remove duplicate row in df
df = df.drop_duplicates()Return a new DataFrame with duplicate rows removed
# Return a new DataFrame with duplicate rows removed
from pyspark.sql import Row
df = sc.parallelize([
Row(name='Alice', age=5, height=80),
Row(name='Alice', age=5, height=80),
Row(name='Alice', age=10, height=80)]).toDF()
df.dropDuplicates().show()
# +---+------+-----+
# |age|height| name|
# +---+------+-----+
# | 5| 80|Alice|
# | 10| 80|Alice|
# +---+------+-----+
df.dropDuplicates(['name', 'height']).show()
# +---+------+-----+
# |age|height| name|
# +---+------+-----+
# | 5| 80|Alice|
# +---+------+-----+delete duplicate rows
WITH CTE AS(
SELECT [col1], [col2], [col3], [col4], [col5], [col6], [col7],
RN = ROW_NUMBER()OVER(PARTITION BY col1 ORDER BY col1)
FROM dbo.Table1
)
DELETE FROM CTE WHERE RN > 1Copyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
