mex-p1.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

from google.colab import drive
drive.mount('/content/drive')

file_path = "/content/drive/MyDrive/mex-data/CarPrice_Assignment.csv"
df = pd.read_csv(file_path)

# Drop unnecessary columns
df = df.drop(columns=['car_ID', 'CarName'])

# Identify categorical and numerical columns
categorical_cols = df.select_dtypes(include=['object']).columns.tolist()
numerical_cols = df.select_dtypes(include=['int64', 'float64']).columns.tolist()
numerical_cols.remove('price')  # Target variable

# Define preprocessing pipeline
preprocessor = ColumnTransformer(
    transformers=[
        ('num', 'passthrough', numerical_cols),
        ('cat', OneHotEncoder(handle_unknown='ignore'), categorical_cols)
    ])

# Split dataset into train (70%) and test (30%)
X = df.drop(columns=['price'])
y = df['price']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Define model pipeline
model = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('regressor', RandomForestRegressor(n_estimators=100, random_state=42))
])

# Train the model
model.fit(X_train, y_train)

# Predict on test set
y_pred = model.predict(X_test)

# Evaluate model performance
mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)

# Print performance metrics
print(f"Mean Absolute Error (MAE): {mae:.2f}")
print(f"Root Mean Squared Error (RMSE): {rmse:.2f}")
print(f"R² Score: {r2:.4f}")

# Scatter plot of actual vs. predicted prices
plt.figure(figsize=(8,6))
plt.scatter(y_test, y_pred, alpha=0.7, color='blue', label="Predicted vs. Actual")
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], color='red', linestyle='--', label="Perfect Prediction")

plt.xlabel("Actual Price")
plt.ylabel("Predicted Price")
plt.title("Actual vs. Predicted Car Prices")

plt.legend()
plt.grid(True)
plt.show()