change test file

tensnsorflow/feature_test.py

@@ -173,28 +173,28 @@ def feature_engineer():
                       16 + apps_number + level2_number + level3_number + len(unique_values)))
     value_map = dict(zip(unique_values, temp))
 
-    sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
-          "u.channel,c.top,cut.time,dl.app_list,feat.level3_ids,doctor.hospital_id," \
-          "wiki.tag as tag1,question.tag as tag2,search.tag as tag3,budan.tag as tag4," \
-          "ot.tag as tag5,sixin.tag as tag6,cart.tag as tag7," \
-          "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
-          "from jerry_test.esmm_train_data_dwell e left join jerry_test.user_feature u on e.device_id = u.device_id " \
-          "left join jerry_test.cid_type_top c on e.device_id = c.device_id " \
-          "left join jerry_test.cid_time_cut cut on e.cid_id = cut.cid " \
-          "left join jerry_test.device_app_list dl on e.device_id = dl.device_id " \
-          "left join jerry_test.diary_feat feat on e.cid_id = feat.diary_id " \
-          "left join jerry_test.knowledge k on feat.level2 = k.level2_id " \
-          "left join jerry_test.wiki_tag wiki on e.device_id = wiki.device_id " \
-          "left join jerry_test.question_tag question on e.device_id = question.device_id " \
-          "left join jerry_test.search_tag search on e.device_id = search.device_id " \
-          "left join jerry_test.budan_tag budan on e.device_id = budan.device_id " \
-          "left join jerry_test.order_tag ot on e.device_id = ot.device_id " \
-          "left join jerry_test.sixin_tag sixin on e.device_id = sixin.device_id " \
-          "left join jerry_test.cart_tag cart on e.device_id = cart.device_id " \
-          "left join eagle.src_zhengxing_api_service service on e.diary_service_id = service.id " \
-          "left join eagle.src_zhengxing_api_doctor doctor on service.doctor_id = doctor.id " \
-          "where e.stat_date >= '{}'".format(start)
-
+    # sql = "select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer," \
+    #       "u.channel,c.top,cut.time,dl.app_list,feat.level3_ids,doctor.hospital_id," \
+    #       "wiki.tag as tag1,question.tag as tag2,search.tag as tag3,budan.tag as tag4," \
+    #       "ot.tag as tag5,sixin.tag as tag6,cart.tag as tag7," \
+    #       "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
+    #       "from jerry_test.esmm_train_data_dwell e left join jerry_test.user_feature u on e.device_id = u.device_id " \
+    #       "left join jerry_test.cid_type_top c on e.device_id = c.device_id " \
+    #       "left join jerry_test.cid_time_cut cut on e.cid_id = cut.cid " \
+    #       "left join jerry_test.device_app_list dl on e.device_id = dl.device_id " \
+    #       "left join jerry_test.diary_feat feat on e.cid_id = feat.diary_id " \
+    #       "left join jerry_test.knowledge k on feat.level2 = k.level2_id " \
+    #       "left join jerry_test.wiki_tag wiki on e.device_id = wiki.device_id " \
+    #       "left join jerry_test.question_tag question on e.device_id = question.device_id " \
+    #       "left join jerry_test.search_tag search on e.device_id = search.device_id " \
+    #       "left join jerry_test.budan_tag budan on e.device_id = budan.device_id " \
+    #       "left join jerry_test.order_tag ot on e.device_id = ot.device_id " \
+    #       "left join jerry_test.sixin_tag sixin on e.device_id = sixin.device_id " \
+    #       "left join jerry_test.cart_tag cart on e.device_id = cart.device_id " \
+    #       "left join eagle.src_zhengxing_api_service service on e.diary_service_id = service.id " \
+    #       "left join eagle.src_zhengxing_api_doctor doctor on service.doctor_id = doctor.id " \
+    #       "where e.stat_date >= '{}'".format(start)
+    #
     # df = spark.sql(sql)
     #
     # df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
@@ -240,7 +240,7 @@ def feature_engineer():
     # print(rdd.count())
     #
     # get_pre_number()
-
+    #
     # test = rdd.filter(lambda x: x[0] == validate_date).map(
     #     lambda x: (x[1], x[2], x[3], x[4], x[5], x[6], x[7], x[8], x[9],
     #                x[10], x[11], x[12], x[13],x[14]))
@@ -251,7 +251,7 @@ def feature_engineer():
     #     .repartition(1).write.format("tfrecords").save(path=path + "va/", mode="overwrite")
     #
     # print("va tfrecord done")
-
+    #
     # rdd.unpersist()
 
     return validate_date, value_map, app_list_map, leve2_map, leve3_map
@@ -314,29 +314,31 @@ 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],x[17])))\
-        .toDF("city","uid","cid_id","number")
-    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],x[17])))\
+    #     .toDF("city","uid","cid_id","number")
+    # 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]))) \
+                          .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[3],x[4],x[5]))) \
         .toDF("y","z","app_list", "level2_list", "level3_list","tag1_list", "tag2_list", "tag3_list", "tag4_list",
-              "tag5_list", "tag6_list", "tag7_list", "ids","number").repartition(100).write.format("tfrecords") \
+              "tag5_list", "tag6_list", "tag7_list", "ids","number","city","uid","cid_id").repartition(100).write.format("tfrecords") \
             .save(path=path+"test_native/", mode="overwrite")
     print("native tfrecord done")
     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],x[17]))) \
-        .toDF("city", "uid", "cid_id","number")
-    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],x[17]))) \
+    #     .toDF("city", "uid", "cid_id","number")
+    # 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], x[12], x[13], x[14], x[15], x[16],x[17]))) \
+        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[3],x[4],x[5]))) \
         .toDF("y", "z", "app_list", "level2_list", "level3_list", "tag1_list", "tag2_list", "tag3_list", "tag4_list",
-              "tag5_list", "tag6_list", "tag7_list", "ids","number").repartition(100).write.format("tfrecords") \
+              "tag5_list", "tag6_list", "tag7_list", "ids","number","city","uid","cid_id").repartition(100).write.format("tfrecords") \
         .save(path=path + "test_nearby/", mode="overwrite")
     print("nearby tfrecord done")