CODTECH-Task1

import pandas as pd data=pd.read_csv(r"C:\Users\saisi\Downloads\BostonHousing.csv") data crim zn indus chas nox rm age dis rad tax ptratio b lstat medv 0 0.00632 18.0 2.31 0 0.538 6.575 65.2 4.0900 1 296 15.3 396.90 4.98 24.0 1 0.02731 0.0 7.07 0 0.469 6.421 78.9 4.9671 2 242 17.8 396.90 9.14 21.6 2 0.02729 0.0 7.07 0 0.469 7.185 61.1 4.9671 2 242 17.8 392.83 4.03 34.7 3 0.03237 0.0 2.18 0 0.458 6.998 45.8 6.0622 3 222 18.7 394.63 2.94 33.4 4 0.06905 0.0 2.18 0 0.458 7.147 54.2 6.0622 3 222 18.7 396.90 5.33 36.2 ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... 501 0.06263 0.0 11.93 0 0.573 6.593 69.1 2.4786 1 273 21.0 391.99 9.67 22.4 502 0.04527 0.0 11.93 0 0.573 6.120 76.7 2.2875 1 273 21.0 396.90 9.08 20.6 503 0.06076 0.0 11.93 0 0.573 6.976 91.0 2.1675 1 273 21.0 396.90 5.64 23.9 504 0.10959 0.0 11.93 0 0.573 6.794 89.3 2.3889 1 273 21.0 393.45 6.48 22.0 505 0.04741 0.0 11.93 0 0.573 6.030 80.8 2.5050 1 273 21.0 396.90 7.88 11.9 506 rows × 14 columns from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, r2_score features = ['rm', 'zn', 'dis', 'crim'] X = data[features] y = data['medv'] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) model = LinearRegression() model.fit(X_train, y_train) y_pred = model.predict(X_test) mse = mean_squared_error(y_test, y_pred) r2 = r2_score(y_test, y_pred) print(f"Mean Squared Error: {mse}") print(f"R^2 Score: {r2}") Answer: Mean Squared Error: 38.403725688472726 R^2 Score: 0.47631604380052006