Train_Randomclassifier_and_save_model

# Import necessary libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import os
import pickle

# ================================
# Step 1: Load Dataset
# ================================
def load_dataset(file_path):
    """
    Load the dataset from the given file path.
    """
    try:
        df = pd.read_csv(file_path)
        print(" Dataset loaded successfully.")
        return df
    except Exception as e:
        print(f"❌ Error loading dataset: {e}")
        exit()

# ================================
# Step 2: Preprocess Data
# ================================
def preprocess_data(df):
    """
    Preprocess the dataset by dropping non-significant columns and checking for missing values.
    """
    # Drop non-significant columns (if they exist)
    df = df.drop(columns=["id", "dataset"], errors="ignore")
    print("\n Non-significant columns dropped (if present).")

    # Check for missing values
    if df.isnull().sum().sum() > 0:
        print("\n Missing values detected:")
        print(df.isnull().sum())
        # You can handle missing values here (e.g., imputation) if needed
    else:
        print("\n No missing values detected.")

    # Display basic info about the dataset
    print("\nDataset Preview:\n", df.head())
    print("\nDataset Summary:\n", df.info())

    return df

# ================================
# Step 3: Train-Test Split
# ================================
def split_data(df):
    """
    Split the dataset into training and testing sets.
    """
    X = df.iloc[:, :-1]  # Features (all columns except the last one)
    y = df.iloc[:, -1]   # Target (last column)

    # Perform an 80-20 split
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42, stratify=y
    )
    print("\n  Data split into training and testing sets (80-20 split).")
    return X_train, X_test, y_train, y_test

# ================================
# Step 4: Train the Model
# ================================
def train_model(X_train, y_train):
    """
    Train a Random Forest Classifier on the training data.
    """
    rf_model = RandomForestClassifier(
        n_estimators=100, random_state=42, n_jobs=-1
    )
    rf_model.fit(X_train, y_train)
    print("\n Random Forest model trained successfully.")
    return rf_model

# ================================
# Step 5: Evaluate the Model
# ================================
def evaluate_model(model, X_test, y_test):
    """
    Evaluate the trained model on the test data.
    """
    # Make predictions
    y_pred = model.predict(X_test)

    # Calculate accuracy
    accuracy = accuracy_score(y_test, y_pred)
    print(f"\n Model Accuracy: {accuracy:.4f}")

    # Print classification report
    print("\n Classification Report:\n")
    print(classification_report(y_test, y_pred))

    # Print confusion matrix
    print("\n Confusion Matrix:\n")
    print(confusion_matrix(y_test, y_pred))

    return accuracy

# ================================
# Step 6: Save the Model
# ================================
def save_model(model, model_path):
    """
    Save the trained model to a file using pickle.
    """
    try:
        with open(model_path, 'wb') as file:
            pickle.dump(model, file)
        print(f"\n  Model saved successfully at: {model_path}")
    except Exception as e:
        print(f" Error saving model: {e}")

# ================================
# Main Execution
# ================================
if __name__ == "__main__":
    # Define file paths
    file_path = "/content/balanced_heart_diseases.csv" #update as per your concerns
    model_path = "random_forest_model.p"

    # Step 1: Load dataset
    df = load_dataset(file_path)

    # Step 2: Preprocess data
    df = preprocess_data(df)

    # Step 3: Split data
    X_train, X_test, y_train, y_test = split_data(df)

    # Step 4: Train the model
    rf_model = train_model(X_train, y_train)

    # Step 5: Evaluate the model
    evaluate_model(rf_model, X_test, y_test)

    # Step 6: Save the model
    save_model(rf_model, model_path)