pandas remove duplicates code example

Example 1: 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)

Example 2: remove duplicate row in df

df = df.drop_duplicates()

Example 3: remove duplicates function python

def remove_dupiclates(list_):
	new_list = []
	for a in list_:
    	if a not in new_list:
        	new_list.append(a)
	return new_list

Example 4: remove duplicates python

mylist = ["a", "b", "a", "c", "c"]
mylist = list(dict.fromkeys(mylist))

Example 5: remove duplicate columns python dataframe

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

Example 6: python remove duplicates

if mylist:
    mylist.sort()
    last = mylist[-1]
    for i in range(len(mylist)-2, -1, -1):
        if last == mylist[i]:
            del mylist[i]
        else:
            last = mylist[i]
# Quicker if all elements are hashables:
mylist = list(set(mylist))