#Python
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
import os

def create_sample_csv():
    """
    Creates a sample CSV file for demonstration purposes.
    The data will have some missing values to show preprocessing.
    """
    data = {
        'age': [25, 30, 35, 40, 45, 50, 55, 60, 65, np.nan, 75, 80],
        'salary': [50000, 55000, 60000, 65000, 70000, np.nan, 80000, 85000, 90000, 95000, 100000, 105000],
        'purchased': [0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1]
    }
    df = pd.DataFrame(data)
    df.to_csv('sample_data.csv', index=False)
    print("Created 'sample_data.csv'")

def run_ml_pipeline():
    """
    Main function to run the machine learning pipeline.
    """
    # --- 1. Load Data ---
    # We assume 'sample_data.csv' is in the same directory.
    try:
        df = pd.read_csv('sample_data.csv')
        print("\n--- Data Loaded Successfully ---")
        print("Original Data Head:")
        print(df.head())
    except FileNotFoundError:
        print("Error: 'sample_data.csv' not found. Please create it first.")
        return

    # --- 2. Data Preparation ---
    print("\n--- Data Preparation ---")

    # Handle missing values by filling with the mean of the column
    df['age'].fillna(df['age'].mean(), inplace=True)
    df['salary'].fillna(df['salary'].mean(), inplace=True)
    print("\nData after handling missing values:")
    print(df.info())

    # Define features (X) and the target (y)
    # X contains the independent variables (features) used for prediction.
    # y contains the dependent variable (target) that we want to predict.
    X = df[['age', 'salary']]
    y = df['purchased']

    # --- 3. Split Data into Training and Testing sets ---
    # We split the data to train the model on one subset and test it on another.
    # test_size=0.25 means 25% of the data will be used for testing.
    # random_state ensures the split is the same every time we run the code.
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
    print(f"\nData split into {len(X_train)} training samples and {len(X_test)} testing samples.")

    # --- 4. Feature Scaling ---
    # It's important to scale features so that all of them are on a similar scale.
    # This helps the logistic regression model converge faster and perform better.
    scaler = StandardScaler()
    X_train_scaled = scaler.fit_transform(X_train)
    X_test_scaled = scaler.transform(X_test)
    print("\nFeatures have been scaled.")

    # --- 5. Train the Machine Learning Model ---
    # We will use Logistic Regression, a simple and effective model for binary classification.
    print("\n--- Model Training ---")
    model = LogisticRegression()
    model.fit(X_train_scaled, y_train)
    print("Model training complete.")

    # --- 6. Make Predictions ---
    print("\n--- Prediction ---")
    y_pred = model.predict(X_test_scaled)
    print("Predictions made on the test set.")
    # You can uncomment the line below to see the predictions vs actual values
    # print(f"Predictions: {y_pred}, Actual: {y_test.values}")

    # --- 7. Evaluate the Model ---
    print("\n--- Model Evaluation ---")
    accuracy = accuracy_score(y_test, y_pred)
    print(f"Model Accuracy: {accuracy:.2f}")

    print("\nClassification Report:")
    # The classification report gives us precision, recall, and f1-score.
    # Precision: Out of all positive predictions, how many were actually positive.
    # Recall: Out of all actual positive cases, how many did the model predict correctly.
    print(classification_report(y_test, y_pred))

def cleanup():
    """Removes the generated CSV file."""
    if os.path.exists('sample_data.csv'):
        os.remove('sample_data.csv')
        print("\nCleaned up 'sample_data.csv'")

if __name__ == '__main__':
    create_sample_csv()
    run_ml_pipeline()
    cleanup()