regression_autos

# -*- coding: utf-8 -*-
"""Regression Autos

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1beRq-XbKLbs_4AOP_0nIX12uKUdTQW6U
"""

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# Load the dataset
file_path = "/content/_autos - regression - autos.csv"  # Replace with your actual file path
data = pd.read_csv(file_path)

# Preprocessing: Handle missing values, convert data types, etc.
# Fill missing numerical values with the median
data.fillna(data.median(numeric_only=True), inplace=True)

# Encode categorical variables using one-hot encoding
data = pd.get_dummies(data, drop_first=True)

# Define the features (X) and target variable (y)
# Assuming 'price' is the target variable
X = data.drop(columns=['price'])
y = data['price']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train a linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

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

# Evaluate the model
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Display results
print(f"Mean Squared Error: {mse}")
print(f"R-squared: {r2}")

# Optional: Display coefficients for interpretation
coefficients = pd.DataFrame(model.coef_, X.columns, columns=['Coefficient'])
print(coefficients)