I am using sklearn to run a random forest. I am setting the seed for the random forest, as well as splitting the data for cross validation. When I re-run the code consecutive times, it gives me the same result. However, re-running the same code after a month, I got slightly different feature importances. In some other similar analyses, the accuracy metrics are different too. The data has not been changed. I am running on Google Colab. Here is my code: # Configuration file_path = '/content/drive/My Drive/dataset.csv' columns_to_keep = [ 'target_column', 'feature_a', 'feature_b', 'feature_c', 'feature_d', 'feature_e', 'feature_f', 'feature_g', 'feature_h', 'feature_i', 'feature_j', 'feature_k', 'feature_l', 'feature_m', 'feature_n', 'feature_o', 'feature_p', 'feature_q', 'feature_r', 'feature_s', 'feature_t', 'feature_u', 'feature_v', 'feature_w', 'feature_x', 'feature_y', 'feature_z', 'feature_aa', 'feature_ab', 'feature_ac', 'feature_ad', 'feature_ae', 'feature_af', 'feature_ag', 'feature_ah', 'feature_ai', 'feature_aj', 'feature_ak', 'feature_al', 'feature_am', 'feature_an' ] df = pd.read_csv(file_path, usecols=columns_to_keep) categorical_columns = ['feature_ak', 'feature_al', 'feature_am', 'feature_an', 'feature_ao'] one_hot_columns = ['feature_al', 'feature_ak'] df = df.dropna() # One-hot encode the specified column le = LabelEncoder() for col in one_hot_columns: df[col] = le.fit_transform(df[col]) # Convert specified columns to categorical for col in categorical_columns: df[col] = df[col].astype('category') # Split into features and target X = df.drop(columns=['target_column']) y = df['target_column'] # Initialize the RandomForestClassifier model rf_model = RandomForestClassifier(n_estimators=100, random_state=42) # Initialize k-fold cross-validation kf = KFold(n_splits=5, shuffle=True, random_state=42) # Store results feature_importances_list = [] all_y_true = [] all_y_pred = [] # Perform k-fold cross-validation for fold_num, (train_index, test_index) in enumerate(kf.split(X), start=1): # Split the data X_train, X_test = X.iloc[train_index], X.iloc[test_index] y_train, y_test = y.iloc[train_index], y.iloc[test_index] # Train the Random Forest model rf_model.fit(X_train, y_train) # Predict on the test set y_pred = rf_model.predict(X_test) # Collect all true and predicted labels all_y_true.extend(y_test) all_y_pred.extend(y_pred) # Get feature importances for this fold feature_importances_list.append(rf_model.feature_importances_) # Calculate and print the accuracy for this fold accuracy_fold = accuracy_score(y_test, y_pred) print(f"Fold {fold_num} Accuracy: {accuracy_fold:.4f}") # Calculate accuracy across all predictions accuracy_cv = accuracy_score(all_y_true, all_y_pred) # Generate a classification report final_report = classification_report(all_y_true, all_y_pred, digits=3) # Average feature importances across folds average_importance = sum(feature_importances_list) / len(feature_importances_list) # Create a DataFrame with feature names and their corresponding average importance feature_names = X.columns importance_df = pd.DataFrame({ 'Feature': feature_names, 'Importance': average_importance }).sort_values(by='Importance', ascending=False) # Print Results print(f"Overall Accuracy of Random Forest model with k-fold CV: {accuracy_cv:.4f}") print("\nFinal Classification Report:") print(final_report) print("\nRandom Forest Feature Importances (averaged across folds):") print(importance_df.head(20)) Continue reading...
