def my_test():
compress.empty_folder(os.path.join(setting.data_path, 'trainWeek'))
compress.empty_folder(os.path.join(setting.data_path, 'predictWeek'))
train_week = get_train_week()
pre_week = get_pre_week()
train_pool = potThread.PotThread(2)
train_pool.run_pot_threads(merge_train_week, train_week)
pre_pool = potThread.PotThread(2)
pre_pool.run_pot_threads(merge_pre_week, pre_week)
def test():
compress.empty_folder(os.path.join(setting.data_path, 'trainMonth'))
compress.empty_folder(os.path.join(setting.data_path, 'predictMonth'))
train_month = get_train_month()
print(train_month)
pre_month = get_pre_month()
print(pre_month)
train_pool = potThread.PotThread(2)
train_pool.run_pot_threads(merge_train_month, train_month)
pre_pool = potThread.PotThread(2)
pre_pool.run_pot_threads(merge_pre_month, pre_month)
def build_feature(df):
start_day = week_extract.get_min_month()
df_train = df[(df['date'] >= start_day)
& (df['date'] < timeOpt.add_months(start_day, 2))]
df_pre = df[(df['date'] >= timeOpt.add_months(start_day, 1))
& (df['date'] < timeOpt.add_months(start_day, 3))]
df_for_churn = set(df[(df['date'] >= timeOpt.add_months(start_day, 2))
& (df['date'] < timeOpt.add_months(start_day, 3))]
['esn'].astype('str').values)
compress.empty_folder(setting.model_path)
train_result_df = build(df_train, df_for_churn, TRAIN)
train_result_df.to_csv(os.path.join(setting.model_path, r"trainData.csv"),
index=False)
pre_result_df = build(df_pre, df_for_churn, PREDICT)
pre_result_df[(pre_result_df['churnLabel'] < 1)].to_csv(os.path.join(
setting.model_path, r"predictData.csv"),
index=False)
return 0
def get_xgboost_predict_result():
pot_xgboost = PotXGBoost()
data = pd.read_csv(os.path.join(setting.model_path, 'trainData.csv'),
error_bad_lines=False,
index_col=False)
pre = pd.read_csv(os.path.join(setting.model_path, 'predictData.csv'),
error_bad_lines=False,
index_col=False)
data = data[setting.parameter_json["train_pre_columns"]]
pre = pre[setting.parameter_json["train_pre_columns"]]
is_use_rsrp = setting.load_parameter()['use_rsrp_sinr']
if not is_use_rsrp.lower() == 'true':
data = data.drop(setting.rsrp_sinr_columns, axis=1)
pre = pre.drop(setting.rsrp_sinr_columns, axis=1)
pot_xgboost.train(data)
pot_xgboost.predict(pre)
compress.empty_folder(setting.result_path)
pot_xgboost.pre_result.to_csv(
os.path.join(setting.result_path, 'predict_result.csv'))
importance_df = json_to_df(pot_xgboost.features_importance)
importance_df.to_csv(
os.path.join(setting.result_path, 'features_importance.csv'))
def cpe_analysis(self, status):
try:
uiThread.UiThread(self.check_health)
if status[0] == 3:
self.import_cpe_thread()
self.xg_pre()
elif status[0] == 2:
compress.empty_folder(setting.post_eva_path)
self.import_with_suite_thread()
self.xg_pre()
post_evaluate.main(True)
compress.compress_result()
self.analysis_button['state'] = NORMAL
self.export_button['state'] = NORMAL
self.show_log(timeOpt.get_time() +
": click Export button to export the data.")
self.THREAD_FLAG = False
except Exception as e:
self.THREAD_FLAG = False
self.show_log(timeOpt.get_time() + ": Analysis failed!\n" + str(e))
tk.messagebox.showerror("ERROR",
message='Analysis failed!\n' + str(e))
self.analysis_button['state'] = NORMAL
self.export_button['state'] = NORMAL
def day_extract():
compress.empty_folder(os.path.join(setting.data_path, 'day'))
day_dict = get_day_df_dict()
merge_day_data(day_dict)
def get_extract_data():
compress.empty_folder(os.path.join(setting.data_path, 'extractData'))
all_file = compress.get_all_csv_file(compress.cpe_unzip_path)
return all_file
def copy_data(self, source, path):
compress.empty_folder(path)
self.copy_file(source, path)