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.linear_model import LinearRegression

clf = LinearRegression()

clf.fit(data.data, data.target)

predicted = clf.predict(data.data)

plt.scatter(data.target, predicted)
plt.plot([0, 50], [0, 50], '--k')
plt.axis('tight')
plt.xlabel('True price ($1000s)')
plt.ylabel('Predicted price ($1000s)')

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