Hugging Face's logo

Spaces:
masa729406
/
chEstyleU
Runtime error

App Files Community
chEstyleU
File size: 5,540 Bytes 
4f59094
763a979
4f59094
 
932aa7b
a8cff4f
932aa7b
7e798dd
 
4f59094
7e798dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
359e36e
 
 
 
 
 
 
 
 
76cef3f
6a2c3c8
4f59094
 
359e36e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f59094
359e36e
 
 
7e493b4
4f59094
 
 
359e36e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a2c3c8
359e36e
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
 
import altair

import gradio as gr
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


# # 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']

from sklearn.linear_model import LinearRegression
from sklearn.metrics import log_loss
from sklearn.preprocessing import StandardScaler
linear_regression = LinearRegression()
linear_regression.fit(X,y)


def outbreak(date):
  if date:

    

    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.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'})

    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()