In [ ]:

    

## Preprocessing

from sklearn.datasets import load_boston
from sklearn.cross_validation import train_test_split

boston = load_boston()
X = boston["data"]
y = boston["target"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state = 10)


    

In [ ]:

    

## Models, Predictions, and Metrics

from sklearn import linear_model
from sklearn.ensemble import RandomForestRegressor

def fit_and_score_model(model_type, hyperparameter, X_train, y_train, X_test, y_test):
    if model_type == "Ridge":
        ridge = linear_model.Ridge(alpha=hyperparameter)
        ridge.fit(X_train, y_train)
        return ridge.score(X_test, y_test)
    if model_type == "RandomForestRegressor":
        rf = RandomForestRegressor(n_estimators=hyperparameter)
        rf.fit(X_train, y_train)
        return rf.score(X_test, y_test)

for alpha in range(4):
    ridge_score = fit_and_score_model("Ridge", alpha, X_train, y_train, X_test, y_test)
    print("Ridge (alpha=" + str(alpha) + ") score: " + str(ridge_score))
for n_estimator in [1,5,7,10]:
    rf_score = fit_and_score_model("RandomForestRegressor", n_estimator, X_train, y_train, X_test, y_test)
    print("Random Forest (n_estimator=" + str(n_estimator) + ") score: " + str(rf_score))