%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn import datasets

boston = datasets.load_boston()
print boston.DESCR

boston.keys()

boston.data.shape

boston.feature_names

df = pd.DataFrame(boston.data)
df.head()

df.columns = boston.feature_names
df['MEDV'] = boston.target
df.head()

df.describe()

plt.hist(df.MEDV)
plt.title('Housing prices')
plt.xlabel('price')
plt.ylabel('frequency')
plt.show()

plt.scatter(df.RM, df.MEDV)
plt.title('Average Number of Rooms vs Housing prices')
plt.xlabel('average number of rooms')
plt.ylabel('price')
plt.show()

from pandas.tools.plotting import scatter_matrix
scatter_matrix(df, figsize=(14, 14), diagonal='hist')

corrs = df.corr()
corrs

plt.pcolor(corrs, cmap='bwr', vmin=-1.0, vmax=1.0)
plt.yticks(np.arange(0.5, len(corrs.index), 1), corrs.index)
plt.xticks(np.arange(0.5, len(corrs.columns), 1), corrs.columns)
plt.colorbar()

from sklearn.linear_model import LinearRegression
lr = LinearRegression(normalize=True)
lr.fit(boston.data, boston.target)
predicted = lr.predict(boston.data)
plt.hist(boston.target - predicted, bins=50)
plt.show()

zip(boston.feature_names, lr.coef_)

from sklearn.linear_model import RidgeCV
rcv = RidgeCV(alphas=np.array([0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 1.0]), normalize=True)
rcv.fit(boston.data, boston.target)
rcv.alpha_

zip(boston.feature_names, rcv.coef_)

from sklearn.linear_model import LassoCV
lcv = LassoCV(alphas=np.array([0.001, 0.003, 0.01, 0.03, 0.1, 0.3, 1.0]), normalize=True)
lcv.fit(boston.data, boston.target)
lcv.alpha_

zip(boston.feature_names, lcv.coef_)

plt.scatter(df.INDUS, df.MEDV)

plt.scatter(df.AGE, df.MEDV)

plt.scatter(df.RAD, df.MEDV)

plt.scatter(df.TAX, df.MEDV)

from sklearn.linear_model import ElasticNetCV
encv = ElasticNetCV(alphas=np.array([0.0001, 0.0003, 0.01, 0.03, 0.1, 0.3, 1.0]), \
                    l1_ratio=np.array([0.5, 0.8, 0.9, 0.95, 0.99, 0.995, 1.0]), normalize=True)
encv.fit(boston.data, boston.target)
zip(boston.feature_names, encv.coef_)

encv.alpha_, encv.l1_ratio_