python统计excel中重复数据_Python pandas 获取Excel重复记录

# We will use data structures and data analysis tools provided in Pandas library

import pandas as pd

# Import retail sales data from an Excel Workbook into a data frame

# path = '/Documents/analysis/python/examples/2015sales.xlsx'

path = 'F:/python/an.xlsx'

xlsx = pd.ExcelFile(path)

df = pd.read_excel(xlsx, 'Sheet1')

# Let's add a new boolean column to our dataframe that will identify a duplicated order line item (False=Not a duplicate; True=Duplicate)

df['is_duplicated'] = df.duplicated(['ip'])

# We can sum on a boolean column to get a count of duplicate order line items

# df['is_duplicated'].sum()

# Get the records of duplicated, If you need non-dup just use False instead

df_dup = df.loc[df['is_duplicated'] == True]

# Finally let's save our cleaned up data to a csv file

df_dup.to_csv('dup.csv', encoding='utf-8')