def main():
features_train, features_test, labels_train, labels_test = preprocess()
clf = GaussianNB()
timer = timing.Timer()
with timer:
clf.fit(features_train, labels_train)
print('fit took', timer())
with timer:
predictions = clf.predict(features_test)
print('predict took', timer())
with timer:
score = metrics.accuracy_score(labels_test, predictions)
print('score took', timer())
print('SCORE', score)
Chris has label 1
"""
import sys
from time import time
sys.path.append("../tools/")
from tools.email_preprocess import preprocess
from sklearn import tree
from sklearn.metrics import accuracy_score
### features_train and features_test are the features for the training
### and testing datasets, respectively
### labels_train and labels_test are the corresponding item labels
features_train, features_test, labels_train, labels_test = preprocess()
#########################################################
### your code goes here ###
clf = tree.DecisionTreeClassifier(min_samples_split=40)
clf = clf.fit(features_train, labels_train)
pred = clf.predict(features_test)
acc = accuracy_score(labels_test, pred)
print 'number of features:{}, accuracy:{}'.format(len(features_train[0]), acc)
#########################################################