Tutorial 11: Linear Regression — Housing

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.metrics import mean_absolute_error, mean_squared_error

housing = fetch_california_housing()
X, y = housing.data, housing.target
feature_names = housing.feature_names

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

pipe = Pipeline([
    ("scaler", StandardScaler()),
    ("model", LinearRegression()),
])
pipe.fit(X_train, y_train)
y_pred = pipe.predict(X_test)

rmse = mean_squared_error(y_test, y_pred, squared=False)
mae = mean_absolute_error(y_test, y_pred)
print(f"RMSE: ${rmse * 100_000:,.0f}")
print(f"MAE:  ${mae * 100_000:,.0f}")

coefs = pipe.named_steps["model"].coef_
for name, coef in sorted(zip(feature_names, coefs), key=lambda x: -abs(x[1])):
    print(f"  {name:15s} {coef:+.4f}")

plt.scatter(y_test, y_pred, alpha=0.3, s=10)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], "r--")
plt.xlabel("Actual ($100k)")
plt.ylabel("Predicted ($100k)")
plt.savefig("housing_predictions.png", dpi=120)