Car Price Prediction

App.py

@@ -40,7 +40,44 @@
 st.write(
 	"- **Parkinson's Disease Detector**: Assess your risk of Parkinson's Disease with advanced machine learning algorithms."
 )
+st.write(
+
+	"- **Car Price Predictor**: Predict the market price of a car based on features such as make, model, year, mileage, and condition."
+
+)
+
+
 
+# Car Price Predictor Section
+
+with st.expander("Car Price Predictor - More Information"):
+	st.subheader("Introduction")
+	st.write(
+		"""
+		The Car Price Predictor estimates the market value of a vehicle based on various input features, including make, model, year, mileage, and condition. This tool leverages machine learning algorithms to provide accurate pricing estimates tailored to the current automotive market.
+		"""
+	)
+	# Dataset section
+	st.subheader("Car Price Dataset")
+	st.write(
+		"""
+		The dataset used for this model contains historical sales data for vehicles, including various features that influence car prices. The goal is to predict the selling price based on characteristics that are commonly evaluated in the market.
+		"""
+	)
+	# Input features section
+	st.subheader("Additional Variable Information")
+	st.write(
+		"""
+		- **Make**: The brand of the car (e.g., Toyota, Ford).
+		- **Model**: The specific model of the car (e.g., Camry, Mustang).
+		- **Year**: The manufacturing year of the vehicle.
+		- **Mileage**: The total distance driven by the car, usually measured in miles.
+		- **Condition**: The state of the vehicle (e.g., new, used, certified pre-owned).
+		- **Engine Size**: The size of the car's engine, often measured in liters.
+		- **Fuel Type**: The type of fuel the car uses (e.g., gasoline, diesel, electric).
+		- **Transmission**: The type of transmission (e.g., automatic, manual).
+		"""
+	)
 # Parkinson's Disease Detector Section
 with st.expander("Parkinson's Disease Detector - More Information"):
 	st.subheader("Introduction")

form_configs/car_price_prediction.json

@@ -0,0 +1,66 @@
+{
+  "Car Price Detection Form": {
+    "Car Age (in years)": {
+      "field_name": "car_age",
+      "type": "number",
+      "min_value": 0,
+      "max_value": 20,
+      "default_value": 5,
+      "step": 1
+    },
+    "Mileage (in kilometers)": {
+      "field_name": "mileage",
+      "type": "number",
+      "min_value": 0,
+      "max_value": 300000,
+      "default_value": 50000,
+      "step": 1000
+    },
+    "Engine Size (in liters)": {
+      "field_name": "engine_size",
+      "type": "float",
+      "min_value": 0.5,
+      "max_value": 5.0,
+      "default_value": 1.5,
+      "step": 0.1
+    },
+    "Fuel Type": {
+      "field_name": "fuel_type",
+      "type": "dropdown",
+      "options": ["Petrol", "Diesel", "Electric", "Hybrid"],
+      "default_value": "Petrol"
+    },
+    "Transmission Type": {
+      "field_name": "transmission",
+      "type": "dropdown",
+      "options": ["Automatic", "Manual"],
+      "default_value": "Automatic"
+    },
+    "Number of Previous Owners": {
+      "field_name": "previous_owners",
+      "type": "number",
+      "min_value": 0,
+      "max_value": 5,
+      "default_value": 1,
+      "step": 1
+    },
+    "Car Brand": {
+      "field_name": "car_brand",
+      "type": "dropdown",
+      "options": ["Toyota", "Honda", "Ford", "BMW", "Mercedes"],
+      "default_value": "Toyota"
+    },
+    "Condition of the Car": {
+      "field_name": "condition",
+      "type": "dropdown",
+      "options": ["New", "Like New", "Used", "Certified Pre-Owned"],
+      "default_value": "Used"
+    },
+    "Color": {
+      "field_name": "color",
+      "type": "dropdown",
+      "options": ["Red", "Blue", "Black", "White", "Silver", "Gray"],
+      "default_value": "Black"
+    }
+  }
+}

models/car_price/model.py

@@ -0,0 +1,38 @@
+# model.py
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression, Lasso
+from sklearn.preprocessing import LabelEncoder
+
+def load_and_preprocess_data(file_path):
+    # Load dataset from the provided CSV file
+    df = pd.read_csv(file_path)
+
+    # Selecting relevant columns for prediction
+    relevant_columns = ['year', 'selling_price', 'km_driven', 'fuel', 'seller_type', 'transmission']
+    df = df[relevant_columns]
+
+    # Convert categorical features to numerical using LabelEncoder
+    le = LabelEncoder()
+    df['fuel'] = le.fit_transform(df['fuel'])
+    df['seller_type'] = le.fit_transform(df['seller_type'])
+    df['transmission'] = le.fit_transform(df['transmission'])
+
+    # Define features and target variable
+    X = df[['year', 'km_driven', 'fuel', 'seller_type', 'transmission']]
+    y = df['selling_price']
+
+    # Split the data into training and testing sets (80% train, 20% test)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    return X_train, X_test, y_train, y_test
+
+def train_linear_regression(X_train, y_train):
+    lr_model = LinearRegression()
+    lr_model.fit(X_train, y_train)
+    return lr_model
+
+def train_lasso_regression(X_train, y_train):
+    lasso_model = Lasso(alpha=0.1)
+    lasso_model.fit(X_train, y_train)
+    return lasso_model

models/car_price/modelEvaluation.py

@@ -0,0 +1,34 @@
+# modelEvaluation.py
+from sklearn.metrics import mean_squared_error, r2_score
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+def evaluate_model(model, X_test, y_test):
+    predictions = model.predict(X_test)
+    mse = mean_squared_error(y_test, predictions)
+    r2 = r2_score(y_test, predictions)
+    print(f'Mean Squared Error: {mse}')
+    print(f'R² Score: {r2}')
+    return predictions
+
+def plot_predictions(y_test, predictions, model_name):
+    plt.figure(figsize=(10, 6))
+    sns.scatterplot(x=y_test, y=predictions, alpha=0.6)
+    plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], '--r')  # Diagonal line
+    plt.title(f'{model_name} Predictions vs Actual Selling Prices')
+    plt.xlabel('Actual Selling Prices')
+    plt.ylabel('Predicted Selling Prices')
+    plt.xlim(y_test.min() - 1000, y_test.max() + 1000)
+    plt.ylim(y_test.min() - 1000, y_test.max() + 1000)
+    plt.grid()
+    plt.show()
+
+def plot_feature_importance(model, feature_names):
+    importance = model.coef_ if hasattr(model, 'coef_') else None
+    if importance is not None:
+        plt.figure(figsize=(10, 6))
+        sns.barplot(x=importance, y=feature_names)
+        plt.title('Feature Importance')
+        plt.xlabel('Coefficient Value')
+        plt.ylabel('Features')
+        plt.show()

models/car_price/predict.py

@@ -0,0 +1,29 @@
+# predict.py
+from model import load_and_preprocess_data, train_linear_regression, train_lasso_regression
+from modelEvaluation import evaluate_model, plot_predictions, plot_feature_importance
+
+def main():
+    # Path to the CSV file
+    file_path = 'data//car_data.csv'  # Ensure this CSV file is in the same directory
+
+    # Load and preprocess data
+    X_train, X_test, y_train, y_test = load_and_preprocess_data(file_path)
+
+    # Train models
+    lr_model = train_linear_regression(X_train, y_train)
+    lasso_model = train_lasso_regression(X_train, y_train)
+
+    # Evaluate models
+    print("Evaluating Linear Regression:")
+    lr_predictions = evaluate_model(lr_model, X_test, y_test)
+    plot_predictions(y_test, lr_predictions, "Linear Regression")
+
+    print("\nEvaluating Lasso Regression:")
+    lasso_predictions = evaluate_model(lasso_model, X_test, y_test)
+    plot_predictions(y_test, lasso_predictions, "Lasso Regression")
+
+    # Plot feature importance for Lasso Regression
+    plot_feature_importance(lasso_model, X_train.columns)
+
+if __name__ == "__main__":
+    main()

pages/Car_price_Predictor.py

@@ -0,0 +1,4 @@
+from page_handler import PageHandler
+
+page_handler = PageHandler("pages/pages.json")
+page_handler.render_page("Car Price Predictor")

pages/pages.json

@@ -150,5 +150,28 @@
       "type": "model_details"
     }
   ]
-}
+
+},
+  "Car Price Predictor": {
+    "title": "Car Price Predictor",
+    "page_title": "Car Price Predictor",
+    "page_icon": "\ud83d\ude97",
+    "model_predict_file_path": "models/car_price/predict.py",
+    "model_function": "get_prediction",
+    "model_detail_function": "model_details",
+    "form_config_path": "form_configs/car_price.json",
+    "tabs": [
+      {
+        "name": "Car Price Estimator",
+        "type": "form",
+        "form_name": "Car Price Form"
+      },
+      {
+        "name": "Model Details",
+        "type": "model_details",
+        "problem_statement": "This model predicts car prices based on various features such as brand, model, year, mileage, and condition.",
+        "description": "Using a regression algorithm, this model analyzes historical sales data to provide accurate price estimations for cars based on their characteristics."
+      }
+    ]
+ }
 }