xxxxxxxxxx
# Drop rows when containing duplicate in variable
library(dplyr)
df <- df %>% distinct(<your_variable>, .keep_all = TRUE)
xxxxxxxxxx
# 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')
xxxxxxxxxx
# Remove duplicates from data frame:
example_df[!duplicated(example_df), ]Code language: R (r)
xxxxxxxxxx
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)
xxxxxxxxxx
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)