change test file

eda/esmm/Model_pipline/feature_engineering.py

@@ -182,7 +182,7 @@ def feature_engineer():
                 "channel", "top", "time", "stat_date", "hospital_id",
                 "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time",
                 "app_list", "level3_ids", "level2_ids", "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
-                "search_tag2", "search_tag3"]
+                "search_tag2", "search_tag3","content_level"]
     unique_values.extend(features)
     print("unique_values length")
     print(len(unique_values))
@@ -222,7 +222,7 @@ def feature_engineer():
 
     df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
                              "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids",
-                             "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7"])
+                             "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7","content_level"])
 
     df = df.na.fill(dict(zip(features, features)))
 
@@ -230,7 +230,8 @@ def feature_engineer():
                     "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
                     "ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time",
                     "hospital_id", "treatment_method", "price_min", "price_max", "treatment_time",
-                    "maintain_time", "recover_time", "search_tag2", "search_tag3","cid_id","device_id")\
+                    "maintain_time", "recover_time", "search_tag2", "search_tag3","cid_id","device_id",
+                    "content_level")\
         .rdd.repartition(200).map(
         lambda x: (x[0], float(x[1]), float(x[2]), app_list_func(x[3], app_list_map), app_list_func(x[4], leve2_map),
                    app_list_func(x[5], leve3_map), app_list_func(x[6], leve2_map), app_list_func(x[7], leve2_map),
@@ -240,7 +241,7 @@ def feature_engineer():
                     value_map.get(x[16], 5), value_map.get(x[17], 6), value_map.get(x[18], 7), value_map.get(x[19], 8),
                     value_map.get(x[20], 9), value_map.get(x[21], 10),
                     value_map.get(x[22], 11), value_map.get(x[23], 12), value_map.get(x[24], 13),
-                    value_map.get(x[25], 14), value_map.get(x[26], 15)],
+                    value_map.get(x[25], 14), value_map.get(x[26], 15),value_map.get(x[31], 16)],
                    app_list_func(x[27], leve2_map), app_list_func(x[28], leve3_map),x[13],x[29],x[30]
                    ))
 
@@ -290,7 +291,8 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
           "dl.app_list,e.hospital_id,feat.level3_ids," \
           "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,doris.search_tag2,doris.search_tag3," \
-          "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time " \
+          "k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time," \
+          "concat('star','_',star.content_level) as content_level " \
           "from jerry_test.esmm_pre_data 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 " \
@@ -305,13 +307,15 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
           "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 jerry_test.knowledge k on feat.level2 = k.level2_id " \
-          "left join jerry_test.search_doris doris on e.device_id = doris.device_id and e.stat_date = doris.get_date"
+          "left join jerry_test.search_doris doris on e.device_id = doris.device_id and e.stat_date = doris.get_date " \
+          "left join eagle.src_mimas_prod_api_diary star on e.cid_id = star.id " \
+          "where device_id = '868771031984211'"
 
     features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "time", "hospital_id",
                 "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time",
                 "app_list", "level3_ids", "level2_ids", "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
-                "search_tag2", "search_tag3"]
+                "search_tag2", "search_tag3","content_level"]
 
     df = spark.sql(sql)
     df = df.drop_duplicates(["ucity_id", "device_id", "cid_id"])
@@ -322,7 +326,7 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
                     "tag1", "tag2", "tag3", "tag4", "tag5", "tag6", "tag7",
                     "ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time",
                     "hospital_id", "treatment_method", "price_min", "price_max", "treatment_time",
-                    "maintain_time", "recover_time", "search_tag2", "search_tag3") \
+                    "maintain_time", "recover_time", "search_tag2", "search_tag3","content_level") \
         .rdd.repartition(200).map(lambda x: (x[0], float(x[1]), float(x[2]), x[3], x[4], x[5],
                                              app_list_func(x[6], app_list_map), app_list_func(x[7], leve2_map),
                                              app_list_func(x[8], leve3_map), app_list_func(x[9], leve2_map),
@@ -336,7 +340,7 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
                                               value_map.get(x[23], 9), value_map.get(x[24], 10),
                                               value_map.get(x[25], 11), value_map.get(x[26], 12),
                                               value_map.get(x[27], 13), value_map.get(x[28], 14),
-                                              value_map.get(x[29], 15)],
+                                              value_map.get(x[29], 15),value_map.get(x[32], 16)],
                                              app_list_func(x[30], leve2_map),app_list_func(x[31], leve3_map)))
 
     rdd.persist(storageLevel= StorageLevel.MEMORY_ONLY_SER)
@@ -389,14 +393,7 @@ if __name__ == '__main__':
     path = "hdfs:///strategy/esmm/"
     local_path = "/home/gmuser/esmm/"
 
-    sql = "select e.cid_id,concat('star','_',star.content_level) as content_level " \
-          "from jerry_test.esmm_train_data_dwell e " \
-          "left join eagle.src_mimas_prod_api_diary star on e.cid_id = star.id " \
-          "where e.stat_date = '2019-08-13'"
-
-    spark.sql(sql).show()
-
-    # 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)
 
     spark.stop()