data = sqlContext.sql("select a.churn,b.pay_amount,c.all_balance from db_bi.t_cust_churn a left join db_bi.t_cust_pay b on a.cust_id=b.cust_id left join db_bi.t_cust_balance c on a.cust_id=c.cust_id limit 5000").cache()
def labelData(df):
return df.map(lambda row: LabeledPoint(row[0], row[1:]))
traindata = labelData(data) --this step works well.
from pyspark.ml.classification import LogisticRegression
lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
lrModel = lr.fit(lrdata)
lrModel = lr.fit(lrdata)
AttributeError Traceback (most recent call last)
<ipython-input-40-b84a106121e6> in <module>()
----> 1 lrModel = lr.fit(lrdata)
/home/hadoop/spark/python/pyspark/ml/pipeline.pyc in fit(self, dataset, params)
67 return self.copy(params)._fit(dataset)
68 else:
---> 69 return self._fit(dataset)
70 else:
71 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/home/hadoop/spark/python/pyspark/ml/wrapper.pyc in _fit(self, dataset)
131
132 def _fit(self, dataset):
--> 133 java_model = self._fit_java(dataset)
134 return self._create_model(java_model)
135
/home/hadoop/spark/python/pyspark/ml/wrapper.pyc in _fit_java(self, dataset)
128 """
129 self._transfer_params_to_java()
--> 130 return self._java_obj.fit(dataset._jdf)
131
132 def _fit(self, dataset):
AttributeError: 'PipelinedRDD' object has no attribute '_jdf'