Python pandas如何根据指定条件筛选数据

import pandas as pd
import numpy as np
df=pd.DataFrame(np.arange(16).reshape(4,4),columns=["sh","bj","sz","gz"],index=["one","two","three","four"])

df[df["sh"]>5]

df[df["sh"].map(lambda x:x>5)]

df[df["sh"]==5]

df[df["sh"].map(lambda x:x==5)]

df[df["sh"].isin([5])]

province = pd.DataFrame(['广东', '广西', '福建', '福建省'], columns=['省份'])
province.loc[province["省份"].str.contains("福")]#筛选出福建省数据

import re
province = pd.DataFrame(['广东', '广西', '福建', '福建省'], columns=['省份'])
#自定义函数，如果包含“广”字，则返回True,否则返回False
def func(x):
    if re.search(".*广.*",x):
        return(True)
    else:
        return(False)
province[province["省份"].apply(func)]

df=pd.DataFrame({"date":["2020efgdh0228","2021hijik0228","2019hokh0201"],"value":[9999,777,4]})

#筛选出2019年的数据
df[df["date"].map(lambda x:x[0:4])=="2019"]

df[df.duplicated(subset=["one"],keep="last")]#返回除最后一次出现的重复值

df[df.duplicated(subset=["one"],keep=False)]#返回所有重复值