import numpy as np
from sklearn import datasets, linear_model
np.set_printoptions(precision=4)
datatrain = np.genfromtxt('crime-train.txt', delimiter='\t', skip_header=1)
datatest = np.genfromtxt('crime-test.txt', delimiter='\t', skip_header=1)
trainY = datatrain[:,0]
trainX = np.delete(datatrain,0,axis=1)
testY = datatest[:,0]
testX = np.delete(datatest,0,axis=1)
regr = linear_model.LinearRegression()
regr.fit(trainX, trainY)
print('Coefficient of determination training set: %.8f'
      % regr.score(trainX, trainY))
print('Coefficient of determination for test set: %.8f'
      % regr.score(testX, testY))