Fill in null with previously known good value with pyspark

Question

Is there a way to replace null values in pyspark dataframe with the last valid value? There is addtional timestamp and session columns

Answer 1

This seems to be doing the trick using Window functions:

import sys
from pyspark.sql.window import Window
import pyspark.sql.functions as func

def fill_nulls(df):
    df_na = df.na.fill(-1)
    lag = df_na.withColumn('id_lag', func.lag('id', default=-1)\
                           .over(Window.partitionBy('session')\
                                 .orderBy('timestamp')))

    switch = lag.withColumn('id_change',
                            ((lag['id'] != lag['id_lag']) &
                             (lag['id'] != -1)).cast('integer'))


    switch_sess = switch.withColumn(
        'sub_session',
        func.sum("id_change")
        .over(
            Window.partitionBy("session")
            .orderBy("timestamp")
            .rowsBetween(-sys.maxsize, 0))
    )

    fid = switch_sess.withColumn('nn_id',
                           func.first('id')\
                           .over(Window.partitionBy('session', 'sub_session')\
                                 .orderBy('timestamp')))

    fid_na = fid.replace(-1, 'null')

    ff = fid_na.drop('id').drop('id_lag')\
                          .drop('id_change')\
                          .drop('sub_session').\
                          withColumnRenamed('nn_id', 'id')

    return ff

Here is the full null_test.py.