def ensemble(data_set, features_list):
from data_sorter import featuresProcess
from data_sorter import split
data = featuresProcess(data_set, features_list)
labels, features = split(data)
from sklearn.ensemble import BaggingClassifier
clf = BaggingClassifier(n_estimators=int(sys.argv[1]),
random_state=202,
bootstrap=True)
pickle.dump(clf, open("classifier_ada.pkl", "w"))
pickle.dump(features_list, open("features_list.pkl", "w"))
pickle.dump(data_set, open("dataset.pkl", "w"))
def ensemble(data_set, features_list):
print data_set
from data_sorter import featuresProcess
from data_sorter import split
data = featuresProcess(data_set, features_list)
labels, features = split(data)
from sklearn.ensemble import AdaBoostClassifier
clf = AdaBoostClassifier(n_estimators=int(sys.argv[1]),
random_state=202,
learning_rate=float(sys.argv[2]),
algorithm="SAMME.R")
pickle.dump(clf, open("classifier_ada.pkl", "w"))
pickle.dump(features_list, open("features_list.pkl", "w"))
pickle.dump(data_set, open("dataset.pkl", "w"))
email_to_poi = get_information("from_this_person_to_poi", "from_messages", data)
count = 0
for ii in data:
data[ii]["email_from_poi"] = email_from_poi[count]
data[ii]["email_to_poi"] = email_to_poi[count]
count += 1
features_list = ["poi", "salary", "bonus", "email_from_poi", "email_to_poi",'deferral_payments', 'total_payments']
dataset = featuresProcess(data, features_list)
labels, features = split(dataset)
features_train, features_test, labels_train, labels_test = cross_validation.train_test_split(features, labels, test_size=0.1, random_state=42)
time_start = time.time()
dtree = DecisionTreeClassifier()
dtree.fit(features_train, labels_train)
score = dtree.score(features_test, labels_test)
print "Accuracy ", score
print "Decesion tree took time : ", time.time() - time_start
feat_ranks = dtree.feature_importances_
indices = np.argsort(feat_ranks)[::-1]
for ii in range(5):
print "{} feature {} ({})".format(ii+1, features_list[ii + 1], feat_ranks[indices[ii]])
