def MNB_test(x, y):
print 'MNB test'
train_x, train_y, test_x, test_y = pp.split_data_set(x, y)
clf = MultinomialNB()
crossvalidation(clf, x, y)
clf.fit(train_x, train_y)
rst = clf.predict(test_x)
print calculate_RMSE(rst, test_y)
print pp.print_mean_median(rst)
def MLR_test(x, y):
print 'MLR test'
train_x, train_y, test_x, test_y = pp.split_data_set(x, y)
clf = LogisticRegression(solver='lbfgs', multi_class='multinomial', C=4)
crossvalidation(clf, x, y)
clf.fit(train_x, train_y)
rst = clf.predict(test_x)
print calculate_RMSE(rst, test_y)
print pp.print_mean_median(rst)
def tree_test(x, y):
print 'DecisionTree'
train_x, train_y, test_x, test_y = pp.split_data_set(x, y)
clf = tree.DecisionTreeClassifier()
crossvalidation(clf, x, y)
clf.fit(train_x, train_y)
rst = clf.predict(test_x)
train_rst = clf.predict(train_x)
print calculate_RMSE(train_rst, train_y)
print calculate_RMSE(rst, test_y)
print pp.print_mean_median(rst)
def random_forest_test(x, y):
print 'RandomForest',
train_x, train_y, test_x, test_y = pp.split_data_set(x, y)
clf = RandomForestClassifier()
crossvalidation(clf, x, y)
clf.fit(train_x, train_y)
rst = clf.predict(test_x)
print rst
print test_y
print calculate_RMSE(rst, test_y)
print 'mean rst: ',
pp.print_mean_median(rst)
def svm_test(x, y):
train_x, train_y, test_x, test_y = pp.split_data_set(x, y)
clf = svm.SVC(C=0.001, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape=None, degree=3, gamma='auto', kernel='linear',
max_iter=-1, probability=False, random_state=None, shrinking=True,
tol=0.001, verbose=False)
print 'fitting: '
crossvalidation(clf, x, y)
clf.fit(train_x, train_y)
print 'predicting: '
rst = clf.predict(test_x)
# print sum(rst == test_y) / len(test_y) * 1.0
print calculate_RMSE(rst, test_y)
pp.print_mean_median(rst)
