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')
# 予測を実施
pred_df = self.skproc.proc_predict_sk_model(exp_data)
print("End_baoz_predict run: pred_df", pred_df.shape)
import_df = self.skproc.create_import_data(pred_df)
if self.export_mode:
print("export data")
import_df.to_pickle(self.intermediate_folder +
self.skproc.version_str + '/' +
'export_data.pkl')
if self.skproc.version_str == "win":
analyze_df = self.skproc.eval_pred_data(import_df)
print(analyze_df)
self.skproc.import_data(import_df)
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish predict job:" +
self.skproc.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
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")
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start download jrdb file")
with self.output().open("w") as target:
download = JrdbDownload()
download.procedure_download()
download.move_file()
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")
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start predict job:" + self.skproc.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.skproc.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):
# 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")
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start Sub_create_feature_select_data job:" +
self.skproc.version_str)
with self.output().open("w") as target:
file_name = self.intermediate_folder + "_learning.pkl"
with open(file_name, 'rb') as f:
learning_df = pickle.load(f)
learning_df = self.skproc.merge_learning_df(learning_df)
self.skproc.create_featrue_select_data(learning_df)
Output.post_slack_text(
dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish Sub_create_feature_select_data job:" +
self.skproc.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")
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start Sub_get_learning_data job:" +
self.skproc.version_str)
with self.output().open("w") as target:
print("------ learning_dfを作成")
self.skproc.set_learning_df()
print("------ 学習用データを保存")
self.skproc.learning_df.to_pickle(self.intermediate_folder +
'_learning.pkl')
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish Sub_get_learning_data job:" +
self.skproc.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")
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" start End_baoz_learning job:" +
self.skproc.version_str)
with self.output().open("w") as target:
file_name = self.intermediate_folder + "_learning.pkl"
with open(file_name, 'rb') as f:
df = pickle.load(f)
# 学習を実施
df = self.skproc.merge_learning_df(df)
self.skproc.proc_learning_sk_model(df)
Output.post_slack_text(dt.now().strftime("%Y/%m/%d %H:%M:%S") +
" finish End_baoz_learning job:" +
self.skproc.version_str)
print(__class__.__name__ +
" says: task finished".format(task=self.__class__.__name__))
from modules.report import Report
from modules.output import Output
from modules.import_to_cosmosdb import Import_to_CosmosDB
from datetime import datetime as dt
from datetime import timedelta
n = 0
start_date = (dt.now() + timedelta(days=n)).strftime('%Y/%m/%d')
end_date = (dt.now() + timedelta(days=n)).strftime('%Y/%m/%d')
mock_flag = False
output = Output()
rep = Report(start_date, end_date, mock_flag)
post_text = ''
now_time = dt.now()
def export_to_dropbox():
start_date = dt.now().strftime('%Y/%m') + '/01'
end_date = dt.now().strftime('%Y/%m/%d')
rep = Report(start_date, end_date, mock_flag)
rep.export_bet_df()
rep.export_race_df()
rep.export_raceuma_df()
current_text = rep.get_current_text()
if rep.check_flag:
bet_text = rep.get_todays_bet_text()
post_text += current_text
def run(self):
print("---" + __class__.__name__ + ": run")
with self.output().open("w") as target:
target_sr = pd.read_pickle(self.dict_path +
'model/kaime/target_sr.pkl')
cond_df = pd.read_pickle(self.dict_path +
'model/kaime/cond_df.pkl')
to = Output(self.start_date, self.end_date, self.term_start_date,
self.term_end_date, self.test_flag, target_sr, cond_df)
to.set_pred_df()
to.set_result_df()
to.create_raceuma_score_file()
to.create_main_mark_file()
to.create_raceuma_mark_file()
to.create_result_race_comment_file()
to.create_result_raceuma_comment_file()
to.create_target_mark_df()
to.create_vote_file()
to.create_pbi_file()
to.create_pbi_result_file()
if args.pdbs:
pdbs = args.pdbs
if args.depth_files:
depth_files = args.depth_files
if args.out:
out = args.out[0]
exp_list = Reference(referee).get_residues()
#obtain models from input and run scoring.
#scores collected in models dictionary
models = {}
if pdbs and not depth_files:
for pdb in pdbs:
depth = Depth(pdb, None, depth_path)
models[pdb.split('.pdb')[0]] = Score(depth, exp_list).score_mono()
elif depth_files:
for depth_file in depth_files:
depth = Depth(None, depth_file, depth_path)
models[depth_file.split('-residue.depth')[0]] = Score(
depth, exp_list).score_mono()
else:
print("Please specify pdbs or depth files, use -h flag for help.")
sys.exit()
Output(models, out)