pip install plotly

pip install plotly numpy pandas

#导入所需库
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go

#读取数据
locations=pd.read_csv(r'data/locations.csv')

locations

#发现数据中vaccines列中包含了多个品牌的情况，将这类数拆为多条
vaccines_by_country=pd.DataFrame()
for i in locations.iterrows():
    df=pd.DataFrame({'Country':i[1].location,'vaccines':i[1].vaccines.split(',')})
    vaccines_by_country=pd.concat([vaccines_by_country,df])
vaccines_by_country['vaccines']=vaccines_by_country.vaccines.str.strip()# 去掉空格

vaccines_by_country.vaccines.unique() # 查看疫苗的种类

#绘图
fig=px.choropleth(vaccines_by_country,
                locations='Country',
                locationmode='country names',
                color='vaccines',
                facet_col='vaccines',
                facet_col_wrap=3)
fig.update_layout(width=1200, height=1000)
fig.show()

#读取数据
vacc_by_manu=pd.read_csv(r'data/vaccinations-by-manufacturer.csv')

#定义函数，用于从原始数据中组织宽表
def query(df,country,date,vaccine):
    try:
        result=df.loc[(df.location==country)&(df.date==date)&(df.vaccine==vaccine)].total_vaccinations.iloc[0]
    except:
        result=np.nan
    return result

vacc_by_manu

#组织宽表
vacc_combined=pd.DataFrame(columns=['location','date','Pfizer/BioNTech', 'Sinovac', 'Moderna', 'Oxford/AstraZeneca'])
for i in vacc_by_manu.location.unique():
    for j in vacc_by_manu.date.unique():
        for z in vacc_by_manu.vaccine.unique():
            result=query(vacc_by_manu,i,j,z)
            if vacc_combined.loc[(vacc_combined.location==i)&(vacc_combined.date==j)].empty:
                result_df=pd.DataFrame({'location':i,'date':j,z:result},index=['new'])
                vacc_combined=pd.concat([vacc_combined,result_df])
            else:
                vacc_combined.loc[(vacc_combined.location==i)&(vacc_combined.date==j),z]=result

vacc_combined

#补全缺失数据
temp=pd.DataFrame()
for i in vacc_combined.location.unique():#按国家进行不全
    r=vacc_combined.loc[vacc_combined.location==i]
    r=r.fillna(method='ffill',axis=0)#先按最近一次的数据进行补全
    temp=pd.concat([temp,r])#若没有最近的数据，认为该项为0
temp=temp.fillna(0).reset_index(drop=True)
temp

#绘制堆叠柱状图
fig=px.bar(temp,
        x='location',
        y=vacc_by_manu.vaccine.unique(),
        animation_frame='date',
        color_discrete_sequence=['#636efa','#19d3f3','#ab63fa','#00cc96']#为了查看方便，品牌颜色与前一部分对应
        )
fig.show()