Compatibility with PySpark 3.0.0 and NumPy

[browshanravan]

When I run StratifiedCrossValidator instead of CrossValidator with my pipeline, I get the following error, which I suspect relates to the newer version of PySpark and/or NumPy since spark_stratifier installs pyspark-2.3.2 and numpy==1.15.1 as part of its installation.

Any plans for upgrading the package?

---------------------------------------------------------------------------
AnalysisException                         Traceback (most recent call last)
<ipython-input-4-e237f44298bb> in <module>
    237 
    238 
--> 239 cvModel = crossval.fit(train)
    240 predictions = cvModel.transform(test)

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/pyspark/ml/base.py in fit(self, dataset, params)
    127                 return self.copy(params)._fit(dataset)
    128             else:
--> 129                 return self._fit(dataset)
    130         else:
    131             raise ValueError("Params must be either a param map or a list/tuple of param maps, "

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/spark_stratifier/stratifier.py in _fit(self, dataset)
     45     metrics = [0.0] * numModels
     46 
---> 47     stratified_data = self.stratify_data(dataset)
     48 
     49     for i in range(nFolds):

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/spark_stratifier/stratifier.py in stratify_data(self, dataset)
     26     split_ratio = 1.0 / nFolds
     27 
---> 28     passes = dataset[dataset['label'] == 1]
     29     fails = dataset[dataset['label'] == 0]
     30 

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/pyspark/sql/dataframe.py in __getitem__(self, item)
   1378         """
   1379         if isinstance(item, basestring):
-> 1380             jc = self._jdf.apply(item)
   1381             return Column(jc)
   1382         elif isinstance(item, Column):

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args)
   1303         answer = self.gateway_client.send_command(command)
   1304         return_value = get_return_value(
-> 1305             answer, self.gateway_client, self.target_id, self.name)
   1306 
   1307         for temp_arg in temp_args:

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
    135                 # Hide where the exception came from that shows a non-Pythonic
    136                 # JVM exception message.
--> 137                 raise_from(converted)
    138             else:
    139                 raise

~/PycharmProjects/Data School/DS_Pandas_tut/venv/lib/python3.7/site-packages/pyspark/sql/utils.py in raise_from(e)

AnalysisException: Cannot resolve column name "label" among (type, amount, oldbalanceOrg, newbalanceOrig, isFraud, sample_weight_per_class);