dist test

eda/esmm/Model_pipline/dist_predict.py

@@ -298,5 +298,17 @@ if __name__ == "__main__":
         # print("耗时(秒)：")
         # print((time.time()-b))
 
-        print("hello"+ "*"*100)
+        sentenceData = spark.createDataFrame([
+            (0.0, "I like Spark"),
+            (1.0, "Pandas is useful"),
+            (2.0, "They are coded by Python ")
+        ], ["label", "sentence"])
+
+
+        print("rdd data")
+        sentenceData.select("label").show()
+
+        print("pandas data")
+        pandas_df = sentenceData.toPandas()
+        print(pandas_df)