pip install plotly

pip install plotly numpy pandas

#導(dǎo)入所需庫(kù)
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go

#讀取數(shù)據(jù)
locations=pd.read_csv(r'data/locations.csv')

locations

#發(fā)現(xiàn)數(shù)據(jù)中vaccines列中包含了多個(gè)品牌的情況，將這類(lèi)數(shù)拆為多條
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() # 查看疫苗的種類(lèi)

#繪圖
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()

#讀取數(shù)據(jù)
vacc_by_manu=pd.read_csv(r'data/vaccinations-by-manufacturer.csv')

#定義函數(shù)，用于從原始數(shù)據(jù)中組織寬表
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

#組織寬表
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

#補(bǔ)全缺失數(shù)據(jù)
temp=pd.DataFrame()
for i in vacc_combined.location.unique():#按國(guó)家進(jìn)行不全
    r=vacc_combined.loc[vacc_combined.location==i]
    r=r.fillna(method='ffill',axis=0)#先按最近一次的數(shù)據(jù)進(jìn)行補(bǔ)全
    temp=pd.concat([temp,r])#若沒(méi)有最近的數(shù)據(jù)，認(rèn)為該項(xiàng)為0
temp=temp.fillna(0).reset_index(drop=True)
temp

#繪制堆疊柱狀圖
fig=px.bar(temp,
        x='location',
        y=vacc_by_manu.vaccine.unique(),
        animation_frame='date',
        color_discrete_sequence=['#636efa','#19d3f3','#ab63fa','#00cc96']#為了查看方便，品牌顏色與前一部分對(duì)應(yīng)
        )
fig.show()