PYTHON

Remove duplicates with pandas

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)

pandas remove repeated index

df[~df.index.duplicated()]

drop duplicate index pandas

df3 = df3[~df3.index.duplicated(keep='first')]

remove duplicates in dataframe by index python

# Remove by index
df = df[df.index.duplicated(keep='first')]

# Other methods to remove duplicates
import pandas as pd

df = df.drop_duplicates()

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

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

pandas remove repeated index

idx = pd.Index(['lama', 'cow', 'lama', 'beetle', 'lama', 'hippo'])
idx.drop_duplicates(keep='first')
Index(['lama', 'cow', 'beetle', 'hippo'], dtype='object')
idx.drop_duplicates(keep='last')
Index(['cow', 'beetle','lamb', 'hippo'], dtype='object')
idx.drop_duplicates(keep='False')
Index(['cow', 'beetle','hippo'], dtype='object')

df index drop duplicates

df3 = df3[~df3.index.duplicated(keep='first')]

pandas remove duplicates

df.drop_duplicates()