规范特征工程文件中一个变量名字

tensnsorflow/feature_test.py

@@ -309,7 +309,7 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     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.coalesce(1).write.format('com.databricks.spark.csv').save(path + "native/", header='true')
+    native_pre.repartion(1).write.format('com.databricks.spark.csv').save(path + "native/", 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]))) \
         .toDF("y","z","app_list", "level2_list", "level3_list","tag1_list", "tag2_list", "tag3_list", "tag4_list",
@@ -322,7 +322,7 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     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.coalesce(1).write.format('com.databricks.spark.csv').save(path + "nearby/", header='true')
+    nearby_pre.repartion(1).write.format('com.databricks.spark.csv').save(path + "nearby/", header='true')
 
     spark.createDataFrame(rdd.filter(lambda x: x[0] == 1)
                           .map(
@@ -350,8 +350,33 @@ if __name__ == '__main__':
     path = "hdfs:///strategy/esmm/"
     local_path = "/home/gmuser/esmm/"
 
-    validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
-    get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+    # validate_date, value_map, app_list_map, leve2_map, leve3_map = feature_engineer()
+    # get_predict(validate_date, value_map, app_list_map, leve2_map, leve3_map)
+
+    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 >= '2019-06-10'"
+
+    df = spark.sql(sql)
+    df.save("hdfs:///strategy/esmm/native/d.csv", "com.databricks.spark.csv")
 
     spark.stop()