def predict(train_x, train_y, test_x):
labels = toLabels(train_y)
print('classifying')
# pred_probs=np.genfromtxt(open(dir + '/classify.csv','rb'), delimiter=',')
# print(pred_probs.shape)
labels = Imputer().fit_transform(labels.reshape(-1, 1))
gbc = GradientBoostingClassifier(n_estimators=3000, max_depth=9)
gbc.fit(train_x, labels)
pred_probs = gbc.predict_proba(test_x)[:, 1]
output_classify(pred_probs)
ind_train = np.where(labels > 0.55)[0]
ind_test = np.where(pred_probs > 0.55)[0]
print('gbm regression...')
gbm_predict = gbm_predict_func(train_x[ind_train], train_y[ind_train],
test_x[ind_test])
gbm = np.zeros(len(test_x))
gbm[ind_test] = gbm_predict
np.savetxt("gbr.csv", gbm, delimiter=',')
print('svm regression...')
svm_predict = svm_predict_func(train_x[ind_train], train_y[ind_train],
test_x[ind_test])
svm = np.zeros(len(test_x))
svm[ind_test] = svm_predict
np.savetxt("svr.csv", svm, delimiter=',')
return 0.6 * gbm + 0.4 * svm
def print_evaluation_metrics(trained_model,trained_model_name,X_test,y_test):
print '--------- For Model : ', trained_model_name,' ---------------\n'
predicted_values = trained_model.predict(X_test)
print metrics.classification_report(y_test,predicted_values)
print "Accuracy Score : ",metrics.accuracy_score(y_test,predicted_values)
print "---------------------------------------\n"
order_product_filename = 'order_products__train.csv'
orders_filename = 'orders.csv'
order_product_frame = pd.read_csv(order_product_filename)
order_frame = pd.read_csv(orders_filename)
order_master_frame = pd.merge(order_product_frame,order_frame,how='outer',left_on='order_id',right_on='order_id')
columns_to_drop = ['user_id','eval_set','order_id','reordered']
target_class_labels = order_master_frame['reordered'].values
order_master_frame.drop(columns_to_drop,axis=1,inplace=True)
del order_product_frame
del order_frame
order_master_frame_values = Imputer().fit_transform(order_master_frame.values)
target_class_labels = Imputer().fit_transform(target_class_labels.reshape(-1,1))
target_class_labels = map(lambda x:int(x),target_class_labels)
X_train,X_test,y_train,y_test = train_test_split(order_master_frame_values,target_class_labels,test_size=0.2,random_state=42)
classifier_list, classifier_name_list = get_ensemble_models()
for classifier,classifier_name in zip(classifier_list,classifier_name_list):
classifier.fit(X_train,y_train)
print_evaluation_metrics(classifier,classifier_name,X_test,y_test)