我有一个关于使用pyspark进行计数向量化的问题
这是我的数据框，没有空值
from pyspark.sql.functions import isnan, when, count, col, rand
datatrain.select([count(when(isnan(c), c)).alias(c) for c in datatrain.columns]).show()
+------+-------+--------------+---------------+
|labels|subject|cleanedSubject|subjectLanguage|
+------+-------+--------------+---------------+
| 0| 0| 0| 0|
+------+-------+--------------+---------------+
=
datatrain = datatrain.orderBy(rand(42))
datatrain.show(5)
+-------------------+--------------------+--------------------+---------------+
| labels| subject| cleanedSubject|subjectLanguage|
+-------------------+--------------------+--------------------+---------------+
|CATEGORY_PROMOTIONS|sebuah survei yan...| buah survei baru| id|
| CATEGORY_UPDATES|[reminder] pengum...|reminder pengumum...| et|
| CATEGORY_UPDATES|“what have we lea...|learn googl publi...| en|
| CATEGORY_SOCIAL|nova hairiyanov a...|nova hairiyanov a...| cy|
| CATEGORY_UPDATES|payout request re...|payout request re...| fr|
+-------------------+--------------------+--------------------+---------------+
这是我的管道
tokenizer = RegexTokenizer(inputCol="cleanedSubject",outputCol="cleanedSubject_token")
countVectorizer = CountVectorizer(inputCol="cleanedSubject_token",outputCol="features")
stringIndexer = StringIndexer(inputCol="labels",outputCol="label",stringOrderType="alphabetAsc")
classifier = LogisticRegression(regParam=0.1)
pipeline = Pipeline(stages=[stringIndexer,tokenizer,countVectorizer,classifier])
但是，尽管管道合适，但给我一个错误：
> Py4JJavaError Traceback (most recent call
> last) <ipython-input-230-beaf2f2c4310> in <module>
> ----> 1 pipeline = pipeline.fit(datatrain)
>
> /etc/spark/python/pyspark/ml/base.py in fit(self, dataset, params)
> 130 return self.copy(params)._fit(dataset)
> 131 else:
> --> 132 return self._fit(dataset)
> 133 else:
> 134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
>
> /etc/spark/python/pyspark/ml/pipeline.py in _fit(self, dataset)
> 107 dataset = stage.transform(dataset)
> 108 else: # must be an Estimator
> --> 109 model = stage.fit(dataset)
> 110 transformers.append(model)
> 111 if i < indexOfLastEstimator:
>
> /etc/spark/python/pyspark/ml/base.py in fit(self, dataset, params)
> 130 return self.copy(params)._fit(dataset)
> 131 else:
> --> 132 return self._fit(dataset)
> 133 else:
> 134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
>
> /etc/spark/python/pyspark/ml/wrapper.py in _fit(self, dataset)
> 293
> 294 def _fit(self, dataset):
> --> 295 java_model = self._fit_java(dataset)
> 296 model = self._create_model(java_model)
> 297 return self._copyValues(model)
>
> /etc/spark/python/pyspark/ml/wrapper.py in _fit_java(self, dataset)
> 290 """
> 291 self._transfer_params_to_java()
> --> 292 return self._java_obj.fit(dataset._jdf)
> 293
> 294 def _fit(self, dataset):
>
> /usr/lib/python3.7/site-packages/py4j/java_gateway.py in
> __call__(self, *args) 1284 answer = self.gateway_client.send_command(command) 1285 return_value
> = get_return_value(
> -> 1286 answer, self.gateway_client, self.target_id, self.name) 1287 1288 for temp_arg in temp_args:
>
> /etc/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
> 61 def deco(*a, **kw):
> 62 try:
> ---> 63 return f(*a, **kw)
> 64 except py4j.protocol.Py4JJavaError as e:
> 65 s = e.java_exception.toString()
>
> /usr/lib/python3.7/site-packages/py4j/protocol.py in
> get_return_value(answer, gateway_client, target_id, name)
> 326 raise Py4JJavaError(
> 327 "An error occurred while calling {0}{1}{2}.\n".
> --> 328 format(target_id, ".", name), value)
> 329 else:
> 330 raise Py4JError(
>
> Py4JJavaError: An error occurred while calling o1503.fit. :
> org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 13 in stage 190.0 failed 1 times, most recent failure: Lost task
> 13.0 in stage 190.0 (TID 5217, localhost, executor driver): org.apache.spark.SparkException: Failed to execute user defined
> function($anonfun$createTransformFunc$2: (string) => array<string>)
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown
> Source) at
> org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
[1]: https://i.stack.imgur.com/4DjZD.png [2]: https://i.stack.imgur.com/zKknc.png
我尝试用权标器手动转换数据集，并将其放入countvectorizer中，但给出相同的错误。谢谢你的帮助
火花2.4.1
python 3.7.2