from sklearn.datasets import load_boston
data = load_boston()
print data.keys()

print data.data.shape
print data.target.shape

print data.DESCR

%pylab inline

plt.hist(data.target)
plt.xlabel('price ($1000s)')
plt.ylabel('count')



from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)

from sklearn.linear_model import LinearRegression

clf = LinearRegression()

clf.fit(X_train, y_train)

predicted = clf.predict(X_test)
expected = y_test

plt.scatter(expected, predicted)
plt.plot([0, 50], [0, 50], '--k')
plt.axis('tight')
plt.xlabel('True price ($1000s)')
plt.ylabel('Predicted price ($1000s)')
print "RMS:", np.sqrt(np.mean((predicted - expected) ** 2))

from sklearn.ensemble import GradientBoostingRegressor
# Instantiate the model, fit the results, and scatter in vs. out


%load solutions/04B_houses_regression.py