import numpy as np import pandas as pd import pickle import warnings from sklearn.pipeline import Pipeline from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.linear_model import LogisticRegression from sklearn.metrics import accuracy_score, classification_report warnings.filterwarnings("ignore") # Load dataset data = pd.read_csv("D:/Project/PG Projects/Fire Prediction 2/fire_prediction_dataset_large.csv") # Convert to NumPy array data = np.array(data) # Extract features and target variable X = data[1:, 1:-1].astype('float') y = data[1:, -1].astype('int') # Split dataset into training and testing sets X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y) # Define pipeline with scaling and logistic regression pipeline = Pipeline([ ('scaler', StandardScaler()), ('log_reg', LogisticRegression(solver='liblinear')) ]) # Hyperparameter tuning param_grid = { 'log_reg__C': [0.01, 0.1, 1, 10, 100], 'log_reg__penalty': ['l1', 'l2'] } grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring='accuracy', n_jobs=-1) grid_search.fit(X_train, y_train) # Best model best_model = grid_search.best_estimator_ # Evaluate model y_pred = best_model.predict(X_test) accuracy = accuracy_score(y_test, y_pred) report = classification_report(y_test, y_pred) print(f"Best Model Accuracy: {accuracy:.4f}") print("Classification Report:\n", report) # Save the best model with open('advanced_model.pkl', 'wb') as model_file: pickle.dump(best_model, model_file)