adsk2050 commented on PR #21082:
URL: https://github.com/apache/spark/pull/21082#issuecomment-1163170533
Hello! this is great work! Thank you for contributing. This code will enable
to run functions on window, which take in pd.Series -> Any.
I am wondering if GROUPED_MAP pandas UDF as window functions is also in
pipeline or not?
(Basically pd.Series -> pd.Series over Window.)
For example:
```
from pyspark.sql import functions as F
from pyspark.sql.types import *
def doCoolStuff(df: pd.DataFrame) -> pd.DataFrame:
events = df["event"].to_list()
count = 1
sets = []
for event in events:
sets.append(str(count))
if event=="buy":
count+=1
df["coolStuff"] = pd.Series(data=sets)
return df
df = spark.createDataFrame(pd.DataFrame([[1, random.choice(list(range(10))),
i, random.random()] for i in range(100)], columns=["user_id", "source_id",
"epoch_timestamp", "event_prob"]))\
.withColumn("event", F.when(F.col("event_prob")>F.lit(0.9),
"buy").otherwise("view"))\
.withColumn("coolStuff", F.lit(""))\
.persist()
doCoolStuffPDUDF = F.pandas_udf(
f=doCoolStuff,
returnType=df.schema,
functionType=F.PandasUDFType.GROUPED_MAP)
df\
.orderBy(F.col("epoch_timestamp"))\
.groupby("user_id", "source_id")\
.apply(doCoolStuffPDUDF)\
.orderBy(F.col("user_id"), F.col("source_id"),
F.col("epoch_timestamp").desc())\
.display()
```
This could simplified to:
```
from pyspark.sql import functions as F
from pyspark.sql.types import *
from pyspark.sql.window import Window
def doCoolStuff(events: pd.Series) -> pd.Series:
count = 1
sets = []
for event in events:
sets.append(str(count))
if event=="buy":
count+=1
return pd.Series(data=sets)
doCoolStuffPDUDF = F.pandas_udf(
f=doCoolStuff,
returnType=StringType(),
functionType=F.PandasUDFType.GROUPED_MAP)
df = spark.createDataFrame(pd.DataFrame([[1, random.choice(list(range(10))),
i, random.random()] for i in range(100)], columns=["user_id", "source_id",
"epoch_timestamp", "event_prob"]))\
.withColumn("event", F.when(F.col("event_prob")>F.lit(0.9),
"buy").otherwise("view"))\
.withColumn("coolStuff", doCoolStuffPDUDF(F.col("event"))\
.over(Window.partitionBy("user_id",
"source_id").orderBy(F.col("epoch_timestamp"))\
.orderBy(F.col("user_id"), F.col("source_id"),
F.col("epoch_timestamp").desc())\
.persist()
df.display()
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
