Update app.py

app.py

@@ -5,67 +5,71 @@ from math import sqrt
 import pandas as pd
 import numpy as np
 from datetime import datetime
+import matplotlib
+matplotlib.use("Agg")
 import matplotlib.pyplot as plt
-# matplotlib.use("Agg")
-
-# pip install beautifulsoup4
-# pip install requests_html
-import requests
-from bs4 import BeautifulSoup as bs
-from requests_html import AsyncHTMLSession
-
-# Webページを取得して解析する
-load_url = "https://www.football-lab.jp/kyot/match/"
-html = requests.get(load_url)
-soup = bs(html.content, "html.parser")
-
-url23 = 'https://www.football-lab.jp/ka-f/match/'
-dfs23 = pd.read_html(url23)
-url22 = 'https://www.football-lab.jp/ka-f/match/?year=2022'
-dfs22 = pd.read_html(url22)
-url21 = 'https://www.football-lab.jp/ka-f/match/?year=2021'
-dfs21 = pd.read_html(url21)
-url20 = 'https://www.football-lab.jp/ka-f/match/?year=2020'
-dfs20 = pd.read_html(url20)
-
-#シーズン毎に分類
-res23 = pd.DataFrame([['S2023']]*len(dfs23[0])).join(dfs23, lsuffix='0')
-res22 = pd.DataFrame([['S2022']]*len(dfs22[0])).join(dfs22, lsuffix='0')
-res21 = pd.DataFrame([['S2021']]*len(dfs21[0])).join(dfs21, lsuffix='0')
-res20 = pd.DataFrame([['S2020']]*len(dfs20[0])).join(dfs20, lsuffix='0')
-
-df_tmp = pd.concat([res23, res22, res21, res20]) 
-df = df_tmp
-
-df = df.rename(columns={'会場': 'stadium', 0: 'year', '開催日': 'date', '観客数': 'audience'})
-df = df.query('stadium=="等々力"').reset_index()
-df = df.query('audience.notna()', engine='python').reset_index()
-df = df[['audience', 'year', 'date']]
-#seasonカラムから年を抽出
-df["year"] = df["year"].apply(lambda x: str(x)[1:5])
-#開催日から月と日を分割
-df['month']  = df['date'].str.split(pat='.', expand=True)[0]
-df['day'] = df['date'].str.split(pat='.', expand=True)[1]
-#数値データを日付データに変換
-df['date'] = pd.to_datetime({'year': df['year'], 'month': df['month'], 'day': df['day']})
-#日付昇順に並び替える
-df = df.sort_values('date', ascending=True)
-df['date_ymd'] = pd.to_datetime(df['date']).dt.strftime('%Y%m%d')
-df['date_ym'] = pd.to_datetime(df['date']).dt.strftime('%Y%m')
-df["date_ymd"] = df["date_ymd"].astype(int)
-df['date_before'] = df['date_ymd'] - 1
-df["date_before"] = df["date_before"]
-df = df[['audience', 'date_ymd', 'date_before']] 
-df['last_audience'] = df['audience'].shift(1)
-
-df_aji = pd.read_csv('fish_price.csv')
-
-df_train = pd.merge(df, df_aji, left_on='date_before', right_on='date', how='left')
-
-df_train = df_train.query('date > 20201202')
-df_train = df_train.drop(['date_before', 'date_ymd'], axis=1)
-df_train["audience"] = df_train["audience"].str.replace(",", "").astype(int)
-df_train["last_audience"] = df_train["last_audience"].str.replace(",", "").astype(int)
+
+
+# # pip install beautifulsoup4
+# # pip install requests_html
+# import requests
+# from bs4 import BeautifulSoup as bs
+# from requests_html import AsyncHTMLSession
+
+# # Webページを取得して解析する
+# load_url = "https://www.football-lab.jp/kyot/match/"
+# html = requests.get(load_url)
+# soup = bs(html.content, "html.parser")
+
+# url23 = 'https://www.football-lab.jp/ka-f/match/'
+# dfs23 = pd.read_html(url23)
+# url22 = 'https://www.football-lab.jp/ka-f/match/?year=2022'
+# dfs22 = pd.read_html(url22)
+# url21 = 'https://www.football-lab.jp/ka-f/match/?year=2021'
+# dfs21 = pd.read_html(url21)
+# url20 = 'https://www.football-lab.jp/ka-f/match/?year=2020'
+# dfs20 = pd.read_html(url20)
+
+# #シーズン毎に分類
+# res23 = pd.DataFrame([['S2023']]*len(dfs23[0])).join(dfs23, lsuffix='0')
+# res22 = pd.DataFrame([['S2022']]*len(dfs22[0])).join(dfs22, lsuffix='0')
+# res21 = pd.DataFrame([['S2021']]*len(dfs21[0])).join(dfs21, lsuffix='0')
+# res20 = pd.DataFrame([['S2020']]*len(dfs20[0])).join(dfs20, lsuffix='0')
+
+# df_tmp = pd.concat([res23, res22, res21, res20]) 
+# df = df_tmp
+
+# df = df.rename(columns={'会場': 'stadium', 0: 'year', '開催日': 'date', '観客数': 'audience'})
+# df = df.query('stadium=="等々力"').reset_index()
+# df = df.query('audience.notna()', engine='python').reset_index()
+# df = df[['audience', 'year', 'date']]
+# #seasonカラムから年を抽出
+# df["year"] = df["year"].apply(lambda x: str(x)[1:5])
+# #開催日から月と日を分割
+# df['month']  = df['date'].str.split(pat='.', expand=True)[0]
+# df['day'] = df['date'].str.split(pat='.', expand=True)[1]
+# #数値データを日付データに変換
+# df['date'] = pd.to_datetime({'year': df['year'], 'month': df['month'], 'day': df['day']})
+# #日付昇順に並び替える
+# df = df.sort_values('date', ascending=True)
+# df['date_ymd'] = pd.to_datetime(df['date']).dt.strftime('%Y%m%d')
+# df['date_ym'] = pd.to_datetime(df['date']).dt.strftime('%Y%m')
+# df["date_ymd"] = df["date_ymd"].astype(int)
+# df['date_before'] = df['date_ymd'] - 1
+# df["date_before"] = df["date_before"]
+# df = df[['audience', 'date_ymd', 'date_before']] 
+# df['last_audience'] = df['audience'].shift(1)
+
+# df_aji = pd.read_csv('fish_price.csv')
+
+# df_train = pd.merge(df, df_aji, left_on='date_before', right_on='date', how='left')
+
+# df_train = df_train.query('date > 20201202')
+# df_train = df_train.drop(['date_before', 'date_ymd'], axis=1)
+# df_train["audience"] = df_train["audience"].str.replace(",", "").astype(int)
+# df_train["last_audience"] = df_train["last_audience"].str.replace(",", "").astype(int)
+
+df_train = pd.read_csv('df_train.csv')
 
 X = df_train.drop('audience', axis=1)
 y = df_train['audience']