# %% Best Hyper-parameters Training
alg = SVD()
alg.biased = Grid_Search_Result.best_params['rmse']['biased']
alg.n_epochs = Grid_Search_Result.best_params['rmse']['n_epochs']
alg.n_factors = Grid_Search_Result.best_params['rmse']['n_factors']
alg.reg_pu = Grid_Search_Result.best_params['rmse']['reg_all']
alg.reg_qi = Grid_Search_Result.best_params['rmse']['reg_all']
alg.lr_pu = Grid_Search_Result.best_params['rmse']['lr_all']
alg.lr_qi = Grid_Search_Result.best_params['rmse']['lr_all']
alg.fit(data_train.build_full_trainset())
# %% Loading Test Data
file_path = "Data/sample_submission.csv"
data_test = utils.load_data_desired(file_path)
# %% Prediction
Predict_Test = []
for line in data_test:
Predict_Test.append(alg.predict(str(line[1]), str(line[0])).est)
# %% Save Prediction
file = open("testfile.csv", "w")
file.write("Id,Prediction\n")
for i in range(len(Predict_Test)):
line = data_test[i]
temp = 'r' + str(line[0]) + '_c' + str(line[1]) + ',' + str(
int(round(Predict_Test[i]))) + '\n'
alg.reg_pu = 0.1
alg.reg_qi = 0.1
alg.verbose = True
start = time.time()
alg.fit(data_train.build_full_trainset())
end = time.time()
print("***********************************************")
print("Exe time:")
print(end - start)
# %% Loading train data
file_path = "Data/data_train.csv"
data_train = utils.load_data_desired(file_path)
# %% Overall Labels for training
Pred_NotCliped_label = []
Real_label = []
Clip = False
for line in data_train:
Real_label.append(line[2])
Pred_NotCliped_label.append(
alg.predict(str(line[1]), str(line[0]), clip=False).est)
Pred_NotCliped_label = np.array(Pred_NotCliped_label)
Real_label = np.array(Real_label)