.cheetah.cheetah.cheetah class method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.find_ngram"]], "index() (telf.applications.cheetah.cheetah.cheetah method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.index"]], "ngram_ordered (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.ngram_ordered"]], "ngram_window_size (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.ngram_window_size"]], "query (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.query"]], "search() (telf.applications.cheetah.cheetah.cheetah method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.search"]], "hnmfk (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.HNMFk"]], "node (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.Node"]], "onlinenode (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.OnlineNode"]], "telf.factorization.hnmfk": [[2, "module-TELF.factorization.HNMFk"]], "fit() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.fit"]], "get_node() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.get_node"]], "go_to_children() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_children"]], "go_to_parent() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_parent"]], "go_to_root() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_root"]], "traverse_nodes() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.traverse_nodes"]], "nmfk (class in telf.factorization.nmfk)": [[3, "TELF.factorization.NMFk.NMFk"], [7, "TELF.factorization.NMFk.NMFk"]], "telf.factorization.nmfk": [[3, "module-TELF.factorization.NMFk"], [7, "module-TELF.factorization.NMFk"]], "fit() (telf.factorization.nmfk.nmfk method)": [[3, "TELF.factorization.NMFk.NMFk.fit"], [7, "TELF.factorization.NMFk.NMFk.fit"]], "rescalk (class in telf.factorization.rescalk)": [[4, "TELF.factorization.RESCALk.RESCALk"], [7, "TELF.factorization.RESCALk.RESCALk"]], "telf.factorization.rescalk": [[4, "module-TELF.factorization.RESCALk"], [7, "module-TELF.factorization.RESCALk"]], "fit() (telf.factorization.rescalk.rescalk method)": [[4, "TELF.factorization.RESCALk.RESCALk.fit"], [7, "TELF.factorization.RESCALk.RESCALk.fit"]], "symnmfk (class in telf.factorization.symnmfk)": [[5, "TELF.factorization.SymNMFk.SymNMFk"]], "telf.factorization.symnmfk": [[5, "module-TELF.factorization.SymNMFk"]], "fit() (telf.factorization.symnmfk.symnmfk method)": [[5, "TELF.factorization.SymNMFk.SymNMFk.fit"]], "telf": [[6, "module-TELF"]], "telf.version": [[6, "module-TELF.version"]], "telf.factorization": [[7, "module-TELF.factorization"]], "telf.factorization.trinmfk": [[7, "module-TELF.factorization.TriNMFk"], [15, "module-TELF.factorization.TriNMFk"]], "trinmfk (class in telf.factorization.trinmfk)": [[7, "TELF.factorization.TriNMFk.TriNMFk"], [15, "TELF.factorization.TriNMFk.TriNMFk"]], "fit_nmfk() (telf.factorization.trinmfk.trinmfk method)": [[7, "TELF.factorization.TriNMFk.TriNMFk.fit_nmfk"], [15, "TELF.factorization.TriNMFk.TriNMFk.fit_nmfk"]], "fit_tri_nmfk() (telf.factorization.trinmfk.trinmfk method)": [[7, "TELF.factorization.TriNMFk.TriNMFk.fit_tri_nmfk"], [15, "TELF.factorization.TriNMFk.TriNMFk.fit_tri_nmfk"]], "a_update() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.A_update"]], "h_update() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.H_update"]], "h_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.H_update"]], "h_update_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.H_update_ADMM"]], "h_update_mu() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.H_update_MU"]], "r_update() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.R_update"]], "s_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.S_update"]], "telf.factorization.decompositions": [[8, "module-TELF.factorization.decompositions"]], "telf.factorization.decompositions.nmf_fro_admm": [[8, "module-TELF.factorization.decompositions.nmf_fro_admm"]], "telf.factorization.decompositions.nmf_fro_mu": [[8, "module-TELF.factorization.decompositions.nmf_fro_mu"]], "telf.factorization.decompositions.nmf_kl_admm": [[8, "module-TELF.factorization.decompositions.nmf_kl_admm"]], "telf.factorization.decompositions.nmf_kl_mu": [[8, "module-TELF.factorization.decompositions.nmf_kl_mu"]], "telf.factorization.decompositions.nmf_mc_fro_mu": [[8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"]], "telf.factorization.decompositions.rescal_fro_mu": [[8, "module-TELF.factorization.decompositions.rescal_fro_mu"]], "telf.factorization.decompositions.tri_nmf_fro_mu": [[8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"]], "w_update() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.W_update"]], "w_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.W_update"]], "w_update_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.W_update_ADMM"]], "w_update_mu() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.W_update_MU"]], "coord_desc_thresh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.coord_desc_thresh"]], "coord_desc_thresh_onefactor() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.coord_desc_thresh_onefactor"]], "find_thres_wh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.find_thres_WH"]], "nmf() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.nmf"]], "nmf_with_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.nmf_with_ADMM"]], "old_find_thres_wh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.old_find_thres_WH"]], "old_nmf() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.old_nmf"]], "rescal() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.rescal"]], "roc_w_h() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.roc_W_H"]], "thres_norm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.thres_norm"]], "trinmf() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.trinmf"]], "telf.factorization.decompositions.utilities": [[9, "module-TELF.factorization.decompositions.utilities"]], "telf.factorization.decompositions.utilities.bool_clustering": [[9, "module-TELF.factorization.decompositions.utilities.bool_clustering"]], "telf.factorization.decompositions.utilities.bool_noise": [[9, "module-TELF.factorization.decompositions.utilities.bool_noise"]], "telf.factorization.decompositions.utilities.clustering": [[9, "module-TELF.factorization.decompositions.utilities.clustering"]], "telf.factorization.decompositions.utilities.concensus_matrix": [[9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"]], "telf.factorization.decompositions.utilities.data_reshaping": [[9, "module-TELF.factorization.decompositions.utilities.data_reshaping"]], "telf.factorization.decompositions.utilities.generic_utils": [[9, "module-TELF.factorization.decompositions.utilities.generic_utils"]], "telf.factorization.decompositions.utilities.math_utils": [[9, "module-TELF.factorization.decompositions.utilities.math_utils"]], "telf.factorization.decompositions.utilities.nnsvd": [[9, "module-TELF.factorization.decompositions.utilities.nnsvd"]], "telf.factorization.decompositions.utilities.resample": [[9, "module-TELF.factorization.decompositions.utilities.resample"]], "telf.factorization.decompositions.utilities.silhouettes": [[9, "module-TELF.factorization.decompositions.utilities.silhouettes"]], "add_bool_noise() (in module telf.factorization.decompositions.utilities.bool_noise)": [[9, "TELF.factorization.decompositions.utilities.bool_noise.add_Bool_noise"]], "add_bool_posneg_noise() (in module telf.factorization.decompositions.utilities.bool_noise)": [[9, "TELF.factorization.decompositions.utilities.bool_noise.add_Bool_posneg_noise"]], "bary_coords() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.bary_coords"]], "bary_proj() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.bary_proj"]], "compute_connectivity_mat() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.compute_connectivity_mat"]], "compute_consensus_matrix() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.compute_consensus_matrix"]], "custom_bool_clustering() (in module telf.factorization.decompositions.utilities.bool_clustering)": [[9, "TELF.factorization.decompositions.utilities.bool_clustering.custom_bool_clustering"]], "custom_k_means() (in module telf.factorization.decompositions.utilities.clustering)": [[9, "TELF.factorization.decompositions.utilities.clustering.custom_k_means"]], "custom_silhouettes() (in module telf.factorization.decompositions.utilities.silhouettes)": [[9, "TELF.factorization.decompositions.utilities.silhouettes.custom_silhouettes"]], "fold() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.fold"]], "fro_norm() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.fro_norm"]], "get_cupyx() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_cupyx"]], "get_np() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_np"]], "get_pac() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.get_pac"]], "get_scipy() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_scipy"]], "grid_eval() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.grid_eval"]], "kl_divergence() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.kl_divergence"]], "masked_nmf() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.masked_nmf"]], "move_axis() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.move_axis"]], "nan_to_num() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.nan_to_num"]], "nnsvd() (in module telf.factorization.decompositions.utilities.nnsvd)": [[9, "TELF.factorization.decompositions.utilities.nnsvd.nnsvd"]], "norm_x() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.norm_X"]], "nz_indices() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.nz_indices"]], "poisson() (in module telf.factorization.decompositions.utilities.resample)": [[9, "TELF.factorization.decompositions.utilities.resample.poisson"]], "prune() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.prune"]], "relative_error() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_error"]], "relative_error_rescal() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_error_rescal"]], "relative_trinmf_error() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_trinmf_error"]], "reorder_con_mat() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.reorder_con_mat"]], "silhouettes() (in module telf.factorization.decompositions.utilities.clustering)": [[9, "TELF.factorization.decompositions.utilities.clustering.silhouettes"]], "sparse_divide_product() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.sparse_divide_product"]], "sparse_dot_product() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.sparse_dot_product"]], "unfold() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.unfold"]], "uniform_product() (in module telf.factorization.decompositions.utilities.resample)": [[9, "TELF.factorization.decompositions.utilities.resample.uniform_product"]], "unprune() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.unprune"]], "update_opts() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.update_opts"]], "h_clustering() (in module telf.factorization.utilities.clustering)": [[10, "TELF.factorization.utilities.clustering.H_clustering"]], "telf.factorization.utilities": [[10, "module-TELF.factorization.utilities"]], "telf.factorization.utilities.clustering": [[10, "module-TELF.factorization.utilities.clustering"]], "telf.factorization.utilities.co_occurance_matrix": [[10, "module-TELF.factorization.utilities.co_occurance_matrix"]], "telf.factorization.utilities.organize_n_jobs": [[10, "module-TELF.factorization.utilities.organize_n_jobs"]], "telf.factorization.utilities.plot_nmfk": [[10, "module-TELF.factorization.utilities.plot_NMFk"]], "telf.factorization.utilities.pvalue_analysis": [[10, "module-TELF.factorization.utilities.pvalue_analysis"]], "telf.factorization.utilities.sppmi_matrix": [[10, "module-TELF.factorization.utilities.sppmi_matrix"]], "telf.factorization.utilities.take_note": [[10, "module-TELF.factorization.utilities.take_note"]], "telf.factorization.utilities.vectorize": [[10, "module-TELF.factorization.utilities.vectorize"]], "append_to_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.append_to_note"]], "co_occurrence() (in module telf.factorization.utilities.co_occurance_matrix)": [[10, "TELF.factorization.utilities.co_occurance_matrix.co_occurrence"]], "count() (in module telf.factorization.utilities.vectorize)": [[10, "TELF.factorization.utilities.vectorize.count"]], "format_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.format_note"]], "organize_n_jobs() (in module telf.factorization.utilities.organize_n_jobs)": [[10, "TELF.factorization.utilities.organize_n_jobs.organize_n_jobs"]], "plot_bnmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_BNMFk"]], "plot_h_clustering() (in module telf.factorization.utilities.clustering)": [[10, "TELF.factorization.utilities.clustering.plot_H_clustering"]], "plot_nmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_NMFk"]], "plot_symnmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_SymNMFk"]], "plot_consensus_mat() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_consensus_mat"]], "plot_cophenetic_coeff() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_cophenetic_coeff"]], "pvalue_analysis() (in module telf.factorization.utilities.pvalue_analysis)": [[10, "TELF.factorization.utilities.pvalue_analysis.pvalue_analysis"]], "sppmi() (in module telf.factorization.utilities.sppmi_matrix)": [[10, "TELF.factorization.utilities.sppmi_matrix.sppmi"]], "take_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.take_note"]], "take_note_fmat() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.take_note_fmat"]], "tfidf() (in module telf.factorization.utilities.vectorize)": [[10, "TELF.factorization.utilities.vectorize.tfidf"]], "telf.pre_processing": [[11, "module-TELF.pre_processing"]], "telf.pre_processing.beaver": [[12, "module-TELF.pre_processing.Beaver"]], "telf.pre_processing.beaver.cooccurrence": [[12, "module-TELF.pre_processing.Beaver.cooccurrence"]], "telf.pre_processing.beaver.sppmi": [[12, "module-TELF.pre_processing.Beaver.sppmi"]], "telf.pre_processing.beaver.tenmat": [[12, "module-TELF.pre_processing.Beaver.tenmat"]], "telf.pre_processing.beaver.vectorize": [[12, "module-TELF.pre_processing.Beaver.vectorize"]], "co_occurrence() (in module telf.pre_processing.beaver.cooccurrence)": [[12, "TELF.pre_processing.Beaver.cooccurrence.co_occurrence"]], "count() (in module telf.pre_processing.beaver.vectorize)": [[12, "TELF.pre_processing.Beaver.vectorize.count"]], "fold() (in module telf.pre_processing.beaver.tenmat)": [[12, "TELF.pre_processing.Beaver.tenmat.fold"]], "sppmi() (in module telf.pre_processing.beaver.sppmi)": [[12, "TELF.pre_processing.Beaver.sppmi.sppmi"]], "tfidf() (in module telf.pre_processing.beaver.vectorize)": [[12, "TELF.pre_processing.Beaver.vectorize.tfidf"]], "unfold() (in module telf.pre_processing.beaver.tenmat)": [[12, "TELF.pre_processing.Beaver.tenmat.unfold"]], "default_operator_pipeline (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_OPERATOR_PIPELINE"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_OPERATOR_PIPELINE"]], "default_pipeline (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_PIPELINE"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_PIPELINE"]], "parallel_backend_options (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.PARALLEL_BACKEND_OPTIONS"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.PARALLEL_BACKEND_OPTIONS"]], "telf.pre_processing.vulture": [[13, "module-TELF.pre_processing.Vulture"]], "telf.pre_processing.vulture.modules": [[13, "module-TELF.pre_processing.Vulture.modules"]], "telf.pre_processing.vulture.vulture": [[13, "module-TELF.pre_processing.Vulture.vulture"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "vulture (class in telf.pre_processing.vulture.vulture)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture"], [16, "TELF.pre_processing.Vulture.vulture.Vulture"]], "cache (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.cache"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.cache"]], "chunk_tuple_list() (in module telf.pre_processing.vulture.vulture)": [[13, "TELF.pre_processing.Vulture.vulture.chunk_tuple_list"], [16, "TELF.pre_processing.Vulture.vulture.chunk_tuple_list"]], "clean() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.clean"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.clean"]], "clean_dataframe() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.clean_dataframe"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.clean_dataframe"]], "n_jobs (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.n_jobs"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.n_jobs"]], "n_nodes (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.n_nodes"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.n_nodes"]], "operate() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.operate"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.operate"]], "parallel_backend (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.parallel_backend"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.parallel_backend"]], "save_path (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.save_path"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.save_path"]], "use_mpi() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.use_mpi"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.use_mpi"]], "verbose (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.verbose"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.verbose"]], "telf.pre_processing.vulture.tokens_analysis": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis"]], "telf.pre_processing.vulture.tokens_analysis.top_words": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"]], "get_top_words() (in module telf.pre_processing.vulture.tokens_analysis.top_words)": [[14, "TELF.pre_processing.Vulture.tokens_analysis.top_words.get_top_words"]]}})
\ No newline at end of file
+Search.setIndex({"docnames": ["Beaver", "Cheetah", "HNMFk", "NMFk", "RESCALk", "SymNMFk", "TELF", "TELF.factorization", "TELF.factorization.decompositions", "TELF.factorization.decompositions.utilities", "TELF.factorization.utilities", "TELF.pre_processing", "TELF.pre_processing.Beaver", "TELF.pre_processing.Vulture", "TELF.pre_processing.Vulture.tokens_analysis", "TriNMFk", "Vulture", "index", "modules"], "filenames": ["Beaver.rst", "Cheetah.rst", "HNMFk.rst", "NMFk.rst", "RESCALk.rst", "SymNMFk.rst", "TELF.rst", "TELF.factorization.rst", "TELF.factorization.decompositions.rst", "TELF.factorization.decompositions.utilities.rst", "TELF.factorization.utilities.rst", "TELF.pre_processing.rst", "TELF.pre_processing.Beaver.rst", "TELF.pre_processing.Vulture.rst", "TELF.pre_processing.Vulture.tokens_analysis.rst", "TriNMFk.rst", "Vulture.rst", "index.rst", "modules.rst"], "titles": ["TELF.pre_processing.Beaver: Fast matrix and tensor building tool", "TELF.applications.Cheetah: Advanced search by keywords and phrases", "TELF.factorization.HNMFk: Hierarchical Non-negative Matrix Factorization with Automatic Model Determination", "TELF.factorization.NMFk: Non-negative Matrix Factorization with Automatic Model Determination", "TELF.factorization.RESCALk: RESCAL with Automatic Model Determination", "TELF.factorization.SymNMFk: Symmetric Non-negative Matrix Factorization with Automatic Model Determination", "TELF package", "TELF.factorization package", "TELF.factorization.decompositions package", "TELF.factorization.decompositions.utilities package", "TELF.factorization.utilities package", "TELF.pre_processing package", "TELF.pre_processing.Beaver package", "TELF.pre_processing.Vulture package", "TELF.pre_processing.Vulture.tokens_analysis package", "TELF.factorization.TriNMFk: NMFk with Automatic Determination of Latent Clusters and Patterns", "TELF.pre_processing.Vulture: Advanced text pre-processing and cleaning tool for NLP and text-mining", "Tensor Extraction of Latent Features (T-ELF)", "TELF"], "terms": {"i": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17], "sever": 0, "can": [0, 1, 2, 3, 4, 7, 15, 16, 17], "found": [0, 1, 3, 4, 16], "here": [0, 2, 3, 4, 5, 12, 15, 16, 17], "we": [0, 2, 3, 4, 15, 16], "show": [0, 3, 4, 7, 10, 15], "usag": [0, 5], "creat": [0, 1, 3, 4, 7, 9, 10, 12, 13, 16, 17], "document": [0, 1, 7, 10, 12, 13, 14, 15, 16, 17], "word": [0, 1, 10, 12, 14], "first": [0, 2, 3, 4, 7, 9, 10, 12, 15, 16], "let": [0, 16], "": [0, 1, 2, 3, 4, 5, 7, 8, 9, 12, 13, 15, 16, 17], "load": [0, 2, 16, 17], "dataset": [0, 1, 12, 16, 17], "import": [0, 3, 4, 10, 15, 16], "panda": [0, 1, 16], "pd": [0, 1, 12, 14, 16], "df": [0, 10, 13, 14, 16], "read_csv": 0, "data": [0, 1, 2, 3, 4, 7, 10, 12, 15, 16, 17], "sampl": [0, 1, 2, 3, 4, 7], "csv": [0, 1, 12], "info": 0, "next": [0, 15], "vocabulari": [0, 10, 12], "from": [0, 2, 3, 4, 7, 9, 10, 12, 15, 16, 17], "set": [0, 1, 2, 3, 4, 7, 9, 12, 13, 15, 16, 17], "target_column": [0, 12], "clean_abstract": 0, "min_df": [0, 12], "10": [0, 2, 3, 4, 7, 12, 14, 15, 16, 17], "max_df": [0, 12], "0": [0, 3, 4, 5, 7, 8, 9, 10, 12, 15, 16, 17], "5": [0, 1, 12, 15, 17], "get_vocabulari": [0, 11, 12], "option": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15, 17], "matrix_typ": [0, 12], "tfidf": [0, 7, 10, 11, 12], "highlight": [0, 12], "aberr": 0, "abil": 0, "ablat": 0, "abl": 0, "weight": [0, 3, 7, 12], "2": [0, 2, 4, 8, 12, 17], "save_path": [0, 1, 3, 4, 5, 7, 11, 12, 13, 15, 16], "documents_word": [0, 11, 12], "cam": 0, "scipi": [0, 2, 3, 4, 7, 9, 10, 12, 15], "spars": [0, 2, 3, 4, 7, 8, 9, 10, 12, 15], "ss": 0, "save": [0, 1, 2, 3, 4, 7, 10, 12, 14, 15], "file": [0, 1, 10, 17], "which": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "coo": 0, "format": [0, 2, 8, 10], "x_csr_spars": 0, "load_npz": 0, "npz": 0, "2022": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "triad": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nation": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "secur": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "llc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "all": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "right": [0, 3, 4, 5, 7, 8, 9, 10, 12, 13, 15, 16, 17], "reserv": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "thi": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 15, 16, 17], "program": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "wa": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "produc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "under": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "u": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "govern": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "contract": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "89233218cna000001": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "lo": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "alamo": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "laboratori": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "lanl": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "oper": [0, 2, 3, 4, 5, 7, 10, 11, 12, 13, 15, 16, 17], "depart": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "energi": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nuclear": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "administr": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "ar": [0, 1, 3, 4, 5, 7, 9, 10, 12, 13, 14, 15, 16, 17], "The": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 14, 15, 16, 17], "grant": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "itself": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "other": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "act": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "its": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "behalf": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "nonexclus": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "paid": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "up": [0, 1, 3, 4, 5, 7, 12, 13, 15, 16, 17], "irrevoc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "worldwid": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "licens": [0, 3, 4, 5, 7, 12, 13, 15, 16], "materi": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "reproduc": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "prepar": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "deriv": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "work": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "distribut": [0, 3, 4, 5, 7, 9, 12, 13, 15, 16, 17], "copi": [0, 3, 4, 5, 7, 9, 12, 13, 15, 16, 17], "public": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "perform": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "publicli": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "displai": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "permit": [0, 3, 4, 5, 7, 12, 13, 15, 16, 17], "do": [0, 2, 3, 4, 5, 7, 10, 12, 13, 15, 16, 17], "so": [0, 2, 3, 4, 5, 7, 8, 12, 13, 15, 16, 17], "class": [0, 1, 2, 3, 4, 5, 7, 10, 12, 13, 15, 16], "n_node": [0, 2, 3, 4, 5, 7, 11, 12, 13, 16], "1": [0, 1, 2, 3, 4, 5, 7, 8, 9, 12, 13, 14, 15, 16, 17], "n_job": [0, 3, 4, 5, 7, 10, 11, 12, 13, 15, 16], "sourc": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17], "base": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16, 17], "object": [0, 1, 2, 3, 4, 5, 7, 8, 12, 13, 15, 16], "supported_output_format": [0, 11, 12], "pydata": [0, 12], "citation_tensor": [0, 11, 12], "datafram": [0, 1, 12, 14], "tupl": [0, 7, 10, 12, 13, 15, 16], "author_id": [0, 1, 12], "paper_id": [0, 12], "refer": [0, 12], "year": [0, 1, 12, 17], "dimension_ord": [0, 12], "list": [0, 1, 2, 3, 4, 7, 8, 10, 12, 13, 14, 15, 16, 17], "split_authors_with": [0, 12], "str": [0, 1, 2, 3, 4, 7, 10, 12, 14, 15], "split_references_with": [0, 12], "none": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16], "int": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 13, 14, 15, 16], "joblib_backend": [0, 12], "loki": [0, 12, 13, 16], "verbos": [0, 1, 2, 3, 4, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16], "bool": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15], "fals": [0, 1, 2, 3, 4, 5, 7, 9, 10, 12, 13, 15, 16], "return_object": [0, 12], "true": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 12, 14, 15], "output_mod": [0, 12], "an": [0, 1, 3, 4, 7, 9, 12, 15, 17], "author": [0, 1, 10, 12], "paper": [0, 1, 12], "time": [0, 1, 2, 3, 4, 7, 8, 9, 12, 14, 15], "non": [0, 7, 9, 12, 15, 17], "zero": [0, 8, 9, 12], "entri": [0, 1, 10, 12], "x": [0, 2, 3, 4, 5, 7, 8, 9, 10, 12, 15], "j": [0, 8, 9, 12], "k": [0, 2, 3, 4, 5, 7, 8, 9, 10, 12, 15, 17], "mean": [0, 9, 12], "cite": [0, 12], "paramet": [0, 2, 3, 4, 7, 8, 9, 12, 13, 14, 15, 16], "contain": [0, 1, 9, 10, 12, 13, 16], "target": [0, 9, 12], "column": [0, 1, 2, 3, 4, 7, 9, 12, 13, 14, 15, 16], "name": [0, 1, 3, 4, 5, 7, 10, 12, 15, 17], "default": [0, 1, 2, 3, 4, 7, 9, 10, 12, 14, 15], "when": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15, 17], "assign": [0, 9, 12], "type": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15], "order": [0, 1, 9, 10, 12, 16], "should": [0, 1, 2, 3, 7, 12, 15], "preserv": [0, 1, 12], "e": [0, 12, 17], "g": [0, 12], "come": [0, 12], "last": [0, 1, 12], "dimens": [0, 9, 12], "appear": [0, 1, 12], "For": [0, 1, 2, 12], "what": [0, 3, 4, 7, 12], "symbol": [0, 12], "us": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 15, 17], "get": [0, 1, 12, 17], "individu": [0, 12], "element": [0, 9, 10, 12], "string": [0, 1, 10, 12], "If": [0, 1, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15], "output": [0, 3, 4, 7, 8, 9, 10, 12, 16], "number": [0, 2, 3, 4, 7, 8, 9, 10, 12, 14, 15, 17], "node": [0, 1, 2, 3, 4, 7, 10, 12, 13, 16, 17], "job": [0, 2, 3, 4, 7, 12, 15], "joblib": [0, 12], "parallel": [0, 3, 4, 7, 12, 13, 15, 16], "backend": [0, 12, 13, 16], "multiprocess": [0, 12, 13, 16], "vebos": [0, 1, 12], "flag": [0, 1, 9, 12, 14], "determin": [0, 1, 7, 12, 17], "whether": [0, 9, 12, 17], "gener": [0, 1, 2, 3, 4, 7, 9, 12, 15], "return": [0, 2, 3, 4, 7, 8, 9, 12, 14, 15], "In": [0, 10, 12], "case": [0, 10, 12], "larg": [0, 12, 17], "mai": [0, 10, 12, 17], "better": [0, 12], "disk": [0, 12], "without": [0, 12, 17], "see": [0, 1, 5, 7, 12, 15, 17], "support": [0, 1, 12], "coauthor_tensor": [0, 11, 12], "authorid": [0, 12], "authors_idx_map": [0, 12], "dict": [0, 1, 2, 3, 4, 7, 8, 10, 12, 14, 15], "time_idx_map": [0, 12], "co": [0, 9, 10, 12], "second": [0, 1, 12], "index": [0, 1, 2, 10, 12, 17], "map": [0, 1, 12], "pass": [0, 1, 3, 4, 7, 12, 16], "cocitation_tensor": [0, 11, 12], "note": [0, 1, 3, 4, 5, 7, 10, 12, 15], "normal": [0, 12, 13, 16], "two": [0, 1, 12], "b": [0, 1, 9, 12, 13, 16, 17], "where": [0, 1, 2, 9, 10, 12], "n": [0, 1, 8, 9, 12, 13, 14, 16, 17], "singl": [0, 1, 2, 9, 10, 12], "receiv": [0, 12], "citat": [0, 12], "each": [0, 2, 3, 4, 7, 9, 10, 12, 15], "cooccurrence_matrix": [0, 11, 12], "abstract": [0, 1, 12], "cooccurrence_set": [0, 12], "sppmi_set": [0, 12], "occur": [0, 10, 12, 14], "sppmi": [0, 6, 7, 10, 11], "text": [0, 1, 8, 10, 12, 14, 17], "token": [0, 1, 12, 14], "retriv": [0, 12], "via": [0, 12, 17], "empti": [0, 1, 3, 7, 12], "space": [0, 10, 12], "window_s": [0, 1, 10, 12], "20": [0, 3, 4, 5, 7, 10, 12, 15], "dens": [0, 3, 4, 9, 10, 12, 15], "sentenc": [0, 10, 12], "shift": [0, 10, 12], "4": [0, 1, 3, 4, 7, 10, 12, 15, 17], "vector": [0, 6, 7, 9, 11], "tf": [0, 10, 12, 14], "idf": [0, 10, 12], "count": [0, 7, 10, 11, 12], "float": [0, 1, 3, 4, 7, 9, 12], "get_ngram": [0, 11, 12], "limit": [0, 12, 17], "gram": [0, 1, 12, 14], "restrict": [0, 12], "top": [0, 8, 12, 14], "ngram": [0, 1, 12], "max_featur": [0, 12], "kwarg": [0, 9, 10, 12], "ignor": [0, 1, 12], "term": [0, 1, 12, 14], "have": [0, 12], "frequenc": [0, 12, 14], "strictli": [0, 12], "higher": [0, 12], "than": [0, 1, 12], "given": [0, 1, 2, 3, 4, 7, 9, 12, 13, 14, 15, 16], "threshold": [0, 3, 7, 12], "corpu": [0, 12], "specif": [0, 12, 13, 16, 17], "stop": [0, 2, 3, 7, 12, 15], "rang": [0, 2, 3, 4, 7, 12, 15], "repres": [0, 12, 13, 16], "proport": [0, 12], "integ": [0, 12], "absolut": [0, 12], "lower": [0, 12], "valu": [0, 1, 2, 3, 4, 7, 10, 12, 13, 14, 15, 16], "also": [0, 10, 12], "call": [0, 1, 8, 10, 12], "cut": [0, 12, 17], "off": [0, 9, 12], "literatur": [0, 12], "onli": [0, 1, 2, 3, 4, 7, 12, 15, 17], "consid": [0, 12], "across": [0, 12, 17], "properti": [0, 1, 12, 13, 16], "participation_tensor": [0, 11, 12], "boolean": [0, 9, 12], "publish": [0, 1, 12], "something_word": [0, 11, 12], "split_something_with": [0, 12], "someth": [0, 12], "specifi": [0, 1, 2, 3, 4, 7, 12, 15], "variabl": [0, 2, 12], "evel": [0, 12], "seper": [0, 2, 12], "autho1": [0, 12], "author2": [0, 12], "inform": [0, 2, 10, 12, 17], "something_words_tim": [0, 11, 12], "tfidf_transform": [0, 12], "unfold_at": [0, 12], "unfold": [0, 8, 9, 11, 12], "over": [0, 3, 4, 7, 12], "tool": [1, 13, 17], "custom": [1, 2, 3, 7, 9], "fast": [1, 12, 13, 16, 17], "tue": 1, "feb": 1, "15": 1, "17": 1, "05": 1, "54": 1, "maksimekineren": [1, 10, 12], "init": [1, 3, 4, 7, 15], "affili": 1, "titl": [1, 17], "retriev": 1, "A": [1, 8, 9, 10, 17], "dictionari": [1, 2, 8, 10, 14], "kei": [1, 10, 13, 14, 16], "classmethod": 1, "find_ngram": 1, "queri": 1, "within": 1, "slide": 1, "window": [1, 10, 12], "algorithm": [1, 8, 9, 12], "need": [1, 8], "maintain": 1, "posit": [1, 10, 12, 17], "match": 1, "multipl": [1, 3, 7, 8, 10], "separ": [1, 10], "whitespac": 1, "check": 1, "duplic": 1, "allow": 1, "size": [1, 2, 10, 12], "len": [1, 14], "ever": 1, "cannot": [1, 2], "fit": [1, 2, 3, 4, 5, 6, 7, 15, 17], "otherwis": [1, 17], "index_fil": 1, "reindex": 1, "indic": [1, 2, 8, 9, 10, 12], "select": [1, 2, 7, 15], "expect": 1, "respect": [1, 13, 16], "slic": 1, "structur": [1, 17], "exampl": [1, 2, 5, 7, 12, 17], "notebook": 1, "pre": [1, 3, 4, 13, 15, 17], "process": [1, 2, 3, 4, 7, 10, 13, 17], "vultur": [1, 6, 11, 17], "simpl": [1, 3, 4, 7, 13, 16], "clean": [1, 11, 13, 17], "lowercas": 1, "special": [1, 17], "charact": [1, 10], "remov": [1, 3, 4, 7, 9, 15], "delimit": 1, "categori": 1, "correspond": [1, 9, 13, 16], "current": [1, 2, 10], "path": [1, 3, 4, 10, 15, 16], "previous": 1, "one": [1, 2, 14, 17], "doe": 1, "exist": 1, "them": 1, "futur": 1, "new": 1, "overwrit": 1, "ngram_ord": 1, "statu": 1, "ngram_window_s": 1, "numer": 1, "either": [1, 3, 4, 15], "union": 1, "and_search": 1, "in_titl": 1, "in_abstract": 1, "author_filt": 1, "affiliation_filt": 1, "country_filt": 1, "year_filt": 1, "do_results_t": 1, "link_search": 1, "filter": [1, 3, 7], "both": [1, 7, 15, 17], "result": [1, 2, 3, 4, 7, 15, 16, 17], "intersect": 1, "try": [1, 2, 16], "never": 1, "error": [1, 3, 4, 7, 9, 15, 17], "nonetyp": 1, "lookup": 1, "split": [1, 13, 16], "convert": 1, "lowecas": 1, "strip": 1, "extra": 1, "laser": 1, "neg": [1, 7, 15, 17], "angl": [1, 9], "deflect": 1, "bigram": 1, "blue": 1, "green": 1, "unigram": 1, "appli": [1, 7, 15, 17], "being": [1, 9, 10], "look": 1, "simulten": 1, "between": [1, 10], "subset": 1, "defin": [1, 2], "id": [1, 14], "countri": 1, "more": [1, 3, 7, 13, 16], "how": [1, 2, 13, 14, 16], "mani": [1, 13, 14, 16], "examin": 1, "aa": 1, "bb": 1, "cc": 1, "dd": 1, "greater": 1, "length": 1, "while": [1, 10], "tabl": [1, 14], "provid": [1, 3, 4, 15, 17], "explain": 1, "why": 1, "certain": 1, "were": 1, "argument": [1, 8, 9], "control": 1, "link": [1, 17], "inclus": 1, "step": [1, 2, 13, 16, 17], "take": [1, 10], "howev": [1, 17], "partner": 1, "overrid": 1, "sinc": 1, "anoth": 1, "had": 1, "alreadi": [1, 9], "topic": [1, 2], "henc": 1, "return_data": 1, "results_t": 1, "add_with_union_of_oth": [1, 17], "d": [1, 8, 13, 16, 17], "comput": [1, 3, 4, 7, 9, 10, 12, 15, 16, 17], "addit": [1, 2], "associ": 1, "ad": 1, "whose": [1, 10], "modifi": 1, "valueerror": 1, "includ": [2, 3, 4, 7, 15, 17], "miss": [2, 3, 7], "predict": [2, 3, 4, 7, 15], "ha": [2, 3, 4, 7, 9, 15, 16], "hpc": [2, 3, 4, 7, 17], "schedul": 2, "200": [2, 3], "complet": [2, 3, 7], "300": 2, "signal": 2, "exit": 2, "400": 2, "nmfk_param": [2, 7, 15], "cluster_on": 2, "h": [2, 3, 7, 8, 9, 10, 15], "depth": 2, "sample_thresh": 2, "ks_deep_min": 2, "ks_deep_max": 2, "ks_deep_step": 2, "k2": 2, "experiment_nam": [2, 7, 15], "hnmfk_output": 2, "generate_x_callback": 2, "comm_buff_s": 2, "10000000": 2, "capabl": [2, 3, 4, 5, 7, 15, 16], "nmfk": [2, 6, 17, 18], "same": [2, 8], "item": 2, "hmmfk": 2, "append": [2, 3, 4, 8, 15], "nmfk_params0": 2, "nmfk_params1": 2, "nmfk_params2": 2, "requir": 2, "param": [2, 3, 4, 9, 12], "collect_output": [2, 3, 4, 5, 7, 15], "save_output": [2, 3, 4, 5, 7], "predict_k": [2, 3, 7, 15], "cluster": [2, 6, 7, 8, 17], "w": [2, 3, 7, 8, 9, 12, 13, 15, 16], "ff": 2, "row": [2, 3, 4, 7, 8, 9, 15], "deep": 2, "go": 2, "after": [2, 3, 7, 15], "root": 2, "goe": 2, "until": 2, "further": 2, "criteria": [2, 3, 7, 15], "num": [2, 9], "search": [2, 17], "minimum": 2, "start": 2, "optin": 2, "maximum": [2, 3, 4, 7, 9], "parent": 2, "decomposit": [2, 3, 6, 7], "done": [2, 3, 4, 7, 15], "instead": 2, "find": [2, 9], "stabl": [2, 9], "latent": [2, 3, 4, 7], "featur": 2, "re": [2, 13, 16], "befor": [2, 3, 7, 15], "slice": [2, 9], "origin": [2, 3, 4, 7], "taken": 2, "equal": 2, "serial": 2, "def": 2, "__call__": 2, "original_indic": 2, "new_x": 2, "save_at_nod": 2, "hyper": 2, "user_node_data": 2, "print": [2, 10, 12], "progress": [2, 3, 4, 7, 10, 12, 15], "from_checkpoint": 2, "save_checkpoint": 2, "input": [2, 3, 4, 7, 8, 9, 10, 12, 15], "np": [2, 3, 4, 7, 9, 10, 12, 15], "ndarrai": [2, 3, 4, 7, 8, 9, 10, 12, 15], "_csr": [2, 3, 4, 7, 9, 15], "csr_matrix": [2, 3, 4, 7, 9, 10, 15], "continu": 2, "checkpoint": 2, "get_nod": 2, "graph": 2, "iter": [2, 3, 4, 7, 8, 9, 15], "onlin": 2, "kept": 2, "memori": 2, "go_to_children": 2, "idx": 2, "child": 2, "go_to_par": 2, "go_to_root": 2, "traverse_nod": 2, "persist": 2, "node_nam": 2, "parent_top": 2, "parent_node_nam": 2, "child_node_nam": 2, "num_sampl": 2, "leaf": 2, "onlinenod": [2, 17], "node_path": 2, "parent_nod": 2, "child_nod": 2, "synthet": [3, 4, 15], "It": [3, 4, 13, 15, 16], "script": [3, 4, 15], "locat": [3, 4, 7, 10, 14, 15, 17], "sy": [3, 4, 15], "generate_x": [3, 4, 15], "gen_data": [3, 4], "gen_data_spars": 3, "xsp": 3, "shape": [3, 4, 7, 9, 12, 15], "100": [3, 4, 7, 8, 9, 15, 17], "densiti": 3, "01": [3, 15], "r": [3, 4, 8, 9, 17], "now": [3, 4, 16], "n_perturb": [3, 4, 5, 7, 15], "36": 3, "n_iter": [3, 4, 5, 7, 15], "epsilon": [3, 4, 5, 7, 9, 15], "015": [3, 4, 5, 7], "nnsvd": [3, 4, 7, 8, 15], "use_gpu": [3, 4, 5, 7, 8, 9, 10, 15], "predict_k_method": [3, 7, 15], "sill": [3, 7, 15], "nmf_verbos": [3, 5, 7, 8, 15], "transpos": [3, 4, 5, 7, 15], "sill_thresh": [3, 7, 15], "9": [3, 10, 16], "prune": [3, 4, 7, 8, 9, 15], "nmf_method": [3, 5, 7, 15], "nmf_kl_mu": [3, 6, 7], "calculate_error": [3, 4, 7, 10, 15], "use_consensus_stop": [3, 5, 7, 8, 15], "calculate_pac": [3, 5, 7, 15], "perturb_typ": [3, 4, 5, 7, 15], "uniform": [3, 4, 5, 7, 9, 15], "11": [3, 17], "example_nmfk": 3, "run": [3, 4, 16], "plot": [3, 4, 7, 9, 10, 15], "estim": [3, 4, 7, 15, 17], "rank": [3, 4, 7, 9, 17], "perturb_verbos": [3, 4, 5, 7], "8": [3, 4, 7, 15], "nmf_func": [3, 7], "nmf_fro_mu": [3, 6, 7, 15], "nmf_obj_param": [3, 5, 7], "perturb_multiprocess": [3, 4, 5, 7], "consensus_mat": [3, 7, 15], "mask": [3, 5, 7, 8, 9, 15], "get_plot_data": [3, 4, 5, 7, 15], "simple_plot": [3, 4, 7, 10, 15], "bootstrap": [3, 4, 7, 15], "random": [3, 4, 5, 7, 9], "matric": [3, 4, 7, 8, 9, 12, 15], "around": [3, 4, 7], "nmf": [3, 7, 8, 9, 10, 15], "amount": [3, 4, 7, 9], "poisson": [3, 4, 7, 8, 9], "poission": [3, 4, 7], "resourc": [3, 4, 7, 15], "initil": [3, 4, 7, 8, 15], "procedur": [3, 4, 7], "gpu": [3, 4, 7, 9, 15, 17], "collect": [3, 4, 7, 14], "even": [3, 7, 17], "figur": [3, 7], "method": [3, 7, 8, 9, 15], "pvalu": [3, 7], "l": [3, 7, 13, 16], "statist": [3, 4, 7, 14, 17], "wise": [3, 7], "silhouett": [3, 4, 7, 8, 15], "score": [3, 4, 7, 9, 15], "significantli": [3, 7, 13, 16], "longer": [3, 4, 7], "altough": [3, 7], "accur": [3, 7], "hand": [3, 7], "much": [3, 7], "faster": [3, 7], "perturb": [3, 4, 7, 9], "func": [3, 4, 7], "frobeni": [3, 4, 7], "norm": [3, 4, 7, 8, 9], "updat": [3, 7, 8], "rule": [3, 7], "kl": [3, 7, 8], "diverg": [3, 7, 8], "nmf_recommend": [3, 7], "recommend": [3, 7], "collabor": [3, 7], "wnmf": [3, 7], "possibl": [3, 7, 17], "left": [3, 7, 8, 9, 10], "min": [3, 7], "calcul": [3, 4, 7, 9], "rel": [3, 4, 7, 9], "reconstruct": [3, 4, 7], "make": [3, 4, 7, 17], "consensu": [3, 7, 9, 15], "earli": [3, 7, 15], "numpi": [3, 7, 9, 10, 15], "arrai": [3, 7, 8, 9, 10, 12, 15, 17], "point": [3, 7, 9, 15], "out": [3, 7, 10, 15, 17], "dure": [3, 7, 15], "pac": [3, 7, 9, 15], "stabil": [3, 7], "intermidi": [3, 4, 7], "hide": [3, 4, 7], "averag": [3, 4, 7], "experi": [3, 4, 7, 10, 15], "log": [3, 4, 7, 8, 10, 15], "took": [3, 4, 7, 15], "depend": [3, 4, 7, 15, 17], "field": [3, 4, 7, 15, 17], "plot_data": [3, 4, 7, 15], "k_predict": [3, 7, 10, 15], "intig": [3, 7, 15], "alwai": [3, 4, 7, 15], "give": [3, 4, 7, 15], "total": [3, 4, 7, 14, 15], "recalk": 4, "matrix": [4, 7, 8, 9, 10, 12, 15, 17], "1000": [4, 5, 8, 9], "gen": 4, "rescal_verbos": [4, 7, 8], "rescal_method": [4, 7], "rescal_fro_mu": [4, 6, 7], "7": [4, 5], "rescal_func": [4, 7], "rescal_obj_param": [4, 7], "implement": [4, 7], "yet": [4, 7], "symmetr": [4, 7, 17], "init_typ": 5, "newton": 5, "graph_typ": 5, "full": 5, "similarity_typ": 5, "gaussian": 5, "nearest_neighbor": 5, "pac_thresh": 5, "factor": [6, 12, 17, 18], "nmf_fro_admm": [6, 7], "nmf_kl_admm": [6, 7], "nmf_mc_fro_mu": [6, 7], "tri_nmf_fro_mu": [6, 7], "util": [6, 7, 8], "co_occurance_matrix": [6, 7], "organize_n_job": [6, 7], "plot_nmfk": [6, 7], "pvalue_analysi": [6, 7], "sppmi_matrix": [6, 7, 12], "take_not": [6, 7], "rescalk": [6, 17, 18], "trinmfk": [6, 17, 18], "fit_nmfk": [6, 7, 15], "fit_tri_nmfk": [6, 7, 15], "pre_process": [6, 17, 18], "beaver": [6, 11, 17], "cooccurr": [6, 10, 11], "tenmat": [6, 11], "bool_clust": [7, 8], "bool_nois": [7, 8], "concensus_matrix": [7, 8], "data_reshap": [7, 8], "generic_util": [7, 8], "math_util": [7, 8], "resampl": [7, 8], "h_updat": [7, 8], "w_updat": [7, 8], "h_update_admm": [7, 8], "h_update_mu": [7, 8], "w_update_admm": [7, 8], "w_update_mu": [7, 8], "coord_desc_thresh": [7, 8], "coord_desc_thresh_onefactor": [7, 8], "find_thres_wh": [7, 8], "nmf_with_admm": [7, 8], "old_find_thres_wh": [7, 8], "old_nmf": [7, 8], "roc_w_h": [7, 8], "thres_norm": [7, 8], "a_upd": [7, 8], "r_updat": [7, 8], "rescal": [7, 8, 17], "s_updat": [7, 8], "trinmf": [7, 8], "h_cluster": [7, 10], "plot_h_clust": [7, 10], "co_occurr": [7, 10, 11, 12], "plot_bnmfk": [7, 10], "plot_symnmfk": [7, 10], "plot_consensus_mat": [7, 10], "plot_cophenetic_coeff": [7, 10], "append_to_not": [7, 10], "format_not": [7, 10], "take_note_fmat": [7, 10], "automat": [7, 13, 16, 17], "model": [7, 15, 17], "avail": [7, 17], "function": [7, 8, 10, 12, 17], "alpha": [7, 8, 15], "n_init": [7, 15], "pattern": [7, 13, 16, 17], "wk": [7, 15], "hk": [7, 15], "rate": [7, 15], "k1k2": [7, 15], "3": [7, 12, 15, 17], "mix": [7, 15], "along": [7, 12, 15], "custom_bool_clust": [8, 9], "add_bool_nois": [8, 9], "add_bool_posneg_nois": [8, 9], "custom_k_mean": [8, 9], "compute_connectivity_mat": [8, 9], "compute_consensus_matrix": [8, 9], "reorder_con_mat": [8, 9], "fold": [8, 9, 11, 12], "move_axi": [8, 9], "bary_proj": [8, 9], "get_cupyx": [8, 9], "get_np": [8, 9], "get_scipi": [8, 9], "grid_ev": [8, 9], "update_opt": [8, 9], "bary_coord": [8, 9], "fro_norm": [8, 9], "get_pac": [8, 9], "kl_diverg": [8, 9], "masked_nmf": [8, 9], "nan_to_num": [8, 9], "norm_x": [8, 9], "nz_indic": [8, 9], "relative_error": [8, 9], "relative_error_resc": [8, 9], "relative_trinmf_error": [8, 9], "sparse_divide_product": [8, 9], "sparse_dot_product": [8, 9], "unprun": [8, 9], "uniform_product": [8, 9], "custom_silhouett": [8, 9], "opt": 8, "dual": 8, "admm": 8, "nonneg": [8, 9, 12], "optim": [8, 17], "frobeniu": 8, "loss": [8, 17], "underset": 8, "operatornam": 8, "minim": 8, "frac": 8, "vert": 8, "vert_f": 8, "subject": 8, "quad": 8, "geq": 8, "m": [8, 9, 10, 12, 17], "decompos": 8, "initi": [8, 9], "hist": 8, "niter": 8, "rho": 8, "doubl": [8, 9], "converg": 8, "w_opt": 8, "h_opt": 8, "kullback": 8, "leibler": 8, "_": [8, 13, 16], "sum_": 8, "x_": [8, 9], "wh": [8, 9], "nz_row": [8, 9], "1d": [8, 9], "csr": [8, 10, 12], "nz_col": [8, 9], "col": [8, 9], "csc": 8, "_f": [8, 9], "wt": 8, "ht": 8, "max_it": [8, 9], "wn": 8, "hn": 8, "best": 8, "npoint": 8, "lowerthr": 8, "upperthr": 8, "penal": 8, "adapt": [8, 17], "grid_search": 8, "sum": 8, "x_i": 8, "r_i": 8, "pair": [8, 10], "a_opt": 8, "r_opt": 8, "alpha_h": 8, "alpha_w": 8, "tri": 8, "With": 8, "orthogon": 8, "constraint": 8, "kw": [8, 9], "kx": 8, "kh": [8, 9], "middl": [8, 9], "w_all": 9, "centroid": [9, 10], "distanc": 9, "ham": 9, "noiseperc": 9, "greedi": 9, "approxim": [9, 13, 16], "quadrat": 9, "problem": [9, 17], "p": [9, 16], "group": 9, "construct": [9, 17], "three": 9, "tensor": [9, 12], "ambient": 9, "been": 9, "reach": 9, "warn": 9, "organ": 9, "dimension": 9, "ith": 9, "cosin": 9, "sil": [9, 10], "measur": 9, "h_all": 9, "perturb_col": 9, "c": [9, 10, 12, 17], "return_index": 9, "hc": 9, "axi": [9, 12], "num_var": 9, "barycentr": 9, "coordin": 9, "activ": [9, 17], "extrem": 9, "rai": 9, "theta": 9, "arg": 9, "fn": 9, "grid": 9, "num_cpu": 9, "y": 9, "3d": 9, "cdf": 9, "itr": 9, "replac": 9, "nan": 9, "els": 9, "normx": 9, "you": [9, 17], "know": 9, "rel_err": 9, "kk": 9, "wsh": 9, "effici": [9, 12], "svd": 9, "gilli": 9, "et": 9, "al": 9, "http": [9, 12, 17], "arxiv": 9, "org": [9, 12, 17], "pdf": 9, "1807": 9, "04020": 9, "desir": 9, "random_st": [9, 15], "y_": 9, "multipli": 9, "gather": 10, "clusters_inform": 10, "centroid_similar": 10, "carri": 10, "filenam": [10, 14], "matplotlib": [10, 15], "mon": [10, 12], "nov": [10, 12], "22": [10, 12], "18": [10, 12], "38": [10, 12], "26": [10, 12], "2021": [10, 12], "form": [10, 12, 17], "consecut": [10, 12], "analysi": [10, 12, 17], "unqiu": [10, 12], "present": [10, 12, 17], "build": [10, 12, 17], "bool_err": 10, "plot_predict": 10, "plot_fin": 10, "descript": 10, "fignam": 10, "coeff": 10, "errregr": 10, "sill_min": 10, "sill_thr": 10, "cooc": [10, 12], "pointwis": [10, 12], "mutual": [10, 12], "cooccur": [10, 12], "erik": [10, 12, 17], "skau": [10, 12, 17], "lock": 10, "write": 10, "newlin": 10, "safe": 10, "thread": [10, 13, 16], "applic": [10, 12, 13, 16, 17], "protect": 10, "ensur": [10, 17], "simultan": 10, "enter": 10, "directori": [10, 16, 17], "rtype": 10, "16": [10, 17], "align": 10, "rest": 10, "accord": 10, "tab": 10, "follow": [10, 17], "written": [10, 17], "sort_index": 10, "record": 10, "some": [10, 17], "stat": 10, "manner": 10, "These": 10, "store": 10, "signifi": 10, "care": 10, "sort": 10, "batch": 10, "caus": [10, 17], "sklearn": [10, 12], "librari": [10, 12, 16, 17], "bag": [10, 12], "submodul": [11, 18], "tokens_analysi": [11, 13], "top_word": [11, 13], "default_operator_pipelin": [11, 13, 16], "default_pipelin": [11, 13, 16], "parallel_backend_opt": [11, 13, 16], "cach": [11, 13, 16], "clean_datafram": [11, 13, 16], "parallel_backend": [11, 12, 13, 16], "use_mpi": [11, 13, 16], "chunk_tuple_list": [11, 13, 16, 17], "py": [12, 17], "softwar": [12, 17], "latest": 12, "releas": 12, "brett": 12, "bader": 12, "tamara": 12, "kolda": 12, "toolbox": [12, 17], "matlab": 12, "version": [12, 17, 18], "www": 12, "tensortoolbox": 12, "april": 12, "t": 12, "862": 12, "prototyp": 12, "acm": 12, "tran": 12, "mathemat": [12, 17], "32": 12, "635": 12, "653": 12, "2006": 12, "dx": 12, "doi": [12, 17], "1145": 12, "1186785": 12, "1186794": 12, "kruskal": 12, "tucker": 12, "siam": 12, "scientif": 12, "30": 12, "205": 12, "231": 12, "2007": 12, "1137": 12, "060676489": 12, "chi": 12, "2012": 12, "On": [12, 17], "sparsiti": 12, "journal": 12, "33": 12, "pp": 12, "1272": 12, "1299": 12, "maksim": [12, 17], "ekin": 12, "eren": [12, 17], "mode": 12, "dim": 12, "unfol": 12, "get_top_word": [13, 14], "tmp": [13, 16], "multi": [13, 16, 17], "design": [13, 16], "natur": [13, 16, 17], "cleaner": [13, 16], "nedetector": [13, 16], "module_typ": [13, 16], "simpleclean": [13, 16], "effective_stop_word": [13, 16], "characterist": [13, 16], "acknowledg": [13, 16], "predominantli": [13, 16], "investig": [13, 16], "unfortun": [13, 16], "substanti": [13, 16], "nevertheless": [13, 16], "demonstr": [13, 16], "introduct": [13, 16], "suffici": [13, 16], "particularli": [13, 16], "consequ": [13, 16], "successfulli": [13, 16], "background": [13, 16], "1359": [13, 16], "standardize_hyphen": [13, 16], "compil": [13, 16], "u002d": [13, 16], "u2010": [13, 16], "u2011": [13, 16], "u2012": [13, 16], "u2013": [13, 16], "u2014": [13, 16], "u2015": [13, 16], "u2212": [13, 16], "u2e3a": [13, 16], "u2e3b": [13, 16], "remove_copyright_stat": [13, 16], "remove_stop_phras": [13, 16], "make_lower_cas": [13, 16], "remove_trailing_dash": [13, 16], "make_hyphens_word": [13, 16], "z": [13, 16], "remove_next_lin": [13, 16], "remove_email": [13, 16], "remove_formula": [13, 16], "remove_dash": [13, 16], "remove_between_": [13, 16], "remove_": [13, 16], "remove_numb": [13, 16], "remove_standalone_numb": [13, 16], "remove_nonascii_boundari": [13, 16], "x00": [13, 16], "x7f": [13, 16], "remove_nonascii": [13, 16], "remove_tag": [13, 16], "lt": [13, 16], "gt": [13, 16], "remove_special_charact": [13, 16], "isolate_frozen": [13, 16], "remove_extra_whitespac": [13, 16], "remove_stop_word": [13, 16], "min_charact": [13, 16], "exclude_hyphenated_stopword": [13, 16], "sw_pattern": [13, 16], "substitut": [13, 16, 17], "append_to_original_df": [13, 16], "concat_cleaned_col": [13, 16], "file_nam": [13, 16], "n_chunk": [13, 16], "sub": [13, 16], "yield": [13, 16], "top_n": 14, "n_gram": 14, "df_fraction": 14, "tf_fraction": 14, "uniqu": 14, "report": 14, "gen_trinmf_data": 15, "pyplot": 15, "plt": 15, "kwkh": 15, "factor_wh": 15, "factor_": 15, "wtrue": 15, "strue": 15, "htrue": 15, "64": 15, "2000": 15, "tri_nmfk_param": 15, "portion": 15, "trinfmk": 15, "tri_nmfk_result": 15, "pickl": 16, "data_dir": 16, "o": 16, "join": 16, "pathlib": 16, "resolv": [16, 17], "data_fil": 16, "open": [16, 17], "rb": 16, "lemmatizeclean": 16, "substitutionclean": 16, "removenonenglishclean": 16, "default_stop_word": 16, "stop_word": 16, "default_stop_phras": 16, "stop_phras": 16, "results_dir": 16, "results_fil": 16, "clean_docu": 16, "mkdir": 16, "except": 16, "fileexistserror": 16, "pipelin": 16, "disabl": 16, "ascii_ratio": 16, "stopwords_ratio": 16, "25": 16, "spaci": [16, 17], "cleaned_docu": 16, "machin": 17, "learn": 17, "packag": [17, 18], "part": 17, "win": 17, "smarttensor": 17, "ai": 17, "project": 17, "customiz": 17, "solut": 17, "craft": 17, "comprehens": 17, "facilit": 17, "decis": 17, "leverag": 17, "high": 17, "edg": 17, "architectur": 17, "our": 17, "analyz": 17, "divers": 17, "central": 17, "core": 17, "lie": 17, "discov": 17, "facet": 17, "hidden": 17, "detail": 17, "autom": 17, "pivot": 17, "precis": 17, "conceal": 17, "addition": 17, "incorpor": 17, "modul": [17, 18], "post": 17, "tailor": 17, "task": 17, "mine": 17, "languag": 17, "robust": 17, "span": 17, "multitud": 17, "disciplin": 17, "analyt": 17, "Its": 17, "proven": 17, "efficaci": 17, "extend": 17, "variou": 17, "scale": 17, "dynam": 17, "network": 17, "biologi": 17, "scienc": 17, "medicin": 17, "chemistri": 17, "compress": 17, "climat": 17, "studi": 17, "relat": 17, "databas": 17, "privaci": 17, "economi": 17, "agricultur": 17, "websit": 17, "code": 17, "pip": 17, "conda": 17, "telf": 17, "python": 17, "git": 17, "github": 17, "com": 17, "clone": 17, "cd": 17, "setup": 17, "env": 17, "environment_gpu": 17, "yml": 17, "environment_cpu": 17, "cpu": 17, "telf_conda": 17, "nlp": 17, "nltk": 17, "download": 17, "en_core_web_lg": 17, "en_core_web_trf": 17, "wordnet": 17, "omw": 17, "cupi": 17, "skip": 17, "forg": 17, "mpi": 17, "openmpi": 17, "mpi4pi": 17, "system": 17, "tutori": 17, "jupyt": 17, "consider": 17, "linux": 17, "devic": 17, "cuda": 17, "configur": 17, "cudatoolkit": 17, "cudnn": 17, "pleas": 17, "apa": 17, "solovyev": 17, "barron": 17, "bhattarai": 17, "truong": 17, "boureima": 17, "rasmussen": 17, "alexandrov": 17, "2023": 17, "5281": 17, "zenodo": 17, "10257897": 17, "bibtex": 17, "nick": 17, "ryan": 17, "manish": 17, "duc": 17, "ismael": 17, "kim": 17, "boian": 17, "month": 17, "oct": 17, "url": 17, "advanc": 17, "research": 17, "cyber": 17, "nichola": 17, "theoret": 17, "divis": 17, "c22048": 17, "bsd": 17, "redistribut": 17, "binari": 17, "modif": 17, "condit": 17, "met": 17, "must": 17, "retain": 17, "abov": 17, "disclaim": 17, "neither": 17, "holder": 17, "nor": 17, "contributor": 17, "endors": 17, "promot": 17, "product": 17, "prior": 17, "permiss": 17, "BY": 17, "THE": 17, "AND": 17, "AS": 17, "ani": 17, "express": 17, "OR": 17, "impli": 17, "warranti": 17, "BUT": 17, "NOT": 17, "TO": 17, "OF": 17, "merchant": 17, "FOR": 17, "particular": 17, "purpos": 17, "IN": 17, "NO": 17, "event": 17, "shall": 17, "BE": 17, "liabl": 17, "direct": 17, "indirect": 17, "incident": 17, "exemplari": 17, "consequenti": 17, "damag": 17, "procur": 17, "good": 17, "servic": 17, "profit": 17, "busi": 17, "interrupt": 17, "ON": 17, "theori": 17, "liabil": 17, "strict": 17, "tort": 17, "neglig": 17, "aris": 17, "wai": 17, "IF": 17, "advis": 17, "SUCH": 17, "ran": 17, "folder": 17, "pytest": 17, "hnmfk": 17, "hierarch": 17, "symnmfk": 17, "cheetah": 17, "keyword": 17, "phrase": 17, "page": 17, "subpackag": 18, "content": 18}, "objects": {"": [[6, 0, 0, "-", "TELF"]], "TELF.applications.Cheetah": [[1, 0, 0, "-", "cheetah"]], "TELF.applications.Cheetah.cheetah": [[1, 1, 1, "", "Cheetah"], [1, 5, 1, "", "add_with_union_of_others"]], "TELF.applications.Cheetah.cheetah.Cheetah": [[1, 2, 1, "", "COLUMNS"], [1, 3, 1, "", "columns"], [1, 4, 1, "", "find_ngram"], [1, 4, 1, "", "index"], [1, 3, 1, "", "ngram_ordered"], [1, 3, 1, "", "ngram_window_size"], [1, 3, 1, "", "query"], [1, 4, 1, "", "search"]], "TELF": [[7, 0, 0, "-", "factorization"], [11, 0, 0, "-", "pre_processing"], [6, 0, 0, "-", "version"]], "TELF.factorization": [[2, 0, 0, "-", "HNMFk"], [7, 0, 0, "-", "NMFk"], [7, 0, 0, "-", "RESCALk"], [5, 0, 0, "-", "SymNMFk"], [15, 0, 0, "-", "TriNMFk"], [8, 0, 0, "-", "decompositions"], [10, 0, 0, "-", "utilities"]], "TELF.factorization.HNMFk": [[2, 1, 1, "", "HNMFk"], [2, 1, 1, "", "Node"], [2, 1, 1, "", "OnlineNode"]], "TELF.factorization.HNMFk.HNMFk": [[2, 4, 1, "", "fit"], [2, 4, 1, "", "get_node"], [2, 4, 1, "", "go_to_children"], [2, 4, 1, "", "go_to_parent"], [2, 4, 1, "", "go_to_root"], [2, 4, 1, "", "traverse_nodes"]], "TELF.factorization.NMFk": [[7, 1, 1, "", "NMFk"]], "TELF.factorization.NMFk.NMFk": [[7, 4, 1, "", "fit"]], "TELF.factorization.RESCALk": [[7, 1, 1, "", "RESCALk"]], "TELF.factorization.RESCALk.RESCALk": [[7, 4, 1, "", "fit"]], "TELF.factorization.SymNMFk": [[5, 1, 1, "", "SymNMFk"]], "TELF.factorization.SymNMFk.SymNMFk": [[5, 4, 1, "", "fit"]], "TELF.factorization.TriNMFk": [[15, 1, 1, "", "TriNMFk"]], "TELF.factorization.TriNMFk.TriNMFk": [[15, 4, 1, "", "fit_nmfk"], [15, 4, 1, "", "fit_tri_nmfk"]], "TELF.factorization.decompositions": [[8, 0, 0, "-", "nmf_fro_admm"], [8, 0, 0, "-", "nmf_fro_mu"], [8, 0, 0, "-", "nmf_kl_admm"], [8, 0, 0, "-", "nmf_kl_mu"], [8, 0, 0, "-", "nmf_mc_fro_mu"], [8, 0, 0, "-", "rescal_fro_mu"], [8, 0, 0, "-", "tri_nmf_fro_mu"], [9, 0, 0, "-", "utilities"]], "TELF.factorization.decompositions.nmf_fro_admm": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_fro_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_kl_admm": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_kl_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "nmf"]], "TELF.factorization.decompositions.nmf_mc_fro_mu": [[8, 5, 1, "", "H_update_ADMM"], [8, 5, 1, "", "H_update_MU"], [8, 5, 1, "", "W_update_ADMM"], [8, 5, 1, "", "W_update_MU"], [8, 5, 1, "", "coord_desc_thresh"], [8, 5, 1, "", "coord_desc_thresh_onefactor"], [8, 5, 1, "", "find_thres_WH"], [8, 5, 1, "", "nmf"], [8, 5, 1, "", "nmf_with_ADMM"], [8, 5, 1, "", "old_find_thres_WH"], [8, 5, 1, "", "old_nmf"], [8, 5, 1, "", "roc_W_H"], [8, 5, 1, "", "thres_norm"]], "TELF.factorization.decompositions.rescal_fro_mu": [[8, 5, 1, "", "A_update"], [8, 5, 1, "", "R_update"], [8, 5, 1, "", "rescal"]], "TELF.factorization.decompositions.tri_nmf_fro_mu": [[8, 5, 1, "", "H_update"], [8, 5, 1, "", "S_update"], [8, 5, 1, "", "W_update"], [8, 5, 1, "", "trinmf"]], "TELF.factorization.decompositions.utilities": [[9, 0, 0, "-", "bool_clustering"], [9, 0, 0, "-", "bool_noise"], [9, 0, 0, "-", "clustering"], [9, 0, 0, "-", "concensus_matrix"], [9, 0, 0, "-", "data_reshaping"], [9, 0, 0, "-", "generic_utils"], [9, 0, 0, "-", "math_utils"], [9, 0, 0, "-", "nnsvd"], [9, 0, 0, "-", "resample"], [9, 0, 0, "-", "silhouettes"]], "TELF.factorization.decompositions.utilities.bool_clustering": [[9, 5, 1, "", "custom_bool_clustering"]], "TELF.factorization.decompositions.utilities.bool_noise": [[9, 5, 1, "", "add_Bool_noise"], [9, 5, 1, "", "add_Bool_posneg_noise"]], "TELF.factorization.decompositions.utilities.clustering": [[9, 5, 1, "", "custom_k_means"], [9, 5, 1, "", "silhouettes"]], "TELF.factorization.decompositions.utilities.concensus_matrix": [[9, 5, 1, "", "compute_connectivity_mat"], [9, 5, 1, "", "compute_consensus_matrix"], [9, 5, 1, "", "reorder_con_mat"]], "TELF.factorization.decompositions.utilities.data_reshaping": [[9, 5, 1, "", "fold"], [9, 5, 1, "", "move_axis"], [9, 5, 1, "", "unfold"]], "TELF.factorization.decompositions.utilities.generic_utils": [[9, 5, 1, "", "bary_proj"], [9, 5, 1, "", "get_cupyx"], [9, 5, 1, "", "get_np"], [9, 5, 1, "", "get_scipy"], [9, 5, 1, "", "grid_eval"], [9, 5, 1, "", "update_opts"]], "TELF.factorization.decompositions.utilities.math_utils": [[9, 5, 1, "", "bary_coords"], [9, 5, 1, "", "fro_norm"], [9, 5, 1, "", "get_pac"], [9, 5, 1, "", "kl_divergence"], [9, 5, 1, "", "masked_nmf"], [9, 5, 1, "", "nan_to_num"], [9, 5, 1, "", "norm_X"], [9, 5, 1, "", "nz_indices"], [9, 5, 1, "", "prune"], [9, 5, 1, "", "relative_error"], [9, 5, 1, "", "relative_error_rescal"], [9, 5, 1, "", "relative_trinmf_error"], [9, 5, 1, "", "sparse_divide_product"], [9, 5, 1, "", "sparse_dot_product"], [9, 5, 1, "", "unprune"]], "TELF.factorization.decompositions.utilities.nnsvd": [[9, 5, 1, "", "nnsvd"]], "TELF.factorization.decompositions.utilities.resample": [[9, 5, 1, "", "poisson"], [9, 5, 1, "", "uniform_product"]], "TELF.factorization.decompositions.utilities.silhouettes": [[9, 5, 1, "", "custom_silhouettes"]], "TELF.factorization.utilities": [[10, 0, 0, "-", "clustering"], [10, 0, 0, "-", "co_occurance_matrix"], [10, 0, 0, "-", "organize_n_jobs"], [10, 0, 0, "-", "plot_NMFk"], [10, 0, 0, "-", "pvalue_analysis"], [10, 0, 0, "-", "sppmi_matrix"], [10, 0, 0, "-", "take_note"], [10, 0, 0, "-", "vectorize"]], "TELF.factorization.utilities.clustering": [[10, 5, 1, "", "H_clustering"], [10, 5, 1, "", "plot_H_clustering"]], "TELF.factorization.utilities.co_occurance_matrix": [[10, 5, 1, "", "co_occurrence"]], "TELF.factorization.utilities.organize_n_jobs": [[10, 5, 1, "", "organize_n_jobs"]], "TELF.factorization.utilities.plot_NMFk": [[10, 5, 1, "", "plot_BNMFk"], [10, 5, 1, "", "plot_NMFk"], [10, 5, 1, "", "plot_SymNMFk"], [10, 5, 1, "", "plot_consensus_mat"], [10, 5, 1, "", "plot_cophenetic_coeff"]], "TELF.factorization.utilities.pvalue_analysis": [[10, 5, 1, "", "pvalue_analysis"]], "TELF.factorization.utilities.sppmi_matrix": [[10, 5, 1, "", "sppmi"]], "TELF.factorization.utilities.take_note": [[10, 5, 1, "", "append_to_note"], [10, 5, 1, "", "format_note"], [10, 5, 1, "", "take_note"], [10, 5, 1, "", "take_note_fmat"]], "TELF.factorization.utilities.vectorize": [[10, 5, 1, "", "count"], [10, 5, 1, "", "tfidf"]], "TELF.pre_processing": [[12, 0, 0, "-", "Beaver"], [13, 0, 0, "-", "Vulture"]], "TELF.pre_processing.Beaver": [[12, 0, 0, "-", "beaver"], [12, 0, 0, "-", "cooccurrence"], [12, 0, 0, "-", "sppmi"], [12, 0, 0, "-", "tenmat"], [12, 0, 0, "-", "vectorize"]], "TELF.pre_processing.Beaver.beaver": [[12, 1, 1, "", "Beaver"]], "TELF.pre_processing.Beaver.beaver.Beaver": [[12, 2, 1, "", "SUPPORTED_OUTPUT_FORMATS"], [12, 4, 1, "", "citation_tensor"], [12, 4, 1, "", "coauthor_tensor"], [12, 4, 1, "", "cocitation_tensor"], [12, 4, 1, "", "cooccurrence_matrix"], [12, 4, 1, "", "documents_words"], [12, 4, 1, "", "get_ngrams"], [12, 4, 1, "", "get_vocabulary"], [12, 3, 1, "", "n_jobs"], [12, 3, 1, "", "n_nodes"], [12, 4, 1, "", "participation_tensor"], [12, 4, 1, "", "something_words"], [12, 4, 1, "", "something_words_time"]], "TELF.pre_processing.Beaver.cooccurrence": [[12, 5, 1, "", "co_occurrence"]], "TELF.pre_processing.Beaver.sppmi": [[12, 5, 1, "", "sppmi"]], "TELF.pre_processing.Beaver.tenmat": [[12, 5, 1, "", "fold"], [12, 5, 1, "", "unfold"]], "TELF.pre_processing.Beaver.vectorize": [[12, 5, 1, "", "count"], [12, 5, 1, "", "tfidf"]], "TELF.pre_processing.Vulture": [[13, 0, 0, "-", "modules"], [14, 0, 0, "-", "tokens_analysis"], [16, 0, 0, "-", "vulture"]], "TELF.pre_processing.Vulture.tokens_analysis": [[14, 0, 0, "-", "top_words"]], "TELF.pre_processing.Vulture.tokens_analysis.top_words": [[14, 5, 1, "", "get_top_words"]], "TELF.pre_processing.Vulture.vulture": [[16, 1, 1, "", "Vulture"], [16, 5, 1, "", "chunk_tuple_list"]], "TELF.pre_processing.Vulture.vulture.Vulture": [[16, 2, 1, "", "DEFAULT_OPERATOR_PIPELINE"], [16, 2, 1, "", "DEFAULT_PIPELINE"], [16, 2, 1, "", "PARALLEL_BACKEND_OPTIONS"], [16, 3, 1, "", "cache"], [16, 4, 1, "", "clean"], [16, 4, 1, "", "clean_dataframe"], [16, 3, 1, "", "n_jobs"], [16, 3, 1, "", "n_nodes"], [16, 4, 1, "", "operate"], [16, 3, 1, "", "parallel_backend"], [16, 3, 1, "", "save_path"], [16, 4, 1, "", "use_mpi"], [16, 3, 1, "", "verbose"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:property", "4": "py:method", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "property", "Python property"], "4": ["py", "method", "Python method"], "5": ["py", "function", "Python function"]}, "titleterms": {"telf": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18], "pre_process": [0, 11, 12, 13, 14, 16], "beaver": [0, 12], "fast": 0, "matrix": [0, 2, 3, 5], "tensor": [0, 17], "build": 0, "tool": [0, 16], "exampl": [0, 3, 4, 15, 16], "avail": [0, 1, 2, 3, 4, 5, 15, 16], "function": [0, 1, 2, 3, 4, 5, 15, 16], "modul": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16], "content": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], "applic": 1, "cheetah": 1, "advanc": [1, 16], "search": 1, "keyword": 1, "phrase": 1, "paramet": [1, 10], "return": [1, 10], "rais": 1, "factor": [2, 3, 4, 5, 7, 8, 9, 10, 15], "hnmfk": 2, "hierarch": 2, "non": [2, 3, 5], "neg": [2, 3, 5], "automat": [2, 3, 4, 5, 15], "model": [2, 3, 4, 5], "determin": [2, 3, 4, 5, 15], "nmfk": [3, 7, 15], "rescalk": [4, 7], "rescal": 4, "symnmfk": 5, "symmetr": 5, "packag": [6, 7, 8, 9, 10, 11, 12, 13, 14], "subpackag": [6, 7, 8, 11, 13], "submodul": [6, 7, 8, 9, 10, 12, 13, 14], "version": 6, "trinmfk": [7, 15], "decomposit": [8, 9], "nmf_fro_admm": 8, "nmf_fro_mu": 8, "nmf_kl_admm": 8, "nmf_kl_mu": 8, "nmf_mc_fro_mu": 8, "rescal_fro_mu": 8, "tri_nmf_fro_mu": 8, "util": [9, 10], "bool_clust": 9, "bool_nois": 9, "cluster": [9, 10, 15], "concensus_matrix": 9, "data_reshap": 9, "generic_util": 9, "math_util": 9, "nnsvd": 9, "resampl": 9, "silhouett": 9, "co_occurance_matrix": 10, "organize_n_job": 10, "plot_nmfk": 10, "pvalue_analysi": 10, "sppmi_matrix": 10, "take_not": 10, "vector": [10, 12], "cooccurr": 12, "sppmi": 12, "tenmat": 12, "vultur": [13, 14, 16], "tokens_analysi": 14, "top_word": 14, "latent": [15, 17], "pattern": 15, "text": 16, "pre": 16, "process": 16, "clean": 16, "nlp": 16, "mine": 16, "extract": 17, "featur": 17, "t": 17, "elf": 17, "resourc": 17, "instal": 17, "capabl": 17, "how": 17, "cite": 17, "author": 17, "copyright": 17, "notic": 17, "licens": 17, "develop": 17, "test": 17, "suit": 17, "indic": 17, "tabl": 17}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinxcontrib.bibtex": 9, "sphinx": 60}, "alltitles": {"TELF.pre_processing.Beaver: Fast matrix and tensor building tool": [[0, "telf-pre-processing-beaver-fast-matrix-and-tensor-building-tool"]], "Example": [[0, "example"], [3, "example"], [4, "example"], [15, "example"], [16, "example"]], "Available Functions": [[0, "available-functions"], [1, "available-functions"], [2, "available-functions"], [3, "available-functions"], [4, "available-functions"], [5, "available-functions"], [15, "available-functions"], [16, "available-functions"]], "Module Contents": [[0, "module-TELF.pre_processing.Beaver.beaver"], [1, "module-TELF.applications.Cheetah.cheetah"], [2, "module-TELF.factorization.HNMFk"], [3, "module-TELF.factorization.NMFk"], [4, "module-TELF.factorization.RESCALk"], [5, "module-TELF.factorization.SymNMFk"], [15, "module-TELF.factorization.TriNMFk"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "TELF.applications.Cheetah: Advanced search by keywords and phrases": [[1, "telf-applications-cheetah-advanced-search-by-keywords-and-phrases"]], "Parameters:": [[1, "parameters"], [10, "parameters"], [10, "id1"], [10, "id2"], [10, "id3"]], "Returns:": [[1, "returns"], [10, "returns"]], "Raises:": [[1, "raises"]], "TELF.factorization.HNMFk: Hierarchical Non-negative Matrix Factorization with Automatic Model Determination": [[2, "telf-factorization-hnmfk-hierarchical-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF.factorization.NMFk: Non-negative Matrix Factorization with Automatic Model Determination": [[3, "telf-factorization-nmfk-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF.factorization.RESCALk: RESCAL with Automatic Model Determination": [[4, "telf-factorization-rescalk-rescal-with-automatic-model-determination"]], "TELF.factorization.SymNMFk: Symmetric Non-negative Matrix Factorization with Automatic Model Determination": [[5, "telf-factorization-symnmfk-symmetric-non-negative-matrix-factorization-with-automatic-model-determination"]], "TELF package": [[6, "telf-package"]], "Subpackages": [[6, "subpackages"], [7, "subpackages"], [8, "subpackages"], [11, "subpackages"], [13, "subpackages"]], "Submodules": [[6, "submodules"], [7, "submodules"], [8, "submodules"], [9, "submodules"], [10, "submodules"], [12, "submodules"], [13, "submodules"], [14, "submodules"]], "TELF.version module": [[6, "module-TELF.version"]], "Module contents": [[6, "module-TELF"], [7, "module-TELF.factorization"], [8, "module-TELF.factorization.decompositions"], [9, "module-TELF.factorization.decompositions.utilities"], [10, "module-TELF.factorization.utilities"], [11, "module-TELF.pre_processing"], [12, "module-TELF.pre_processing.Beaver"], [13, "module-TELF.pre_processing.Vulture"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis"]], "TELF.factorization package": [[7, "telf-factorization-package"]], "TELF.factorization.NMFk module": [[7, "module-TELF.factorization.NMFk"]], "TELF.factorization.RESCALk module": [[7, "module-TELF.factorization.RESCALk"]], "TELF.factorization.TriNMFk module": [[7, "module-TELF.factorization.TriNMFk"]], "TELF.factorization.decompositions package": [[8, "telf-factorization-decompositions-package"]], "TELF.factorization.decompositions.nmf_fro_admm module": [[8, "module-TELF.factorization.decompositions.nmf_fro_admm"]], "TELF.factorization.decompositions.nmf_fro_mu module": [[8, "module-TELF.factorization.decompositions.nmf_fro_mu"]], "TELF.factorization.decompositions.nmf_kl_admm module": [[8, "module-TELF.factorization.decompositions.nmf_kl_admm"]], "TELF.factorization.decompositions.nmf_kl_mu module": [[8, "module-TELF.factorization.decompositions.nmf_kl_mu"]], "TELF.factorization.decompositions.nmf_mc_fro_mu module": [[8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"]], "TELF.factorization.decompositions.rescal_fro_mu module": [[8, "module-TELF.factorization.decompositions.rescal_fro_mu"]], "TELF.factorization.decompositions.tri_nmf_fro_mu module": [[8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"]], "TELF.factorization.decompositions.utilities package": [[9, "telf-factorization-decompositions-utilities-package"]], "TELF.factorization.decompositions.utilities.bool_clustering module": [[9, "module-TELF.factorization.decompositions.utilities.bool_clustering"]], "TELF.factorization.decompositions.utilities.bool_noise module": [[9, "module-TELF.factorization.decompositions.utilities.bool_noise"]], "TELF.factorization.decompositions.utilities.clustering module": [[9, "module-TELF.factorization.decompositions.utilities.clustering"]], "TELF.factorization.decompositions.utilities.concensus_matrix module": [[9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"]], "TELF.factorization.decompositions.utilities.data_reshaping module": [[9, "module-TELF.factorization.decompositions.utilities.data_reshaping"]], "TELF.factorization.decompositions.utilities.generic_utils module": [[9, "module-TELF.factorization.decompositions.utilities.generic_utils"]], "TELF.factorization.decompositions.utilities.math_utils module": [[9, "module-TELF.factorization.decompositions.utilities.math_utils"]], "TELF.factorization.decompositions.utilities.nnsvd module": [[9, "module-TELF.factorization.decompositions.utilities.nnsvd"]], "TELF.factorization.decompositions.utilities.resample module": [[9, "module-TELF.factorization.decompositions.utilities.resample"]], "TELF.factorization.decompositions.utilities.silhouettes module": [[9, "module-TELF.factorization.decompositions.utilities.silhouettes"]], "TELF.factorization.utilities package": [[10, "telf-factorization-utilities-package"]], "TELF.factorization.utilities.clustering module": [[10, "module-TELF.factorization.utilities.clustering"]], "TELF.factorization.utilities.co_occurance_matrix module": [[10, "module-TELF.factorization.utilities.co_occurance_matrix"]], "TELF.factorization.utilities.organize_n_jobs module": [[10, "module-TELF.factorization.utilities.organize_n_jobs"]], "TELF.factorization.utilities.plot_NMFk module": [[10, "module-TELF.factorization.utilities.plot_NMFk"]], "TELF.factorization.utilities.pvalue_analysis module": [[10, "module-TELF.factorization.utilities.pvalue_analysis"]], "TELF.factorization.utilities.sppmi_matrix module": [[10, "module-TELF.factorization.utilities.sppmi_matrix"]], "TELF.factorization.utilities.take_note module": [[10, "module-TELF.factorization.utilities.take_note"]], "TELF.factorization.utilities.vectorize module": [[10, "module-TELF.factorization.utilities.vectorize"]], "TELF.pre_processing package": [[11, "telf-pre-processing-package"]], "TELF.pre_processing.Beaver package": [[12, "telf-pre-processing-beaver-package"]], "TELF.pre_processing.Beaver.beaver module": [[12, "module-TELF.pre_processing.Beaver.beaver"]], "TELF.pre_processing.Beaver.cooccurrence module": [[12, "module-TELF.pre_processing.Beaver.cooccurrence"]], "TELF.pre_processing.Beaver.sppmi module": [[12, "module-TELF.pre_processing.Beaver.sppmi"]], "TELF.pre_processing.Beaver.tenmat module": [[12, "module-TELF.pre_processing.Beaver.tenmat"]], "TELF.pre_processing.Beaver.vectorize module": [[12, "module-TELF.pre_processing.Beaver.vectorize"]], "TELF.pre_processing.Vulture package": [[13, "telf-pre-processing-vulture-package"]], "TELF.pre_processing.Vulture.modules module": [[13, "module-TELF.pre_processing.Vulture.modules"]], "TELF.pre_processing.Vulture.vulture module": [[13, "module-TELF.pre_processing.Vulture.vulture"]], "TELF.pre_processing.Vulture.tokens_analysis package": [[14, "telf-pre-processing-vulture-tokens-analysis-package"]], "TELF.pre_processing.Vulture.tokens_analysis.top_words module": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"]], "TELF.factorization.TriNMFk: NMFk with Automatic Determination of Latent Clusters and Patterns": [[15, "telf-factorization-trinmfk-nmfk-with-automatic-determination-of-latent-clusters-and-patterns"]], "TELF.pre_processing.Vulture: Advanced text pre-processing and cleaning tool for NLP and text-mining": [[16, "telf-pre-processing-vulture-advanced-text-pre-processing-and-cleaning-tool-for-nlp-and-text-mining"]], "Tensor Extraction of Latent Features (T-ELF)": [[17, "tensor-extraction-of-latent-features-t-elf"]], "Resources": [[17, "resources"]], "Installation": [[17, "installation"]], "Capabilities": [[17, "capabilities"]], "How to Cite T-ELF?": [[17, "how-to-cite-t-elf"]], "Authors": [[17, "authors"]], "Copyright Notice": [[17, "copyright-notice"]], "License": [[17, "license"]], "Developer Test Suite": [[17, "developer-test-suite"]], "Contents:": [[17, null]], "Indices and tables": [[17, "indices-and-tables"]], "TELF": [[18, "telf"]]}, "indexentries": {"beaver (class in telf.pre_processing.beaver.beaver)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver"], [12, "TELF.pre_processing.Beaver.beaver.Beaver"]], "supported_output_formats (telf.pre_processing.beaver.beaver.beaver attribute)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.SUPPORTED_OUTPUT_FORMATS"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.SUPPORTED_OUTPUT_FORMATS"]], "telf.pre_processing.beaver.beaver": [[0, "module-TELF.pre_processing.Beaver.beaver"], [12, "module-TELF.pre_processing.Beaver.beaver"]], "citation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.citation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.citation_tensor"]], "coauthor_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.coauthor_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.coauthor_tensor"]], "cocitation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.cocitation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.cocitation_tensor"]], "cooccurrence_matrix() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.cooccurrence_matrix"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.cooccurrence_matrix"]], "documents_words() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.documents_words"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.documents_words"]], "get_ngrams() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.get_ngrams"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.get_ngrams"]], "get_vocabulary() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.get_vocabulary"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.get_vocabulary"]], "module": [[0, "module-TELF.pre_processing.Beaver.beaver"], [1, "module-TELF.applications.Cheetah.cheetah"], [2, "module-TELF.factorization.HNMFk"], [3, "module-TELF.factorization.NMFk"], [4, "module-TELF.factorization.RESCALk"], [5, "module-TELF.factorization.SymNMFk"], [6, "module-TELF"], [6, "module-TELF.version"], [7, "module-TELF.factorization"], [7, "module-TELF.factorization.NMFk"], [7, "module-TELF.factorization.RESCALk"], [7, "module-TELF.factorization.TriNMFk"], [8, "module-TELF.factorization.decompositions"], [8, "module-TELF.factorization.decompositions.nmf_fro_admm"], [8, "module-TELF.factorization.decompositions.nmf_fro_mu"], [8, "module-TELF.factorization.decompositions.nmf_kl_admm"], [8, "module-TELF.factorization.decompositions.nmf_kl_mu"], [8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"], [8, "module-TELF.factorization.decompositions.rescal_fro_mu"], [8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"], [9, "module-TELF.factorization.decompositions.utilities"], [9, "module-TELF.factorization.decompositions.utilities.bool_clustering"], [9, "module-TELF.factorization.decompositions.utilities.bool_noise"], [9, "module-TELF.factorization.decompositions.utilities.clustering"], [9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"], [9, "module-TELF.factorization.decompositions.utilities.data_reshaping"], [9, "module-TELF.factorization.decompositions.utilities.generic_utils"], [9, "module-TELF.factorization.decompositions.utilities.math_utils"], [9, "module-TELF.factorization.decompositions.utilities.nnsvd"], [9, "module-TELF.factorization.decompositions.utilities.resample"], [9, "module-TELF.factorization.decompositions.utilities.silhouettes"], [10, "module-TELF.factorization.utilities"], [10, "module-TELF.factorization.utilities.clustering"], [10, "module-TELF.factorization.utilities.co_occurance_matrix"], [10, "module-TELF.factorization.utilities.organize_n_jobs"], [10, "module-TELF.factorization.utilities.plot_NMFk"], [10, "module-TELF.factorization.utilities.pvalue_analysis"], [10, "module-TELF.factorization.utilities.sppmi_matrix"], [10, "module-TELF.factorization.utilities.take_note"], [10, "module-TELF.factorization.utilities.vectorize"], [11, "module-TELF.pre_processing"], [12, "module-TELF.pre_processing.Beaver"], [12, "module-TELF.pre_processing.Beaver.beaver"], [12, "module-TELF.pre_processing.Beaver.cooccurrence"], [12, "module-TELF.pre_processing.Beaver.sppmi"], [12, "module-TELF.pre_processing.Beaver.tenmat"], [12, "module-TELF.pre_processing.Beaver.vectorize"], [13, "module-TELF.pre_processing.Vulture"], [13, "module-TELF.pre_processing.Vulture.modules"], [13, "module-TELF.pre_processing.Vulture.vulture"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis"], [14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"], [15, "module-TELF.factorization.TriNMFk"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "n_jobs (telf.pre_processing.beaver.beaver.beaver property)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.n_jobs"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.n_jobs"]], "n_nodes (telf.pre_processing.beaver.beaver.beaver property)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.n_nodes"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.n_nodes"]], "participation_tensor() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.participation_tensor"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.participation_tensor"]], "something_words() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.something_words"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.something_words"]], "something_words_time() (telf.pre_processing.beaver.beaver.beaver method)": [[0, "TELF.pre_processing.Beaver.beaver.Beaver.something_words_time"], [12, "TELF.pre_processing.Beaver.beaver.Beaver.something_words_time"]], "columns (telf.applications.cheetah.cheetah.cheetah attribute)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.COLUMNS"]], "cheetah (class in telf.applications.cheetah.cheetah)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah"]], "telf.applications.cheetah.cheetah": [[1, "module-TELF.applications.Cheetah.cheetah"]], "add_with_union_of_others() (in module telf.applications.cheetah.cheetah)": [[1, "TELF.applications.Cheetah.cheetah.add_with_union_of_others"]], "columns (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.columns"]], "find_ngram() (telf.applications.cheetah.cheetah.cheetah class method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.find_ngram"]], "index() (telf.applications.cheetah.cheetah.cheetah method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.index"]], "ngram_ordered (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.ngram_ordered"]], "ngram_window_size (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.ngram_window_size"]], "query (telf.applications.cheetah.cheetah.cheetah property)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.query"]], "search() (telf.applications.cheetah.cheetah.cheetah method)": [[1, "TELF.applications.Cheetah.cheetah.Cheetah.search"]], "hnmfk (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.HNMFk"]], "node (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.Node"]], "onlinenode (class in telf.factorization.hnmfk)": [[2, "TELF.factorization.HNMFk.OnlineNode"]], "telf.factorization.hnmfk": [[2, "module-TELF.factorization.HNMFk"]], "fit() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.fit"]], "get_node() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.get_node"]], "go_to_children() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_children"]], "go_to_parent() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_parent"]], "go_to_root() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.go_to_root"]], "traverse_nodes() (telf.factorization.hnmfk.hnmfk method)": [[2, "TELF.factorization.HNMFk.HNMFk.traverse_nodes"]], "nmfk (class in telf.factorization.nmfk)": [[3, "TELF.factorization.NMFk.NMFk"], [7, "TELF.factorization.NMFk.NMFk"]], "telf.factorization.nmfk": [[3, "module-TELF.factorization.NMFk"], [7, "module-TELF.factorization.NMFk"]], "fit() (telf.factorization.nmfk.nmfk method)": [[3, "TELF.factorization.NMFk.NMFk.fit"], [7, "TELF.factorization.NMFk.NMFk.fit"]], "rescalk (class in telf.factorization.rescalk)": [[4, "TELF.factorization.RESCALk.RESCALk"], [7, "TELF.factorization.RESCALk.RESCALk"]], "telf.factorization.rescalk": [[4, "module-TELF.factorization.RESCALk"], [7, "module-TELF.factorization.RESCALk"]], "fit() (telf.factorization.rescalk.rescalk method)": [[4, "TELF.factorization.RESCALk.RESCALk.fit"], [7, "TELF.factorization.RESCALk.RESCALk.fit"]], "symnmfk (class in telf.factorization.symnmfk)": [[5, "TELF.factorization.SymNMFk.SymNMFk"]], "telf.factorization.symnmfk": [[5, "module-TELF.factorization.SymNMFk"]], "fit() (telf.factorization.symnmfk.symnmfk method)": [[5, "TELF.factorization.SymNMFk.SymNMFk.fit"]], "telf": [[6, "module-TELF"]], "telf.version": [[6, "module-TELF.version"]], "telf.factorization": [[7, "module-TELF.factorization"]], "telf.factorization.trinmfk": [[7, "module-TELF.factorization.TriNMFk"], [15, "module-TELF.factorization.TriNMFk"]], "trinmfk (class in telf.factorization.trinmfk)": [[7, "TELF.factorization.TriNMFk.TriNMFk"], [15, "TELF.factorization.TriNMFk.TriNMFk"]], "fit_nmfk() (telf.factorization.trinmfk.trinmfk method)": [[7, "TELF.factorization.TriNMFk.TriNMFk.fit_nmfk"], [15, "TELF.factorization.TriNMFk.TriNMFk.fit_nmfk"]], "fit_tri_nmfk() (telf.factorization.trinmfk.trinmfk method)": [[7, "TELF.factorization.TriNMFk.TriNMFk.fit_tri_nmfk"], [15, "TELF.factorization.TriNMFk.TriNMFk.fit_tri_nmfk"]], "a_update() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.A_update"]], "h_update() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.H_update"]], "h_update() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.H_update"]], "h_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.H_update"]], "h_update_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.H_update_ADMM"]], "h_update_mu() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.H_update_MU"]], "r_update() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.R_update"]], "s_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.S_update"]], "telf.factorization.decompositions": [[8, "module-TELF.factorization.decompositions"]], "telf.factorization.decompositions.nmf_fro_admm": [[8, "module-TELF.factorization.decompositions.nmf_fro_admm"]], "telf.factorization.decompositions.nmf_fro_mu": [[8, "module-TELF.factorization.decompositions.nmf_fro_mu"]], "telf.factorization.decompositions.nmf_kl_admm": [[8, "module-TELF.factorization.decompositions.nmf_kl_admm"]], "telf.factorization.decompositions.nmf_kl_mu": [[8, "module-TELF.factorization.decompositions.nmf_kl_mu"]], "telf.factorization.decompositions.nmf_mc_fro_mu": [[8, "module-TELF.factorization.decompositions.nmf_mc_fro_mu"]], "telf.factorization.decompositions.rescal_fro_mu": [[8, "module-TELF.factorization.decompositions.rescal_fro_mu"]], "telf.factorization.decompositions.tri_nmf_fro_mu": [[8, "module-TELF.factorization.decompositions.tri_nmf_fro_mu"]], "w_update() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.W_update"]], "w_update() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.W_update"]], "w_update() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.W_update"]], "w_update_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.W_update_ADMM"]], "w_update_mu() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.W_update_MU"]], "coord_desc_thresh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.coord_desc_thresh"]], "coord_desc_thresh_onefactor() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.coord_desc_thresh_onefactor"]], "find_thres_wh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.find_thres_WH"]], "nmf() (in module telf.factorization.decompositions.nmf_fro_admm)": [[8, "TELF.factorization.decompositions.nmf_fro_admm.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_fro_mu.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_kl_admm)": [[8, "TELF.factorization.decompositions.nmf_kl_admm.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_kl_mu)": [[8, "TELF.factorization.decompositions.nmf_kl_mu.nmf"]], "nmf() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.nmf"]], "nmf_with_admm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.nmf_with_ADMM"]], "old_find_thres_wh() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.old_find_thres_WH"]], "old_nmf() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.old_nmf"]], "rescal() (in module telf.factorization.decompositions.rescal_fro_mu)": [[8, "TELF.factorization.decompositions.rescal_fro_mu.rescal"]], "roc_w_h() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.roc_W_H"]], "thres_norm() (in module telf.factorization.decompositions.nmf_mc_fro_mu)": [[8, "TELF.factorization.decompositions.nmf_mc_fro_mu.thres_norm"]], "trinmf() (in module telf.factorization.decompositions.tri_nmf_fro_mu)": [[8, "TELF.factorization.decompositions.tri_nmf_fro_mu.trinmf"]], "telf.factorization.decompositions.utilities": [[9, "module-TELF.factorization.decompositions.utilities"]], "telf.factorization.decompositions.utilities.bool_clustering": [[9, "module-TELF.factorization.decompositions.utilities.bool_clustering"]], "telf.factorization.decompositions.utilities.bool_noise": [[9, "module-TELF.factorization.decompositions.utilities.bool_noise"]], "telf.factorization.decompositions.utilities.clustering": [[9, "module-TELF.factorization.decompositions.utilities.clustering"]], "telf.factorization.decompositions.utilities.concensus_matrix": [[9, "module-TELF.factorization.decompositions.utilities.concensus_matrix"]], "telf.factorization.decompositions.utilities.data_reshaping": [[9, "module-TELF.factorization.decompositions.utilities.data_reshaping"]], "telf.factorization.decompositions.utilities.generic_utils": [[9, "module-TELF.factorization.decompositions.utilities.generic_utils"]], "telf.factorization.decompositions.utilities.math_utils": [[9, "module-TELF.factorization.decompositions.utilities.math_utils"]], "telf.factorization.decompositions.utilities.nnsvd": [[9, "module-TELF.factorization.decompositions.utilities.nnsvd"]], "telf.factorization.decompositions.utilities.resample": [[9, "module-TELF.factorization.decompositions.utilities.resample"]], "telf.factorization.decompositions.utilities.silhouettes": [[9, "module-TELF.factorization.decompositions.utilities.silhouettes"]], "add_bool_noise() (in module telf.factorization.decompositions.utilities.bool_noise)": [[9, "TELF.factorization.decompositions.utilities.bool_noise.add_Bool_noise"]], "add_bool_posneg_noise() (in module telf.factorization.decompositions.utilities.bool_noise)": [[9, "TELF.factorization.decompositions.utilities.bool_noise.add_Bool_posneg_noise"]], "bary_coords() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.bary_coords"]], "bary_proj() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.bary_proj"]], "compute_connectivity_mat() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.compute_connectivity_mat"]], "compute_consensus_matrix() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.compute_consensus_matrix"]], "custom_bool_clustering() (in module telf.factorization.decompositions.utilities.bool_clustering)": [[9, "TELF.factorization.decompositions.utilities.bool_clustering.custom_bool_clustering"]], "custom_k_means() (in module telf.factorization.decompositions.utilities.clustering)": [[9, "TELF.factorization.decompositions.utilities.clustering.custom_k_means"]], "custom_silhouettes() (in module telf.factorization.decompositions.utilities.silhouettes)": [[9, "TELF.factorization.decompositions.utilities.silhouettes.custom_silhouettes"]], "fold() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.fold"]], "fro_norm() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.fro_norm"]], "get_cupyx() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_cupyx"]], "get_np() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_np"]], "get_pac() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.get_pac"]], "get_scipy() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.get_scipy"]], "grid_eval() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.grid_eval"]], "kl_divergence() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.kl_divergence"]], "masked_nmf() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.masked_nmf"]], "move_axis() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.move_axis"]], "nan_to_num() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.nan_to_num"]], "nnsvd() (in module telf.factorization.decompositions.utilities.nnsvd)": [[9, "TELF.factorization.decompositions.utilities.nnsvd.nnsvd"]], "norm_x() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.norm_X"]], "nz_indices() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.nz_indices"]], "poisson() (in module telf.factorization.decompositions.utilities.resample)": [[9, "TELF.factorization.decompositions.utilities.resample.poisson"]], "prune() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.prune"]], "relative_error() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_error"]], "relative_error_rescal() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_error_rescal"]], "relative_trinmf_error() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.relative_trinmf_error"]], "reorder_con_mat() (in module telf.factorization.decompositions.utilities.concensus_matrix)": [[9, "TELF.factorization.decompositions.utilities.concensus_matrix.reorder_con_mat"]], "silhouettes() (in module telf.factorization.decompositions.utilities.clustering)": [[9, "TELF.factorization.decompositions.utilities.clustering.silhouettes"]], "sparse_divide_product() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.sparse_divide_product"]], "sparse_dot_product() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.sparse_dot_product"]], "unfold() (in module telf.factorization.decompositions.utilities.data_reshaping)": [[9, "TELF.factorization.decompositions.utilities.data_reshaping.unfold"]], "uniform_product() (in module telf.factorization.decompositions.utilities.resample)": [[9, "TELF.factorization.decompositions.utilities.resample.uniform_product"]], "unprune() (in module telf.factorization.decompositions.utilities.math_utils)": [[9, "TELF.factorization.decompositions.utilities.math_utils.unprune"]], "update_opts() (in module telf.factorization.decompositions.utilities.generic_utils)": [[9, "TELF.factorization.decompositions.utilities.generic_utils.update_opts"]], "h_clustering() (in module telf.factorization.utilities.clustering)": [[10, "TELF.factorization.utilities.clustering.H_clustering"]], "telf.factorization.utilities": [[10, "module-TELF.factorization.utilities"]], "telf.factorization.utilities.clustering": [[10, "module-TELF.factorization.utilities.clustering"]], "telf.factorization.utilities.co_occurance_matrix": [[10, "module-TELF.factorization.utilities.co_occurance_matrix"]], "telf.factorization.utilities.organize_n_jobs": [[10, "module-TELF.factorization.utilities.organize_n_jobs"]], "telf.factorization.utilities.plot_nmfk": [[10, "module-TELF.factorization.utilities.plot_NMFk"]], "telf.factorization.utilities.pvalue_analysis": [[10, "module-TELF.factorization.utilities.pvalue_analysis"]], "telf.factorization.utilities.sppmi_matrix": [[10, "module-TELF.factorization.utilities.sppmi_matrix"]], "telf.factorization.utilities.take_note": [[10, "module-TELF.factorization.utilities.take_note"]], "telf.factorization.utilities.vectorize": [[10, "module-TELF.factorization.utilities.vectorize"]], "append_to_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.append_to_note"]], "co_occurrence() (in module telf.factorization.utilities.co_occurance_matrix)": [[10, "TELF.factorization.utilities.co_occurance_matrix.co_occurrence"]], "count() (in module telf.factorization.utilities.vectorize)": [[10, "TELF.factorization.utilities.vectorize.count"]], "format_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.format_note"]], "organize_n_jobs() (in module telf.factorization.utilities.organize_n_jobs)": [[10, "TELF.factorization.utilities.organize_n_jobs.organize_n_jobs"]], "plot_bnmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_BNMFk"]], "plot_h_clustering() (in module telf.factorization.utilities.clustering)": [[10, "TELF.factorization.utilities.clustering.plot_H_clustering"]], "plot_nmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_NMFk"]], "plot_symnmfk() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_SymNMFk"]], "plot_consensus_mat() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_consensus_mat"]], "plot_cophenetic_coeff() (in module telf.factorization.utilities.plot_nmfk)": [[10, "TELF.factorization.utilities.plot_NMFk.plot_cophenetic_coeff"]], "pvalue_analysis() (in module telf.factorization.utilities.pvalue_analysis)": [[10, "TELF.factorization.utilities.pvalue_analysis.pvalue_analysis"]], "sppmi() (in module telf.factorization.utilities.sppmi_matrix)": [[10, "TELF.factorization.utilities.sppmi_matrix.sppmi"]], "take_note() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.take_note"]], "take_note_fmat() (in module telf.factorization.utilities.take_note)": [[10, "TELF.factorization.utilities.take_note.take_note_fmat"]], "tfidf() (in module telf.factorization.utilities.vectorize)": [[10, "TELF.factorization.utilities.vectorize.tfidf"]], "telf.pre_processing": [[11, "module-TELF.pre_processing"]], "telf.pre_processing.beaver": [[12, "module-TELF.pre_processing.Beaver"]], "telf.pre_processing.beaver.cooccurrence": [[12, "module-TELF.pre_processing.Beaver.cooccurrence"]], "telf.pre_processing.beaver.sppmi": [[12, "module-TELF.pre_processing.Beaver.sppmi"]], "telf.pre_processing.beaver.tenmat": [[12, "module-TELF.pre_processing.Beaver.tenmat"]], "telf.pre_processing.beaver.vectorize": [[12, "module-TELF.pre_processing.Beaver.vectorize"]], "co_occurrence() (in module telf.pre_processing.beaver.cooccurrence)": [[12, "TELF.pre_processing.Beaver.cooccurrence.co_occurrence"]], "count() (in module telf.pre_processing.beaver.vectorize)": [[12, "TELF.pre_processing.Beaver.vectorize.count"]], "fold() (in module telf.pre_processing.beaver.tenmat)": [[12, "TELF.pre_processing.Beaver.tenmat.fold"]], "sppmi() (in module telf.pre_processing.beaver.sppmi)": [[12, "TELF.pre_processing.Beaver.sppmi.sppmi"]], "tfidf() (in module telf.pre_processing.beaver.vectorize)": [[12, "TELF.pre_processing.Beaver.vectorize.tfidf"]], "unfold() (in module telf.pre_processing.beaver.tenmat)": [[12, "TELF.pre_processing.Beaver.tenmat.unfold"]], "default_operator_pipeline (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_OPERATOR_PIPELINE"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_OPERATOR_PIPELINE"]], "default_pipeline (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_PIPELINE"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.DEFAULT_PIPELINE"]], "parallel_backend_options (telf.pre_processing.vulture.vulture.vulture attribute)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.PARALLEL_BACKEND_OPTIONS"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.PARALLEL_BACKEND_OPTIONS"]], "telf.pre_processing.vulture": [[13, "module-TELF.pre_processing.Vulture"]], "telf.pre_processing.vulture.modules": [[13, "module-TELF.pre_processing.Vulture.modules"]], "telf.pre_processing.vulture.vulture": [[13, "module-TELF.pre_processing.Vulture.vulture"], [16, "module-TELF.pre_processing.Vulture.vulture"]], "vulture (class in telf.pre_processing.vulture.vulture)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture"], [16, "TELF.pre_processing.Vulture.vulture.Vulture"]], "cache (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.cache"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.cache"]], "chunk_tuple_list() (in module telf.pre_processing.vulture.vulture)": [[13, "TELF.pre_processing.Vulture.vulture.chunk_tuple_list"], [16, "TELF.pre_processing.Vulture.vulture.chunk_tuple_list"]], "clean() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.clean"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.clean"]], "clean_dataframe() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.clean_dataframe"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.clean_dataframe"]], "n_jobs (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.n_jobs"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.n_jobs"]], "n_nodes (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.n_nodes"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.n_nodes"]], "operate() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.operate"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.operate"]], "parallel_backend (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.parallel_backend"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.parallel_backend"]], "save_path (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.save_path"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.save_path"]], "use_mpi() (telf.pre_processing.vulture.vulture.vulture method)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.use_mpi"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.use_mpi"]], "verbose (telf.pre_processing.vulture.vulture.vulture property)": [[13, "TELF.pre_processing.Vulture.vulture.Vulture.verbose"], [16, "TELF.pre_processing.Vulture.vulture.Vulture.verbose"]], "telf.pre_processing.vulture.tokens_analysis": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis"]], "telf.pre_processing.vulture.tokens_analysis.top_words": [[14, "module-TELF.pre_processing.Vulture.tokens_analysis.top_words"]], "get_top_words() (in module telf.pre_processing.vulture.tokens_analysis.top_words)": [[14, "TELF.pre_processing.Vulture.tokens_analysis.top_words.get_top_words"]]}})
\ No newline at end of file