diff --git a/Stock_Price_Prediction(Updated).ipynb b/Stock_Price_Prediction(Updated).ipynb index 540eace..93a2869 100644 --- a/Stock_Price_Prediction(Updated).ipynb +++ b/Stock_Price_Prediction(Updated).ipynb @@ -1,4844 +1,4844 @@ { - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "id": "8tzEK_mSvRoh" - }, - "outputs": [], - "source": [ - "import pandas as pd\n", - "import numpy as np\n", - "import matplotlib.pyplot as plt\n", - "from sklearn.model_selection import train_test_split\n", - "from sklearn.impute import SimpleImputer\n", - "from sklearn.preprocessing import MinMaxScaler\n", - "from sklearn.linear_model import LinearRegression\n", - "from sklearn.svm import SVR\n", - "from sklearn.tree import DecisionTreeRegressor\n", - "from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor, GradientBoostingRegressor\n", - "from sklearn.metrics import mean_squared_error, mean_absolute_error, mean_absolute_percentage_error\n", - "from sklearn.neighbors import KNeighborsRegressor\n", - "from tensorflow.keras.models import Sequential\n", - "from tensorflow.keras.layers import Dense,LSTM" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 206 - }, - "id": "NbBSc2jLvZWx", - "outputId": "457e0a63-90a0-4e1c-b846-95e4e50c31dc" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
DateOpenHighLowCloseAdj CloseVolume
001-01-199618.69114718.97892218.54018418.82324012.40993143733533.0
102-01-199618.89400518.96476717.73819218.22410612.01493156167280.0
203-01-199618.32789218.56848917.64383917.73819211.69457768296318.0
304-01-199617.50231217.83254217.22397217.67686311.65414286073880.0
405-01-199617.73819217.78536617.45985217.57779311.58882776613039.0
\n", - "
" - ], - "text/plain": [ - " Date Open High Low Close Adj Close \\\n", - "0 01-01-1996 18.691147 18.978922 18.540184 18.823240 12.409931 \n", - "1 02-01-1996 18.894005 18.964767 17.738192 18.224106 12.014931 \n", - "2 03-01-1996 18.327892 18.568489 17.643839 17.738192 11.694577 \n", - "3 04-01-1996 17.502312 17.832542 17.223972 17.676863 11.654142 \n", - "4 05-01-1996 17.738192 17.785366 17.459852 17.577793 11.588827 \n", - "\n", - " Volume \n", - "0 43733533.0 \n", - "1 56167280.0 \n", - "2 68296318.0 \n", - "3 86073880.0 \n", - "4 76613039.0 " - ] - }, - "execution_count": 2, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Load the dataset\n", - "df = pd.read_csv('/content/SBIN.csv')\n", - "df.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": { - "id": "2QdTvORzwEJw" - }, - "outputs": [], - "source": [ - "# Drop the 'Date' and 'Adj Close' columns\n", - "df.drop(['Date', 'Adj Close'], axis=1, inplace=True)" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 206 - }, - "id": "xMfr71b2w3eX", - "outputId": "a6990b82-ef82-454f-c0ba-fc0c21cc91ca" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
OpenHighLowCloseVolume
018.69114718.97892218.54018418.82324043733533.0
118.89400518.96476717.73819218.22410656167280.0
218.32789218.56848917.64383917.73819268296318.0
317.50231217.83254217.22397217.67686386073880.0
417.73819217.78536617.45985217.57779376613039.0
\n", - "
" - ], - "text/plain": [ - " Open High Low Close Volume\n", - "0 18.691147 18.978922 18.540184 18.823240 43733533.0\n", - "1 18.894005 18.964767 17.738192 18.224106 56167280.0\n", - "2 18.327892 18.568489 17.643839 17.738192 68296318.0\n", - "3 17.502312 17.832542 17.223972 17.676863 86073880.0\n", - "4 17.738192 17.785366 17.459852 17.577793 76613039.0" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "df.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "# Handle missing values\n", - "imputer = SimpleImputer(strategy='mean')\n", - "df = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": { - "id": "dUw_auE7w8JA" - }, - "outputs": [], - "source": [ - "# Select features and target variable\n", - "X = df[['Open', 'High', 'Low', 'Volume']]\n", - "y = df['Close']" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": { - "id": "FD2542-uxMhN" - }, - "outputs": [], - "source": [ - "# Split the data into training and testing sets\n", - "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": { - "id": "IfBxpcjIw-h7" - }, - "outputs": [], - "source": [ - "# Scale the features using Min-Max scaling\n", - "scaler = MinMaxScaler()\n", - "X_train_scaled = scaler.fit_transform(X_train)\n", - "X_test_scaled = scaler.transform(X_test)" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "BUsngQNexIjX", - "outputId": "6b739018-4a7d-48d9-a3ec-591a5cd0784e" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "(5659, 4)" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "X_train.shape" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "GAb1kDEZxQD6", - "outputId": "4babae88-adba-49ad-9d56-514bd7abde50" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "(1415, 4)" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "X_test.shape" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": { - "id": "SrzPIdvxxSWL" - }, - "outputs": [], - "source": [ - "# Function to evaluate and print RMSE, MAE, and MAPE\n", - "def evaluate_model(model, X_test, y_test):\n", - " predictions = model.predict(X_test)\n", - " rmse = np.sqrt(mean_squared_error(y_test, predictions))\n", - " mae = mean_absolute_error(y_test, predictions)\n", - " mape = mean_absolute_percentage_error(y_test, predictions)\n", - "\n", - " print(f\"RMSE: {rmse}\")\n", - " print(f\"MAE: {mae}\")\n", - " print(f\"MAPE: {mape}\\n\")\n", - "\n", - " return rmse, mae, mape\n" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": { - "id": "1V0eOGD_xVCq" - }, - "outputs": [], - "source": [ - "\n", - "metrics = {\n", - " \"Model\": [],\n", - " \"RMSE\": [],\n", - " \"MAE\": [],\n", - " \"MAPE\": []\n", - "}" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4gNvcwrH55rP" - }, - "source": [ - "# **1. Linear Regression**" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": { - "id": "uTbRFCB4xXHU" - }, - "outputs": [], - "source": [ - "# Create a linear regression model\n", - "model1 = LinearRegression()" - ] - }, - { - "cell_type": "code", - "execution_count": 14, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 241 - }, - "id": "UKaUaJ6sxaYG", - "outputId": "a28ae8d2-9430-4a1b-e9ba-475edfb7c788" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "5286 257.350006\n", - "3408 129.464996\n", - "5477 279.350006\n", - "6906 588.500000\n", - "530 21.644367\n", - "Name: Close, dtype: float64" - ] - }, - "execution_count": 14, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "y_train.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "6iJA5FrBxdEs", - "outputId": "6667305e-dd8d-445e-df54-c470c5b1e5ae" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
LinearRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "LinearRegression()" - ] - }, - "execution_count": 15, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model1.fit(X_train, y_train)" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "k-T73PFExiZD", - "outputId": "c794cf2c-c031-42c5-83ec-9432a9082d0f" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 1.688136464368173\n", - "MAE: 0.9433353485344464\n", - "MAPE: 0.006085435990852853\n", - "\n" - ] - } - ], - "source": [ - "rmse, mae, mape = evaluate_model(model1, X_test, y_test)\n", - "metrics[\"Model\"].append(\"Linear Regressor\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "qEVWWYIS592D" - }, - "source": [ - "# 2. Support Vector Regression" - ] - }, - { - "cell_type": "code", - "execution_count": 17, - "metadata": { - "id": "LeUTf8Vhxj_k" - }, - "outputs": [], - "source": [ - "# Create an SVR model\n", - "model2 = SVR()" - ] + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "8tzEK_mSvRoh" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.impute import SimpleImputer\n", + "from sklearn.preprocessing import MinMaxScaler\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.svm import SVR\n", + "from sklearn.tree import DecisionTreeRegressor\n", + "from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor, GradientBoostingRegressor\n", + "from sklearn.metrics import mean_squared_error, mean_absolute_error, mean_absolute_percentage_error\n", + "from sklearn.neighbors import KNeighborsRegressor\n", + "from tensorflow.keras.models import Sequential\n", + "from tensorflow.keras.layers import Dense,LSTM" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 }, + "id": "NbBSc2jLvZWx", + "outputId": "457e0a63-90a0-4e1c-b846-95e4e50c31dc" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 18, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "ud3Yhe5Vzvyh", - "outputId": "08f14bf4-3c1f-4973-c72a-52e2c264e759" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
SVR()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "SVR()" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
DateOpenHighLowCloseAdj CloseVolume
001-01-199618.69114718.97892218.54018418.82324012.40993143733533.0
102-01-199618.89400518.96476717.73819218.22410612.01493156167280.0
203-01-199618.32789218.56848917.64383917.73819211.69457768296318.0
304-01-199617.50231217.83254217.22397217.67686311.65414286073880.0
405-01-199617.73819217.78536617.45985217.57779311.58882776613039.0
\n", + "
" ], - "source": [ - "# Train the model\n", - "model2.fit(X_train, y_train)" + "text/plain": [ + " Date Open High Low Close Adj Close \\\n", + "0 01-01-1996 18.691147 18.978922 18.540184 18.823240 12.409931 \n", + "1 02-01-1996 18.894005 18.964767 17.738192 18.224106 12.014931 \n", + "2 03-01-1996 18.327892 18.568489 17.643839 17.738192 11.694577 \n", + "3 04-01-1996 17.502312 17.832542 17.223972 17.676863 11.654142 \n", + "4 05-01-1996 17.738192 17.785366 17.459852 17.577793 11.588827 \n", + "\n", + " Volume \n", + "0 43733533.0 \n", + "1 56167280.0 \n", + "2 68296318.0 \n", + "3 86073880.0 \n", + "4 76613039.0 " ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load the dataset\n", + "df = pd.read_csv('/content/SBIN.csv')\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "2QdTvORzwEJw" + }, + "outputs": [], + "source": [ + "# Drop the 'Date' and 'Adj Close' columns\n", + "df.drop(['Date', 'Adj Close'], axis=1, inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 }, + "id": "xMfr71b2w3eX", + "outputId": "a6990b82-ef82-454f-c0ba-fc0c21cc91ca" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 19, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "eiqL4fTuzxWH", - "outputId": "4a88e15a-0922-4c3c-906b-3d5d6efee119" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 147.71103599153602\n", - "MAE: 110.99419106508152\n", - "MAPE: 1.9715076513294716\n", - "\n" - ] - } + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
OpenHighLowCloseVolume
018.69114718.97892218.54018418.82324043733533.0
118.89400518.96476717.73819218.22410656167280.0
218.32789218.56848917.64383917.73819268296318.0
317.50231217.83254217.22397217.67686386073880.0
417.73819217.78536617.45985217.57779376613039.0
\n", + "
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model2, X_test, y_test)\n", - "metrics[\"Model\"].append(\"SVR\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" + "text/plain": [ + " Open High Low Close Volume\n", + "0 18.691147 18.978922 18.540184 18.823240 43733533.0\n", + "1 18.894005 18.964767 17.738192 18.224106 56167280.0\n", + "2 18.327892 18.568489 17.643839 17.738192 68296318.0\n", + "3 17.502312 17.832542 17.223972 17.676863 86073880.0\n", + "4 17.738192 17.785366 17.459852 17.577793 76613039.0" ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "# Handle missing values\n", + "imputer = SimpleImputer(strategy='mean')\n", + "df = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "dUw_auE7w8JA" + }, + "outputs": [], + "source": [ + "# Select features and target variable\n", + "X = df[['Open', 'High', 'Low', 'Volume']]\n", + "y = df['Close']" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "FD2542-uxMhN" + }, + "outputs": [], + "source": [ + "# Split the data into training and testing sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "IfBxpcjIw-h7" + }, + "outputs": [], + "source": [ + "# Scale the features using Min-Max scaling\n", + "scaler = MinMaxScaler()\n", + "X_train_scaled = scaler.fit_transform(X_train)\n", + "X_test_scaled = scaler.transform(X_test)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "BUsngQNexIjX", + "outputId": "6b739018-4a7d-48d9-a3ec-591a5cd0784e" + }, + "outputs": [ { - "cell_type": "markdown", - "metadata": { - "id": "PlDcozy-6OGR" - }, - "source": [ - "# 3. Random Forest Regressor" + "data": { + "text/plain": [ + "(5659, 4)" ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X_train.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "GAb1kDEZxQD6", + "outputId": "4babae88-adba-49ad-9d56-514bd7abde50" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 20, - "metadata": { - "id": "iaN8nOOO6cBg" - }, - "outputs": [], - "source": [ - "model3 = RandomForestRegressor()" + "data": { + "text/plain": [ + "(1415, 4)" ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X_test.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "SrzPIdvxxSWL" + }, + "outputs": [], + "source": [ + "# Function to evaluate and print RMSE, MAE, and MAPE\n", + "def evaluate_model(model, X_test, y_test):\n", + " predictions = model.predict(X_test)\n", + " rmse = np.sqrt(mean_squared_error(y_test, predictions))\n", + " mae = mean_absolute_error(y_test, predictions)\n", + " mape = mean_absolute_percentage_error(y_test, predictions)\n", + "\n", + " print(f\"RMSE: {rmse}\")\n", + " print(f\"MAE: {mae}\")\n", + " print(f\"MAPE: {mape}\\n\")\n", + "\n", + " return rmse, mae, mape\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "1V0eOGD_xVCq" + }, + "outputs": [], + "source": [ + "\n", + "metrics = {\n", + " \"Model\": [],\n", + " \"RMSE\": [],\n", + " \"MAE\": [],\n", + " \"MAPE\": []\n", + "}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4gNvcwrH55rP" + }, + "source": [ + "# **1. Linear Regression**" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "id": "uTbRFCB4xXHU" + }, + "outputs": [], + "source": [ + "# Create a linear regression model\n", + "model1 = LinearRegression()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 241 }, + "id": "UKaUaJ6sxaYG", + "outputId": "a28ae8d2-9430-4a1b-e9ba-475edfb7c788" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 21, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "wZ7x_Yp06fI_", - "outputId": "8f64c153-17f2-4939-9344-58db634aee31" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
RandomForestRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "RandomForestRegressor()" - ] - }, - "execution_count": 21, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model3.fit(X_train, y_train)" + "data": { + "text/plain": [ + "5286 257.350006\n", + "3408 129.464996\n", + "5477 279.350006\n", + "6906 588.500000\n", + "530 21.644367\n", + "Name: Close, dtype: float64" ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "y_train.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "6iJA5FrBxdEs", + "outputId": "6667305e-dd8d-445e-df54-c470c5b1e5ae" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 22, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "IwK7IZ3E6g_n", - "outputId": "1fa15097-6587-4b81-a0f0-e65ac6c6ba8f" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 224.92098628418847\n", - "MAE: 162.97484777804317\n", - "MAPE: 0.750567780636277\n", - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but RandomForestRegressor was fitted with feature names\n", - " warnings.warn(\n" - ] - } + "data": { + "text/html": [ + "
LinearRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model3, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"Random Forest\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ijTIDEEa6izO" - }, - "source": [ - "# 4. Gradient Boosting Models" - ] - }, - { - "cell_type": "code", - "execution_count": 23, - "metadata": { - "id": "EO6OFflr6nJo" - }, - "outputs": [], - "source": [ - "model4 = GradientBoostingRegressor()" + "text/plain": [ + "LinearRegression()" ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model1.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "k-T73PFExiZD", + "outputId": "c794cf2c-c031-42c5-83ec-9432a9082d0f" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 24, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "vrwnbrEi6o1X", - "outputId": "dbf1c6ff-ffcc-4b47-fbf6-8ba7f64a5f16" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
GradientBoostingRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "GradientBoostingRegressor()" - ] - }, - "execution_count": 24, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model4.fit(X_train, y_train)" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 1.688136464368173\n", + "MAE: 0.9433353485344464\n", + "MAPE: 0.006085435990852853\n", + "\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model1, X_test, y_test)\n", + "metrics[\"Model\"].append(\"Linear Regressor\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qEVWWYIS592D" + }, + "source": [ + "# 2. Support Vector Regression" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "LeUTf8Vhxj_k" + }, + "outputs": [], + "source": [ + "# Create an SVR model\n", + "model2 = SVR()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "ud3Yhe5Vzvyh", + "outputId": "08f14bf4-3c1f-4973-c72a-52e2c264e759" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 25, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "-pTBa0fD6qqx", - "outputId": "16225599-0077-447e-a1f5-3e2aa2f7ba8f" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 224.41069433522418\n", - "MAE: 162.27122816197573\n", - "MAPE: 0.7378541693598378\n", - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but GradientBoostingRegressor was fitted with feature names\n", - " warnings.warn(\n" - ] - } + "data": { + "text/html": [ + "
SVR()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model4, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"GBM\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "eGcU-e6C6sJI" - }, - "source": [ - "# 5. Extreme Graident Boosting" - ] - }, - { - "cell_type": "code", - "execution_count": 26, - "metadata": { - "id": "0GQmPNFd6uxx" - }, - "outputs": [], - "source": [ - "import xgboost as xgb\n", - "# Create an XGBoost model\n", - "model5 = xgb.XGBRegressor()" + "text/plain": [ + "SVR()" ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model2.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "eiqL4fTuzxWH", + "outputId": "4a88e15a-0922-4c3c-906b-3d5d6efee119" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 27, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 253 - }, - "id": "kfo1ZNft6xTp", - "outputId": "edfefbbd-744d-4c08-80bb-7ca2ffb3f765" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
-              "             colsample_bylevel=None, colsample_bynode=None,\n",
-              "             colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-              "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
-              "             gamma=None, grow_policy=None, importance_type=None,\n",
-              "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-              "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
-              "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
-              "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-              "             multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-              "             num_parallel_tree=None, random_state=None, ...)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "XGBRegressor(base_score=None, booster=None, callbacks=None,\n", - " colsample_bylevel=None, colsample_bynode=None,\n", - " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", - " enable_categorical=False, eval_metric=None, feature_types=None,\n", - " gamma=None, grow_policy=None, importance_type=None,\n", - " interaction_constraints=None, learning_rate=None, max_bin=None,\n", - " max_cat_threshold=None, max_cat_to_onehot=None,\n", - " max_delta_step=None, max_depth=None, max_leaves=None,\n", - " min_child_weight=None, missing=nan, monotone_constraints=None,\n", - " multi_strategy=None, n_estimators=None, n_jobs=None,\n", - " num_parallel_tree=None, random_state=None, ...)" - ] - }, - "execution_count": 27, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model5.fit(X_train, y_train)" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 147.71103599153602\n", + "MAE: 110.99419106508152\n", + "MAPE: 1.9715076513294716\n", + "\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model2, X_test, y_test)\n", + "metrics[\"Model\"].append(\"SVR\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "PlDcozy-6OGR" + }, + "source": [ + "# 3. Random Forest Regressor" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "iaN8nOOO6cBg" + }, + "outputs": [], + "source": [ + "model3 = RandomForestRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "wZ7x_Yp06fI_", + "outputId": "8f64c153-17f2-4939-9344-58db634aee31" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 28, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "7QwLt9iS6zSj", - "outputId": "bfc728a1-e169-44ea-8a4e-4b18e29f8c0e" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 224.66436370022384\n", - "MAE: 162.62070643817412\n", - "MAPE: 0.7441437311249671\n", - "\n" - ] - } + "data": { + "text/html": [ + "
RandomForestRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model5, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"XGBoost\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "sUD1VQBF605K" - }, - "source": [ - "# 6. AdaBoost Regressor" + "text/plain": [ + "RandomForestRegressor()" ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model3.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "IwK7IZ3E6g_n", + "outputId": "1fa15097-6587-4b81-a0f0-e65ac6c6ba8f" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 29, - "metadata": { - "id": "0foTLiQp63Y9" - }, - "outputs": [], - "source": [ - "model6 = AdaBoostRegressor()" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 224.92098628418847\n", + "MAE: 162.97484777804317\n", + "MAPE: 0.750567780636277\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": 30, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "bkzSWYA365MO", - "outputId": "c1f2bc96-a89c-4c83-873b-0836fa97c154" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
AdaBoostRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "AdaBoostRegressor()" - ] - }, - "execution_count": 30, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model6.fit(X_train, y_train)" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but RandomForestRegressor was fitted with feature names\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model3, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"Random Forest\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ijTIDEEa6izO" + }, + "source": [ + "# 4. Gradient Boosting Models" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "EO6OFflr6nJo" + }, + "outputs": [], + "source": [ + "model4 = GradientBoostingRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "vrwnbrEi6o1X", + "outputId": "dbf1c6ff-ffcc-4b47-fbf6-8ba7f64a5f16" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 31, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "ZKxqdmp166pF", - "outputId": "b027a6a7-45e7-49e3-f93c-ed787d86e83f" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 211.78853786766155\n", - "MAE: 150.2478993232628\n", - "MAPE: 0.7064489351945415\n", - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but AdaBoostRegressor was fitted with feature names\n", - " warnings.warn(\n" - ] - } + "data": { + "text/html": [ + "
GradientBoostingRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model6, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"AdaBoost Regressor\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "mtfkPIRi67xo" - }, - "source": [ - "# 7. Decision Tree" + "text/plain": [ + "GradientBoostingRegressor()" ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model4.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "-pTBa0fD6qqx", + "outputId": "16225599-0077-447e-a1f5-3e2aa2f7ba8f" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 32, - "metadata": { - "id": "E6EyzrH36_Fq" - }, - "outputs": [], - "source": [ - "model7 = DecisionTreeRegressor()" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 224.41069433522418\n", + "MAE: 162.27122816197573\n", + "MAPE: 0.7378541693598378\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": 33, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "DTp5VIYx7AWt", - "outputId": "8c71c048-7309-4aa2-ede9-517e62deaee3" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
DecisionTreeRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "DecisionTreeRegressor()" - ] - }, - "execution_count": 33, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model7.fit(X_train, y_train)" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but GradientBoostingRegressor was fitted with feature names\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model4, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"GBM\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "eGcU-e6C6sJI" + }, + "source": [ + "# 5. Extreme Graident Boosting" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "id": "0GQmPNFd6uxx" + }, + "outputs": [], + "source": [ + "import xgboost as xgb\n", + "# Create an XGBoost model\n", + "model5 = xgb.XGBRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 253 }, + "id": "kfo1ZNft6xTp", + "outputId": "edfefbbd-744d-4c08-80bb-7ca2ffb3f765" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 34, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "3YC-pSgv7Dh4", - "outputId": "cd1a1793-3a36-4028-919f-90d79f0c1b46" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 224.85857555038172\n", - "MAE: 162.88870413804315\n", - "MAPE: 0.7490024715971244\n", - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but DecisionTreeRegressor was fitted with feature names\n", - " warnings.warn(\n" - ] - } + "data": { + "text/html": [ + "
XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+       "             colsample_bylevel=None, colsample_bynode=None,\n",
+       "             colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "             gamma=None, grow_policy=None, importance_type=None,\n",
+       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "             multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "             num_parallel_tree=None, random_state=None, ...)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model7, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"Decision Tree\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "WfJAZHnP7E_2" - }, - "source": [ - "# 8. KNeighbors Regressor" + "text/plain": [ + "XGBRegressor(base_score=None, booster=None, callbacks=None,\n", + " colsample_bylevel=None, colsample_bynode=None,\n", + " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", + " enable_categorical=False, eval_metric=None, feature_types=None,\n", + " gamma=None, grow_policy=None, importance_type=None,\n", + " interaction_constraints=None, learning_rate=None, max_bin=None,\n", + " max_cat_threshold=None, max_cat_to_onehot=None,\n", + " max_delta_step=None, max_depth=None, max_leaves=None,\n", + " min_child_weight=None, missing=nan, monotone_constraints=None,\n", + " multi_strategy=None, n_estimators=None, n_jobs=None,\n", + " num_parallel_tree=None, random_state=None, ...)" ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model5.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "7QwLt9iS6zSj", + "outputId": "bfc728a1-e169-44ea-8a4e-4b18e29f8c0e" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 35, - "metadata": { - "id": "smujnWTRzzDL" - }, - "outputs": [], - "source": [ - "# Create a KNN model\n", - "model8 = KNeighborsRegressor()" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 224.66436370022384\n", + "MAE: 162.62070643817412\n", + "MAPE: 0.7441437311249671\n", + "\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model5, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"XGBoost\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "sUD1VQBF605K" + }, + "source": [ + "# 6. AdaBoost Regressor" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "id": "0foTLiQp63Y9" + }, + "outputs": [], + "source": [ + "model6 = AdaBoostRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "bkzSWYA365MO", + "outputId": "c1f2bc96-a89c-4c83-873b-0836fa97c154" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 36, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 80 - }, - "id": "zeokqhKd0Aj8", - "outputId": "018dff42-47da-4f2f-8bf9-16938de97723" - }, - "outputs": [ - { - "data": { - "text/html": [ - "
KNeighborsRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ], - "text/plain": [ - "KNeighborsRegressor()" - ] - }, - "execution_count": 36, - "metadata": {}, - "output_type": "execute_result" - } + "data": { + "text/html": [ + "
AdaBoostRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "# Train the model\n", - "model8.fit(X_train, y_train)" + "text/plain": [ + "AdaBoostRegressor()" ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model6.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "ZKxqdmp166pF", + "outputId": "b027a6a7-45e7-49e3-f93c-ed787d86e83f" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 37, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "X2uNfESC0CA8", - "outputId": "6c449192-697f-4bb9-9a8e-bc9aed955532" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "RMSE: 224.35603706259303\n", - "MAE: 162.1962430618594\n", - "MAPE: 0.7365233640314862\n", - "\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but KNeighborsRegressor was fitted with feature names\n", - " warnings.warn(\n" - ] - } - ], - "source": [ - "rmse, mae, mape = evaluate_model(model8, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"KNN\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 211.78853786766155\n", + "MAE: 150.2478993232628\n", + "MAPE: 0.7064489351945415\n", + "\n" + ] }, { - "cell_type": "markdown", - "metadata": { - "id": "X3yNCskZ7KMV" - }, - "source": [ - "# 9. Artificial Neural Networks" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but AdaBoostRegressor was fitted with feature names\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model6, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"AdaBoost Regressor\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mtfkPIRi67xo" + }, + "source": [ + "# 7. Decision Tree" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "E6EyzrH36_Fq" + }, + "outputs": [], + "source": [ + "model7 = DecisionTreeRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "DTp5VIYx7AWt", + "outputId": "8c71c048-7309-4aa2-ede9-517e62deaee3" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 38, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "syd9MRhf0Df1", - "outputId": "1c546101-530f-4e5c-af43-79fd68b68347" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\keras\\src\\layers\\core\\dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", - " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" - ] - } + "data": { + "text/html": [ + "
DecisionTreeRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "# Create an ANN model\n", - "model9 = Sequential()\n", - "model9.add(Dense(32, activation='relu', input_shape=(X_train.shape[1],)))\n", - "model9.add(Dense(16, activation='relu'))\n", - "model9.add(Dense(1, activation='linear'))" + "text/plain": [ + "DecisionTreeRegressor()" ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model7.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "3YC-pSgv7Dh4", + "outputId": "cd1a1793-3a36-4028-919f-90d79f0c1b46" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 39, - "metadata": { - "id": "pdlxN-Dp0IZr" - }, - "outputs": [], - "source": [ - "# Compile the model\n", - "model9.compile(loss='mean_squared_error', optimizer='adam')" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 224.85857555038172\n", + "MAE: 162.88870413804315\n", + "MAPE: 0.7490024715971244\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": 40, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "qcryLURL0KIH", - "outputId": "54e02177-ee86-46bf-cfef-496cb59b8577" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 40, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train the model\n", - "model9.fit(X_train_scaled, y_train, epochs=100, batch_size=32, verbose=0)" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but DecisionTreeRegressor was fitted with feature names\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model7, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"Decision Tree\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "WfJAZHnP7E_2" + }, + "source": [ + "# 8. KNeighbors Regressor" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "id": "smujnWTRzzDL" + }, + "outputs": [], + "source": [ + "# Create a KNN model\n", + "model8 = KNeighborsRegressor()" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 }, + "id": "zeokqhKd0Aj8", + "outputId": "018dff42-47da-4f2f-8bf9-16938de97723" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 41, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "Xu6Cwjey0MaP", - "outputId": "92beea16-08fa-45d1-c817-88b1b1e3c688" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step\n", - "RMSE: 2.8762951713017757\n", - "MAE: 1.8845151984048805\n", - "MAPE: 0.015311824533529984\n", - "\n" - ] - } + "data": { + "text/html": [ + "
KNeighborsRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], - "source": [ - "rmse, mae, mape = evaluate_model(model9, X_test_scaled, y_test)\n", - "metrics[\"Model\"].append(\"ANN\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "Yet4TgKq7OZl" - }, - "source": [ - "# 10. Long Short Term Memory" + "text/plain": [ + "KNeighborsRegressor()" ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model8.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "X2uNfESC0CA8", + "outputId": "6c449192-697f-4bb9-9a8e-bc9aed955532" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 42, - "metadata": { - "id": "keiZDN4w7UH0" - }, - "outputs": [], - "source": [ - "n_features = X_train_scaled.shape[1]\n", - "n_steps = 10\n", - "n_samples_train = X_train_scaled.shape[0] - n_steps + 1\n", - "n_samples_test = X_test_scaled.shape[0] - n_steps + 1\n", - "\n", - "# Reshape the input data\n", - "X_train_reshaped = np.array([X_train_scaled[i:i+n_steps, :] for i in range(n_samples_train)])\n", - "X_test_reshaped = np.array([X_test_scaled[i:i+n_steps, :] for i in range(n_samples_test)])" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "RMSE: 224.35603706259303\n", + "MAE: 162.1962430618594\n", + "MAPE: 0.7365233640314862\n", + "\n" + ] }, { - "cell_type": "code", - "execution_count": 43, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "nRRTkQTD7Vjd", - "outputId": "8c0e1de9-8382-482f-dc46-d6148e3f535e" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:204: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", - " super().__init__(**kwargs)\n" - ] - } - ], - "source": [ - "model10 = Sequential()\n", - "model10.add(LSTM(64, activation='relu', input_shape=(n_steps, n_features)))\n", - "model10.add(Dense(1))" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but KNeighborsRegressor was fitted with feature names\n", + " warnings.warn(\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model8, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"KNN\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "X3yNCskZ7KMV" + }, + "source": [ + "# 9. Artificial Neural Networks" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "syd9MRhf0Df1", + "outputId": "1c546101-530f-4e5c-af43-79fd68b68347" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 44, - "metadata": { - "id": "3UJtO3wC7WWe" - }, - "outputs": [], - "source": [ - "# Compile the model\n", - "model10.compile(loss='mean_squared_error', optimizer='adam')\n" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\keras\\src\\layers\\core\\dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], + "source": [ + "# Create an ANN model\n", + "model9 = Sequential()\n", + "model9.add(Dense(32, activation='relu', input_shape=(X_train.shape[1],)))\n", + "model9.add(Dense(16, activation='relu'))\n", + "model9.add(Dense(1, activation='linear'))" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "id": "pdlxN-Dp0IZr" + }, + "outputs": [], + "source": [ + "# Compile the model\n", + "model9.compile(loss='mean_squared_error', optimizer='adam')" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "qcryLURL0KIH", + "outputId": "54e02177-ee86-46bf-cfef-496cb59b8577" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "ld9dofMD7YNO", - "outputId": "2b3021f3-d88f-431c-a059-a9b6e065a29b" - }, - "outputs": [], - "source": [ - "model10.fit(X_train_reshaped, y_train[n_steps-1:], epochs=100, batch_size=32, verbose=0)" + "data": { + "text/plain": [ + "" ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train the model\n", + "model9.fit(X_train_scaled, y_train, epochs=100, batch_size=32, verbose=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "Xu6Cwjey0MaP", + "outputId": "92beea16-08fa-45d1-c817-88b1b1e3c688" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 55, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "lOTdB8Bj7aXM", - "outputId": "c844bad9-4c1e-447f-dad9-7b86f57dee9b" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1m44/44\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step\n", - "RMSE: 15.048059609987224\n", - "MAE: 12.060430640867935\n", - "MAPE: 0.21836694109231441\n", - "\n" - ] - } - ], - "source": [ - "rmse, mae, mape = evaluate_model(model10, X_test_reshaped, y_test[n_steps-1:])\n", - "\n", - "# Store metrics\n", - "metrics[\"Model\"].append(\"LSTM\")\n", - "metrics[\"RMSE\"].append(rmse)\n", - "metrics[\"MAE\"].append(mae)\n", - "metrics[\"MAPE\"].append(mape)" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step\n", + "RMSE: 2.8762951713017757\n", + "MAE: 1.8845151984048805\n", + "MAPE: 0.015311824533529984\n", + "\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model9, X_test_scaled, y_test)\n", + "metrics[\"Model\"].append(\"ANN\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Yet4TgKq7OZl" + }, + "source": [ + "# 10. Long Short Term Memory" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "id": "keiZDN4w7UH0" + }, + "outputs": [], + "source": [ + "n_features = X_train_scaled.shape[1]\n", + "n_steps = 10\n", + "n_samples_train = X_train_scaled.shape[0] - n_steps + 1\n", + "n_samples_test = X_test_scaled.shape[0] - n_steps + 1\n", + "\n", + "# Reshape the input data\n", + "X_train_reshaped = np.array([X_train_scaled[i:i+n_steps, :] for i in range(n_samples_train)])\n", + "X_test_reshaped = np.array([X_test_scaled[i:i+n_steps, :] for i in range(n_samples_test)])" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "nRRTkQTD7Vjd", + "outputId": "8c0e1de9-8382-482f-dc46-d6148e3f535e" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 60, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 506 - }, - "id": "O8DHEHgI0wNg", - "outputId": "5cd999c9-0cca-4d23-da28-8655ce099354" - }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAr8AAAHpCAYAAACLJlSZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACCCElEQVR4nO3ddVhU2f8H8PfQKCUYiImB3SJgYhF2rt251qproa7dvXZ3rd3did3JYoGKugZIx3x+f/Cb+2WMXQMdhnm/nodnl3vPjJ/LzNx5z5lzzlWJiICIiIiIyAAY6boAIiIiIqKfheGXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIKImAgAB4eXnB1tYWKpUK27Zt03VJWo4dOwaVSoVjx45pbV+1ahXy588PU1NT2NnZKdsnT56MXLlywdjYGMWLF/+ptaZGn/v7f4nly5dDpVLh0aNHyV4XEX05hl8i+maaN3PNj4mJCbJkyYK2bdvi6dOnH7X39PSESqVC3rx5P3l/Bw8eVO5r06ZNWvtu3LiBRo0aIUeOHLCwsECWLFlQvXp1zJo1S6tdzpw5tWpK+uPj4/Ofx9SmTRvcuHEDY8eOxapVq1C6dOmv+It8nUePHmnVZ2pqivTp06Ns2bIYPHgwnjx58kX3c/fuXbRt2xa5c+fGokWLsHDhQgDAgQMHMGDAAJQrVw7Lli3DuHHjftixfK8zZ85gxIgRePfu3Re1b9u2LVQqFWxsbBAVFfXR/oCAAOXvOmXKlGSuloj0mYmuCyAi/Tdq1Cg4OzsjOjoa/v7+WL58OU6dOoWbN2/CwsJCq62FhQX+/vtvnD9/HmXKlNHat2bNGlhYWCA6Olpr+5kzZ1C5cmVkz54dnTp1gqOjI4KCguDv748///wTPXv21GpfvHhx/P777x/V6eTk9K/HERUVhbNnz2LIkCHo0aPH1/wJvkuzZs1Qo0YNqNVqvH37FhcuXMCMGTPw559/YsmSJWjatKnStmLFioiKioKZmZmy7dixY1Cr1fjzzz+RJ08eZfuRI0dgZGSEJUuWaLVPic6cOYORI0eibdu2Wj3X/8bExASRkZHYuXMnfvnlF619n3suEREx/BLRd/P19VV6SDt27Ij06dNj4sSJ2LFjx0ehJHfu3IiPj8e6deu0wm90dDS2bt2KmjVrYvPmzVq3GTt2LGxtbXHhwoWPgtHLly8/qidLlixo2bLlVx/Hq1evAOCLw9eXiIiIQNq0af+1TcmSJT+q9/Hjx/Dy8kKbNm1QoEABFCtWDABgZGT00QcKzd/gU38bS0vLZA2+kZGRSJMmTbLd3/cwNzdHuXLlsG7duo+eZ2vXrv3kc4mIiMMeiCjZVahQAQAQGBj4yf3NmjXDX3/9BbVarWzbuXMnIiMjPwoxmvspVKjQJ0NpxowZk6XmESNGIEeOHACA/v37Q6VSIWfOnMr+K1euwNfXFzY2NrCyskLVqlXh7++vdR+aYSDHjx9Ht27dkDFjRmTNmvWb6smRIweWL1+O2NhYTJo0Sdn+4ZjTnDlzYvjw4QCADBkyQKVSYcSIEVCpVFi2bBkiIiKUr/+XL1+u3M/q1atRqlQpWFpawt7eHk2bNkVQUJBWDZ6enihcuDAuXbqEihUrIk2aNBg8eDAAICYmBsOHD0eePHlgbm6ObNmyYcCAAYiJidG6D5VKhR49emDbtm0oXLgwzM3NUahQIezbt0/rb9+/f38AgLOzs1Lvl4yNbd68Ofbu3as1XOLChQsICAhA8+bNP3mbBw8eoHHjxrC3t0eaNGng7u6O3bt3f9QuODgY9erVQ9q0aZExY0b06dPno+PTOHfuHHx8fGBra4s0adKgUqVKOH369H/Wf/HiRXh7eyN9+vSwtLSEs7Mz2rdv/5+3I6Jvx55fIkp2mtCSLl26T+5v3rw5RowYgWPHjqFKlSoAEnvqqlat+skwmyNHDpw9exY3b95E4cKF//Pfj4uLwz///PPR9rRp08LS0vKTt2nQoAHs7OzQp08fZRiClZUVAODWrVuoUKECbGxsMGDAAJiammLBggXw9PTE8ePH4ebmpnVf3bp1Q4YMGTBs2DBERET8Z72f4+Hhgdy5c+PgwYOfbTNjxgysXLkSW7duxbx582BlZYWiRYsiT548WLhwIc6fP4/FixcDAMqWLQsgsSf9jz/+wC+//IKOHTvi1atXmDVrFipWrIgrV65ofch4/fo1fH190bRpU7Rs2RKZMmWCWq1GnTp1cOrUKXTu3BkFChTAjRs3MH36dNy/f/+jSYKnTp3Cli1b0K1bN1hbW2PmzJlo2LAhnjx5AgcHBzRo0AD379/HunXrMH36dKRPnx5AYpj/Lw0aNEDXrl2xZcsWJTSuXbsW+fPnR8mSJT9q/+LFC5QtWxaRkZHo1asXHBwcsGLFCtSpUwebNm1C/fr1ASQOgalatSqePHmCXr16wcnJCatWrcKRI0c+us8jR47A19cXpUqVwvDhw2FkZIRly5ahSpUqOHny5EfDezRevnwJLy8vZMiQAYMGDYKdnR0ePXqELVu2/OdxE9F3ECKib7Rs2TIBIIcOHZJXr15JUFCQbNq0STJkyCDm5uYSFBSk1b5SpUpSqFAhEREpXbq0dOjQQURE3r59K2ZmZrJixQo5evSoAJCNGzcqtztw4IAYGxuLsbGxeHh4yIABA2T//v0SGxv7UU05cuQQAJ/8GT9+/L8ez8OHDwWATJ48WWt7vXr1xMzMTAIDA5Vtz549E2tra6lYseJHf4/y5ctLfHz8f/79PvfvJVW3bl0BIKGhoSIiyt/n6NGjSpvhw4cLAHn16pXWbdu0aSNp06bV2vbo0SMxNjaWsWPHam2/ceOGmJiYaG2vVKmSAJD58+drtV21apUYGRnJyZMntbbPnz9fAMjp06eVbQDEzMxM/v77b2XbtWvXBIDMmjVL2TZ58mQBIA8fPvzs3+Jzx9aoUSOpWrWqiIgkJCSIo6OjjBw58pN/3969ewsArdrfv38vzs7OkjNnTklISBARkRkzZggA2bBhg9IuIiJC8uTJo/X3V6vVkjdvXvH29ha1Wq20jYyMFGdnZ6levbqyTfP80Bzj1q1bBYBcuHDhi46ZiJIHhz0Q0XerVq0aMmTIgGzZsqFRo0ZImzYtduzY8a9f+Tdv3hxbtmxBbGwsNm3aBGNjY6XX7UPVq1fH2bNnUadOHVy7dg2TJk2Ct7c3smTJgh07dnzU3s3NDQcPHvzop1mzZl99bAkJCThw4ADq1auHXLlyKdszZ86M5s2b49SpUwgLC9O6TadOnWBsbPzV/9anaHqf379/nyz3t2XLFqjVavzyyy/4559/lB9HR0fkzZsXR48e1Wpvbm6Odu3aaW3buHEjChQogPz582vdh6YX/8P7qFatGnLnzq38XrRoUdjY2ODBgwfJckzNmzfHsWPHEBISgiNHjiAkJOSzQx727NmDMmXKoHz58so2KysrdO7cGY8ePcLt27eVdpkzZ0ajRo2UdmnSpEHnzp217u/q1avKEIvXr18rf4uIiAhUrVoVJ06c0Brek5Smh33Xrl2Ii4v7nj8BEX0FDnsgou82Z84cuLi4IDQ0FEuXLsWJEydgbm7+r7dp2rQp+vXrh71792LNmjWoVasWrK2tP9ve1dVVCcvXrl3D1q1bMX36dDRq1AhXr15FwYIFlbbp06dHtWrVkuXYXr16hcjISOTLl++jfQUKFIBarUZQUBAKFSqkbHd2dk6WfxsAwsPDAeBf/zZfIyAgACLy2eXmTE1NtX7PkiXLRxPmAgICcOfOnc8OS/hwEmL27Nk/apMuXTq8ffv2a0r/rBo1asDa2hp//fUXrl69CldXV+TJk+eTY4YfP3780TAVIPGx1OwvXLgwHj9+jDx58kClUmm1+/B5EBAQACBxibzPCQ0N/eQQoEqVKqFhw4YYOXIkpk+fDk9PT9SrVw/Nmzf/z9cPEX07hl8i+m5lypRRVnuoV68eypcvj+bNm+PevXtKz+WHMmfODE9PT0ydOhWnT5/+4ln5ZmZmcHV1haurK1xcXNCuXTts3LhRmfSVEnxuXPG3uHnzJjJmzAgbG5tkuT+1Wg2VSoW9e/d+snf6w8frU8eiVqtRpEgRTJs27ZP/RrZs2bR+/1wvuIh8adn/ytzcHA0aNMCKFSvw4MEDjBgxIlnu90toenUnT5782YuIfO41oFnP2t/fHzt37sT+/fvRvn17TJ06Ff7+/p+9HRF9H4ZfIkpWxsbGGD9+PCpXrozZs2dj0KBBn23bvHlzdOzYEXZ2dqhRo8ZX/1uawP38+fNvrve/ZMiQAWnSpMG9e/c+2nf37l0YGRl9FPaSy9mzZxEYGPhNy7Z9Tu7cuSEicHZ2houLyzffx7Vr11C1atWPeka/1ffeT/PmzbF06VIYGRlprYv8oRw5cnz2sdTs1/z35s2bEBGt2j68rWY4h42NzTd/2+Du7g53d3eMHTsWa9euRYsWLbB+/Xp07Njxm+6PiP4dx/wSUbLz9PREmTJlMGPGjH+9yECjRo0wfPhwzJ0791/Xoj169Ognewn37NkD4OOvopOTsbExvLy8sH37dq2v0V+8eIG1a9eifPnyydYrm9Tjx4/Rtm1bmJmZKcuAJYcGDRrA2NgYI0eO/OhvKiJ4/fr1f97HL7/8gqdPn2LRokUf7YuKivqmFS40ayF/6RXePlS5cmWMHj0as2fPhqOj42fb1ahRA+fPn8fZs2eVbREREVi4cCFy5sypDJ+pUaMGnj17pnWlwcjISOXqeRqlSpVC7ty5MWXKFGWISlKataM/5e3btx89Bpre488tqUZE3489v0T0Q/Tv3x+NGzfG8uXL0bVr10+2sbW1/aKvqHv27InIyEjUr18f+fPnR2xsLM6cOYO//voLOXPm/GhC1tOnT7F69eqP7sfKygr16tX76mMZM2YMDh48iPLly6Nbt24wMTHBggULEBMTo7UG77e6fPkyVq9eDbVajXfv3uHChQvYvHkzVCoVVq1ahaJFi373v6GRO3dujBkzBn5+fnj06BHq1asHa2trPHz4EFu3bkXnzp3Rr1+/f72PVq1aYcOGDejatSuOHj2KcuXKISEhAXfv3sWGDRuwf//+r74sdKlSpQAAQ4YMQdOmTWFqaoratWv/5wVCNIyMjDB06ND/bDdo0CCsW7cOvr6+6NWrF+zt7bFixQo8fPgQmzdvhpFRYp9Qp06dMHv2bLRu3RqXLl1C5syZsWrVqo8u8GFkZITFixfD19cXhQoVQrt27ZAlSxY8ffoUR48ehY2NDXbu3PnJWlasWIG5c+eifv36yJ07N96/f49FixbBxsbmm74JIaIvw/BLRD9EgwYNlB6x7139YMqUKdi4cSP27NmDhQsXIjY2FtmzZ0e3bt0wdOjQjy5+cfXqVbRq1eqj+8mRI8c3hd9ChQrh5MmT8PPzw/jx46FWq+Hm5obVq1d/cvLU11q3bh3WrVsHExMT2NjYIG/evOjduze6du36ycli32vQoEFwcXHB9OnTMXLkSACJ43S9vLxQp06d/7y9kZERtm3bhunTpytrDKdJkwa5cuXCb7/99k3DKVxdXTF69GjMnz8f+/btg1qtxsOHD784/H6pTJky4cyZMxg4cCBmzZqF6OhoFC1aFDt37kTNmjWVdmnSpMHhw4fRs2dPzJo1C2nSpEGLFi3g6+sLHx8frfv09PTE2bNnlZ7n8PBwODo6ws3NDV26dPlsLZUqVcL58+exfv16vHjxAra2tihTpgzWrFmTrJMmiUibSpJrxgERERERUQrHMb9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoNLnSHx8pTPnj2DtbV1sl2tiIiIiIh+HhHB+/fv4eTkpKzZ/SkMvwCePXv2wy5PSkREREQ/T1BQELJmzfrZ/Qy/AKytrQEk/rF+xGVKiYiIiOjHCgsLQ7Zs2ZRc9zkMv4Ay1MHGxobhl4iIiEiP/dcQVk54IyIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkME10XQJRabLn3XNclfJMG+TLruoQUSV8fT4CP6efo62PKx5MoeTH8EtFX0dcAATBEkGHga5To33HYAxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAyGia4LICIi3dpy77muS/gmDfJl1nUJRKSH2PNLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMhk7D7/jx4+Hq6gpra2tkzJgR9erVw71797TaREdHo3v37nBwcICVlRUaNmyIFy9eaLV58uQJatasiTRp0iBjxozo378/4uPjf+ahEBEREZEe0Gn4PX78OLp37w5/f38cPHgQcXFx8PLyQkREhNKmT58+2LlzJzZu3Ijjx4/j2bNnaNCggbI/ISEBNWvWRGxsLM6cOYMVK1Zg+fLlGDZsmC4OiYiIiIhSMBNd/uP79u3T+n358uXImDEjLl26hIoVKyI0NBRLlizB2rVrUaVKFQDAsmXLUKBAAfj7+8Pd3R0HDhzA7du3cejQIWTKlAnFixfH6NGjMXDgQIwYMQJmZma6ODQiIiIiSoFS1Jjf0NBQAIC9vT0A4NKlS4iLi0O1atWUNvnz50f27Nlx9uxZAMDZs2dRpEgRZMqUSWnj7e2NsLAw3Lp165P/TkxMDMLCwrR+iIiIiCj1SzHhV61Wo3fv3ihXrhwKFy4MAAgJCYGZmRns7Oy02mbKlAkhISFKm6TBV7Nfs+9Txo8fD1tbW+UnW7ZsyXw0RERERJQSpZjw2717d9y8eRPr16//4f+Wn58fQkNDlZ+goKAf/m8SERERke7pdMyvRo8ePbBr1y6cOHECWbNmVbY7OjoiNjYW79690+r9ffHiBRwdHZU258+f17o/zWoQmjYfMjc3h7m5eTIfBRERERGldDrt+RUR9OjRA1u3bsWRI0fg7Oystb9UqVIwNTXF4cOHlW337t3DkydP4OHhAQDw8PDAjRs38PLlS6XNwYMHYWNjg4IFC/6cAyEiIiIivaDTnt/u3btj7dq12L59O6ytrZUxura2trC0tIStrS06dOiAvn37wt7eHjY2NujZsyc8PDzg7u4OAPDy8kLBggXRqlUrTJo0CSEhIRg6dCi6d+/O3l0iIiIi0qLT8Dtv3jwAgKenp9b2ZcuWoW3btgCA6dOnw8jICA0bNkRMTAy8vb0xd+5cpa2xsTF27dqFX3/9FR4eHkibNi3atGmDUaNG/azDICIiIiI9odPwKyL/2cbCwgJz5szBnDlzPtsmR44c2LNnT3KWRkRERESpUIpZ7YGIiIiI6Edj+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwdBp+T5w4gdq1a8PJyQkqlQrbtm3T2t+2bVuoVCqtHx8fH602b968QYsWLWBjYwM7Ozt06NAB4eHhP/EoiIiIiEhf6DT8RkREoFixYpgzZ85n2/j4+OD58+fKz7p167T2t2jRArdu3cLBgwexa9cunDhxAp07d/7RpRMRERGRHjLR5T/u6+sLX1/ff21jbm4OR0fHT+67c+cO9u3bhwsXLqB06dIAgFmzZqFGjRqYMmUKnJycPnm7mJgYxMTEKL+HhYV94xEQERERkT5J8WN+jx07howZMyJfvnz49ddf8fr1a2Xf2bNnYWdnpwRfAKhWrRqMjIxw7ty5z97n+PHjYWtrq/xky5bthx4DEREREaUMKTr8+vj4YOXKlTh8+DAmTpyI48ePw9fXFwkJCQCAkJAQZMyYUes2JiYmsLe3R0hIyGfv18/PD6GhocpPUFDQDz0OIiIiIkoZdDrs4b80bdpU+f8iRYqgaNGiyJ07N44dO4aqVat+8/2am5vD3Nw8OUokIiIiIj2SosPvh3LlyoX06dPj77//RtWqVeHo6IiXL19qtYmPj8ebN28+O06Yfq4t957ruoRv1iBfZl2XQERERMksRQ97+FBwcDBev36NzJkTQ4mHhwfevXuHS5cuKW2OHDkCtVoNNzc3XZVJRERERCmUTnt+w8PD8ffffyu/P3z4EFevXoW9vT3s7e0xcuRINGzYEI6OjggMDMSAAQOQJ08eeHt7AwAKFCgAHx8fdOrUCfPnz0dcXBx69OiBpk2bfnalByIiIiIyXDrt+b148SJKlCiBEiVKAAD69u2LEiVKYNiwYTA2Nsb169dRp04duLi4oEOHDihVqhROnjypNV53zZo1yJ8/P6pWrYoaNWqgfPnyWLhwoa4OiYiIiIhSMJ32/Hp6ekJEPrt///79/3kf9vb2WLt2bXKWRURERESplF6N+SUiIiIi+h4Mv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYHxV+H358uW/7o+Pj8f58+e/qyAiIiIioh/lq8Jv5syZtQJwkSJFEBQUpPz++vVreHh4JF91RERERETJ6KvCr4ho/f7o0SPExcX9axsiIiIiopQi2cf8qlSq5L5LIiIiIqJkwQlvRERERGQwTL6msUqlwvv372FhYQERgUqlQnh4OMLCwgBA+S8RERERUUr0VeFXRODi4qL1e4kSJbR+57AHIiIiIkqpvir8Hj169EfVQURERET0w31V+K1UqdKPqoOIiIiI6If7qvAbHx+PhIQEmJubK9tevHiB+fPnIyIiAnXq1EH58uWTvUgiIiIiouTwVeG3U6dOMDMzw4IFCwAA79+/h6urK6Kjo5E5c2ZMnz4d27dvR40aNX5IsURERERE3+Orljo7ffo0GjZsqPy+cuVKJCQkICAgANeuXUPfvn0xefLkZC+SiIiIiCg5fFX4ffr0KfLmzav8fvjwYTRs2BC2trYAgDZt2uDWrVvJWyERERERUTL5qvBrYWGBqKgo5Xd/f3+4ublp7Q8PD0++6oiIiIiIktFXhd/ixYtj1apVAICTJ0/ixYsXqFKlirI/MDAQTk5OyVshEREREVEy+aoJb8OGDYOvry82bNiA58+fo23btsicObOyf+vWrShXrlyyF0lERERElBy+ep3fS5cu4cCBA3B0dETjxo219hcvXhxlypRJ1gKJiIiIiJLLV4VfAChQoAAKFCjwyX2dO3f+7oKIiIiIiH6Urwq/J06c+KJ2FStW/KZiiIiIiIh+pK8Kv56enlCpVAAAEflkG5VKhYSEhO+vjIiIiIgomX1V+E2XLh2sra3Rtm1btGrVCunTp/9RdRERERERJbuvWurs+fPnmDhxIs6ePYsiRYqgQ4cOOHPmDGxsbGBra6v8EBERERGlRF8Vfs3MzNCkSRPs378fd+/eRdGiRdGjRw9ky5YNQ4YMQXx8/I+qk4iIiIjou31V+E0qe/bsGDZsGA4dOgQXFxdMmDABYWFhyVkbEREREVGy+qbwGxMTg7Vr16JatWooXLgw0qdPj927d8Pe3j656yMiIiIiSjZfNeHt/PnzWLZsGdavX4+cOXOiXbt22LBhA0MvEREREemFrwq/7u7uyJ49O3r16oVSpUoBAE6dOvVRuzp16iRPdUREREREyeirr/D25MkTjB49+rP7uc4vEREREaVUXxV+1Wr1f7aJjIz85mKIiIiIiH6kb17t4UMxMTGYNm0acuXKlVx3SURERESUrL4q/MbExMDPzw+lS5dG2bJlsW3bNgDA0qVL4ezsjOnTp6NPnz4/ok4iIiIiou/2VcMehg0bhgULFqBatWo4c+YMGjdujHbt2sHf3x/Tpk1D48aNYWxs/KNqJSIiIiL6Ll8Vfjdu3IiVK1eiTp06uHnzJooWLYr4+Hhcu3YNKpXqR9VIRERERJQsvmrYQ3BwsLLEWeHChWFubo4+ffow+BIRERGRXviq8JuQkAAzMzPldxMTE1hZWSV7UUREREREP8JXDXsQEbRt2xbm5uYAgOjoaHTt2hVp06bVardly5bkq5CIiIiIKJl8Vc9vmzZtkDFjRtja2sLW1hYtW7aEk5OT8rvm50udOHECtWvXhpOTE1QqlbJ6hIaIYNiwYcicOTMsLS1RrVo1BAQEaLV58+YNWrRoARsbG9jZ2aFDhw4IDw//msMiIiIiIgPxVT2/y5YtS9Z/PCIiAsWKFUP79u3RoEGDj/ZPmjQJM2fOxIoVK+Ds7Iw//vgD3t7euH37NiwsLAAALVq0wPPnz3Hw4EHExcWhXbt26Ny5M9auXZustRIRERGR/vvqyxsnJ19fX/j6+n5yn4hgxowZGDp0KOrWrQsAWLlyJTJlyoRt27ahadOmuHPnDvbt24cLFy6gdOnSAIBZs2ahRo0amDJlCpycnD553zExMYiJiVF+DwsLS+YjIyIiIqKUKNmu8JbcHj58iJCQEFSrVk3ZZmtrCzc3N5w9exYAcPbsWdjZ2SnBFwCqVasGIyMjnDt37rP3PX78eK1hGtmyZftxB0JEREREKUaKDb8hISEAgEyZMmltz5Qpk7IvJCQEGTNm1NpvYmICe3t7pc2n+Pn5ITQ0VPkJCgpK5uqJiIiIKCXS6bAHXTE3N1dWrCAiIiIiw5Fie34dHR0BAC9evNDa/uLFC2Wfo6MjXr58qbU/Pj4eb968UdoQEREREWmk2PDr7OwMR0dHHD58WNkWFhaGc+fOwcPDAwDg4eGBd+/e4dKlS0qbI0eOQK1Ww83N7afXTEREREQpm06HPYSHh+Pvv/9Wfn/48CGuXr0Ke3t7ZM+eHb1798aYMWOQN29eZakzJycn1KtXDwBQoEAB+Pj4oFOnTpg/fz7i4uLQo0cPNG3a9LMrPRARERGR4dJp+L148SIqV66s/N63b18AiRfTWL58OQYMGICIiAh07twZ7969Q/ny5bFv3z5ljV8AWLNmDXr06IGqVavCyMgIDRs2xMyZM3/6sRARERFRyqfT8Ovp6QkR+ex+lUqFUaNGYdSoUZ9tY29vzwtaEBEREdEXSbFjfomIiIiIkhvDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBSNHhd8SIEVCpVFo/+fPnV/ZHR0eje/fucHBwgJWVFRo2bIgXL17osGIiIiIiSslSdPgFgEKFCuH58+fKz6lTp5R9ffr0wc6dO7Fx40YcP34cz549Q4MGDXRYLRERERGlZCa6LuC/mJiYwNHR8aPtoaGhWLJkCdauXYsqVaoAAJYtW4YCBQrA398f7u7uP7tUIiIiIkrhUnzPb0BAAJycnJArVy60aNECT548AQBcunQJcXFxqFatmtI2f/78yJ49O86ePfuv9xkTE4OwsDCtHyIiIiJK/VJ0+HVzc8Py5cuxb98+zJs3Dw8fPkSFChXw/v17hISEwMzMDHZ2dlq3yZQpE0JCQv71fsePHw9bW1vlJ1u2bD/wKIiIiIgopUjRwx58fX2V/y9atCjc3NyQI0cObNiwAZaWlt98v35+fujbt6/ye1hYGAMwERERkQFI0T2/H7Kzs4OLiwv+/vtvODo6IjY2Fu/evdNq8+LFi0+OEU7K3NwcNjY2Wj9ERERElPrpVfgNDw9HYGAgMmfOjFKlSsHU1BSHDx9W9t+7dw9PnjyBh4eHDqskIiIiopQqRQ976NevH2rXro0cOXLg2bNnGD58OIyNjdGsWTPY2tqiQ4cO6Nu3L+zt7WFjY4OePXvCw8ODKz0QERER0Sel6PAbHByMZs2a4fXr18iQIQPKly8Pf39/ZMiQAQAwffp0GBkZoWHDhoiJiYG3tzfmzp2r46qJiIiIKKVK0eF3/fr1/7rfwsICc+bMwZw5c35SRURERESkz/RqzC8RERER0fdg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhgMv0RERERkMBh+iYiIiMhgMPwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDBMdF0AEREREX3elnvPdV3CN2mQL7OuS/gk9vwSERERkcFg+CUiIiIig8HwS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD4JSIiIiKDwfBLRERERAaD4ZeIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDBMdF1AcpkzZw4mT56MkJAQFCtWDLNmzUKZMmV0XRYRERH9AFvuPdd1Cd+sQb7Mui7BoKWK8PvXX3+hb9++mD9/Ptzc3DBjxgx4e3vj3r17yJgxo67L+yS+aImIiIh+vlQRfqdNm4ZOnTqhXbt2AID58+dj9+7dWLp0KQYNGvRR+5iYGMTExCi/h4aGAgDCwsJ+TsEAIsPf/7R/K7mFhaX94raGcpyA/h6roRwnwOfu5+jrsfI4P01fjxPga/Rz9PVYv/Y4v//fS8xxIvKv7fQ+/MbGxuLSpUvw8/NTthkZGaFatWo4e/bsJ28zfvx4jBw58qPt2bJl+2F1EhEREdGP9/79e9ja2n52v96H33/++QcJCQnIlCmT1vZMmTLh7t27n7yNn58f+vbtq/yuVqvx5s0bODg4QKVS/dB6f4awsDBky5YNQUFBsLGx0XU5PwyPM3UxlOMEDOdYeZypi6EcJ2A4x5rajlNE8P79ezg5Of1rO70Pv9/C3Nwc5ubmWtvs7Ox0U8wPZGNjkyqezP+Fx5m6GMpxAoZzrDzO1MVQjhMwnGNNTcf5bz2+Gnq/1Fn69OlhbGyMFy9eaG1/8eIFHB0ddVQVEREREaVEeh9+zczMUKpUKRw+fFjZplarcfjwYXh4eOiwMiIiIiJKaVLFsIe+ffuiTZs2KF26NMqUKYMZM2YgIiJCWf3B0Jibm2P48OEfDe1IbXicqYuhHCdgOMfK40xdDOU4AcM5VkM5zg+p5L/Wg9ATs2fPVi5yUbx4ccycORNubm66LouIiIiIUpBUE36JiIiIiP6L3o/5JSIiIiL6Ugy/RERERGQwGH6JiIiIyGAw/BIRERGRwWD41RNqtVr5/4SEBB1WQkSGLOm5KDY2VoeVEH29pM9fMlwMv3rCyCjxoZo8eTJWr17NF7Ce+tTj9v79ex1U8vNoFpQxhA9thnCMmnPR4MGDsW7dOsTExOi4IkpOqXUBqEePHuHevXswMjIyqPfP1Pp4fi+G3xQu6Yt0xYoVmDx5MooWLQqVSqXDqn6O1BgkjIyM8PjxY8yYMQMAsHHjRrRu3RqhoaG6LewHuX79OqpUqYJ3797B2Ng4VT6mwP8+wBgbG+PixYupMhAmPRcdPHgQs2fPRoECBVLt4vhJP7RFR0fruJof6/nz5wgICACAVPneEh0djcGDB8PT0xN37txJ9QH48ePH2L9/P4DU+XgmB4bfFE7Ty3Lo0CE8efIEI0eORIkSJVLlp7mnT59i7969WL16NaKiomBsbJzqTlDx8fGYN28eli1bhjZt2qBJkyaoW7cubG1tdV1asouNjUWXLl1w/PhxVKhQAW/evEmVATg4OBht27bFgQMHsHnzZpQpUwaXL1/WdVnJTnMuWrx4MQICAjBs2DCUKVNGx1X9GCIClUqFPXv2KFcPHTp0KHbu3Knr0pJddHQ0PD090bdvX9y7d0/X5fwQFhYW6NSpE9zc3NCoUSPcvn071Qbgp0+folSpUhgwYAA2b96s63JSLqEUTa1WS3BwsKhUKlGpVDJ8+HBdl/RDXLt2TfLnzy8FChQQKysrKVCggPzzzz8ikvg3SE0iIyOldu3aolKppEmTJsr2+Ph4HVb1Y4wbN06qVKki7u7ukjVrVuUxTU3Heu/ePfH09JTixYuLubm5rFy5UkREEhISdFxZ8nv9+rUULFhQVCqV9OzZU0RS3+tTY/v27ZImTRoZMmSILFmyRCpUqCD58+eXK1eu6Lq0ZHfs2DHJnDmzNG/eXO7cuaPrcn6Y48ePS82aNaVgwYJy69YtEUl9r9P9+/eLSqUSNzc3qVevnqxfv17XJaVI7PlNgSRJr65KpUKWLFlw8eJF2Nra4vDhw8rXU6nFtWvX4OHhgfr162PXrl1YvXo17t69i27dugFIPV/baB5XMzMz2NnZoXr16ggODsb48eMBIFX2inp4eODSpUvo1KkTihcvjhIlSqSqHmARgYuLCzp06IAbN24gV65ccHBwAIBU0bMkH3zDlC5dOmzYsAHVq1fH9u3b8eTJE6hUKr0/zg/9888/mDJlCsaNG4cxY8agefPmuHPnDmrUqIHixYvrurxko1aroVarUalSJWzatAkHDhzA6NGjcffuXV2X9t2ePXuG8+fPIzw8XNlWsWJF+Pn5IXv27GjcuDFu3bqVKl6nSXl5eeGXX35BXFwcjIyMsGTJEmzatEnXZaU8us3e9KGkn0JjY2NF5H+9ZGfPnhULCwtp1qyZPHnyRCf1JbfHjx+LiYmJDBkyRNmWkJAg+fLlkypVquiwsuSl6R27ePGiPH78WNRqtbx9+1Z69Oghbm5uMm7cOK32r1690kWZ3+1TvSh9+/aVtm3bir+/v7i5uUmOHDnk9evXIqLfPcCaxzQ+Pl5OnjwpixYtkpo1a0q1atVkw4YNSjt97Vn68Fz0/v175feAgAApVaqU5MuXT+nN19fj/JT3799LqVKlJCAgQB48eCBZsmSRTp06KfsPHjwoDx480GGF3+fJkydy69YtiYmJ0dp+/PhxSZ8+vTRt2lSve4CfPHkiadKkEZVKJbly5RI/Pz9ZunSpREZGikjiN43169eX/PnzKz3A+nwu0oiOjhYRkW3btkn79u1l165dUqtWLalSpYps2rRJx9WlLOz5TUHUarUyrm7GjBlo27YtvLy8MGnSJAQGBsLd3R2HDh3Cli1b4Ofnh6CgIB1X/P0CAgKQMWNGXLt2Tdk2efJk3L9/H48ePULfvn3RsmVLXLhwAc+fP9dhpd9O/n/84NatW1GjRg3MmjULr1+/hp2dHYYMGQJXV1fs2LED48aNAwAMGzYMv/76q95Nmrp58yY8PT2xc+dO3LhxQ9nu7u6Ohw8fIn/+/FizZg0yZcqEkiVL4u3bt3o7rlvzmB44cAC9evVCoUKF0LFjR0yZMgXGxsZYsGCBMt7OyMgIu3fv1qvHM+m5aOLEiWjYsCGKFSuGQYMG4fjx48iTJw82bNgAKysrlC9fHv/88w+MjIz0ei6CpnYRQWhoKKKionD69Gl4eXnB19cX8+bNAwA8ePAAS5cu1dtv4IKDg+Hs7IzChQujRYsW6N69O/z9/fHq1StUrFgR+/fvx+HDhzFmzBjcunVL1+V+k9DQUOTJkwcFCxZEzpw5ERQUhAEDBsDV1RXe3t64f/8+ypcvj0KFCqFVq1a4f/8+jI2NdV32NwkODsaePXsAQJl8WrJkSRw/fhyvX7/G3LlzkSZNGsybN489wEnpNHrTJw0cOFDs7e1l+PDh0qBBAylbtqwULVpUbt++LSIip0+flrRp04qvr6+8ePFCx9V+m3v37im9nXv37hUXFxepXbu2TJgwQTJkyCBLliyRS5cuyerVq6V+/fri4uIi1tbWMnz4cL0cY7hnzx6xtLSUJUuWfNSr++LFC+nXr5/kzp1bChQoIPb29uLv76+jSr9NZGSkeHp6ikqlkmrVqknVqlWlX79+EhISIiIiXl5e0r17dxERuXnzplSoUEGsra3lzZs3uiz7u2zatEns7Ozk999/l3Pnzinbb926Jd7e3lKtWjWZMmWKDB8+XFQqlV5+WzN48GBxcHCQsWPHyh9//CGFCxfW6tkOCAgQd3d3sbOzk3fv3um42m+jOZ9ERUWJyP96AIcMGSIqlUrq1Kmj1X7w4MFSpEgRvXs8Ncd548YN8fDwEJVKJX5+flKuXDnJmzevZMqUSX777Tc5cOCA7Nq1S9KlSyc9e/aUq1ev6rjyLxcaGqo8jhcvXhRPT09p3ry57NixQ8LCwmTTpk3SqFEjcXNzkzRp0ki2bNlEpVJJxYoVJTY2Vu/eWx49eiQODg6iUqmkUaNGsmXLFnn8+LGIiKxbt04qVaokb9++lcuXL0vt2rXFx8dH1qxZo+OqUwaG3xTm+vXr4uLiIocOHVK2HT9+XGrXri3u7u7y9OlTERE5ceKEeHp66uVXjQkJCTJ+/HhxcnKSp0+fSkxMjOzcuVOKFSsmKpVKDh48+NFtLl++LAsWLJCbN2/qoOLvExMTI23atJH+/fuLiEh4eLjcvn1bBg8eLIsWLZJnz57J+/fv5cCBAzJr1iwJCAjQccVfLz4+Xvbv3y9FixaVwoULy5EjR6R06dLi5eUlLVu2lKlTp4q3t7e8fPlSRBIfTy8vL708VpHE+tOnTy8LFizQ2q4ZzvHgwQNp3ry5lCpVSgoUKCCXLl3SRZnf5e7du5I/f37Zv3+/su3KlSvSpEkT8fLykvv374tI4oeZjh076uXXxpqws3//fvnll1/E19dXGjRoIM+fP5dXr15Ju3btxMzMTGbOnClTp06Vbt26ibW1tV4FQg1NKIyNjZVr166Ju7u7lClTRiIiIiQoKEimTZsmv/zyi1hZWUmtWrXE1NRUmdj44fCIlOjZs2dSrVo1mTVrljK84ezZs+Lp6SleXl5y+PBhrbYnT56UoUOHSq1ateTatWu6KvubxcfHy9WrV6Vw4cLi5uYmxYsXl/bt20uuXLlkzZo18tdff0mdOnXk6NGjIiJy6dIlqVixotSrV0/CwsJ0W3wKwPCbwpw6dUqsrKy0Tq5qtVp2794tRYoUkWPHjn10G30MwOfOnRNra2tZsWKFiCT2HO7YsUMKFy4s3t7eSjvNCVufxcbGSqVKlaRx48YSEhIinTp1Ek9PT3FxcVF6W1KD6OhoOXLkiGTMmFE6deok4eHhcvLkSWnWrJlYWVmJSqWS69evK+314Q31c1avXi3ly5cXEZE3b97I2rVrpUaNGpIlSxYZP368iIi8fftWCVH66OHDh5I5c2bZvXu3iPwvKF67dk3s7e1l7dq1H91GHwPwtm3blFUdli1bJqVKlZIsWbJIcHCwBAUFyfDhw6VAgQJSpkwZ+eWXX+TGjRu6LvmrPX/+XDJnzqy8f8TFxcn169elQIECUrJkSSUMxcXFyYsXL2TTpk3Sq1cvKVGihDImNqWLjo4Wb29v8fDwkEWLFikB+Ny5c+Lp6Sk1atSQ7du3f3Q7fXz/vHDhguTNm1fi4uJk06ZNUr9+fWnQoIHs3LlTVq5cKRUrVpS6deuKSqWSypUrK8d47do1vfvG4kdh+NWhpC86zRvLw4cPpWjRorJ06VKJi4tT9sfGxoqTk5NMnTr1p9f5o3Tv3l0KFSokz549E5HEMLRr1y7Jly+fVK9eXWmX9O+gDz711dmuXbvEzs5OrKyspEGDBkpwGD9+vLi5uellyH/69Kns27dPduzYoXzlHRsbK0ePHhUHBwdp3Lix0vbYsWNy5swZEdHfpbGS1n348GFRqVQyZMgQKVeunNSuXVu6du0qY8eOFZVKJZcvX9ZhpV/vU+eiv//+W7JmzSp//vmniCS+DjX7ypcvL35+fj+/0GT29u1bqVChgkyaNElERIKDgyVnzpzSsWNHrXaa4WX6+DoVSXyt1qlTR6ysrOT06dMikvhB5fr161KkSBEpUqTIJ3sDw8PDf3ap30QzOTw6OloaN24srq6unw3Ae/bs0WWp3+3q1atibW0t3bp1U7Zt2LBBvLy8pGbNmvL48WN59+6dHD16VKpUqaIsvUjaGH51JOmbzezZs2XFihUSGRkparVa6tWrJ8WLF5fjx48rbd6+fSulS5fW+/E6SY979+7dkjt3btm7d6+yLTY2Vnbt2iWFCxcWV1dXXZT4XTTh4NSpUzJ+/Hjp27evcrJ9+vSpnDx5Uqtdr169pHHjxnr3pnrt2jVxcXGR/PnzS/bs2aV69epKAFar1XL06FHJkCGD1KxZU8eVfj/NY6WZSa15Dk+dOlWKFSsmPXv2lEuXLolarRa1Wi2urq5K0NcHSV+T06dPlwEDBigfOCdMmCCmpqayY8cOpU14eLgUK1ZMZs2a9dNr/V6ax0gkMfyFh4dLzpw55enTp/LixQvJkiWLdO7cWWm/Zs0arW8o9PWDm4hIUFCQtGzZUszNzbUC8I0bN6Ro0aJSrFgxJQBrwmRKP95PBfaoqChp2LChlC5d+qMAXK1aNSlfvrzWUB59cvv2bbGyspLBgweLiHbH0ObNm6VKlSpSs2ZNZZiVPvZq/ywMvzo2YMAAcXR0lBkzZiiTg2JjY8XDw0MKFSokPXr0kDlz5kjVqlWlSJEietcLKpL4ldvnFob39PQUT09PrW2xsbGyefNmcXV1VQbv65PNmzeLg4OD1K5dW9q3by8qlUoGDRqkhCeRxPDo5+cntra2ejfe7OrVq2JpaSmDBg2Shw8fyoYNGyRv3rxy/vx5pU3SANygQQMdVvt9NG/+e/fulZYtW0rVqlWlT58+yvCND998/fz8JHfu3PL8+fOfXuv36t+/v2TNmlWmTZumLOMVFxcnvXr1EpVKJZ06dZK+fftKtWrVpHDhwnpzLvpUr/b27dtl2LBhEhMTI15eXjJx4kTJnj27dO3aVQl+z58/l7p168rWrVt1UfZ3i4iIUIKfxqNHj6R58+Zibm4up06dEpH/BeCSJUtK9uzZtZa0S8lu374ttra20qRJE/Hz85PAwEBlTkx0dLS0bNlSSpQoIQsXLpSIiAgRSeyUqFWrll5+9X/t2jVxcHAQBwcHrXPthwG4WrVqUqtWLblw4YIuytQbDL86NGfOHMmQIYNW+Ek643jo0KFSuXJlcXd3l+bNm3+07q8+CA0Nldy5c0vevHmlZcuWcuvWLa3AsG/fPsmVK5fS+6t5o4qNjdWbr9ySunv3ruTIkUOZCBUeHi6mpqYyaNAgpc3Vq1eldevWUrhwYb2bOHPr1i2xsbHROh4RkZIlS8rkyZNl4MCBcurUKeV5fOzYMTE2NpYWLVrootxksX37djE3N5e+fftKq1atxNvbW6ytrZWJJCKJE6batWsn6dOn17shDyIiy5cvl4wZM2q9YSYkJCiP45o1a6ROnTri7e0tnTp10ptzkeZ8cv36dWXs8pUrV8TR0VGWLVsmkZGRyiS2GjVqaN120KBBUqRIEQkKCvrpdX+v+/fvS5kyZaRmzZqyfft2JeiKJH6L2KxZMzEzM1O+iYqPj5crV65IuXLlJDAwUFdlf5WZM2eKSqUSR0dHKVu2rDg6OkrhwoWlX79+cujQIQkNDZX69euLj4+PLF68WPkgoG/fsokkPmfTpEkjnTt3FldXV/Hy8pIjR44o+5MG4C1btoiPj49UqFAhVV6NMLkw/OqIWq2WXr16Sd++fUUkccmg5cuXS8mSJaVevXqyZcsWEUk8eScNi/rS2yKSOH5527ZtMm/ePFm4cKG4uLhI7ty5xcfHR06ePCnv37+XqKgo5atjjZT+Vdu/OXfunFSsWFFEEsdMfvg1qqbH4cKFCxIcHKyTGr+VWq2Whg0bioWFhRw+fFh5nMaMGSOmpqZSpUoVKVKkiJiamsrChQtF5H8XgLh3754uS/9moaGhUrFiRRk1apSy7fHjx9K5c2el1z4yMlIWLlwoTZo00bvVSDTDAAYMGCBt2rQRkcTVG+bMmSOFCxeWPHnyKGMGPwwNKf1cpAm+V69eFRMTE1m0aJHcu3dPJk+eLH369FHahYSESMWKFcXNzU25GELHjh3F1tZW7z6ciiSuOKLprTcxMZEiRYpI1qxZpWrVqjJo0CC5f/++XLp0SXr16iXm5uZy8eJFEUl8rerbJNQJEyaIkZGRbNq0SY4dOyZz585VLqVeunRpqVmzplhaWoqzs7OsXr1aRPTv/SUwMFBMTU2V1YL+/vtvKVq0qHh5eWl9AE/6ely3bp3Ur19fL3u4fxaG35/kU2NvWrRoIVmzZpWZM2eKh4eH1KxZU3r06CHVq1eXKlWqfPT1kz69aK9fvy558uSRunXrKkvMxMfHy+zZs6VOnTpiYmIiPj4+sm7dOlmxYoXevtEkXSrp3LlzcubMGXF2dhZ/f39xdnaWzp07K71jx44dk5o1a+pd6E3qzZs34unpKeXKlZOzZ8/K2LFjxcHBQfbs2aN8tdi8eXPJmDGjsuyXPnv58qVkyZJFli5dqmxTq9Xy8OFDqVq1qowYMUJERN69e6c331R86iqS06dPFyMjI/Hz85OiRYtKgwYNZOLEidKhQwdJly7dR49lSj8XJe3xtbS0lMGDB4tarRYXFxdRqVRSv359rfbBwcHSo0cPKV26tJQsWVIaNmyol6s63LlzR+rXry8nTpyQzp07S506dWTQoEFy48YN6d27t7i6uoqTk5MUKlRImjRpInZ2dqJSqfRu6FXSbxz69esnlpaWyiTiqKgoef36tUyaNEkGDBggtra2kilTJvn77791Ve43S0hIkMOHD8vy5ctF5H/H/SUBWF+Gr+gKw+9PkPTNZs6cObJq1SoRSVzdoFatWlKsWDGZOHGi8hXFtm3bxMPDQ28vAHDnzh1Jly6dDBo0SBmD9aFNmzZJ586dJU2aNJIzZ05RqVQydepUvRygf/LkSUmbNq2sXLlSXr16JbVq1ZI0adJIs2bNROR/QWHQoEFSuXJlvVv6KigoSFavXi1z5syRqKgo+eeff8TDw0OyZMkiNjY2ypAVzXHOnDlT8ufPr3fHmVTScFezZk3p0KHDR28mtWvXloYNG/7s0r5L0tfX3LlzZcSIERIZGSkvX76UESNGSIkSJWTmzJnKpW2vXr0q5cqV++zrOCXSHOOdO3fEwcFBmjRpouy7ceOGlCpVSvLkyfPRpKf4+HiJi4uTyMhIvesB1Vi6dKm4ubmJSOLxt2/fXtzc3GTdunVKm0OHDsmSJUukfPny4uzsLCqVSu7evaurkr/YnTt3ZPDgwfLo0aOP3if69esnpqamyntrUoGBgcr64vokMDBQJkyY8NFjownAgYGBnwzAKX0oUkrB8PsTDRgwQLJkySJjx47VmhCTNOTGxcWJj4+PNG7cOMX3rnxKVFSUNG7cWLmal0ZsbKw8efJE63rxERER8uDBA+nWrZuULVtWL78af/Tokfj5+cnYsWOVbQsWLJCCBQtKmzZt5ObNm3LhwgXp37+/2NnZaa1zqw9u3rwpxYoVk5YtW8qAAQOUN513796Jj4+PuLi4yIEDB7ROuD179pSqVavqXc+D5vWWkJCgdTyTJk2SwoULa02cEUn85qZHjx4SHx+vd6/Vfv36iZOTk8yZM0drUmnSx0xzLvL19dWb49M8P69cuSKWlpZiZWUlLi4ucuzYMWXYxu3bt6VgwYJSs2ZNrbGw+vjB+0Pjxo2TUqVKafUQagLwh6tzREZGyrt375SlJlOy2NhYcXV1FZVKJXnz5pV+/frJX3/9pdWmb9++YmpqqvcrIokkfmORO3du8fX11frgovFhAK5Ro4bermChKwy/P8nMmTMlffr0Wl/tf7iO75IlS8TX11eKFCmiN0vNfCguLk4qVKigdaLdt2+f9O7dW2xsbMTZ2VkqV66sdVyxsbFaoUJf3LlzRzw8PCRHjhwyd+5crX1TpkwRT09PMTIykmLFiknJkiX1bvLBzZs3JV26dDJ06FAJDQ1Vtm/ZskVOnTolERERUqlSJXF3d5ddu3aJiMjIkSPFyspK774y1jwf9+3bJy1atBBPT0/p06ePcknx7t27S+HChaVp06YydepU6dSpk1hbW+vNBQCSWrx4sWTKlElrxriIKBOCIiMjZd26dVK5cmUpXry4ci7Sl3B47do1MTY2ljFjxoiISLly5SRnzpxy7NgxpUf3xo0bUqBAAalVq5ay7Je+SjoWe9SoUVKtWjUR+d/jpQnAHh4eMmfOHKVtSh+z/aFJkybJtGnT5MCBAzJ8+HBJly6dtGjRQubMmaO8focPH65cRl5f3b17V9KnTy8DBw7810uGax6/wMBAyZYtmzRo0EAv30d1heH3J4iLi5POnTvL8OHDRUTk3r17snr1anFzc5OmTZvK7t275enTp9KnTx9p3ry58qTWt5OTSOIEofz580unTp3k7t27Mm7cOMmXL580bNhQ/vzzT1myZInkyZNHmeinL2+on/Pbb79JunTppG7duh+dqMLCwsTf318eP34s//zzj44q/DavX7+WihUrSo8ePbS2T5gwQVQqlVSsWFHOnj0r4eHh4unpKZUqVZJGjRqJhYWFMoFG32zfvl3MzMykQ4cO0qdPH8mZM6eUL19eWSXgzz//lEaNGkmhQoX09pKoIiI9evSQ9u3bi0ji6h0LFiyQ0qVLS/78+WXXrl0SEhIiEydOlM6dO+vduSgiIkLq1asnf/zxh9b2zwXgokWLSoUKFcTf318X5X634OBgady4sRw4cEBEEsOfZphHfHy8cn69d++etG/fXsqWLStTpkzRWb3f4+jRo2JjY6OsSPLs2TMZMWKEWFpaipubmyxcuFDu3bsnY8eOlfTp02t9YNcXcXFx0rp1a2nXrp3W9sjISHn8+LHcvXtXWRJV014kcXK5vqzSkVIw/P4An+qt/eWXXyRbtmyycuVKKV++vHh7e0uvXr2kZMmS4u3trSy4nnQBdn11+PBhMTExkRw5coi1tbXMnz9fAgICRCSxl9fLy0uZWa5PPtcLP2DAAClYsKCMHDlS3r59+3OL+kFu374tuXPnliNHjihvoPPmzRNTU1OZM2eOVK9eXby8vOTMmTMSHh4uJUuWFEtLS73r3RZJfFxfv34t7u7uMmHCBGV7SEiI1K5d+6Pln8LCwrTWbE7JNM/ZpM/d8ePHS6ZMmWTQoEFSqlQpqV+/vgwdOlTatm0rGTJkkPDwcK0VZvTtXJR0GIem11rk0wH4ypUr4ubmprez4gMDA8XDw0N8fX3l0qVL4ufnJ61atfpk2/DwcKlbt67Url1bb+eT9OvXT1q0aKH0djdp0kTy588vrVu3looVK4qpqals3LhRbyfbxsTESMWKFbW+Od29e7d06tRJrKysJF26dOLl5aX1rY2+dyDpikpEBJRs1Go1jIyMAABxcXGIi4tDmjRp8OLFC7Rv3x63b99Gp06d4O3tjVKlSmHLli2YMWMGduzYATs7OwCAiEClUunwKL5fUFAQXr58iRw5ciB9+vTKdrVajaZNmyJfvnwYNWoUAOjFsWoek3PnzuH06dMwMzODs7MzatasCQD4/fffcezYMdSrVw89e/aEnZ2dXj+Oq1evRtu2bREXF6ccQ3BwMB4+fIgKFSrg5s2b6N27N968eYO9e/fC3NwcYWFhyJ49u44r/zaRkZFwc3NDz5490blzZ8TFxcHU1BQvX75EyZIl0a5dO4wePVrXZX6VpOeiN2/ewMLCAsbGxnj79i2mTZuG3bt3o1OnTvDy8kLBggVx9OhRjBgxAlu3boW9vT0A/ToXfa7W+Ph4mJiYAADKly+Pp0+fYuXKlShTpgzMzc0RGxsLMzOzn11usvn777/Ro0cPpE2bFo8fP4aIoHDhwjAyMoKRkRFiYmKgUqlgaWmJ58+fY968eciaNauuy/4mmzZtwrRp03Dq1Cl07twZu3btwuHDh1GoUCHcu3cPe/fuRfXq1VGoUCFdl/rNfHx88Pr1a6xduxYrV67E2rVr4ebmhjp16sDIyAjTp0+Hp6cnxowZAyMjI715faY4usvdqU/ST2DTpk2TmjVripubm3Tp0kW5NnzST9wJCQni7e0tzZo107uxvd8iJiZGhg4dKk5OTnL//n1dl/PFNI/Npk2bxNraWipUqCBFihQRExMTrfVCe/fuLW5ubv85VksfnDx5UszNzWXz5s0iot1zqHmeL1y4UFxdXfXuIgBhYWHy5MkTrbGSoaGhUrBgQenXr5+IJB6jptewTZs20rhxY53U+q0+7OmtVq2alChRQurUqaNMOk06uS0+Pl58fHykdu3aqfJclHTYhqenp9jY2ChjfVPD8d69e1d8fX3FyspKHBwcpGvXruLl5SXe3t7SsGFDqVOnjvj4+OjlGPUPVaxYUYyMjMTJyUkvl8f8HM3z8MyZM1KkSBFxcnKSDBkyyNKlS5UrLoqI1K1bV7y9vXVVZqrB8PsD+Pn5iaOjo0ydOlX27t0rKpVK6tSpo3wlHh4eLuvXrxcfHx+9ntz2NVatWiW9evWSTJkypfgrYH3qa6SAgADJnDmzMrHtzZs3sn79ekmTJo38/vvvSrvOnTuLp6enXi/zJZK4vFnGjBmlTp068ujRo0+2+f3336Vx48YfXeI3Jbt586ZUqFBB8ufPLwULFlTGSoqIrF69WoyMjD6aLFOnTp2Pxj7ri8GDB0v69Oll3bp1snv3bilatKjWGszh4eGydetWqVKlihQrVixVn4uSBmAfHx9lKFZqERAQIDVr1pTq1avr3aoyX0LznNy9e7e4uLgol53W5+dq0g/gSY/j/fv3cuXKFa25Imq1WuLi4pSVd/RtOFJKw/CbzK5fvy4FCxZULuxw7NgxSZMmjXLFK5HES0/27t1bmjRponcTSr7F3bt3xdPTU+rXr6/Mnk+pki6Ov2/fPmW7v7+/uLi4fNTLuWbNGrG0tFQebxFRevn13aZNm8TMzExatWql1WMUGhoq/fv3l3Tp0unVFc2uXr0q1tbW0r17d9m7d69UrVpV8ufPr7zpREREyNChQ0WlUkn37t1lwoQJ0qNHD7GystLLHrNHjx6Jq6ur8tzcsWOH2NnZaa1M8vjxY/njjz+kY8eOqeZc9G9hSN+P7b/cu3dPvL29xdvbW06cOKG1T59DYlIhISGSJ08eGTp0qK5L+S6ayYpJL1P8b+N34+LilG9O9WFd5pSO4fc7ffhkvXjxohQoUEBEEi9WYWVlJfPnzxeRxLVRt2/fLiKJs+lTw+S2L/XixYsUPxRA81heu3ZNVCqV1iVtr1+/LsbGxkqQ0Dx2T58+lVy5cimXzkxN4uPjZf78+WJiYiL58+eX9u3bS5cuXaRWrVri6OiY4nvwk7p+/bqkSZNGWXFFJHGpuooVK8r58+fl+vXryvNz3bp14urqKh4eHuLt7a03qzokPRdFRUVJYGCg2NvbS3h4uOzevVusrKxk3rx5IpIY9GfPni3h4eESGhqql+ciTc3379+XO3fuaE1KNORJQPfv35datWqJu7u73q5i8V9WrVoladOmlXPnzum6lG+mmaz44XrTn7J48WLp0qWLZMiQQa/OuykZw28yGTZsmCxevFiePXsmxYsXlz/++ENsbGyU4CuS2HtYrlw5rXFKqeXTuL77cHH8IUOGaO2PjY2VWrVqSYMGDeTSpUvK9piYGCldurQsW7bsZ5b7U/n7+0uDBg2kWLFiUr58eRk0aJBefWUcGhoqrq6uki1bNq3t/fv3FwsLC3F2dpaMGTNK2bJllUugRkREiFqt1st1M0eOHCmTJk2Sp0+fSu3atWXo0KFibW0tCxYsUNpcv35d6tatKydPnlS26eO5aOPGjZI1a1ZxdHQUd3d3+fPPP5V9hhyA79y5I40aNdJa+SI1CQ4OFk9PT72bb/Ch+/fvi4+Pj3h7e2sF4KSvxTt37kidOnWkc+fOWheJou/D8PuNkp5YN23aJDly5JCTJ0/K27dvpXXr1pI2bVrp3bu30iY6Olpq1aol9evXN+iTckp29+5dMTc317pam4jIzp075f3797Jt2zapWLGi1K5dW3bu3Ck3b96UAQMGSIYMGeThw4e6Kfon0acewQ+FhobK3LlzJUuWLNKlSxcRSbwIia2traxbt06ePHkiCxYskJw5c0qvXr0kOjpaOV59CIRJzyebN28WJycnuXz5ssTHx0vTpk1FpVJJ//79lTbh4eHi6+srNWrU0MtzkeYxef78ueTLl0+WLFkiO3fulP79+0uOHDlk9OjRSlt9PL7koq+XaP5SScfL6rPPBWCRxOdvz549pXLlylpXhaXvx6XOvtORI0ewceNG5M2bF3379gUAnD59GgMHDgQAVK9eHba2tti1axdevHiBy5cvw9TUVGsZItK96OhotGvXDgcPHsTGjRtRuXJlAMDYsWMxf/58HDx4EPnz58fWrVuxbt06bNmyBS4uLoiPj8dff/2FEiVK6PgIfixJsoyU6NHyVxqhoaHYsmULBg4cCCcnJzx79gwbN25EpUqVlDYVK1aEnZ0dduzYocNKv92GDRtw//59mJqaKuef+Ph4VKhQAaGhoahYsSIcHR1x7NgxvHnzBpcuXdLbc9HZs2exZcsWREREYObMmTAxMcHz58+xdOlSzJ8/H126dMHQoUMBQC+PjwxLQEAAevXqBRHBH3/8gXLlyiE2NhZ9+/bF/PnzcfHiRRQvXlzXZaYuOo3eekytVsv169clT548kjZtWq2xhCIiJ06ckAEDBkjOnDnF19dXOnXqlGomlKRWR44ckQYNGkjlypXl/PnzMnPmTLG3t5e9e/dqtYuNjVXGGb58+VJH1dK/CQoKktWrV8uQIUOU1SjCw8Nl2bJlkitXLqlevbrSVnPBiqZNm0rPnj0lLi5OL3p8NdRqtURFRYmNjY2oVCrp3Lmz1v7Y2FgZMGCA+Pr6Su3ateX333/X63NRRESE9OjRQ9KlSycVK1bU2vfs2TMZM2aMODs7i5+fn44qJPp6SXuAjx49KgMGDBBLS0uO8f1BGH6/wqfeEDdu3CgFCxaU0qVLf3JywYdjBvXxzcaQHD9+XOrWrSsuLi5ibm4uZ8+eFZHEx/5TV8uilOfGjRtSsmRJ6dSp00cB6M2bN7Js2TLJlCmTdOrUSdk+dOhQcXBw0JsxdUmfg5pw//btWylatKg4OzuLv7//R8/TpM9hEf0bypK09uvXr0uvXr3E3NxcayyzSOJwiMGDB0uhQoXk1atXfL2S3tBMVkyXLp2YmZlpzS+h5MXw+4WSnkDXrl0rgwcPVn7fsGGDlCxZUlq3bq31ZP3wzYUn4ZQr6WNz8uRJqVmzppQoUUIOHTr0yTaUMt26dUvs7Oxk6NChWmtkrlmzRu7duyciiauuaAJwr169ZMKECWJhYaE3bzRJx7HOnTtXRo4cqUz8efPmjeTMmVPc3d211nrV5+du0qXokl6u+MGDB9KtWzfJly+fLF68WOs2ISEhWo8/kb64e/eu1KlTR6+WkdRHDL9fIOmbzblz56RGjRri7OysNbN4zZo1Urp0aWnTpg2/ptBTSQPCiRMnpG7dulK5cmXZs2fPJ9tQyvLmzRupUKGCVo+uSOIVzlQqlVbP7rt372TFihWSNm1aUalUcvHiRV2U/NWSnosCAwOlcuXKki1bNpk8ebI8e/ZMRBL/Djly5PgoAOsjzett165dUr16dXF3d5eqVasqE4MePXok3bt3l3z58snSpUt1WSpRskn6IY9+DM4C+AKayRL9+/fHsGHDoFarERUVhRkzZmDixIkAgObNm6NPnz64e/cuhg8fjvv37+uyZPoGKpUK8v/zPytUqIC+ffvCxsYG06dPx/bt25U2lDI9efIEb968QbNmzZRtmzdvxoQJE7By5UqUK1cOlSpVwp07d2Bra4vatWtj0aJFCAgIQKlSpXRY+ZfTnIv69OmDFi1awMHBAQ4ODhg6dChWrVqFZ8+eIV26dLhy5QpevXqFevXqITAwUMdVfzuVSoXdu3ejfv36KFWqFOrXrw8TExM0bNgQS5YsQY4cOdCrVy/4+Phg4MCBWL16ta5LJvpupqamui4h9dN1+tYXa9euFTs7Ozl//rxER0fL8+fPpU2bNlK6dGmZNGmS0m7x4sXSvn17g15iR998amykxsmTJ6Vy5cpSp04dCQ8P/9ml0RfQLOm0bt06sba21lrb9OTJk0rvZ0hIiNSqVUssLS2VZYP0sSd/y5YtYmdnJ1evXlUm6/Xt21fSp08vEydOVHqA//nnH2nYsKFeje39cAJpZGSkeHl5Sb9+/bS2//rrr5IxY0a5cOGCiCRemGbAgAHKOs1ERP/GRNfhW18EBgYiT548KFWqFIyMjODo6IhRo0ahe/fumDFjBkxNTdG7d2906NABbdu2hZGREZfYSYHk/5fpevjwId68eYOiRYt+9Clb0wOsUqlQvnx5jB07FtmyZUPatGl1VDV9TkBAAFatWoVRo0bBysoK4eHhePLkCbJnzw4AKF++vNI2U6ZMaNasGYKDg5GQkABAP3vy379/j8yZMyNr1qwwMUk8hU+dOhWxsbEYMWIEjIyM0LRpU2TNmhWbNm0CACQkJMDY2FiXZf+n4cOHIzIyEmPHjoWZmRmAxJ7ut2/fwtHREQAQExMDc3NzzJ07F3fv3sXo0aOxfft2FC1aFAUKFGCPGRF9ESaz/6B5k8yQIQNiY2Px9OlTAIlrR2bPnh1+fn4IDw/H+vXr8eeffwIAjI2NISIMvimQSqXCli1b4OHhgdq1a6No0aLYtm0bIiIiPmon/z8EwsPDA1mzZtVFufQfVq1apXzVXa5cOZQsWRK9evXCkydPAACxsbEAEl+vAHDhwgXkypULtra2uin4K2meg5I4PwNA4tq9L1++hEqlgrGxMSIjIwEAv//+O0xMTLBgwQLs3r0bCQkJyvkrpQdfAChUqBDatGkDMzMz5ZjMzc1hb2+PXbt2Kb/HxMQAAEqXLq08vgC/KiaiL8d09gHNm6SGJsCWL18eDx48wJ9//onIyEhlu4igatWqyJcvH7Zt24YXL14A0M8epdRORPDs2TOMHTsWQ4cOxb59+1CwYEEMHDgQ69evR3h4uFZ7PoYplyYIli1bFhYWFoiJiUG6dOnQqlUrvHz5Eh06dEBwcLDSg/j27Vv4+flhxYoVSi9xSqdWq7Weg5pzU/v27ZElSxbUqlULAJAmTRoAQFRUFFq1aoXKlStj8ODBCAkJ0YvQq/HLL7+gcOHCOHLkCAYMGIBbt24BAPz8/BAcHIzOnTsDSAzAAPDy5UvY2NggLi5OeT4QEX0JDntIIukwhUWLFuHu3bsICAhAly5dULNmTfz111+oU6cOoqOjUbt2beTIkQNjx45F0aJF0aZNGxQqVAgXLlxQ3pQoZdAMYRARpEuXDhUqVEC7du2QNm1abN68GW3btsWkSZMAAE2aNNGLYGToNKHQ2dkZjx49wokTJ1C9enX89ttvCA0NxaJFi1C4cGG0b98eL1++RFhYGC5duoTDhw+jUKFCOq7+vyU9F82bNw8nT55EVFQUChcujNGjR2PevHlo164dSpYsicmTJwMApkyZAgcHB6xcuRIbN27E1q1b0aNHD10exjcJDg7GypUrYWJigt9++w3ly5fHgAEDMHHiRJQrVw4VK1ZEcHAwtm7dCn9/f/b4EtFXY/hNQvNmM2DAAKxZswYNGzZEzpw5Ubt2bQwdOhSjRo3Cjh070KdPH2zduhXGxsbIkCGDMlatQIECSJ8+vY6Pgj6kmTG+fPlyPHnyBBYWFoiPj1f2L1++HG3atMH06dMRHR2Ntm3bcnxvCvXo0SMcOXIElStXhqWlJZydnZE3b15ERUUpbYYNGwZXV1ds27YNJ06cgKWlJapUqYJp06YhT548Oqz+y2nORYMGDcLKlSvRsWNHODk5oVu3bvjnn38wZcoUbNq0CX379kWrVq1gamqKbNmyYdu2bYiKikLmzJmVcc8pnebDaVBQELJmzYrWrVvD1NQU/fv3R3x8PAYNGoQOHTqgSJEimDx5Mq5cuQI7Ozv4+/ujcOHCui6fiPSRLmbZpWT79++X7NmzK2v1Xrp0SVQqlaxdu1Zp8/z5c7l165acO3dOmS0+cOBAyZ07tzx9+lQnddPnnT17VoyNjaVTp07i4eEhdnZ2MnjwYHnz5o1Wu/r164urq6u8e/dOR5XSv4mJiZFatWqJk5OTZM2aVdKnTy/NmzcXlUol9erVk4CAAHnw4IHWbTTrZerjqg7nz5+XvHnzyvHjx0VEZN++fWJpaSnz58/Xanfr1i159OiRcoxDhgyR3Llza616kVJpat6xY4dUqFBBFi5cqOxbs2aNZMmSRbp37y6BgYFat+OVMonoezD8fmDTpk3i6+srIonLm1lZWcncuXNFJHFh/Fu3bmm1v3LlijRp0kQyZMggV65c+dnl0n+4e/eujBs3TqZOnaps69Onj7i6usro0aM/Crr88JKyaS7le/nyZVm7dq1MmjRJChYsKCqVSrJmzSqOjo5StWpVadWqlcyaNUu5eIU+hV/N0mS7du2SEiVKiIjI1q1bxcrKSgm+7969k+3bt2vd7tq1a9KxY0ext7dP8eeipI/Hli1bxMLCQmbMmPHR5aVXrlwpTk5O8ttvv8mNGzd+dplElEoZdPgNDQ2VV69eaW1bvHixFCtWTLZt2yY2NjZK8BVJXEe0ZcuWymUz1Wq1PHr0SAYOHPhRKCbdCwwMlEqVKomjo6PMnj1ba1+fPn2kVKlSMnbs2I96gCnl+lSInTRpkrRs2VKuXLkiBw4ckMGDB4uvr6+4u7vL/fv3dVDl13v58qUEBwdrHd/Vq1elQoUKMnXqVLG2ttbq8T1+/LjUrl1buWSziMidO3dk9uzZcvfu3Z9a+9e4ceOG1rrDQUFBUqxYMeU8GxcXJ5GRkbJr1y7lPLtmzRqxsLCQgQMH8spXRJQsDDb8rl+/Xry8vCR79uzSpk0bOXPmjIgkDmmoWLGiqFQqmTJlitI+MjJSateuLa1bt/7oDZgXtEiZ4uLiZOTIkZIzZ06pXr36Rxep6Nevn+TKlUsmT56sVz2DpG3Dhg1iZ2cnwcHBWtv15aIka9eulTJlyki2bNmkWLFicunSJRH53+WLzczM5I8//lDaR0VFSc2aNaVp06YfPW9T8gUtZs2aJZ6enhIaGqps+/vvvyVnzpxy/PhxSUhIkLFjx0rZsmXFxsZGnJycJCAgQEQSH2N9+SBDRCmfSsTw1ohZsGAB+vfvj969eyNNmjQYNWoUvLy8sH79epiammLJkiVYsGABsmfPjsGDByM4OBgLFy7E06dPcfnyZZiYmPACFimQ/P/EmaTi4+Mxffp0rFu3DmXLlsW4ceNgY2Oj7B8yZAg6duwIZ2fnn10uJQMRwb179+Dl5YWjR48id+7cygUdPvV8SGkWLFiAPn36YMyYMbC2tsasWbOgVqtx5swZ2NjYYM+ePfj111/h5uaGypUrw87ODkuWLMHLly/17lwUHh6OkJAQ5MmTBy9fvoS9vT3i4uLQtGlT3L17F+/fv0eZMmXg7u6OTp06wcPDAzVr1sT06dN1XToRpTY6jd46sHjxYjE3N5cdO3Yo2/r06SMqlUoZJxcdHS2LFy+WChUqiKWlpbi6ukqDBg2Ur9xScu+KodL0gJ0+fVrGjh0rI0eOlC1btohI4uM1YcIEcXNzk27dumn1PFHqkC9fPlm0aJGuy/gqy5YtE2NjY9m3b5+ybeTIkWJkZKS1bePGjdK0aVOxt7cXT09PadasmXIu0peJX0nPmf7+/lK6dGnZvHmziIjcvHlT5syZIzNnzpRXr14pr+W6devKjBkzdFIvEaVuBtPzKyL4559/kClTJpQvXx67d++GtbU1AKBatWo4cuQIdu3aBZVKBU9PT1haWgIAnjx5AhsbG9ja2kKlUiE+Pl65pCilLJo1e11dXREVFYVz586hS5cumDp1KszNzTFx4kTs3bsXuXLlwuzZs5XHn/SX/H/vbokSJVCjRg2MHTtW1yV9kXfv3sHHxwePHj1CSEiIst3LywuHDh3ClClTYGNjg9q1ayNTpkwAgNevX8PGxkZZ11Zfz0WhoaGoWrUqzMzMMGTIEPj4+GhdjCM0NBRTp07F/PnzcerUKbi4uOiwWiJKjVL+d2XJRKVSIUOGDNixYwfOnz+PP/74AxEREWjcuDECAwPRunVr+Pv7o1mzZqhevTrq1q2LJUuWwMLCAnZ2dlCpVFCr1Xr5ZmMIHj58iL59+2Ly5Mk4cuQITp8+jT179mDlypXo378/jI2N0b9/f3h6euL58+cfXc6Y9JNmWEPnzp3RrFkzHVfz5WxsbDB79mw4ODigXLlyAIBmzZohMDAQEydOxJs3b7BixQq4urqiSpUqGDJkCKKjo5XgKyJ6cy7S9K9cvHgRFy5cgK2tLY4ePQpzc3OMGjUKu3btUi7DvGvXLvTq1QvLli3D/v37GXyJ6MfQZbfzz6aZmLZz504xMjISR0dHKVq0qAQFBSltHj16JNu2bZOyZctKvXr1OJktBVq4cKGcOXNGa7LPjRs3JHfu3HL79m0R+d9jvWvXLjEyMpI9e/aISOLXr5pZ5JR66OuExcuXL0vevHnFzMxMChcu/NHqM5s2bZIBAwZIxYoV9fJcpHlcNm/eLE5OTtK+fXtlOcGwsDDx9PQUNzc3Zdm2CxcuyLRp05SJbkREP4LBDHvQ0EwOOXToELy9vdGsWTPMnDkT9vb2H02QkSSXxU3pE2cMhYggW7ZssLa2xqpVq1CqVCmoVCrcunULRYoUwb59++Dl5YWEhAQYGRkhMjIS7u7u6Nq1K7p3767r8ok+cvnyZfTq1Qvv37/H1atXoVKpEBMTA3Nz84/a6svktqSOHj2KWrVqYc6cOahduzYcHByU43j//j3q1KmD2NhY9OvXD/Xq1YNardYaBkFElNz06yyaDIyMjKBWq1GtWjXs3LkT69atwx9//IEXL14oAVfzFZxmqAODb8qg+RDy4MEDWFhYoF27drhw4QLi4+NRqFAhNGvWDCNHjsT58+dhbGwMlUoFS0tLpEmTRu8CAxmOEiVKYNasWYiOjkbZsmURHR0Nc3Nz5TykISJ6+Tw+cOAAmjRpgrZt28LOzg5A4rGICKytrbFjxw5ERERgzpw5iIiIYPAloh9O/86kX0itViv/Hx4errVPE4Br1KiBHTt2YMGCBRg7diyeP38OAFonX318s0mtND1iZmZmOHnyJKKiojBo0CBcunQJANCxY0ekS5cOPXr0wPbt23H27FkMHjwYgYGB8Pb21nH1RJ+mmbC3fv16vHv3DlWrVkV0dPRHIVBfP4Rfu3YNr169AgBlCTrNh9PHjx/D2toaJ0+exJIlS2BlZaXjaonIEKTaZKcJrX369MHkyZM/G4Br1qyJHTt2YPbs2Vi3bp0uSqUvJCIwNzfHhg0b0L9/f2TLlg3Hjh3Dr7/+iitXrqBy5cro378/ChUqhEaNGqF9+/bYuXMnDh48iFy5cum6fDJAp0+fVv5/7NixmDt37mfblihRAuvWrcPt27fRq1evn1HeD6dWq1G6dGmEhYUhICAAwP++UXv27BkGDRqEK1euwNraGjly5NBxtURkKFLdmN+k43OvXr2KWrVqYePGjfDw8Phke83YszNnzqBMmTJ6M4PaUJ08eRLe3t6YNWsWChcujLi4OHTs2BHGxsZYvXo1SpQoAQB48OABTExMkDZtWjg4OOi4ajJEz58/R968eeHj44Ps2bNj0aJFOH/+PAoUKPCvtwsICECuXLn07ut/zbn3+fPniI2NhaWlJTJmzIirV6+iQoUKaNWqFXr27IkCBQogLi4O48aNw+rVq3H48GFkz55d1+UTkQFJdeFXY8qUKQgLC0NsbCwmTJjwr22TBmZ9XTvTUEybNg0bN27EiRMnlGWfwsLC4OrqCisrK8ydOxelSpXiY0gpwuXLl1G2bFmYmpri3LlzKFiwoHIFuv/ype1SAs05dNu2bRgyZAhUKhXevn2LVq1awc/PDxcvXkSrVq2QO3duiAjs7e1x8uRJHDlyRPnASkT0s6TKYQ9RUVG4cOECxowZg7t37/5n+6Rj6RiaUibNZ7TQ0FC8e/dOCb5RUVGwsbHBzJkzceXKFXTu3BnXr1/XZalk4JLON4iPj4eRkRFUKhVGjx4NIHHca9I2wP+e30npS/AFEs+hhw8fRqtWrdClSxdcvHgRv/76KyZNmoR9+/ahatWq2LlzJ5o3b45cuXLB3d0d/v7+DL5EpBOpouf3U0uRPXv2DBMmTMDChQuxY8cOeHl5ccmyVODWrVvw8PCAn58f/Pz8lO1Hjx7FjBkz8Pz5c6xfv55jfEknki5Fdvv2bWTJkgVGRka4efMm6tSpg0qVKmHTpk06rjJ5ac6r3bt3h1qtxrx58xAcHIzKlSujatWqmD9/vq5LJCLSovc9v0mXIlOr1YiJiQEAODk5YejQoWjSpAnq16+PU6dOKWv2UsqneZyuXr2KNWvW4NKlS3j9+jUKFSqEgQMHYvHixcqlbMPDw3Ho0CE4OzvjzJkzDL6kE0mD79ChQ9GtWzecOXMGFhYWKFOmDNavX49jx46hadOmym26deuG5cuX66jib6Pptf6w9/rVq1coX748oqKi4ObmhipVqmDevHkAgA0bNuDo0aM/vVYiok/R657fpG82s2fPxrFjxxAeHo5q1aqhX79+AIDXr1+jT58+2LJlC/bv349y5cqxB1hPbNmyBe3atUOGDBnw9u1bNG/eHH369EHGjBkxe/ZsjBs3Dg4ODrCyskJwcDDHD1KKMGTIECxZsgSLFi1C+fLlkS5dOmXf4cOH0aRJEzg5OcHKygovX77E3bt39WK4leZ8qzl/hoaGwtbWVtnfq1cvHDx4EBEREahXrx6mTp0KU1NTxMXFoXXr1nBxccEff/yhF8dKRKmbXodfDT8/P6xcuRItWrRApkyZ0L9/f/Tv3x/Dhg1D2rRp8fr1a/Tr1w8rVqzA1atXUbRoUV2XTJ+heWMNCgpC9+7dUbt2bbRo0QLLly/H6tWrkStXLowcORK5c+dGYGAgduzYAVtbW1SsWBF58uTRdflk4C5duoTGjRtjxYoVqFChAsLDwxESEoJLly4hT548KFWqFAIDAzF9+nTY2dlhxIgRMDExSfGT2zTB99GjR1i9ejX279+PoKAglCtXDjVq1ECLFi3w+PFjNGvWDEFBQbh37x7SpEmDhIQEDBs2DKtWrcLhw4eRN29eXR8KEZH+h99NmzZh0KBBWL16Ndzd3XHw4EHUqFEDIoLWrVtj9uzZSJMmDV69eoUFCxZg0KBB7HlI4S5cuICVK1fi6dOnWLhwIdKnTw8AWLlyJebPnw9nZ2cMHDiQH2Ioxbl69Sratm2LWbNmwcLCAqtWrcL+/fsRHx8PEcGiRYtQtWpVrduk9BVmNMH3xo0baNiwIUqXLg1ra2tkz54dS5YsQUxMDDp06IBRo0Zh8+bNGDFiBMLDw+Hq6orIyEicP38e+/fv57cyRJRipNwz7hdISEhAVFQUevfuDXd3d+zZswctWrTA/PnzkTFjRtSrVw8ODg4YPnw4MmTIgKFDhwJI+W82hu7gwYP466+/YGJignfv3inht3Xr1gCApUuXYujQoZgwYQIKFiyoy1LJgCUddqVhY2ODuLg49O/fH1euXEH79u0xYcIEuLi4oGXLlnj27NlH95OSz0WaY7x27RrKly+Pbt26wc/PT7lMcePGjTFmzBjMnz8fDg4O+O2331CkSBEsXboUr1+/RvHixTFjxgx+K0NEKYpe9fxqvhJPOmb39evXCAsLg5WVFXx8fNCkSRMMGDAAgYGBKFeuHF6+fIlRo0YpwZf0w5w5czBt2jR4e3tj4MCBWld/WrRoEbZs2YIlS5bAyclJh1WSoUoafG/evIno6GhkypQJ2bJlQ1BQEM6cOQMHBwdUqlQJpqamUKvVcHNzQ8+ePZUPcfri77//RpEiRdCvXz+MHj1aGaKh6UQIDAxEjx49EBQUhK1bt3JoAxGleCm3y+EDSd9sgoODYW5uDpVKhQwZMsDBwQG3bt1CREQEqlevDgCwsLBAw4YN0bJlS5QpU0aXpdO/0HyQiYyMhFqthpWVFQCge/fuCA8Px19//YU///wTvXv3Vq4C1alTJ/zyyy9ak22IfhYRUc5Ffn5+WLduHeLi4vD27Vt069YNnTt3RpMmTQAkrkP9+vVrtGvXDiKCFi1a6LL0r6ZWq7F06VJYW1sjQ4YMABLXH05ISICJiQlEBLlz58bgwYPh6emJmzdvaoVfTi4mopRIL8Jv0jeb0aNHY9euXYiIiEBCQgKmT58OHx8fWFpaIjAwENu2bUNkZCTGjh2L2NhYuLu7Q6VScahDCqR5Y9y9ezcWL16MmzdvokGDBqhUqRJq1KiBgQMHQq1WY+PGjTAxMUG3bt2QM2dOAGDwJZ3RhLmZM2di8eLFWLduHXLmzInjx49j2rRpCA0NRb9+/ZAvXz7MmDED+/btQ0JCAs6ePasEx5Q8uS0pIyMj9OjRA5GRkVi7di0iIyMxaNAg5UIdmr9FqVKl4ODggOfPn2vdnsGXiFIivUiDmhPoiBEjMHv2bKxYsQJ58+bFr7/+imbNmuHy5cvIlSsXFixYgK5du2L9+vVIly4dTp48qQyTYPBNeVQqFXbs2IFmzZqhb9++8PHxwaZNm3DixAm8e/cOzZs3h5+fH4yNjTFv3jyYmZkps+OJdElEcOLECbRq1QrVqlUDAOTJkwd2dnb47bffULRoUeTLlw+NGjVCunTp0KlTJ62hAvrEyckJgwYNwtixY7Ft2zaoVCoMHDgQRkZGSpC/cuUKnJyc4O7urutyiYj+k96chd++fYsTJ05g6dKlqFmzJrZv344rV65g3LhxcHZ2hoigffv2qFKlCiIiIlCgQAEYGRnp5ZuNobh37x6GDBmCadOmoUuXLoiKisIff/wBe3t7zJw5E8bGxsoYblNTU9SrV4+PJemcWq2GiOD9+/dISEgAAMTGxsLMzAwNGzaEv78/Zs2ahQ4dOiBv3rzKMADNUAF95OjoiCFDhmDs2LHYunUrAGDgwIFKD/bmzZuRKVMm5ZsZIqKUTG+u8BYWFobLly+jRIkSOHToEFq2bIlx48bh119/RWRkJMaMGYPg4GDkzJkThQoVgpGREdRqtd6+2aQmn5tTaWlpiZo1a6Jx48YIDg5G4cKF0bhxY6xduxYvX77ExIkTsWTJEgBAnz594Ozs/DPLJgLw8ZXMjIyMYGxsDFdXVyxfvhzBwcEwMzNTgrCTkxOyZcsGc3Nzrdvpy1CHz9EEYFdXV2zduhUTJ04EAIwZMwbLly/H1KlTYW9vr+MqiYj+W4pc7eFzkySaNm0KCwsLbNq0CTNmzEDHjh0BAA8fPkTXrl3RrVs31K1b92eXS/9CM1Hx9evXePHiBRISElCkSBEAiT1hb968QYYMGdClSxeEh4dj/vz5sLa2RvPmzXHy5EmULFkSK1euhI2NDccP0k+XdKLtjRs3EBMTAxsbG7i4uCAhIQFVq1bFo0ePsH//fjg5OcHU1BS1atVC+vTpsX79eh1X/2OEhIRg7NixuHbtGmJiYnD9+nWcPn0aJUuW1HVpRERfJMX1/CadRPHmzRv8888/yr68efNi06ZNaNiwoRJ8379/j+7duyMhIQG1atXSSc30aZrgcPPmTfj6+qJmzZqoXbs2OnfuDCCxJ0wzg/zevXvInDkzrK2tAQDW1tb4/fffsXDhQtja2jL40k/34aoOv/zyC6pUqYJGjRqhadOmMDY2xooVK5A/f36ULFkS5cqVQ5kyZfDixQusWrVKuY/URtMDnCdPHrx58wZnz55l8CUivZIie34BYNiwYdi9ezfevn2LFi1aYPTo0QCANm3a4MKFC8iWLRty5MiBW7duITw8HBcvXlTW0/xw4Xn6+ZIujl+uXDl07doVtWrVwqZNm7Bo0SLMmDEDv/76KxISEhATE4OuXbvi7du3qF27NgIDA7Fq1SpcuHABWbJk0fWhkIGbNm0axo4di02bNiFNmjS4d+8ehg0bBhcXFxw4cAAAsHbtWoSGhsLU1BTt2rXT28ltX+PVq1dQq9XIlCmTrkshIvoqKSb8Jl3+Z968eRgzZgwGDhyId+/eYeLEiahTpw6WL18Oc3NzLF68GP7+/oiPj0fevHkxcOBAmJiYpPo3G33z4eL4QOIQlfz586Nnz56YMmWK0vbAgQOYPn06AgIClMvC8nKopGtxcXFo06YN8uXLh+HDhwNIPFf5+/ujRYsWaNKkiTL2NSl9Ws6MiMjQ6Dwpasb3at4o/P39ERMTgz///BONGjUCAFSrVg3e3t5o06YNFi9ejI4dOyrDHjT0eSZ1apR0cXwHBwdl+/r16xEXF4eAgADMmDED9vb2+OWXX+Dl5YXKlSvjzZs3MDY2Vi5pTKQrmiUSHz9+rExmAxKH65QtWxZ169bFjRs3EBcXB1NTU63bMvgSEaVcOh0f8Msvv+DatWvK77du3ULZsmXRt29fhIWFAUh8AypbtiwOHDiAPXv24Ndff0VISMhH98U3m5RFszh+8+bNsX79esybNw+TJk3C5MmTMWTIELRu3RonTpzArFmzkCdPHlStWhX79u1DpkyZGHxJJ06dOoXFixdj3rx5ePXqFVQqFVQqFerVq4enT5/i6NGjSluVSoWcOXPi3bt3iI2N1WHVRET0tXQafs3MzFCwYEEAiSG3UKFC2Lx5M6ysrHD27FlER0crF6nw8PDAgQMHsGbNGixcuFCXZdMX0iyO7+rqij///BNDhgzBpk2bMHr0aDRs2BAbNmzAhQsXMGjQIOTIkQO5c+fWdclkoBYvXowmTZpg7ty5mDFjBpo0aYJ3794BAHx9fRETE4N58+Zhz549ABLXHd+zZw9y586NtGnT6rByIiL6WjoZ8/vheLg5c+agYMGCqFixIoyNjfHXX3+hZcuW+P333zF69GiYmpoqwyNu3ryJ/Pnzc4iDHnnx4gXGjRuHY8eOoXXr1vj9998B/O/CAAA4Xpt0ZuHChejevTvWrVuHatWq4ciRI/Dz88Phw4eRNWtWAMDFixfx+++/48WLF4iOjoaDgwPi4uJw6dIlrfMTERGlfDqd8KZ5w8iXLx+io6Oxdu1auLu7w9jYGOvXr0erVq3w+++/Y8yYMTAxMdF6g2FY0i+atUEvXLiA+vXrY+DAgQD4OJJurV69Gq1bt8bGjRvRsGFDAInLJ7q6uqJWrVoIDAxE69atUb9+fTx79gyBgYE4deoUsmbNimbNmnGiLRGRHkoR4RcAypcvj5CQECxfvhweHh5KAG7bti3atWuH2bNnc1yvntME4CtXrqBq1aoYOXKkrksiA5aQkABvb2/cvXsXy5YtQ/Xq1QEAdevWxaVLl1C5cmU8f/4cR48exfz589GpU6dP3gfPS0RE+kUn4TfpWrxJe03c3d3xzz//aAXgZcuWYfny5Th27Bi/VkwFQkJC4Ofnh+DgYKxfv15rJQiin+39+/eoX78+IiMjMWrUKMydOxeBgYHYtm0bsmfPDmNjYzRq1AgXLlzAzZs3lYuwEBGR/vpp4ffw4cM4e/Yshg4dCuDfA/Dr16+xfPlyZQiEBsfVpQ4vXrwAAC6OTzql6bV9//49ateujStXrsDe3h6HDh1C7ty5lXPUsGHDcOzYMRw4cAAWFha6LpuIiL7TT1ntISYmBhs2bMCGDRswefLkxH/YyAhqtRoAYGJigri4OACJ6/xmypQJ1atXx61bt7Tuh8E3dciUKRODL+mE5pwD/G95RGtra+zatQtly5aFra0t7t27h9jYWBgZGSEhIQHnz59Hnjx5GHyJiFKJn9bz++zZM0yaNAn+/v5aE56S9gAn/f9evXph+vTpHE9HRMki6fnlzp07iIyMhIuLC6ysrKBSqRAWFoY6deogKioKw4cPh5eXF+rXr48HDx7g2rVrH026JSIi/fRTx/x+bsa/5k3pxYsX+O2339CyZUvUqlULACeUENH3Sxpa//jjD6xduxYxMTEQEYwdOxbe3t7InDkzwsLCULduXcTGxiIsLAxxcXG4ceMGTE1NeS4iIkolfupFLhwdHTFkyBC4urpi69atmDBhQmIRRkZ4/vw5GjZsiMuXL8PHx0e5Dd9siOh7JCQkKMF39OjRWLp0KWbPno3g4GCUKlUKw4YNw+rVq/H8+XPY2Nhg+/btiImJgampqRJ84+PjeS4iIkolfvoV3pIG4G3btmHy5Ml4/fo1WrRogbdv3+LWrVswMTFBQkLCzy6NiFKRHTt2AEj8AC0iuH37Ng4fPoz58+fD19cXe/fuxYkTJ+Di4oLRo0dj1apVePr0KWxsbHDq1ClcvHhRCb5cx5eIKPXQyeWNNQG4TJky2Lx5M3Lnzo2QkBBcvXqVvSxE9N1Wr16NNm3aYNq0aQASJ8va2tqiS5cu8Pb2xsmTJ9G+fXtMmDABhw4dQqVKlTB37lwsWLAAr169goWFhTIpl8GXiCh10Un4BRID8ODBg5EvXz6ULVsW165dYy8LESULd3d3dO3aFYsWLcKkSZMAAFmyZIGXlxfMzMywfPly1KpVCx07dgSQuAKJqakp7t69i/Tp0yv3o5kgR0REqYdOU6ajoyNmzJgBW1tbGBkZMfgS0XdLSEhAnjx50Lt3b1hYWGDZsmWwsrJCt27d4ODggLi4OLx8+RI5cuRQlj4LDw/H6tWrUaZMGahUKq7qQESUiuk8aaZLlw4A+PUiEX03EVGGTB06dAghISF48eIFhgwZArVajR49esDU1BS5cuXCunXr8O7dO9y/fx/h4eEoXbo0VCqV1pJoRESU+ujk8sZERD/S4MGDsXjxYowZMwYxMTHYuXMnHjx4gC5duqB///4AgH79+uGff/6BiYkJ5s2bx+XMiIgMBMMvEaUqwcHBqFWrFgYNGoSmTZsCAAICAjB37lxs2bIF/fr1Q8+ePQForyPOYVdERIaB3+0RUaqSJk0avHz5Ei9fvlS25c2bF927d4eFhQVGjhyJ0aNHA9BeR5zBl4jIMDD8EpHe0kxYS/pfCwsLeHh44NatWwgJCVHa5smTB2XKlIGzszMCAwPBL72IiAwTwy8R6aX169ejY8eOuH//PqKiogAkLk2WJk0aNGjQAOvXr8fChQsRFBQEIHFFh6ioKHTr1g3Lli1TVnUgIiLDwjG/RKR3wsLCULJkSYSFhcHR0RFlypRBhQoV0KZNG6XNnDlzMGrUKBQpUgTp0qVDUFAQoqOjcenSJeWqb1zOjIjI8DD8EpHeSUhIwB9//IEcOXLA1dUVR44cwdixY1GjRg0UKFAAAwcOhKmpKc6ePYsDBw7g5s2byJIlCyZPnsxVHYiIDBzDLxHppb1796JJkyY4deoUihYtiujoaIwbNw5jxoxB0aJF0bx5c9StWxf58uXTuh1XdSAiMmwMv0Skt7p37w4gcYgDABQqVAguLi7IkycPrl27hkOHDmHRokXo0KEDAHCoAxER6f4Kb0RE36pkyZJYtmwZ3r59i6pVqyJdunRYsWIFbGxs8PTpU5w6dQoNGzZU2jP4EhERe36JSK+VKVMGFy9eRMWKFbFlyxbY29t/1IZDHYiISINLnRGRXtJ8bu/VqxcKFSqEqVOnwt7e/pPLlzH4EhGRBsMvEeklzRCGypUr4/Xr1zh48KDWdiIiok9h+CUivZYlSxb4+flhypQpuH37tq7LISKiFI7fBRKR3qtRowYuXryI/Pnz67oUIiJK4TjhjYhSBc0yZryABRER/RuGXyIiIiIyGBzzS0REREQGg+GXiIiIiAwGwy8RERERGQyGXyIiIiIyGAy/RERERGQwGH6JiIiIyGAw/BIRGahjx45BpVLh3bt3X3ybnDlzYsaMGT+sJiKiH43hl4gohWrbti1UKhW6du360b7u3btDpVKhbdu2P78wIiI9xvBLRJSCZcuWDevXr0dUVJSyLTo6GmvXrkX27Nl1WBkRkX5i+CUiSsFKliyJbNmyYcuWLcq2LVu2IHv27ChRooSyLSYmBr169ULGjBlhYWGB8uXL48KFC1r3tWfPHri4uMDS0hKVK1fGo0ePPvr3Tp06hQoVKsDS0hLZsmVDr169EBER8cOOj4joZ2P4JSJK4dq3b49ly5Ypvy9duhTt2rXTajNgwABs3rwZK1aswOXLl5EnTx54e3vjzZs3AICgoCA0aNAAtWvXxtWrV9GxY0cMGjRI6z4CAwPh4+ODhg0b4vr16/jrr79w6tQp9OjR48cfJBHRT8LwS0SUwrVs2RKnTp3C48eP8fjxY5w+fRotW7ZU9kdERGDevHmYPHkyfH19UbBgQSxatAiWlpZYsmQJAGDevHnInTs3pk6dinz58qFFixYfjRceP348WrRogd69eyNv3rwoW7YsZs6ciZUrVyI6OvpnHjIR0Q9jousCiIjo32XIkAE1a9bE8uXLISKoWbMm0qdPr+wPDAxEXFwcypUrp2wzNTVFmTJlcOfOHQDAnTt34ObmpnW/Hh4eWr9fu3YN169fx5o1a5RtIgK1Wo2HDx+iQIECP+LwiIh+KoZfIiI90L59e2X4wZw5c37IvxEeHo4uXbqgV69eH+3j5DoiSi0YfomI9ICPjw9iY2OhUqng7e2ttS937twwMzPD6dOnkSNHDgBAXFwcLly4gN69ewMAChQogB07dmjdzt/fX+v3kiVL4vbt28iTJ8+POxAiIh3jmF8iIj1gbGyMO3fu4Pbt2zA2NtbalzZtWvz666/o378/9u3bh9u3b6NTp06IjIxEhw4dAABdu3ZFQEAA+vfvj3v37mHt2rVYvny51v0MHDgQZ86cQY8ePXD16lUEBARg+/btnPBGRKkKwy8RkZ6wsbGBjY3NJ/dNmDABDRs2RKtWrVCyZEn8/fff2L9/P9KlSwcgcdjC5s2bsW3bNhQrVgzz58/HuHHjtO6jaNGiOH78OO7fv48KFSqgRIkSGDZsGJycnH74sRER/SwqERFdF0FERERE9DOw55eIiIiIDAbDLxEREREZDIZfIiIiIjIYDL9EREREZDAYfomIiIjIYDD8EhEREZHBYPglIiIiIoPB8EtEREREBoPhl4iIiIgMBsMvERERERkMhl8iIiIiMhj/B7c7jiueLZN7AAAAAElFTkSuQmCC", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# Create a DataFrame for metrics\n", - "metrics_df = pd.DataFrame(metrics)\n", - "\n", - "plt.figure(figsize=(20, 5))\n", - "\n", - "# RMSE Plot\n", - "plt.subplot(1, 3, 1)\n", - "plt.bar(metrics_df['Model'], metrics_df['RMSE'], color='lightblue')\n", - "plt.ylabel('RMSE')\n", - "plt.xlabel('Model')\n", - "plt.xticks(rotation=45,ha='right')\n", - "plt.title('RMSE for Different Models')\n", - "\n", - "plt.tight_layout()\n", - "plt.show()\n" - ] + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\balbi\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:204: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(**kwargs)\n" + ] + } + ], + "source": [ + "model10 = Sequential()\n", + "model10.add(LSTM(64, activation='relu', input_shape=(n_steps, n_features)))\n", + "model10.add(Dense(1))" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "id": "3UJtO3wC7WWe" + }, + "outputs": [], + "source": [ + "# Compile the model\n", + "model10.compile(loss='mean_squared_error', optimizer='adam')\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, - { - "cell_type": "code", - "execution_count": 61, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 506 - }, - "id": "mwniKbys0xJ0", - "outputId": "ff2fe79a-78c2-4e13-efef-75e89882656b" - }, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# MAE Plot\n", - "plt.figure(figsize=(20, 5))\n", - "plt.subplot(1, 3, 2)\n", - "plt.bar(metrics_df['Model'], metrics_df['MAE'], color='lightgreen') # Changed to plt.bar()\n", - "plt.ylabel('MAE') # Set y-label to MAE\n", - "plt.xlabel('Model') # Set x-label to Model\n", - "plt.xticks(rotation=45,ha='right') # Rotate x-axis labels for better readability\n", - "plt.title('MAE for Different Models')\n", - "\n", - "plt.tight_layout()\n", - "plt.show()\n" - ] + "id": "ld9dofMD7YNO", + "outputId": "2b3021f3-d88f-431c-a059-a9b6e065a29b" + }, + "outputs": [], + "source": [ + "model10.fit(X_train_reshaped, y_train[n_steps-1:], epochs=100, batch_size=32, verbose=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "lOTdB8Bj7aXM", + "outputId": "c844bad9-4c1e-447f-dad9-7b86f57dee9b" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 62, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 506 - }, - "id": "vxK0_IkL1zaU", - "outputId": "69c4c24b-f6d5-4a4c-f85a-baa8455475e5" - }, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# MAPE Plot\n", - "plt.figure(figsize=(20, 5))\n", - "plt.subplot(1, 3, 3)\n", - "plt.bar(metrics_df['Model'], metrics_df['MAPE'], color='salmon')\n", - "plt.ylabel('MAPE')\n", - "plt.xlabel('Model')\n", - "plt.xticks(rotation=45,ha='right')\n", - "plt.title('MAPE for Different Models')\n", - "\n", - "plt.tight_layout()\n", - "plt.show()\n" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m44/44\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step\n", + "RMSE: 15.048059609987224\n", + "MAE: 12.060430640867935\n", + "MAPE: 0.21836694109231441\n", + "\n" + ] + } + ], + "source": [ + "rmse, mae, mape = evaluate_model(model10, X_test_reshaped, y_test[n_steps-1:])\n", + "\n", + "# Store metrics\n", + "metrics[\"Model\"].append(\"LSTM\")\n", + "metrics[\"RMSE\"].append(rmse)\n", + "metrics[\"MAE\"].append(mae)\n", + "metrics[\"MAPE\"].append(mape)" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 506 }, + "id": "O8DHEHgI0wNg", + "outputId": "5cd999c9-0cca-4d23-da28-8655ce099354" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 46, - "metadata": {}, - "outputs": [], - "source": [ - "import pickle\n", - "with open('prediction.pkl','wb') as file:\n", - " pickle.dump(model5, file) " + "data": { + "image/png": "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", + "text/plain": [ + "
" ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Create a DataFrame for metrics\n", + "metrics_df = pd.DataFrame(metrics)\n", + "\n", + "plt.figure(figsize=(20, 5))\n", + "\n", + "# RMSE Plot\n", + "plt.subplot(1, 3, 1)\n", + "plt.bar(metrics_df['Model'], metrics_df['RMSE'], color='lightblue')\n", + "plt.ylabel('RMSE')\n", + "plt.xlabel('Model')\n", + "plt.xticks(rotation=45,ha='right')\n", + "plt.title('RMSE for Different Models')\n", + "\n", + "plt.tight_layout()\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 506 }, + "id": "mwniKbys0xJ0", + "outputId": "ff2fe79a-78c2-4e13-efef-75e89882656b" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 47, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "New CSV file created with the desired columns!\n" - ] - } - ], - "source": [ - "file_path = \"SBIN.csv\" \n", - "df = pd.read_csv(file_path)\n", - "\n", - "df = df.drop(columns=['Date', 'Adj Close'])\n", - "\n", - "new_file_path = \"Updated_SBIN.csv\"\n", - "df.to_csv(new_file_path, index=False)\n", - "\n", - "print(\"New CSV file created with the desired columns!\")\n" + "data": { + "image/png": "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", + "text/plain": [ + "
" ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# MAE Plot\n", + "plt.figure(figsize=(20, 5))\n", + "plt.subplot(1, 3, 2)\n", + "plt.bar(metrics_df['Model'], metrics_df['MAE'], color='lightgreen') # Changed to plt.bar()\n", + "plt.ylabel('MAE') # Set y-label to MAE\n", + "plt.xlabel('Model') # Set x-label to Model\n", + "plt.xticks(rotation=45,ha='right') # Rotate x-axis labels for better readability\n", + "plt.title('MAE for Different Models')\n", + "\n", + "plt.tight_layout()\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 506 }, + "id": "vxK0_IkL1zaU", + "outputId": "69c4c24b-f6d5-4a4c-f85a-baa8455475e5" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 48, - "metadata": {}, - "outputs": [], - "source": [ - "file_path = \"Updated_SBIN.csv\" # Replace with your actual CSV file path\n", - "df = pd.read_csv(file_path)\n", - "\n", - "# Rearrange the columns so that 'Volume' comes before 'Close'\n", - "df = df[['Open', 'High', 'Low', 'Volume', 'Close']]\n", - "\n", - "# Save the updated dataframe to a new CSV file\n", - "new_file_path = \"Updated_SBIN.csv\" # Replace with your desired output CSV file path\n", - "df.to_csv(new_file_path, index=False)" + "data": { + "image/png": "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", + "text/plain": [ + "
" ] - }, + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# MAPE Plot\n", + "plt.figure(figsize=(20, 5))\n", + "plt.subplot(1, 3, 3)\n", + "plt.bar(metrics_df['Model'], metrics_df['MAPE'], color='salmon')\n", + "plt.ylabel('MAPE')\n", + "plt.xlabel('Model')\n", + "plt.xticks(rotation=45,ha='right')\n", + "plt.title('MAPE for Different Models')\n", + "\n", + "plt.tight_layout()\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [], + "source": [ + "import pickle\n", + "with open('prediction.pkl','wb') as file:\n", + " pickle.dump(model5, file) " + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [ { - "cell_type": "code", - "execution_count": 49, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Original dataset shape: (7074, 5)\n", - "Cleaned dataset shape: (7065, 5)\n", - "Cleaned dataset saved to Updated_SBIN.csv\n" - ] - } - ], - "source": [ - "import pandas as pd\n", - "\n", - "# Load the original dataset\n", - "data_file = \"Updated_SBIN.csv\" # Path to your original CSV file\n", - "df = pd.read_csv(data_file)\n", - "\n", - "# Display the original dataset shape\n", - "print(\"Original dataset shape:\", df.shape)\n", - "\n", - "# Remove rows with any null values\n", - "df_cleaned = df.dropna()\n", - "\n", - "# Display the cleaned dataset shape\n", - "print(\"Cleaned dataset shape:\", df_cleaned.shape)\n", - "\n", - "# Save the cleaned dataset to a new CSV file\n", - "cleaned_data_file = \"Updated_SBIN.csv\" # Path for the cleaned CSV file\n", - "df_cleaned.to_csv(cleaned_data_file, index=False)\n", - "\n", - "print(f\"Cleaned dataset saved to {cleaned_data_file}\")\n" - ] + "name": "stdout", + "output_type": "stream", + "text": [ + "New CSV file created with the desired columns!\n" + ] } - ], - "metadata": { - "colab": { - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.11.6" + ], + "source": [ + "file_path = \"SBIN.csv\" \n", + "df = pd.read_csv(file_path)\n", + "\n", + "df = df.drop(columns=['Date', 'Adj Close'])\n", + "\n", + "new_file_path = \"Updated_SBIN.csv\"\n", + "df.to_csv(new_file_path, index=False)\n", + "\n", + "print(\"New CSV file created with the desired columns!\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [], + "source": [ + "file_path = \"Updated_SBIN.csv\" # Replace with your actual CSV file path\n", + "df = pd.read_csv(file_path)\n", + "\n", + "# Rearrange the columns so that 'Volume' comes before 'Close'\n", + "df = df[['Open', 'High', 'Low', 'Volume', 'Close']]\n", + "\n", + "# Save the updated dataframe to a new CSV file\n", + "new_file_path = \"Updated_SBIN.csv\" # Replace with your desired output CSV file path\n", + "df.to_csv(new_file_path, index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Original dataset shape: (7074, 5)\n", + "Cleaned dataset shape: (7065, 5)\n", + "Cleaned dataset saved to Updated_SBIN.csv\n" + ] } + ], + "source": [ + "import pandas as pd\n", + "\n", + "# Load the original dataset\n", + "data_file = \"Updated_SBIN.csv\" # Path to your original CSV file\n", + "df = pd.read_csv(data_file)\n", + "\n", + "# Display the original dataset shape\n", + "print(\"Original dataset shape:\", df.shape)\n", + "\n", + "# Remove rows with any null values\n", + "df_cleaned = df.dropna()\n", + "\n", + "# Display the cleaned dataset shape\n", + "print(\"Cleaned dataset shape:\", df_cleaned.shape)\n", + "\n", + "# Save the cleaned dataset to a new CSV file\n", + "cleaned_data_file = \"Updated_SBIN.csv\" # Path for the cleaned CSV file\n", + "df_cleaned.to_csv(cleaned_data_file, index=False)\n", + "\n", + "print(f\"Cleaned dataset saved to {cleaned_data_file}\")\n" + ] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" }, - "nbformat": 4, - "nbformat_minor": 0 + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.6" + } + }, + "nbformat": 4, + "nbformat_minor": 0 } diff --git a/templates/stock.html b/templates/stock.html index 0a0acb3..af9dd7b 100644 --- a/templates/stock.html +++ b/templates/stock.html @@ -43,5 +43,18 @@

Stock Price Prediction

xhr.send(formData); } + + +