使用python pandas捉取covid 19 json格式資訊並畫本月份本土病例日線

print('抓covid-19資料畫4月本土病例日線與回歸分析')
url='https://od.cdc.gov.tw/eic/Day_Confirmation_Age_County_Gender_19CoV.json'

匯入套件

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

pandas讀資料

df=pd.read_json(url)
df2022April=df[('2022/04/22'>=df['個案研判日']) & (df['個案研判日']>='2022/04/') & (df['是否為境外移入']=='否')]

完整列印

with pd.option_context('display.max_rows', None, 'display.max_columns', None): 
    print(df2022April)

篩去不用欄位

df2=df2022April.drop(columns=['確定病名','縣市', '性別',\
                            '是否為境外移入','年齡層'])
array=df2.to_numpy()

整理資料用dict存

dic={}
n=0
for x in array:
    z=x[0].split('/')[2]
    key=int(z)
    value=x[2]#因有加key '鄉鎮'
    n+=value
    if key not in dic:
        dic[key]=value
    else:
        dic[key]+=value
print('2022/04本土病例=',n)
print(dic)

迴歸分析

data=np.array(list(dic.items()))
coef=np.polyfit(data[:,0], data[:,1], 5)
reg=np.poly1d(coef)
print(reg)

畫統計圖

plt.rcParams['font.family'] = ['Microsoft JhengHei']
plt.scatter(data[:,0], data[:,1])
plt.plot(data[:,0],reg(data[:,0]), color='r')
plt.title('這是covid-19最近日線')
plt.savefig('covid-19-April-days.jpg')
plt.show()