python统计csv数据，计算重复数据次数，删除重复值

# -- coding: utf-8 --

import os

import numpy as np

import pandas as pd

import time

start=() #用于记录程序运行时间

('G:\\GISworkspace\\Rprocess')

tx=open('level3_river_clipV6.csv')

df=pd.read_csv(tx)

()

Cname=df['NAME_CH']

num=(range(0,len(Cname))) #用于记录每个地名重复出现次数

# print(num)

# print(Cname)

space=range(0,len(Cname))

# print(space,type(space))

space=(space,columns=['name'])

# space['name'][0]=(Cname[2])

# print(space)

# print(df['NAME_CH']) #取某一列

for i in range(len(Cname)):

k = 0 #记录次数

for j in range(len(Cname)):

if (Cname[i]==Cname[j]):

space['name'][i]=Cname[j]

k=k+1

else:

k=k

num[i] = k

# print(space)

# print(num)

num=(data=num,columns=['num'])

# print(num)

frame=[space,num] #concat进行两个dataframe合并

result=(frame,axis=1) #axis=1为向右连接， =0 为向下连接

# print(result)

result=result.drop_duplicates('name',keep='first') #去除重复行，可以利用单列也可以用多列 即 result.drop_duplicates(['col1','col2'],keep='first'),

# keep='first'即只保留第一次出现的值

result.to_csv('Cname_10km.csv') #输出

end=()

print(end-start) #查看程序运行时间 R运行4.7min,python运行时间 31s