Delete function

function/dr_prediction_deployment.py

@@ -1,119 +0,0 @@
-import sys
-import json
-import requests
-
-class DataRobotPredictionError(Exception):
-    """Raised if there are issues getting predictions from DataRobot"""
-
-
-def make_datarobot_deployment_predictions(data, deployment_id):
-    """
-    Make predictions on data provided using DataRobot deployment_id provided.
-    See docs for details:
-         https://app.datarobot.com/docs-jp/predictions/api/dr-predapi.html
-
-    Parameters
-    ----------
-    data : str
-        If using CSV as input:
-        Feature1,Feature2
-        numeric_value,string
-
-        Or if using JSON as input:
-        [{"Feature1":numeric_value,"Feature2":"string"}]
-
-    deployment_id : str
-        The ID of the deployment to make predictions with.
-
-    Returns
-    -------
-    Response schema:
-        https://app.datarobot.com/docs-jp/predictions/api/dr-predapi.html#response-schema
-
-    Raises
-    ------
-    DataRobotPredictionError if there are issues getting predictions from DataRobot
-    """
-    # Set HTTP headers. The charset should match the contents of the file.
-    headers = {
-        # As default, we expect CSV as input data.
-        # Should you wish to supply JSON instead,
-        # comment out the line below and use the line after that instead:
-        'Content-Type': 'text/plain; charset=UTF-8',
-        # 'Content-Type': 'application/json; charset=UTF-8',
-
-        'Authorization': 'Bearer {}'.format('NjQwMDVmNGI0ZDQzZDFhYzI2YThmZDJiOnVZejljTXFNTXNoUnlKMStoUFhXSFdYMEZRck9lY3dobnEvRFZ1aVBHbVE9'),
-        'DataRobot-Key': '84f96e49-d400-ec9c-92fc-30fc6e9329d1',
-    }
-    API_URL = 'https://jppdemo.orm.datarobot.com/predApi/v1.0/deployments/{deployment_id}/predictions'
-    url = API_URL.format(deployment_id=deployment_id)
-
-    # Prediction Explanations:
-    # See the documentation for more information:
-    # https://app.datarobot.com/docs-jp/predictions/api/dr-predapi.html#request-pred-explanations
-    # Should you wish to include Prediction Explanations or Prediction Warnings in the result,
-    # Change the parameters below accordingly, and remove the comment from the params field below:
-
-    params = {
-        # If explanations are required, uncomment the line below
-        # 'maxExplanations': 3,
-        # 'thresholdHigh': 0.5,
-        # 'thresholdLow': 0.15,
-        # If text explanations are required, uncomment the line below.
-        # 'maxNgramExplanations': 'all',
-        # Uncomment this for Prediction Warnings, if enabled for your deployment.
-        # 'predictionWarningEnabled': 'true',
-    }
-    # Make API request for predictions
-    predictions_response = requests.post(
-        url,
-        data=data,
-        headers=headers,
-        # Prediction Explanations:
-        # Uncomment this to include explanations in your prediction
-        # params=params,
-    )
-    _raise_dataroboterror_for_status(predictions_response)
-    # Return a Python dict following the schema in the documentation
-    return predictions_response.json()
-
-
-def _raise_dataroboterror_for_status(response):
-    """Raise DataRobotPredictionError if the request fails along with the response returned"""
-    try:
-        response.raise_for_status()
-    except requests.exceptions.HTTPError:
-        err_msg = '{code} Error: {msg}'.format(
-            code=response.status_code, msg=response.text)
-        raise DataRobotPredictionError(err_msg)
-
-
-def main(filename, deployment_id):
-    """
-    Return an exit code on script completion or error. Codes > 0 are errors to the shell.
-    Also useful as a usage demonstration of
-    `make_datarobot_deployment_predictions(data, deployment_id)`
-    """
-    MAX_PREDICTION_FILE_SIZE_BYTES = 52428800  # 50 MB
-    if not filename:
-        print(
-            'Input file is required argument. '
-            'Usage: python datarobot-predict.py <input-file.csv>')
-        return 1
-    data = open(filename, 'rb').read()
-    data_size = sys.getsizeof(data)
-    if data_size >= MAX_PREDICTION_FILE_SIZE_BYTES:
-        print((
-            'Input file is too large: {} bytes. '
-            'Max allowed size is: {} bytes.'
-        ).format(data_size, MAX_PREDICTION_FILE_SIZE_BYTES))
-        return 1
-    try:
-        predictions = make_datarobot_deployment_predictions(data, deployment_id)
-    except DataRobotPredictionError as exc:
-        print(exc)
-        return 1
-    return predictions
-
-# def prediction_formatting_to_dataframe(prediction_json):
-#     prediction_df = pd.jason_normalize(prediction_json)[['rowId'

function/get_estat.py

@@ -1,31 +0,0 @@
-import pandas as pd
-import datetime
-
-
-def get_household_survey():
-    # e-Statにユーザー登録し、APIキーを取得しておくこと
-    # URL: https://www.e-stat.go.jp/api/
-    API_KEY = "ddc1349cf530bdee69ca6a7ad6c0e2301aeb0780"
-
-    # 取得年月の設定
-    latest_year = int(datetime.datetime.now().strftime('%Y'))
-    year_period = 5
-    years = list(range(latest_year, latest_year - year_period, -1))
-    months = range(1, 13)
-    periods = []
-    for y in years:
-        y = y * 1_000_000
-        for m in months:
-            ym = y + m * 100 + m
-            periods.append(str(ym))
-    periods = ("%2C").join(periods)
-
-    # データ取得
-    url = f"http://api.e-stat.go.jp/rest/3.0/app/getSimpleStatsData?cdTab=01&cdCat02=03&cdArea=00000&cdTime={periods}&appId={API_KEY}&lang=J&statsDataId=0003343671&metaGetFlg=Y&cntGetFlg=N&explanationGetFlg=Y&annotationGetFlg=Y&sectionHeaderFlg=1&replaceSpChars=0"
-    df = pd.read_csv(url, header=28)
-    return df
-
-
-if __name__ == "__main__":
-    df = get_household_survey()
-    df.to_csv("household_survey.csv", index=False)

function/get_fish_qty.py

@@ -1,107 +0,0 @@
-import codecs
-import io
-import random
-import requests
-import time
-from datetime import date, timedelta
-from tqdm import tqdm
-from typing import Generator, Tuple
-
-import numpy as np
-import pandas as pd
-
-
-def date_range(
-    start: date, stop: date, step: timedelta = timedelta(1)
-) -> Generator[date, None, None]:
-    """startからendまで日付をstep日ずつループさせるジェネレータ"""
-    current = start
-    while current < stop:
-        yield current
-        current += step
-
-
-def get_url(download_date: date) -> Tuple[str, str]:
-    """ダウンロードするURLと日付の文字列を返す"""
-    month = download_date.strftime("%Y%m")
-    day = download_date.strftime("%Y%m%d")
-    return (
-        f"https://www.shijou-nippo.metro.tokyo.lg.jp/SN/{month}/{day}/Sui/Sui_K1.csv",
-        day,
-    )
-
-
-def content_wrap(content):
-    """1行目にヘッダ行が来るまでスキップする"""
-    buffer = ""
-    first = True
-    for line in io.BytesIO(content):
-        line_str = codecs.decode(line, "shift-jis")
-        if first:
-            if "品名" in line_str:
-                first = False
-                buffer = line_str
-            else:
-                continue
-        else:
-            buffer += line_str
-    return io.StringIO(buffer)
-
-
-def to_numeric(x):
-    """文字列を数値に変換する"""
-    if isinstance(x, str):
-        return float(x)
-    else:
-        return x
-
-
-def get_fish_price_data(start_date: date, end_date: date, use_fish_list) -> pd.core.frame.DataFrame:
-    """
-    東京卸売市場からデータを引っ張ってくる
-
-    :param start_date: 開始日
-    :param end_date: 終了日
-    :return: あじの値段を結合したデータ
-    """
-    columns = ['date'] + [i + '_卸売数量計(kg)' for i in use_fish_list] + ['全卸売数量計(kg)']
-    fish_qty_df = pd.DataFrame(columns=columns)
-    
-    iterator = tqdm(
-        date_range(start_date, end_date), total=(end_date - start_date).days
-    )
-
-    for download_date in iterator:
-        url, day = get_url(download_date)
-        iterator.set_description(day)
-        response = requests.get(url)
-
-        # URLが存在しないとき
-        temp_df = pd.DataFrame([{'date':day}])
-        if response.status_code == 404:
-            continue
-        assert (
-            response.status_code == 200
-        ), f"Unexpected HTTP response. Please check the website {url}."
-
-        df = pd.read_csv(content_wrap(response.content))
-        
-        
-        for i in use_fish_list:
-            temp = df.loc[df["品名"] == i, ['卸売数量計']]
-            
-            # display(temp)
-            
-            if len(temp) == 0:
-                temp_df[f'{i}_卸売数量計(kg)'] = 0
-            
-            
-            temp_df[f'{i}_卸売数量計(kg)'] = temp['卸売数量計'].sum()
-        
-        all_qty = df[['卸売数量計']].dropna().values[-1][0]
-        
-        temp_df['全卸売数量計(kg)'] = all_qty
-                
-        fish_qty_df = pd.concat([fish_qty_df, temp_df])
-        time.sleep(max(0.5 + random.normalvariate(0, 0.3), 0.1))
-    return fish_qty_df

function/prediction_func.py

@@ -1,119 +0,0 @@
-import pandas as pd
-import numpy as np
-import gradio as gr
-import datetime
-from dateutil.relativedelta import relativedelta
-from function import get_fish_qty, get_estat, dr_prediction_deployment
-
-import yaml
-with open('config/config.yaml') as file:
-    config = yaml.safe_load(file.read())
-
-def create_prediction_data(fish_sell_ach, oil_price_url, fuel_procurement_cost_url):
-    oil_price_df = pd.read_excel(oil_price_url, header=5)
-    oil_price_df = oil_price_df.rename(columns={oil_price_df.columns[0]:'年'})
-    oil_price_df['年'] = oil_price_df['年'].interpolate(method='ffill')
-    oil_price_df['年月'] = oil_price_df['年'] + oil_price_df['月'].astype(str) + '月'
-    oil_price_df['年月'] = pd.to_datetime(oil_price_df['年月'], format='%Y年%m月')
-    oil_price_df['年月'] = oil_price_df['年月'].apply(lambda x:x+relativedelta(months=3))
-    oil_price_df['年月'] = oil_price_df['年月'].apply(lambda x:''.join(str(x).split('-'))[:6]).astype(int)
-    oil_price_df = oil_price_df.drop(['年', '月'], axis=1)
-    for i in oil_price_df.columns:
-        if i != '年月':
-            oil_price_df = oil_price_df.rename(columns={i:f'{i}_lag3'})
-            oil_price_df[f'{i}_lag3'] = oil_price_df[f'{i}_lag3'].shift(1)
-    
-    fuel_procurement_cost_df = pd.read_excel(fuel_procurement_cost_url, header=4)
-    fuel_procurement_cost_df = fuel_procurement_cost_df.iloc[:, 3:]
-    for i in fuel_procurement_cost_df.columns:
-        if '\n' in i:
-            fuel_procurement_cost_df = fuel_procurement_cost_df.rename(columns={i:i.replace('\n', '')})
-
-    fuel_procurement_cost_df['燃料費調整単価適用期間'] = fuel_procurement_cost_df['燃料費調整単価適用期間'].interpolate(method='ffill')
-    fuel_procurement_cost_df['燃料費調整単価適用期間'] = pd.to_datetime(fuel_procurement_cost_df['燃料費調整単価適用期間'],
-                                                             format='%Y年\n%m月').astype(str).apply(lambda x:''.join(x.split('-'))[:6]).astype(int)
-    
-    col_list=['するめいか_卸売数量計(kg)',
-         'いわし_卸売数量計(kg)',
-         'ぶり・わらさ_卸売数量計(kg)',
-         '冷さけ_卸売数量計(kg)', 
-         '塩さけ_卸売数量計(kg)',
-         'さけます類_卸売数量計(kg)',
-         '全卸売数量計(kg)']
-    
-    for shift_i in [7, 14, 21, 28]:
-        change_col_list = [f'{i}_lag{shift_i}' for i in col_list]
-        fish_sell_ach[change_col_list] = fish_sell_ach[col_list].shift(shift_i)
-    
-    fish_sell_ach['target_date'] = fish_sell_ach['date'].apply(lambda x:int((pd.to_datetime(str(x))+relativedelta(months=1)).strftime('%Y%m%d')))
-    fish_sell_ach['年月'] = fish_sell_ach['target_date'].astype(str).str[:6].astype(int)
-    
-    prediction_df = pd.merge(fish_sell_ach, 
-                         oil_price_df,
-                         on='年月',
-                         how='left')
-    
-    for kind in fuel_procurement_cost_df['種別'].unique():
-        temp_df = fuel_procurement_cost_df.loc[fuel_procurement_cost_df['種別']==kind].drop('種別', axis=1)
-        temp_df = temp_df.rename(columns={temp_df.columns[0]:'年月'})
-        for i in temp_df.columns:
-            if i != '年月':
-                temp_df = temp_df.rename(columns={i:f'{i}_{kind}_lag1'})
-                temp_df['年月'] = pd.to_datetime(temp_df['年月'], format='%Y%m')
-                temp_df['年月'] = temp_df['年月'].apply(lambda x:x+relativedelta(months=1))
-                temp_df['年月'] = temp_df['年月'].apply(lambda x:''.join(str(x).split('-'))[:6]).astype(int)
-        prediction_df = pd.merge(prediction_df,
-                                 temp_df,
-                                 on='年月')
-    prediction_df = prediction_df.rename(columns={'date':'forecast_point'})
-    
-    return prediction_df
-
-def prediction_to_dr(oil_price_url, fuel_procurement_cost_url):
-    today = datetime.datetime.now()
-    last_prediction_result = pd.read_csv('data/prediction_result.csv')
-    last_time_fish_arch = pd.read_csv('data/fish_sell_ach.csv')
-    if (str(last_prediction_result['forecast_point'].max()) == today.strftime('%Y%m%d'))|(str(last_time_fish_arch['date'].max()) == int(today.strftime('%Y%m%d'))):
-        pass
-
-    else:
-        start_date = pd.to_datetime(str(last_time_fish_arch['date'].max()))
-        end_date = pd.to_datetime(today + relativedelta(days=1))
-        use_fish_list = config['use_fish_list']
-        temp_sell_ach = get_fish_qty.get_fish_price_data(start_date, end_date, use_fish_list)
-        temp_sell_ach['date'] = temp_sell_ach['date'].astype(int)
-        if str(temp_sell_ach['date'].max()) != today.strftime('%Y%m%d'):
-            pass
-
-        else:
-            temp_sell_ach = pd.concat([last_time_fish_arch,
-                                       temp_sell_ach.loc[~temp_sell_ach['date'].isin(last_time_fish_arch['date'].unique())]])
-            temp_sell_ach.to_csv('data/fish_sell_ach.csv', index=False)
-            prediction_df = create_prediction_data(temp_sell_ach, 
-                                              oil_price_url,
-                                              fuel_procurement_cost_url)
-            prediction_df = prediction_df.loc[(prediction_df['forecast_point'].astype(int)>last_prediction_result['forecast_point'].max())
-                                              &
-                                              (prediction_df['forecast_point'].astype(int)<=int(today.strftime('%Y%m%d')))].reset_index(drop=True)
-
-            display(prediction_df)
-            DEPLOYMENT_ID = '640d791796a6a52d92c368a0'
-            prediction_df.to_csv('data/temp_prediction.csv', index=False)
-            prediction_json = dr_prediction_deployment.main('data/temp_prediction.csv', DEPLOYMENT_ID)
-
-            prediction_result = pd.DataFrame({ 
-                                                'target_date':prediction_df['target_date'],
-                                                'forecast_point':prediction_df['forecast_point'],
-                                                '電気代':pd.json_normalize(prediction_json['data'])['prediction']
-                                            })
-
-            prediction_result = pd.merge(prediction_df,
-                                 prediction_result,
-                                 on=['target_date', 'forecast_point'])
-
-            last_prediction_result = pd.concat([last_prediction_result,
-                                                prediction_result])
-
-            last_prediction_result.to_csv('data/prediction_result.csv', index=False)
-            
-    return last_prediction_result

function/train_modeling.py

@@ -1,221 +0,0 @@
-import pandas as pd
-import numpy as np
-import gradio as gr
-import datetime
-from dateutil.relativedelta import relativedelta
-import datarobot as dr
-from function import get_fish_qty, get_estat, dr_prediction_deployment
-
-import yaml
-with open('config/config.yaml') as file:
-    config = yaml.safe_load(file.read())
-
-def create_train_data():
-    # ターゲットを抽出
-    household_survey = get_estat.get_household_survey()
-    expence_df = pd.DataFrame({'年月':household_survey['時間軸（月次）'].unique()})
-    cate='3.1 電気代'
-    temp_df = household_survey.loc[household_survey['品目分類（2020年改定）'] == cate]
-    unit = temp_df['unit'].unique()[0]
-    temp_df = temp_df.rename(columns={'value':f'{cate}_({unit})'})
-    expence_df = pd.merge(expence_df,
-                          temp_df[['時間軸（月次）', f'{cate}_({unit})']].rename(columns={'時間軸（月次）':'年月'}),
-                          on='年月',
-                          how='left')
-    expence_df = expence_df.rename(columns={'3.1 電気代_(円)':'電気代'})
-    expence_df['年月'] = pd.to_datetime(expence_df['年月'], format='%Y年%m月').astype(str).apply(lambda x:''.join(x.split('-'))[:6]).astype(int)
-    
-    # 原油価格を抽出し作成
-    oil_price_df = pd.read_excel(config['oil_price_url'], header=5)
-    oil_price_df = oil_price_df.rename(columns={oil_price_df.columns[0]:'年'})
-    oil_price_df['年'] = oil_price_df['年'].interpolate(method='ffill')
-    oil_price_df['年月'] = oil_price_df['年'] + oil_price_df['月'].astype(str) + '月'
-    oil_price_df['年月'] = pd.to_datetime(oil_price_df['年月'], format='%Y年%m月').astype(str).apply(lambda x:''.join(x.split('-'))[:6]).astype(int)
-    
-    # 燃料調達価格のデータを作成
-    fuel_procurement_cost_df = pd.read_excel(config['fuel_procurement_cost_url'], header=4)
-    fuel_procurement_cost_df = fuel_procurement_cost_df.iloc[:, 3:]
-    for i in fuel_procurement_cost_df.columns:
-        if '\n' in i:
-            fuel_procurement_cost_df = fuel_procurement_cost_df.rename(columns={i:i.replace('\n', '')})
-
-    fuel_procurement_cost_df['燃料費調整単価適用期間'] = fuel_procurement_cost_df['燃料費調整単価適用期間'].interpolate(method='ffill')
-    fuel_procurement_cost_df['燃料費調整単価適用期間'] = pd.to_datetime(fuel_procurement_cost_df['燃料費調整単価適用期間'],
-                                                             format='%Y年\n%m月').astype(str).apply(lambda x:''.join(x.split('-'))[:6]).astype(int)
-    for kind in fuel_procurement_cost_df['種別'].unique():
-        temp_df = fuel_procurement_cost_df.loc[fuel_procurement_cost_df['種別']==kind].drop('種別', axis=1)
-        temp_df = temp_df.rename(columns={temp_df.columns[0]:'年月'})
-        for i in temp_df.columns:
-            if i != '年月':
-                temp_df = temp_df.rename(columns={i:f'{i}_{kind}_lag1'})
-                temp_df[f'{i}_{kind}_lag1'] = temp_df[f'{i}_{kind}_lag1'].shift(1)
-        expence_df = pd.merge(expence_df,
-                              temp_df,
-                              on='年月',
-                              how='left')
-        
-    # 各データを結合
-    oil_price_df[['ブレント_lag3', 'ドバイ_lag3', 'WTI_lag3', 'OPECバスケット_lag3']] = oil_price_df[['ブレント', 'ドバイ', 'WTI', 'OPECバスケット']].shift(3)
-    expence_df = pd.merge(expence_df,
-                          oil_price_df[['ブレント_lag3', 'ドバイ_lag3', 'WTI_lag3', 'OPECバスケット_lag3', '年月']],
-                          on='年月',
-                          how='left')
-    
-    # 魚の卸売りデータを読み込み
-    last_time_fish_arch = pd.read_csv('data/fish_sell_ach.csv')
-    start_date = pd.to_datetime(str(int(last_time_fish_arch['date'].max())))
-    today = datetime.datetime.now()
-    end_date = pd.to_datetime(today + relativedelta(days=1))
-    use_fish_list = config['use_fish_list']
-    temp_sell_ach = get_fish_qty.get_fish_price_data(start_date, end_date, use_fish_list)
-    temp_sell_ach['date'] = temp_sell_ach['date'].astype(int)
-    sell_ach = pd.concat([last_time_fish_arch,
-                                              temp_sell_ach.loc[~temp_sell_ach['date'].isin(last_time_fish_arch['date'].unique())]])
-    sell_ach.to_csv('data/fish_sell_ach.csv', index=False)
-    
-    # trainデータの作成
-    sell_ach['target_date'] = sell_ach['date'].apply(lambda x:int((pd.to_datetime(str(x))+relativedelta(months=1)).strftime('%Y%m%d')))
-    sell_ach['年月'] = sell_ach['target_date'].astype(str).str[:6].astype(int)
-    
-    col_list=['するめいか_卸売数量計(kg)',
-                 'いわし_卸売数量計(kg)',
-                 'ぶり・わらさ_卸売数量計(kg)',
-                 '冷さけ_卸売数量計(kg)', 
-                 '塩さけ_卸売数量計(kg)',
-                 'さけます類_卸売数量計(kg)',
-                 '全卸売数量計(kg)']
-    
-    for shift_i in [7, 14, 21, 28]:
-        change_col_list = [f'{i}_lag{shift_i}' for i in col_list]
-        sell_ach[change_col_list] = sell_ach[col_list].shift(shift_i)
-    
-    sell_ach = sell_ach.rename(columns={'date':'forecast_point'})
-    train_df = pd.merge(expence_df, 
-                        sell_ach,
-                        on='年月')
-    train_df.to_csv('data/train.csv', index=False)
-    
-    return train_df
-
-
-def modeling():
-    train_df = create_train_data()
-    # モデリングに必要な各設定値
-    ## データロボットとの接続設定
-    token = 'NjQwMDVmNGI0ZDQzZDFhYzI2YThmZDJiOnVZejljTXFNTXNoUnlKMStoUFhXSFdYMEZRck9lY3dobnEvRFZ1aVBHbVE9'
-    ### デモ環境これっぽい
-    endpoint = 'https://app.datarobot.com/api/v2' 
-
-    ## プロジェクト名
-    project_name = f'{datetime.datetime.now().strftime("%Y%m%d")}_ESTYLEU_電気代予測_再学習'
-
-    ## 各種設定
-    ### 特徴量設定
-    target = '電気代'
-    feature_timeline = 'target_date'    #時系列
-    not_use_feature = ['年月', 'forecast_point']
-    # 最適化指標
-    metric = 'RMSE'
-    ### ギャップ
-    gap='P0Y'       #　これで0？要確認
-    ### バックテストの数
-    number_of_backtests = 1
-    end_date = int(train_df[feature_timeline].max())
-    ### 日付
-    holdout_end_date=pd.to_datetime(str(end_date))
-    holdout_start_date=holdout_end_date - relativedelta(years=1)
-    backtest_end_date = holdout_start_date - relativedelta(days=1)
-    backtest_start_date = backtest_end_date - relativedelta(years=1)
-    train_end_date = backtest_start_date - relativedelta(days=1)
-    train_start_date = pd.to_datetime(str(int(train_df[feature_timeline].min())))
-
-    ### モデリングモード
-    # mode = dr.AUTOPILOT_MODE.QUICK
-    mode = dr.AUTOPILOT_MODE.FULL_AUTO
-    dr.Client(
-                    endpoint=endpoint,
-                    token=token
-                )
-
-    # バックテスト設定
-    backtests_setting = [dr.BacktestSpecification(
-                                                                            index=0,
-                                                                            primary_training_start_date=train_start_date, 
-                                                                            primary_training_end_date=train_end_date,
-                                                                            validation_start_date=backtest_start_date, 
-                                                                            validation_end_date=backtest_end_date
-                                                                        )]
-
-    spec = dr.DatetimePartitioningSpecification(
-                                                                        feature_timeline,
-                                                                        use_time_series=False,
-                                                                        disable_holdout=False,
-                                                                        holdout_start_date=holdout_start_date,
-                                                                        holdout_end_date=holdout_end_date,
-                                                                        gap_duration=gap,
-                                                                        number_of_backtests=number_of_backtests,
-                                                                        backtests=backtests_setting,
-                                                                    )
-
-    use_feature_list = train_df.columns.to_list()
-
-    print('now creating project')
-    project = dr.Project.create(
-                                                train_df, 
-                                                project_name=project_name
-                                            )
-
-    raw = [feat_list for feat_list in project.get_featurelists() if feat_list.name == 'Informative Features'][0]
-    raw_features = [feat for feat in raw.features if f'{feature_timeline} ' in feat]
-
-    for i in not_use_feature:
-        if i in use_feature_list:
-            use_feature_list.remove(i)
-
-    use_feature_list = use_feature_list.extend(raw_features)
-    print("start modeling")
-    project.analyze_and_model(
-                                                target = target,
-                                                mode = mode,
-                                                partitioning_method=spec,
-                                                max_wait=3000,
-                                                worker_count=-1,
-                                                featurelist_id = project.create_featurelist('モデリング', use_feature_list).id
-                                            )
-    project.wait_for_autopilot()
-    project.unlock_holdout()
-    
-    model_df = pd.DataFrame(
-        [[model.id,
-          model.model_type,
-          model.metrics['RMSE']['validation'],
-          model.metrics['RMSE']['backtesting'],
-          model.metrics['RMSE']['holdout'],
-          model] for model in project.get_datetime_models() if model.model_type != 'Baseline Predictions Using Most Recent Value'],
-        columns=['ID', 'モデル名', 'バックテスト1', '全てのバックテスト', 'holdout', 'model'])
-    model_df = model_df.sort_values('holdout').reset_index(drop=True)
-    
-    model = model_df['model'][0]
-    
-    try:
-        model_management_df = read_csv('data/model_management.csv')
-    except:
-        model_management_df = pd.DataFrame()
-        
-    temp_model_management_df = pd.DataFrame({
-                                                                           '作成日':[int(datetime.datetime.now().strftime('%Y%m%d'))],
-                                                                           '作成時間':[int(datetime.datetime.now().strftime('%H%M%S'))],
-                                                                           'project_url':[project.get_uri()],
-                                                                           'model_url':[model.get_uri()],
-                                                                           'model_type':[model.model_type]
-                                                                         })
-    
-    model_management_df = pd.concat([model_management_df,
-                                                            temp_model_management_df])
-    model_management_df.to_csv('data/model_management.csv')
-    
-    deployment = dr.Deployment.get(deployment_id='640d791796a6a52d92c368a0')
-    
-    deployment.replace_model(model.id, dr.enums.MODEL_REPLACEMENT_REASON.SCHEDULED_REFRESH)
-    
-