# drop duplicates pandas first column

import pandas as pd 

# making data frame from csv file 

data = pd.read_csv("employees.csv") 

# sorting by first name 

data.sort_values("First Name", inplace = True) 

# dropping ALL duplicte values 

data.drop_duplicates(subset ="First Name",keep = False, inplace = True) 

# displaying data 

print(data)

​

# remove duplicate row in df

df = df.drop_duplicates()

​

#remove duplicate columns python dataframepython by Happy Hawk on May 28 2020 Comment

df = df.loc[:,~df.columns.duplicated()]

​

# dataframe delete duplicate rows with same column value

df = df.drop_duplicates(subset=['Column1', 'Column2'], keep='first')

​

# Exemple

import pandas as pd

df = pd.DataFrame({"A":["foo", "foo", "foo", "bar"], "B":[0,1,1,1], "C":["A","A","B","A"]})

df.drop_duplicates(subset=['A', 'C'], keep=False)

import pandas as pd

​

# Drop all duplicates in the DataFrame

df = df.drop_duplicates()

​

# Drop all duplicates in a specific column of the DataFrame

df = df.drop_duplicates(subset = "column")

​

# Drop all duplicate pairs in DataFrame

df = df.drop_duplicates(subset = ["column", "column2"])

​

# Display DataFrame

print(df)

# Below are quick example

# keep first duplicate row

df2 = df.drop_duplicates()

​

# Using DataFrame.drop_duplicates() to keep first duplicate row

df2 = df.drop_duplicates(keep='first')

​

# keep last duplicate row

df2 = df.drop_duplicates( keep='last')

​

# Remove all duplicate rows 

df2 = df.drop_duplicates(keep=False)

​

# Delete duplicate rows based on specific columns 

df2 = df.drop_duplicates(subset=["Courses", "Fee"], keep=False)

​

# Drop duplicate rows in place

df.drop_duplicates(inplace=True)

​

# Using DataFrame.apply() and lambda function 

df2 = df.apply(lambda x: x.astype(str).str.lower()).drop_duplicates(subset=['Courses', 'Fee'], keep='first')

​

result_df = df.drop_duplicates(subset=['Column1', 'Column2'], keep='first')

print(result_df)

data = data.drop_duplicates(subset=['City'], keep='first')

df.drop_duplicates(keep=False, inplace=True)

dataFrame.drop_duplicates(subset=None, keep='first', inplace=False)

df = df.loc[:,~df.columns.duplicated()].copy()

​

# https://stackoverflow.com/questions/14984119/python-pandas-remove-duplicate-columns

df.loc[:,~df.columns.duplicated()]