dist test

eda/esmm/Model_pipline/dist_predict.py

@@ -281,6 +281,8 @@ if __name__ == "__main__":
         te_result_dataframe = spark.createDataFrame(indices.flatMap(lambda x: x.split(";")).map(
             lambda l: Row(sample_id=l.split(":")[0],uid=l.split(":")[1],city=l.split(":")[2],cid_id=l.split(":")[3],ctcvr=l.split(":")[4])))
 
+        print("nearby rdd data")
+        te_result_dataframe.show()
         nearby_data = te_result_dataframe.toPandas()
         print("nearby pd data")
         nearby_data.head()