app.py

import altair

import gradio as gr
from math import sqrt
import matplotlib

matplotlib.use("Agg")

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

import datetime

from sklearn.linear_model import LinearRegression
from sklearn.metrics import log_loss
from sklearn.preprocessing import StandardScaler

import requests
from bs4 import BeautifulSoup as bs
from requests_html import AsyncHTMLSession

df_train = pd.read_csv('df_train.csv')
X = df_train.drop('audience', axis=1)
y = df_train['audience']
linear_regression = LinearRegression()
model = linear_regression.fit(X,y)

d_today = datetime.date.today()
d_tom = datetime.date.today() + datetime.timedelta(days = 1)

# 動作確認
d_y = datetime.date.today() + datetime.timedelta(days = -1)
if __name__ == "__main__":
    start_date = d_y
    end_date = d_today
    df_aji_pre = get_fish_price_data(start_date=start_date, end_date=end_date)
    df_aji_pre['date'] = df_aji_pre['date'].astype(int)

# if __name__ == "__main__":
#     start_date = d_today
#     end_date = d_tom
#     df_aji_pre = get_fish_price_data(start_date=start_date, end_date=end_date)
#     df_aji_pre['date'] = df_aji_pre['date'].astype(int)

url23 = 'https://www.football-lab.jp/ka-f/match/'
dfs23 = pd.read_html(url23)

#シーズン毎に分類
res23 = pd.DataFrame([['S2023']]*len(dfs23[0])).join(dfs23, lsuffix='0')

df = res23

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_pre = pd.merge(df, df_aji_pre, left_on='date_before', right_on='date', how='left')

# df_pre = df_pre.drop(['date_before', 'date_ymd'], axis=1)
# df_pre["audience"] = df_pre["audience"].str.replace(",", "").astype(int)
# df_pre["last_audience"] = df_pre["last_audience"].str.replace(",", "").astype(int)

# start_date = int(start_date)
# df_pre = df.query('date <= start_date')


df_pre = df.tail(1).reset_index()
df_pre = df_pre.drop('index', axis=1)
df_aji_ft_pre = pd.concat([df_pre, df_aji_pre], axis=1)
df_aji_ft_pre = df_aji_ft_pre[['audience', 'date', 'low_price', 'center_price', 'high_price', 'quantity']]
df_aji_ft_pre = df_aji_ft_pre.rename(columns={'audience': 'last_audience', 0: 'year', '開催日': 'date', '観客数': 'audience'})

def outbreak(date):
  if date:  

    # if __name__ == "__main__":
    #   import datetime
    #   d_today = datetime.date.today()
    #   d_tom = datetime.date.today() + datetime.timedelta(days = 1)
    #   start_date = d_today
    #   end_date = d_tom
    #   df_aji_pre = get_fish_price_data(start_date=start_date, end_date=end_date)
    #   # df_aji_pre.to_csv("fish_price_pre.csv", index=False)
    
    df_pre = df.tail(1).reset_index()
    df_pre = df_pre.drop('index', axis=1)
    df_aji_ft_pre = pd.concat([df_pre, df_aji_pre], axis=1)
    df_aji_ft_pre = df_aji_ft_pre[['audience', 'date', 'low_price', 'center_price', 'high_price', 'quantity']]
    df_aji_ft_pre = df_aji_ft_pre.rename(columns={'audience': 'last_audience', 0: 'year', '開催日': 'date', '観客数': 'audience'})

    X = df_train.drop('audience', axis=1)
    y = df_train['audience']
    
    pred = linear_regression.predict(df_aji_ft_pre)
    df_aji_ft_pre['audience_pred'] = pred
    df_aji_ft_pre['date'] = df_aji_ft_pre['date'].astype(int)

    fig = plt.figure()
    plt.plot(df_train['date'], df_train['audience'], label='original')
    plt.plot(df_aji_ft_pre['date'], df_aji_ft_pre['audience_pred'], '*', label='predict')
    plt.title("prediction of audince")
    plt.ylabel("audience")
    plt.xlabel("Days since Day 0")
    return fig

with gr.Blocks() as demo:
    gr.Markdown(
                            """
                            # 川崎フロンターレの観客動員数の予測
                             川崎フロンターレの等々力陸上競技場での試合の観客数を「あじ」の価格をもとに予測する。
                            ## 使用データ
                             * 東京卸売市場日報
                             * Football Lab 
                            ## 予測ロジック
                            観客動員数は雨天か否かで左右されると考えられる。そこで雨天の可能性をあじの価格を利用し表した。
                            一般的に雨天の場合、低気圧の影響で海面が上昇し漁に出ることが難しくなる。
                            そのため漁獲量が減少し、あじの価格が上昇すると考えられる。
                             """
                        )
    with gr.Row():
      with gr.Column():
        date_input = gr.Checkbox(label='please input date')
        prediction_btn = gr.Button(value="predict")
      with gr.Column():
        prediction = gr.Plot(label = "時系列プロット")
    prediction_btn.click(outbreak, inputs=date_input, outputs=prediction)

demo.launch()