Untitled

 avatar
unknown
plain_text
a year ago
696 B
25
Indexable

import pyspark
from pyspark.sql import SparkSession
from pyspark.sql.window import Window 
import pyspark.sql.functions as F

spark = SparkSession.builder \
                    .master("local") \
                    .appName("Learning DataFrames") \
                    .getOrCreate()

events = spark.read.json("/user/master/data/events/date=2022-05-01")

window = Window().partitionBy('event.message_from').orderBy("event.message_from")

dfWithLag = events.withColumn("lag_7",F.lag("event.message_to", 7).over(window))

dfWithLag.select('event.message_from', 'lag_7') \
.filter(dfWithLag.lag_7.isNotNull()) \
.orderBy(F.col('event.message_to').desc()) \
.show(10, False)


#ключ: tl0Bn1k6Aw
Leave a Comment