def run(self):
"""
渡されたexp_data_nameに基づいてSK_DATA_MODELから説明変数のデータを取得する処理を実施。pickelファイル形式でデータを保存
"""
print("----" + __class__.__name__ + ": run")
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start predict job:" + self.skmodel.version_str)
with self.output().open("w") as target:
print("------ モデル毎に予測データが違うので指定してデータ作成を実行")
predict_df = self.skmodel.create_predict_data()
print("Sub_get_exp_data run: predict_df", predict_df.shape)
predict_df.to_pickle(self.intermediate_folder +
mu.convert_date_to_str(self.end_date) +
'_exp_data.pkl')
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
"""
| 処理の最後
"""
print("---" + __class__.__name__ + ": run")
with self.output().open("w") as target:
exp_data = pd.read_pickle(self.intermediate_folder +
mu.convert_date_to_str(self.end_date) +
'_exp_data.pkl')
print("------ 分類軸毎の学習モデルを作成")
all_pred_df = pd.DataFrame()
class_list = self.skmodel.class_list
for cls_val in class_list:
print("------ " + cls_val + "毎のデータを抽出して処理を実施")
val_list = self.skmodel.get_val_list(exp_data, cls_val)
for val in val_list:
# 対象の競馬場のデータを取得する
print("=============== cls_val:" + cls_val + " val:" +
val + " ===========================")
filter_df = self.skmodel.get_filter_df(
exp_data, cls_val, val)
# 予測を実施
pred_df = self.skmodel.proc_predict_sk_model(
filter_df, cls_val, val)
all_pred_df = pd.concat([all_pred_df, pred_df])
print("End_baoz_predict run: all_pred_df",
all_pred_df.shape)
import_df = self.skmodel.create_import_data(all_pred_df)
if self.export_mode:
print("export data")
import_df.to_pickle(self.intermediate_folder +
'export_data.pkl')
self.skmodel.eval_pred_data(import_df)
else:
self.skmodel.import_data(import_df)
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish predict job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
"""
| 処理の最後
"""
print("---" + __class__.__name__ + ": run")
with self.output().open("w") as target:
if os.path.exists(self.intermediate_folder +
mu.convert_date_to_str(self.end_date) +
'_exp_data.pkl'):
exp_data = pd.read_pickle(
self.intermediate_folder +
mu.convert_date_to_str(self.end_date) + '_exp_data.pkl')
# 予測を実施して予測結果ファイルを作成
all_df = self.skmodel.proc_predict_sk_model(exp_data)
if self.test_flag:
print("精度チェック")
self.skmodel.eval_pred_data(all_df)
else:
slack = OperationSlack()
slack.post_slack_text(
dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish predict job:" + self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
# 特徴量作成処理を実施。learningの全データ分を取得してSkModel特徴作成処理を実行する
print("---" + __class__.__name__ + ": run")
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start Sub_create_feature_select_data job:" +
self.skmodel.version_str)
with self.output().open("w") as target:
file_name = self.intermediate_folder + "_learning_all.pkl"
with open(file_name, 'rb') as f:
learning_df = pickle.load(f)
self.skmodel.create_featrue_select_data(learning_df)
slack.post_slack_text(
dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish Sub_create_feature_select_data job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
# 目的変数、場コード毎に学習を実施し、学習モデルを作成して中間フォルダに格納する
print("---" + __class__.__name__ + ": run")
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start End_baoz_learning job:" +
self.skmodel.version_str)
self.create_folder()
with self.output().open("w") as target:
print("------ 分類軸毎の学習モデルを作成")
class_list = self.skmodel.class_list
for cls_val in class_list:
print("------ " + cls_val + "毎のデータを抽出して処理を実施")
file_name = self.intermediate_folder + cls_val + "_list.pkl"
created_model_list = [
s for s in os.listdir(self.skmodel.model_folder + 'third/')
if cls_val in s
]
with open(file_name, 'rb') as f:
val_list = pickle.load(f)
for val in val_list:
# 対象の競馬場のデータを取得する
print(" cls_val:" + cls_val + " val:" + val)
created_model_list_val = [
s for s in created_model_list if val in s
]
print(created_model_list_val)
if len(created_model_list_val) == len(
self.skmodel.obj_column_list):
print("\r\n ----- skip create model ---- \r\n")
else:
file_name = self.intermediate_folder + "learning_" + cls_val + "_" + val + ".pkl"
with open(file_name, 'rb') as f:
df = pickle.load(f)
# 学習を実施
self.skmodel.proc_learning_sk_model(
df, cls_val, val)
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish End_baoz_learning job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
# 目的変数毎に学習を実施し、学習モデルを作成して中間フォルダに格納する
print("---" + __class__.__name__ + ": run")
if not self.test_flag:
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start End_baoz_learning job:" +
self.skmodel.version_str)
file_name = self.intermediate_folder + "_learning_df.pkl"
with open(file_name, 'rb') as f:
df = pickle.load(f)
# 学習を実施
self.skmodel.proc_learning_sk_model(df)
if not self.test_flag:
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish End_baoz_learning job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
# SkModelを読んで学習データを作成する。すべてのデータを作成後、競馬場毎のデータを作成する
print("----" + __class__.__name__ + ": run")
mu.create_folder(self.intermediate_folder)
if not self.test_flag:
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start Sub_get_learning_data job:" +
self.skmodel.version_str)
with self.output().open("w") as target:
print("------ learning_dfを作成")
self.skmodel.create_learning_data()
print("------ 学習用のデータを保存")
self.skmodel.learning_df.to_pickle(self.intermediate_folder +
'_learning_df.pkl')
if not self.test_flag:
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish Sub_get_learning_data job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
def run(self):
# SkModelを読んで学習データを作成する。すべてのデータを作成後、競馬場毎のデータを作成する
print("----" + __class__.__name__ + ": run")
slack = OperationSlack()
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start Sub_get_learning_data job:" +
self.skmodel.version_str)
with self.output().open("w") as target:
print("------ learning_dfを作成")
self.skmodel.create_learning_data()
print("------ 分類軸用の列を削除")
save_learning_df = self.skmodel.get_all_learning_df_for_save()
print("------ 学習用の全データを保存")
save_learning_df.to_pickle(self.intermediate_folder +
'_learning_all.pkl')
print("------ 分類軸毎の学習処理を開始")
class_list = self.skmodel.class_list
for cls_val in class_list:
print("------ " + cls_val + "毎のデータを抽出して保存")
val_list = self.skmodel.get_val_list(self.skmodel.learning_df,
cls_val)
val_list.to_pickle(self.intermediate_folder + cls_val +
"_list.pkl")
for val in val_list:
filter_df = self.skmodel.get_filter_df(
self.skmodel.learning_df, cls_val, val)
print("Sub_get_learning_data run: filter_df",
filter_df.shape)
filter_df.to_pickle(self.intermediate_folder +
"learning_" + cls_val + "_" + val +
".pkl")
slack.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish Sub_get_learning_data job:" +
self.skmodel.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))