replace NA with median in pyspark using window function - python

I want to replace NA with medain based on partition columns using window function in pyspark?
Sample Input:
Required Output:

Creating your dataframe:
list=([1,5,4],
[1,5,None],
[1,5,1],
[1,5,4],
[2,5,1],
[2,5,2],
[2,5,None],
[2,5,None],
[2,5,4])
df=spark.createDataFrame(list,['I_id','p_id','xyz'])
df.show()
+----+----+----+
|I_id|p_id| xyz|
+----+----+----+
| 1| 5| 4|
| 1| 5|null|
| 1| 5| 1|
| 1| 5| 4|
| 2| 5| 1|
| 2| 5| 2|
| 2| 5|null|
| 2| 5|null|
| 2| 5| 4|
+----+----+----+
To keep the solution as generic and dynamic as possible, I had to create many new columns to compute the median, and to be able to send it to the nulls. With that said, solution will not be slow, and will be scalable for big data.
from pyspark.sql.window import Window
from pyspark.sql import functions as F
from pyspark.sql.functions import when
w= Window().partitionBy("I_id","p_id").orderBy(F.col("xyz").asc_nulls_first())
w2= Window().partitionBy("I_id","p_id")
df.withColumn("xyz1",F.count(F.col("xyz").isNotNull()).over(w))\
.withColumn("xyz2", F.max(F.row_number().over(w)).over(w2))\
.withColumn("xyz3", F.first("xyz1").over(w))\
.withColumn("xyz10", F.col("xyz2")-F.col("xyz3"))\
.withColumn("xyz9", F.when((F.col("xyz2")-F.col("xyz3"))%2!=0, F.col("xyz2")-F.col("xyz3")+1).otherwise(F.col("xyz2")-F.col("xyz3")))\
.withColumn("xyz4", (F.col("xyz9")/2))\
.withColumn("xyz6", F.col("xyz4")+F.col("xyz3"))\
.withColumn("xyz7", F.when(F.col("xyz10")%2==0,(F.col("xyz4")+F.col("xyz3")+1)).otherwise(F.lit(None)))\
.withColumn("xyz5", F.row_number().over(w))\
.withColumn("medianr", F.when(F.col("xyz6")==F.col("xyz5"), F.col("xyz")).when(F.col("xyz7")==F.col("xyz5"),F.col("xyz")).otherwise(F.lit(None)))\
.withColumn("medianr2", (F.mean("medianr").over(w2)))\
.withColumn("xyz", F.when(F.col("xyz").isNull(), F.col("medianr2")).otherwise(F.col("xyz")))\
.select("I_id","p_id","xyz")\
.orderBy("I_id").show()
+----+----+---+
|I_id|p_id|xyz|
+----+----+---+
| 1| 5| 4|
| 1| 5| 1|
| 1| 5| 4|
| 1| 5| 4|
| 2| 5| 2|
| 2| 5| 2|
| 2| 5| 1|
| 2| 5| 2|
| 2| 5| 4|
+----+----+---+

Related

Merging rows that have same credentials -pyspark dataframe

How do can I merge two rows in a pyspark dataframe that satisfy a condition?
Example:
dataframe
+---+---+------+
|src|dst|weight|
+---+---+------+
| 8| 7| 1|
| 1| 1| 93|
| 1| 4| 1|
| 4| 4| 2|
| 4| 1| 3|
| 1| 7| 1|
+---+---+------+
condition: (df.src,df.dst) == (df.dst,df.src)
expected output
summed the weight and deleted (4,1)
+---+---+------+
|src|dst|weight|
+---+---+------+
| 8| 7| 1|
| 1| 1| 93|
| 1| 4| 4| #
| 4| 4| 2|
| 1| 7| 1|
+---+---+------+
or
summed the weights and deleted (1,4)
+---+---+------+
|src|dst|weight|
+---+---+------+
| 8| 7| 1|
| 1| 1| 93|
| 4| 4| 2|
| 4| 1| 4| #
| 1| 7| 1|
+---+---+------+
You can add a src_dst column with the sorted array of src and dst, then get the sum of weights for each src_dst, and remove duplicate rows of src_dst:
from pyspark.sql import functions as F, Window
df2 = df.withColumn(
'src_dst',
F.sort_array(F.array('src', 'dst'))
).withColumn(
'weight',
F.sum('weight').over(Window.partitionBy('src_dst'))
).dropDuplicates(['src_dst']).drop('src_dst')
df2.show()
+---+---+------+
|src|dst|weight|
+---+---+------+
| 1| 7| 1|
| 1| 1| 93|
| 1| 4| 4|
| 8| 7| 1|
| 4| 4| 2|
+---+---+------+

Get the first row that matches some condition over a window in PySpark

To give an example, suppose we have a stream of user actions as follows:
from pyspark.sql import *
spark = SparkSession.builder.appName('test').master('local[8]').getOrCreate()
df = spark.sparkContext.parallelize([
Row(user=1, action=1, time=1),
Row(user=1, action=1, time=2),
Row(user=2, action=1, time=3),
Row(user=1, action=2, time=4),
Row(user=2, action=2, time=5),
Row(user=2, action=2, time=6),
Row(user=1, action=1, time=7),
Row(user=2, action=1, time=8),
]).toDF()
df.show()
The dataframe looks like:
+----+------+----+
|user|action|time|
+----+------+----+
| 1| 1| 1|
| 1| 1| 2|
| 2| 1| 3|
| 1| 2| 4|
| 2| 2| 5|
| 2| 2| 6|
| 1| 1| 7|
| 2| 1| 8|
+----+------+----+
Then, I want to add a column next_alt_time to each row, giving the time when user changes action type in the following rows. For the input above, the output should be:
+----+------+----+-------------+
|user|action|time|next_alt_time|
+----+------+----+-------------+
| 1| 1| 1| 4|
| 1| 1| 2| 4|
| 2| 1| 3| 5|
| 1| 2| 4| 7|
| 2| 2| 5| 8|
| 2| 2| 6| 8|
| 1| 1| 7| null|
| 2| 1| 8| null|
+----+------+----+-------------+
I know I can create a window like this:
wnd = Window().partitionBy('user').orderBy('time').rowsBetween(1, Window.unboundedFollowing)
But then I don't know how to impose a condition over the window and select the first row that has a different action than current row, over the window defined above.
Here's how to do it. Spark cannot keep the dataframe order, but if you check the rows one by one, you can confirm that it's giving your expected answer:
from pyspark.sql import Row
from pyspark.sql.window import Window
import pyspark.sql.functions as F
df = spark.sparkContext.parallelize([
Row(user=1, action=1, time=1),
Row(user=1, action=1, time=2),
Row(user=2, action=1, time=3),
Row(user=1, action=2, time=4),
Row(user=2, action=2, time=5),
Row(user=2, action=2, time=6),
Row(user=1, action=1, time=7),
Row(user=2, action=1, time=8),
]).toDF()
win = Window().partitionBy('user').orderBy('time')
df = df.withColumn('new_action', F.lag('action').over(win) != F.col('action'))
df = df.withColumn('new_action_time', F.when(F.col('new_action'), F.col('time')))
df = df.withColumn('next_alt_time', F.first('new_action', ignorenulls=True).over(win.rowsBetween(1, Window.unboundedFollowing)))
df.show()
+----+------+----+----------+---------------+-------------+
|user|action|time|new_action|new_action_time|next_alt_time|
+----+------+----+----------+---------------+-------------+
| 1| 1| 1| null| null| 4|
| 1| 1| 2| false| null| 4|
| 1| 2| 4| true| 4| 7|
| 1| 1| 7| true| 7| null|
| 2| 1| 3| null| null| 5|
| 2| 2| 5| true| 5| 8|
| 2| 2| 6| false| null| 8|
| 2| 1| 8| true| 8| null|
+----+------+----+----------+---------------+-------------+

How do I count consecutive values with pyspark?

I am trying to count consecutive values that appear in a column with Pyspark. I have the column "a" in my dataframe and expect to create the column "b".
+---+---+
| a| b|
+---+---+
| 0| 1|
| 0| 2|
| 0| 3|
| 0| 4|
| 0| 5|
| 1| 1|
| 1| 2|
| 1| 3|
| 1| 4|
| 1| 5|
| 1| 6|
| 2| 1|
| 2| 2|
| 2| 3|
| 2| 4|
| 2| 5|
| 2| 6|
| 3| 1|
| 3| 2|
| 3| 3|
+---+---+
I have tried to create the column "b" with lag function over some window, but without success.
w = Window\
.partitionBy(df.some_id)\
.orderBy(df.timestamp_column)
df.withColumn(
"b",
f.when(df.a == f.lag(df.a).over(w),
f.sum(f.lit(1)).over(w)).otherwise(f.lit(0))
)
I could resolve this issue with the following code:
df.withColumn("b",
f.row_number().over(Window.partitionBy("a").orderBy("timestamp_column"))

Duplicate Rows in Pyspark DataFrame Dynamic Number of Times Based on Difference between Two Columns [duplicate]

This question already has answers here:
Pyspark Replicate Row based on column value
(2 answers)
Closed 4 years ago.
I have a PySpark dataframe that looks like:
+---+----+----+
| id|day1|day2|
+---+----+----+
| 1| 2| 4|
| 2| 1| 2|
| 3| 3| 3|
+---+----+----+
I want to duplicate each row n number of times where n = day2 - day1. The resulting dataframe would look like:
+---+----+----+
| id|day1|day2|
+---+----+----+
| 1| 2| 4|
| 1| 2| 4|
| 1| 2| 4|
| 2| 1| 2|
| 2| 1| 2|
| 3| 3| 3|
+---+----+----+
How can I do this?
Here is one way to do that.
from pyspark.sql import functions as F
from pyspark.sql.types import *
#F.udf(ArrayType(StringType()))
def gen_array(day1, day2):
return ['' for i in range(day2-day1+1)]
df.withColumn(
"dup",
F.explode(
gen_array(F.col("day1"), F.col("day2"))
)
).drop("dup").show()
+---+----+----+
| id|day1|day2|
+---+----+----+
| 1| 2| 4|
| 1| 2| 4|
| 1| 2| 4|
| 2| 1| 2|
| 2| 1| 2|
| 3| 3| 3|
+---+----+----+
Another option using rdd.flatMap:
df.rdd.flatMap(lambda r: [r] * (r.day2 - r.day1 + 1)).toDF().show()
+---+----+----+
| id|day1|day2|
+---+----+----+
| 1| 2| 4|
| 1| 2| 4|
| 1| 2| 4|
| 2| 1| 2|
| 2| 1| 2|
| 3| 3| 3|
+---+----+----+

Generate a group ID with only one Window function

I am trying to assign a group ID to my table.
For each group in "part" column, acording to order in "ord" column, the 1st elements I encounter in "id" column will receive a new_id 0, then each time I encounter a different ID, i increase the "new_id".
Currently, I need to use 2 window functions and the process is therefore quite slow.
df = sqlContext.createDataFrame(
[
(1,1,'X'),
(1,2,'X'),
(1,3,'X'),
(1,4,'Y'),
(1,5,'Y'),
(1,6,'Y'),
(1,7,'X'),
(1,8,'X'),
(2,1,'X'),
(2,2,'X'),
(2,3,'X'),
(2,4,'Y'),
(2,5,'Y'),
(2,6,'Y'),
(2,7,'X'),
(2,8,'X'),
],
["part", "ord", "id"]
)
df.withColumn(
"new_id",
F.lag(F.col("id")).over(Window.partitionBy("part").orderBy("ord"))!=F.col('id')
).withColumn(
"new_id",
F.sum(
F.col("new_id").cast('int')
).over(Window.partitionBy("part").orderBy("ord"))
).na.fill(0).show()
+----+---+---+------+
|part|ord| id|new_id|
+----+---+---+------+
| 2| 1| X| 0|
| 2| 2| X| 0|
| 2| 3| X| 0|
| 2| 4| Y| 1|
| 2| 5| Y| 1|
| 2| 6| Y| 1|
| 2| 7| X| 2|
| 2| 8| X| 2|
| 1| 1| X| 0|
| 1| 2| X| 0|
| 1| 3| X| 0|
| 1| 4| Y| 1|
| 1| 5| Y| 1|
| 1| 6| Y| 1|
| 1| 7| X| 2|
| 1| 8| X| 2|
+----+---+---+------+
Can I achieve the same using only one window function ?

Categories