In [7]: pdf = gdf1.toPandas() pdf['date'] = epoch2num(pdf['ms'] ) print(pdf.dtypes) pdf count int64 row_key object created datetime64[ns] ms int64 date float64 dtype: object Out[7]: countrow_keycreatedmsdate 02realDonaldTrump2016-03-09 11:44:151457552655736032.822396 11realDonaldTrump2016-03-09 11:44:301457552670736032.822569 21realDonaldTrump2016-03-09 11:44:451457552685736032.822743 33realDonaldTrump2016-03-09 11:45:001457552700736032.822917 41HillaryClinton2016-03-09 11:44:151457552655736032.822396 52HillaryClinton2016-03-09 11:44:301457552670736032.822569 61HillaryClinton2016-03-09 11:44:451457552685736032.822743
From: Andrew Davidson <a...@santacruzintegration.com> Date: Thursday, March 10, 2016 at 2:52 PM To: Ted Yu <yuzhih...@gmail.com> Cc: "user @spark" <user@spark.apache.org> Subject: Re: trouble with NUMPY constructor in UDF > Hi Ted > > In python the data type is float64¹. I have tried using both sql FloatType > and DoubleType how ever I get the same error > > Strange > > andy > > From: Ted Yu <yuzhih...@gmail.com> > Date: Wednesday, March 9, 2016 at 3:28 PM > To: Andrew Davidson <a...@santacruzintegration.com> > Cc: "user @spark" <user@spark.apache.org> > Subject: Re: trouble with NUMPY constructor in UDF > >> bq. epoch2numUDF = udf(foo, FloatType()) >> >> Is it possible that return value from foo is not FloatType ? >> >> On Wed, Mar 9, 2016 at 3:09 PM, Andy Davidson <a...@santacruzintegration.com> >> wrote: >>> I need to convert time stamps into a format I can use with matplotlib >>> plot_date(). epoch2num() works fine if I use it in my driver how ever I get >>> a numpy constructor error if use it in a UDF >>> >>> Any idea what the problem is? >>> >>> Thanks >>> >>> Andy >>> >>> P.s I am using python3 and spark-1.6 >>> >>> from pyspark.sql.functions import udf >>> from pyspark.sql.types import FloatType, DoubleType, DecimalType >>> >>> >>> import pandas as pd >>> import numpy as np >>> >>> from matplotlib.dates import epoch2num >>> >>> gdf1 = cdf1.selectExpr("count", "row_key", "created", >>> "unix_timestamp(created) as ms") >>> gdf1.printSchema() >>> gdf1.show(10, truncate=False) >>> root >>> |-- count: long (nullable = true) >>> |-- row_key: string (nullable = true) >>> |-- created: timestamp (nullable = true) >>> |-- ms: long (nullable = true) >>> >>> +-----+---------------+---------------------+----------+ >>> |count|row_key |created |ms | >>> +-----+---------------+---------------------+----------+ >>> |1 |HillaryClinton |2016-03-09 11:44:15.0|1457552655| >>> |2 |HillaryClinton |2016-03-09 11:44:30.0|1457552670| >>> |1 |HillaryClinton |2016-03-09 11:44:45.0|1457552685| >>> |2 |realDonaldTrump|2016-03-09 11:44:15.0|1457552655| >>> |1 |realDonaldTrump|2016-03-09 11:44:30.0|1457552670| >>> |1 |realDonaldTrump|2016-03-09 11:44:45.0|1457552685| >>> |3 |realDonaldTrump|2016-03-09 11:45:00.0|1457552700| >>> +-----+---------------+---------------------+----------+ >>> >>> >>> def foo(e): >>> return epoch2num(e) >>> >>> epoch2numUDF = udf(foo, FloatType()) >>> #epoch2numUDF = udf(lambda e: epoch2num(e), FloatType()) >>> #epoch2numUDF = udf(lambda e: e + 5000000.5, FloatType()) >>> >>> gdf2 = gdf1.withColumn("date", epoch2numUDF(gdf1.ms <http://gdf1.ms> )) >>> gdf2.printSchema() >>> gdf2.show(truncate=False) >>> >>> >>> Py4JJavaError: An error occurred while calling o925.showString. >>> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 >>> in stage 32.0 failed 1 times, most recent failure: Lost task 0.0 in stage >>> 32.0 (TID 91, localhost): net.razorvine.pickle.PickleException: expected >>> zero arguments for construction of ClassDict (for numpy.dtype) >>> at >>> net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstru >>> ctor.java:23) >>> at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) >>> at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) >>> at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) >>> at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) >>> >>> Works fine if I use PANDAS >>> >>> pdf = gdf1.toPandas() >>> pdf['date'] = epoch2num(pdf['ms'] ) >>> >>> >>