Py4JJavaError while fit_transform(X_rdd)

[alonsopg]

From the documentation examples, I tried to vectorize a list of texts with SparkCountVectorizer:

In:
from splearn.rdd import ArrayRDD
from splearn.feature_extraction.text import SparkCountVectorizer
import pandas as pd

df = pd.read_csv('/Users/user/Downloads/new_labeled_corpus.csv')
#print (df.head())
X = [df['text'].values]
print (type(X))
X_rdd = ArrayRDD(sc.parallelize(X, 4))  # sc is SparkContext
print (X_rdd)

Out:
<class 'list'>
<class 'splearn.rdd.ArrayRDD'> from PythonRDD[27] at RDD at PythonRDD.scala:43

In:
dist = SparkCountVectorizer()
result_dist = dist.fit_transform(X_rdd)  # SparseRDD

However, I got this exception:

Out:
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-15-5070dde8118a> in <module>()
      1 dist = SparkCountVectorizer()
----> 2 result_dist = dist.fit_transform(X_rdd)  # SparseRDD

/usr/local/lib/python3.5/site-packages/splearn/feature_extraction/text.py in fit_transform(self, Z)
    291         # create vocabulary
    292         X = A[:, 'X'] if isinstance(A, DictRDD) else A
--> 293         self.vocabulary_ = self._init_vocab(X)
    294 
    295         # transform according to vocabulary

/usr/local/lib/python3.5/site-packages/splearn/feature_extraction/text.py in _init_vocab(self, analyzed_docs)
    152             accum = analyzed_docs._rdd.context.accumulator(set(), SetAccum())
    153             analyzed_docs.foreach(
--> 154                 lambda x: accum.add(set(chain.from_iterable(x))))
    155             vocabulary = {t: i for i, t in enumerate(accum.value)}
    156         else:

/usr/local/lib/python3.5/site-packages/splearn/rdd.py in bypass(*args, **kwargs)
    172         """
    173         def bypass(*args, **kwargs):
--> 174             result = getattr(self._rdd, attr)(*args, **kwargs)
    175             if isinstance(result, RDD):
    176                 if result is self._rdd:

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/rdd.py in foreach(self, f)
    745                 f(x)
    746             return iter([])
--> 747         self.mapPartitions(processPartition).count()  # Force evaluation
    748 
    749     def foreachPartition(self, f):

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/rdd.py in count(self)
   1002         3
   1003         """
-> 1004         return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
   1005 
   1006     def stats(self):

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/rdd.py in sum(self)
    993         6.0
    994         """
--> 995         return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
    996 
    997     def count(self):

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/rdd.py in fold(self, zeroValue, op)
    867         # zeroValue provided to each partition is unique from the one provided
    868         # to the final reduce call
--> 869         vals = self.mapPartitions(func).collect()
    870         return reduce(op, vals, zeroValue)
    871 

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/rdd.py in collect(self)
    769         """
    770         with SCCallSiteSync(self.context) as css:
--> 771             port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    772         return list(_load_from_socket(port, self._jrdd_deserializer))
    773 

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
    811         answer = self.gateway_client.send_command(command)
    812         return_value = get_return_value(
--> 813             answer, self.gateway_client, self.target_id, self.name)
    814 
    815         for temp_arg in temp_args:

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/pyspark/sql/utils.py in deco(*a, **kw)
     43     def deco(*a, **kw):
     44         try:
---> 45             return f(*a, **kw)
     46         except py4j.protocol.Py4JJavaError as e:
     47             s = e.java_exception.toString()

/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    306                 raise Py4JJavaError(
    307                     "An error occurred while calling {0}{1}{2}.\n".
--> 308                     format(target_id, ".", name), value)
    309             else:
    310                 raise Py4JError(

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 3 in stage 8.0 failed 1 times, most recent failure: Lost task 3.0 in stage 8.0 (TID 35, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
    process()
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
    vs = list(itertools.islice(iterator, batch))
  File "/usr/local/lib/python3.5/site-packages/splearn/feature_extraction/text.py", line 289, in <lambda>
    A = Z.transform(lambda X: list(map(analyze, X)), column='X').persist()
  File "/usr/local/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 238, in <lambda>
    tokenize(preprocess(self.decode(doc))), stop_words)
  File "/usr/local/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 204, in <lambda>
    return lambda x: strip_accents(x.lower())
AttributeError: 'numpy.ndarray' object has no attribute 'lower'

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at scala.Option.foreach(Option.scala:236)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
    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:231)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
    at py4j.Gateway.invoke(Gateway.java:259)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:209)
    at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
    process()
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/usr/local/Cellar/apache-spark/1.6.1/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
    vs = list(itertools.islice(iterator, batch))
  File "/usr/local/lib/python3.5/site-packages/splearn/feature_extraction/text.py", line 289, in <lambda>
    A = Z.transform(lambda X: list(map(analyze, X)), column='X').persist()
  File "/usr/local/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 238, in <lambda>
    tokenize(preprocess(self.decode(doc))), stop_words)
  File "/usr/local/lib/python3.5/site-packages/sklearn/feature_extraction/text.py", line 204, in <lambda>
    return lambda x: strip_accents(x.lower())
AttributeError: 'numpy.ndarray' object has no attribute 'lower'

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    ... 1 more

Any idea of how to correctly vectorize X with sparkit-learn and why this Py4JJavaError occurred?.

[fulibacsi]

Hi,

Instead of: X = [df['text'].values] Use: X = df['text'].values In your version, X is a list of numpy arrays so simply removing the brackets should solve your problem.