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)mylist = ["a", "b", "b", "c", "a"]
mylist = sorted(set(mylist))
print(mylist)result_df = df.drop_duplicates(subset=['Column1', 'Column2'], keep='first')
print(result_df)# HOW TO REMOVE DUPLICATES FROM A LIST:
# 1) CREATE A LIST
my_list = [1, 2, 3, 4, 5, 5, 5, 1]
# 2) CONVERT IT TO A SET AND THEN BACK INTO A LIST
my_list = list(set(my_list))
# 3) DONE!
print(my_list) #WILL PRINT: [1, 2, 3, 4, 5]
mylist = ["a", "b", "a", "c", "c"]
mylist = list(dict.fromkeys(mylist))
print(mylist) mylist = ["a", "b", "a", "c", "c"]
mylist = list(dict.fromkeys(mylist))