change test file

tensnsorflow/zhang.py

@@ -335,10 +335,10 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
 
     rdd.persist(storageLevel= StorageLevel.MEMORY_ONLY_SER)
 
-    # native_pre = spark.createDataFrame(rdd.filter(lambda x:x[0] == 0).map(lambda x:(x[3],x[4],x[5])))\
-    #     .toDF("city","uid","cid_id")
-    # print("native csv")
-    # native_pre.toPandas().to_csv(local_path+"native.csv", header=True)
+    native_pre = spark.createDataFrame(rdd.filter(lambda x:x[0] == 0).map(lambda x:(x[3],x[4],x[5])))\
+        .toDF("city","uid","cid_id")
+    print("native csv")
+    native_pre.toPandas().to_csv(local_path+"native.csv", header=True)
     spark.createDataFrame(rdd.filter(lambda x: x[0] == 0)
                           .map(lambda x: (x[1], x[2], x[6], x[7], x[8], x[9], x[10], x[11],
                                           x[12], x[13], x[14], x[15], x[16], x[17], x[18]))) \
@@ -349,10 +349,10 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     h = time.time()
     print((h-f)/60)
 
-    # nearby_pre = spark.createDataFrame(rdd.filter(lambda x: x[0] == 1).map(lambda x: (x[3], x[4], x[5]))) \
-    #     .toDF("city", "uid", "cid_id")
-    # print("nearby csv")
-    # nearby_pre.toPandas().to_csv(local_path + "nearby.csv", header=True)
+    nearby_pre = spark.createDataFrame(rdd.filter(lambda x: x[0] == 1).map(lambda x: (x[3], x[4], x[5]))) \
+        .toDF("city", "uid", "cid_id")
+    print("nearby csv")
+    nearby_pre.toPandas().to_csv(local_path + "nearby.csv", header=True)
 
     spark.createDataFrame(rdd.filter(lambda x: x[0] == 1)
                           .map(lambda x: (x[1], x[2], x[6], x[7], x[8], x[9], x[10], x[11],