def train_model(self):
self.log_writer.log(self.file_object, 'Start of Training')
try:
data_getter = data_loader.Data_Getter(self.file_object,
self.log_writer)
main_data, additional_data = data_getter.get_data()
preprocessor = data_preprocessing.PreProcessor(
self.file_object, self.log_writer)
is_null_present = preprocessor.is_null_present(main_data)
if is_null_present == True:
main_data = preprocessor.impute_missing_values(main_data)
main_data = preprocessor.map_ip_to_country(main_data,
additional_data)
main_data = preprocessor.difference_signup_and_purchase(main_data)
main_data = preprocessor.encoding_browser(main_data)
main_data = preprocessor.encoding_source(main_data)
main_data = preprocessor.encoding_sex(main_data)
main_data = preprocessor.count_frequency_encoding_country(
main_data)
main_data = preprocessor.remove_unwanted_cols(main_data)
x, y = preprocessor.separate_label_feature(main_data, 'class')
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.3)
#x_train,y_train = preprocessor.over_sampling_smote(x_train,y_train)
model_finder = tuner.Model_Finder(self.file_object,
self.log_writer)
best_model_name, best_model = model_finder.get_best_model(
x_train, y_train, x_test, y_test)
file_op = file_methods.File_Operation(self.file_object,
self.log_writer)
save_model = file_op.save_model(best_model, best_model_name)
self.log_writer.log(self.file_object,
'Successfull End of Training')
self.file_object.close()
except Exception as e:
self.log_writer.log(self.file_object,
'Unsuccessfull End of Training')
self.file_object.close()
raise e
def predict_from_model(self):
self.log_writer.log(self.file_object, 'Start of Prediction')
try:
self.pred_data_val.deletePredictionFile()
data_getter = data_loader_prediction.Data_Getter(
self.file_object, self.log_writer)
main_data, additional_data = data_getter.get_data()
preprocessor = data_preprocessing.PreProcessor(
self.file_object, self.log_writer)
is_null_present = preprocessor.is_null_present(main_data)
if is_null_present == True:
main_data = preprocessor.impute_missing_values(main_data)
main_data = preprocessor.map_ip_to_country(main_data,
additional_data)
main_data = preprocessor.difference_signup_and_purchase(main_data)
main_data = preprocessor.encoding_browser(main_data)
main_data = preprocessor.encoding_source(main_data)
main_data = preprocessor.encoding_sex(main_data)
main_data = preprocessor.count_frequency_encoding_country(
main_data)
main_data, unwanted_data = preprocessor.remove_unwanted_cols(
main_data, return_unwanted_data=True)
#x,y = preprocessor.separate_label_feature(main_data,'class')
#x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3)
#x_train,y_train = preprocessor.over_sampling_smote(x_train,y_train)
#model_finder = tuner.Model_Finder(self.file_object,self.log_writer)
#best_model_name,best_model = model_finder.get_best_model(x_train,y_train,x_test,y_test)
file_loader = file_methods.File_Operation(self.file_object,
self.log_writer)
#save_model = file_op.save_model(best_model,best_model_name)
model_name = file_loader.find_correct_model_file()
model = file_loader.load_model(model_name)
result = list(model.predict(main_data))
data = list(
zip(unwanted_data['user_id'], unwanted_data['signup_time'],
unwanted_data['purchase_time'], unwanted_data['device_id'],
unwanted_data['source'], unwanted_data['browser'],
unwanted_data['sex'], unwanted_data['ip_address'],
unwanted_data['Country'], result))
result = pd.DataFrame(data,
columns=[
'user_id', 'signup_time',
'purchase_time', 'device_id', 'source',
'browser', 'sex', 'ip_address',
'Country', 'Prediction'
])
path = "Prediction_Output_File/Prediction.csv"
result.to_csv(path, header=True, mode='a+')
self.log_writer.log(self.file_object,
'Successfull End of Prediction')
self.file_object.close()
except Exception as e:
self.log_writer.log(
self.file_object,
'Error Occured while doing the Prediction !! Error :: %s' %
str(e))
self.file_object.close()
raise e
return path, result.head().to_json(orient="records")