In [3]:

    

import matplotlib.pyplot as plt
import numpy as np
import sklearn
from sklearn import datasets, linear_model
print sklearn.__version__
# Load the diabetes dataset
diabetes = datasets.load_diabetes()
diabetes_X = diabetes.data


    

    




0.17

In [ ]:

    

# Use only one feature diabetes_X = diabetes.data[:, np.newaxis, 2]

# Split the data into training/testing sets
diabetes_X_train = diabetes_X[:-20]
diabetes_X_test = diabetes_X[-20:]
print "diabetes_X size", diabetes_X.shape
print "diabetes_X_train size", diabetes_X_train.shape
print "diabetes_X_test size", diabetes_X_test.shape

# Split the targets into training/testing sets  - !!!bad way to do that
diabetes_y_train = diabetes.target[:-20]
diabetes_y_test = diabetes.target[-20:]

# Create linear regression object
regr = linear_model.LinearRegression()

# Train the model using the training sets
regr.fit(diabetes_X_train, diabetes_y_train)

print "regr.score", regr.
# The coefficients
print('Coefficients:', regr.coef_)
# The mean square error
print("Residual sum of squares: %.2f"
      % np.mean((regr.predict(diabetes_X_test) - diabetes_y_test) ** 2))
# Explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % regr.score(diabetes_X_test, diabetes_y_test))


    

In [ ]: