Python数据分析与处理(二)——处理中国地区信息

import pandas as pd

data=pd.read_csv("example_data.csv",header=1)

print(data)

data1=pd.read_csv("北京地区信息.csv",header=1,encoding='gbk')

data2=pd.read_csv("天津地区信息.csv",encoding='gbk')

print(data1)

print(data2)

dupnum=data.duplicated()

print(dupnum)

\# 对重复值进行处理

caldup=data.drop_duplicates()

print(caldup)

from pandas import Series

from numpy import NAN

\# import pandas as pd 

series_obj=Series([1,None])

pd.notnull(series_obj)

\# 上面做的是测试

pd.notnull(data)

pd.notnull(data1)

pd.notnull(data2)

import numpy as np

\# 2.4 检查异常值

def three_sig(ser1):

  mean_value=ser1.mean()

\#   标准差

  std_value=ser1.std()

\#   位于3σ范围外的都是异常值

\# 数值大于u+3σ小雨u-3σ

  rule=(mean_value-3*std_value>ser1)|(ser1.mean()+3*ser1.std()<ser1)

  index=np.arange(ser1.shape[0])[rule]

  outrange=ser1.iloc[index]

  return outrange

three_sig(data2["女性"])