PySpark faster toPandas using mapPartitions

faster_toPandas.py

import pandas as pd

def _map_to_pandas(rdds):
    """ Needs to be here due to pickling issues """
    return [pd.DataFrame(list(rdds))]

def toPandas(df, n_partitions=None):
    """
    Returns the contents of `df` as a local `pandas.DataFrame` in a speedy fashion. The DataFrame is
    repartitioned if `n_partitions` is passed.
    :param df:              pyspark.sql.DataFrame
    :param n_partitions:    int or None
    :return:                pandas.DataFrame
    """
    if n_partitions is not None: df = df.repartition(n_partitions)
    df_pand = df.rdd.mapPartitions(_map_to_pandas).collect()
    df_pand = pd.concat(df_pand)
    df_pand.columns = df.columns
    return df_pand

I tried all the above mentioned optimisations and still keep running into memory issues. I even put the new partitions as big number.
I get the following error:

An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Total size of serialized results of 5450 tasks (4.0 GB) is bigger than spark.driver.maxResultSize (4.0 GB)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2362)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2350)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2349)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2349)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1102)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1102)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2581)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2529)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2517)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:897)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2280)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2302)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2321)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2346)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:997)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:392)
at org.apache.spark.rdd.RDD.collect(RDD.scala:996)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:247)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
at py4j.Gateway.invoke(Gateway.java:295)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:251)
at java.lang.Thread.run(Thread.java:748)

You can increase your spark.driver.maxResultSize in your Spark config. It seems like you df is larger than the four gigabyte. Set it to 15g or something similar and try to run it again.