def gradient_boosting_classify(my_train_data, my_train_label, my_test_data, estimators):
clf = GradientBoostingClassifier(n_estimators=estimators)
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("gradient boosting(%d) accuracy: %0.3f (+/- %0.3f)" % (estimators, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "gradient_boosting_%d.csv" % estimators
data_storer.save_data(my_test_label, file_name)
def multinomial_nb_classify(my_train_data, my_train_label, my_test_data):
clf = MultinomialNB(alpha=0.1)
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("multinomial native bayes accuracy: %0.3f (+/- %0.3f)" % (scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "multinomial_nb.csv"
data_storer.save_data(my_test_label, file_name)
def random_forest_classify(my_train_data, my_train_label, my_test_data, estimators):
clf = RandomForestClassifier(n_estimators=estimators)
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("random forest(%d) accuracy: %0.3f (+/- %0.3f)" % (estimators, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "random_forest_%d.csv" % estimators
data_storer.save_data(my_test_label, file_name)
def knn_classify(my_train_data, my_train_label, my_test_data, neighbors):
clf = KNeighborsClassifier(n_neighbors=neighbors)
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("knn(%d) accuracy: %0.3f (+/- %0.3f)" % (neighbors, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "knn_%d.csv" % neighbors
data_storer.save_data(my_test_label, file_name)
def gaussian_nb_classify(my_train_data, my_train_label, my_test_data):
clf = GaussianNB()
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("Gaussian native bayes accuracy: %0.3f (+/- %0.3f)" % (scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "gaussian_nb.csv"
data_storer.save_data(my_test_label, file_name)
def svc_classify(my_train_data, my_train_label, my_test_data, svc_c):
# clf = svm.SVC(C=svc_c, kernel='poly')
clf = svm.SVC(C=svc_c)
scores = cross_validation.cross_val_score(clf, my_train_data, my_train_label, cv=5)
print("svc(C=%.1f) accuracy: %0.3f (+/- %0.3f)" % (svc_c, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "svc_%.1f.csv" % svc_c
data_storer.save_data(my_test_label, file_name)
def multinomial_nb_classify(my_train_data, my_train_label, my_test_data):
clf = MultinomialNB(alpha=0.1)
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("multinomial native bayes accuracy: %0.3f (+/- %0.3f)" %
(scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "multinomial_nb.csv"
data_storer.save_data(my_test_label, file_name)
def gaussian_nb_classify(my_train_data, my_train_label, my_test_data):
clf = GaussianNB()
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("Gaussian native bayes accuracy: %0.3f (+/- %0.3f)" %
(scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "gaussian_nb.csv"
data_storer.save_data(my_test_label, file_name)
def knn_classify(my_train_data, my_train_label, my_test_data, neighbors):
clf = KNeighborsClassifier(n_neighbors=neighbors)
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("knn(%d) accuracy: %0.3f (+/- %0.3f)" %
(neighbors, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "knn_%d.csv" % neighbors
data_storer.save_data(my_test_label, file_name)
def gradient_boosting_classify(my_train_data, my_train_label, my_test_data,
estimators):
clf = GradientBoostingClassifier(n_estimators=estimators)
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("gradient boosting(%d) accuracy: %0.3f (+/- %0.3f)" %
(estimators, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "gradient_boosting_%d.csv" % estimators
data_storer.save_data(my_test_label, file_name)
def random_forest_classify(my_train_data, my_train_label, my_test_data,
estimators):
clf = RandomForestClassifier(n_estimators=estimators)
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("random forest(%d) accuracy: %0.3f (+/- %0.3f)" %
(estimators, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "random_forest_%d.csv" % estimators
data_storer.save_data(my_test_label, file_name)
def svc_classify(my_train_data, my_train_label, my_test_data, svc_c):
# clf = svm.SVC(C=svc_c, kernel='poly')
clf = svm.SVC(C=svc_c)
scores = cross_validation.cross_val_score(clf,
my_train_data,
my_train_label,
cv=5)
print("svc(C=%.1f) accuracy: %0.3f (+/- %0.3f)" %
(svc_c, scores.mean(), scores.std() * 2))
clf.fit(my_train_data, my_train_label)
my_test_label = clf.predict(my_test_data)
file_name = "svc_%.1f.csv" % svc_c
data_storer.save_data(my_test_label, file_name)
