Python数据处理：分类

# coding = utf-8
# 开发时间: 2021/5/13 11:39

import pymysql
import pandas as pd
df = pd.read_csv('me.csv')
# conn = pymysql.connect(host="localhost", user="root", password="123123", database="visualization",charset="utf8")
# df=pd.read_csv('city.csv')
# df_mean = df.groupby('省份')['aqi'].mean()
# df_mean.to_excel('aqi_mean.xlsx')
#
# df['time'] = pd.to_datetime(df['time'])
# df = df.set_index("time")
# df = df.sort_index()
# ser=df['2017-01-01':'2017-12-31','aqi','省份']
# ser.groupby('')
# ser.to_csv('mean3.csv')
# df = pd.read_csv('mean22.csv')
# df_mean = df.groupby('season')
# 季节分组求平均
# ser=df.groupby(['season','省份'])['aqi'].mean()
# ser.to_csv('means.csv')

# df.sort_values(by=['season','aqi']).to_csv('achive.csv')
#
# df.reindex(range(124),method='ffill')
def various(x):
    if x == '北京':
        return '京'
    elif x=='天津市':
        return '津'
    elif x=='上海市':
        return '沪'
    elif x=='重庆市':
        return '渝'
    elif x=='河北省':
        return '豫'
    elif x=='云南省':
        return '云'
    elif x=='辽宁省':
        return '辽'
    elif x=='黑龙江':
        return '黑'
    elif x=='安徽省':
        return '皖'
    elif x=='山东省':
        return '鲁'
    elif x=='新疆维吾尔自治区':
        return '新'
    elif x=='内蒙古自治区':
        return '蒙'
    elif x=='宁夏回族自治区':
        return '宁'
    elif x=='广西壮族自治区':
        return '桂'
    elif x=='江苏省':
        return '苏'
    elif x=='浙江省':
        return '浙'
    elif x=='江苏省':
        return '苏'
    elif x=='浙江省':
        return '浙'
    elif x=='江西省':
        return ''
    elif x=='湖北省':
        return '浙'
    elif x=='甘肃省':
        return ''
    elif x=='山西省':
        return '晋'
    elif x=='陕西省':
        return '陕'
    elif x=='吉林省':
        return '吉'
    elif x=='福建省':
        return '闽'
    elif x=='贵州省':
        return '吉'
    else:
        return '粤'


province=df.pop('省份')
df.insert(1,'province',province)
df['province']=df.loc[:,'province'].apply(various)
df.to_csv('me.csv')