lab_01.py

# -*- coding: utf-8 -*-
"""Lab 01.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1pdlSGy2YMtIhcbH3DUwIEMf9fH8iNwh7

#Mini Project – House Price Prediction

Task D1 — Data Loading & Exploration
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression

# Load house price dataset
house_df = pd.read_csv("House_Prices.csv")

print("First 5 rows of House Prices Dataset:")
print(house_df.head())
print("\n" + "="*50 + "\n")

print("Dataset Information:")
print(house_df.info())
print("\n" + "="*50 + "\n")

print("Descriptive Statistics:")
print(house_df.describe())
print("\n" + "="*50 + "\n")

# Check for missing values
print("Missing Values:")
print(house_df.isnull().sum())
print("\n" + "="*50 + "\n")

print("Dataset Shape:", house_df.shape)
print("Features (X): ['Area (sqft)', 'Bedrooms', 'Age (years)']")
print("Target (y): 'Price (Lakhs)'")

"""Task D2 — Multiple Linear Regression Model Training"""

# Prepare data
X_house = house_df[['Area (sqft)', 'Bedrooms', 'Age (years)']]
y_house = house_df['Price (Lakhs)']

# Create and train model
house_model = LinearRegression()
house_model.fit(X_house, y_house)

print("Regression Coefficients:")
for feature, coef in zip(['Area', 'Bedrooms', 'Age'], house_model.coef_):
    print(f"  {feature}: {coef:.4f}")

print(f"\nIntercept: {house_model.intercept_:.4f}")

print("\nRegression Equation:")
print(f"Price = {house_model.coef_[0]:.4f}×Area + {house_model.coef_[1]:.4f}×Bedrooms + {house_model.coef_[2]:.4f}×Age + {house_model.intercept_:.4f}")

"""Task D3 — Model Evaluation"""

# Task D3 — Model Evaluation
from sklearn.metrics import mean_squared_error, r2_score

# Make predictions
y_house_pred = house_model.predict(X_house)

# Calculate metrics
mse_house = mean_squared_error(y_house, y_house_pred)
r2_house = r2_score(y_house, y_house_pred)

print("House Price Model Performance:")
print(f"Mean Squared Error (MSE): {mse_house:.2f}")
print(f"Root Mean Squared Error (RMSE): {np.sqrt(mse_house):.2f}")
print(f"R² Score: {r2_house:.4f}")
print(f"R² Score Percentage: {r2_house*100:.2f}%")

# Create comparison dataframe
comparison_house = pd.DataFrame({
    'Actual Price': y_house,
    'Predicted Price': y_house_pred,
    'Difference': y_house - y_house_pred,
    'Error %': ((y_house - y_house_pred) / y_house * 100)
})

print("\nFirst 10 predictions vs actual:")
print(comparison_house.head(10))

# Plot actual vs predicted
plt.figure(figsize=(10, 5))
plt.scatter(range(len(y_house)), y_house, color='blue',
            alpha=0.7, label='Actual Price', s=100)
plt.scatter(range(len(y_house_pred)), y_house_pred, color='red',
            alpha=0.7, label='Predicted Price', s=100, marker='x')
plt.xlabel('House Index')
plt.ylabel('Price (Lakhs)')
plt.title('Actual vs Predicted House Prices')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

# Plot residuals
residuals = y_house - y_house_pred
plt.figure(figsize=(10, 4))
plt.scatter(y_house_pred, residuals, alpha=0.7)
plt.axhline(y=0, color='red', linestyle='--')
plt.xlabel('Predicted Price')
plt.ylabel('Residuals (Actual - Predicted)')
plt.title('Residual Plot')
plt.grid(True, alpha=0.3)
plt.show()

"""Task D4 — Predict New House Price"""

# Define new house features
new_house_features = [[1600, 3, 5]]  # Area, Bedrooms, Age

# Make prediction
predicted_price = house_model.predict(new_house_features)

print("New House Details:")
print("-" * 30)
print(f"Area:      {new_house_features[0][0]} sqft")
print(f"Bedrooms:  {new_house_features[0][1]}")
print(f"Age:       {new_house_features[0][2]} years")
print("-" * 30)
print(f"\nPredicted Price: {predicted_price[0]:.2f} Lakhs")

# Show contribution of each feature
print("\nPrice Contribution Breakdown:")
print("-" * 40)
area_contrib = house_model.coef_[0] * new_house_features[0][0]
bedrooms_contrib = house_model.coef_[1] * new_house_features[0][1]
age_contrib = house_model.coef_[2] * new_house_features[0][2]

print(f"Area (1600 × {house_model.coef_[0]:.4f}):    {area_contrib:>7.2f} Lakhs")
print(f"Bedrooms (3 × {house_model.coef_[1]:.4f}):   {bedrooms_contrib:>7.2f} Lakhs")
print(f"Age (5 × {house_model.coef_[2]:.4f}):       {age_contrib:>7.2f} Lakhs")
print(f"Base Price (Intercept):      {house_model.intercept_:>7.2f} Lakhs")
print("-" * 40)
print(f"Total Predicted Price:       {predicted_price[0]:>7.2f} Lakhs")