change test file

rerank_esmm.py

@@ -2,6 +2,7 @@ import pymysql
 import datetime
 import json
 import redis
+import pandas as pd
 
 
 def get_esmm_users():
@@ -9,7 +10,6 @@ def get_esmm_users():
                          passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
     cursor = db.cursor()
     stat_date = (datetime.date.today() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
-    print(stat_date)
     sql = "select distinct device_id,city_id from data_feed_exposure_precise " \
           "where stat_date = '{}'".format(stat_date)
     cursor.execute(sql)
@@ -18,26 +18,34 @@ def get_esmm_users():
     return result
 
 
-def get_user_profile(device_id = "9C5E7C73-380C-4623-8F48-A64C8034E315"):
-    r = redis.Redis(host="172.16.40.135", port=5379, password="", db=2)
-    key = "user:portrait_tags:cl_id:" + str(device_id)
-    tmp = json.loads(r.get(key).decode('utf-8'))
-    tag_score = {}
-    for i in tmp:
-        if i["type"] == "tag":
-            tag_score[i["content"]] = i["score"]
-        elif i["content"] in name_tag.keys():
-            tag_score[name_tag[i["content"]]] = i["score"]
-    tag_sort = sorted(tag_score.items(), key=lambda x: x[1], reverse=True)
-    tags = []
-    if len(tag_sort) > 5:
-        for i in range(5):
-            tags.append(i[0])
-    else:
-        for i in tag_sort:
-            tags.append(i[0])
+def get_user_profile(device_id):
+    try:
+        r = redis.Redis(host="172.16.40.135", port=5379, password="", db=2)
+        key = "user:portrait_tags:cl_id:" + str(device_id)
+        if r.exists(key):
+            tmp = json.loads(r.get(key).decode('utf-8'))
+            tag_score = {}
+            for i in tmp:
+                if i["type"] == "tag":
+                    tag_score[i["content"]] = i["score"]
+                elif i["content"] in name_tag.keys():
+                    tag_score[name_tag[i["content"]]] = i["score"]
+            tag_sort = sorted(tag_score.items(), key=lambda x: x[1], reverse=True)
+            tags = []
+            if len(tag_sort) > 5:
+                for i in range(5):
+                    tags.append(i[0])
+            else:
+                for i in tag_sort:
+                    tags.append(i[0])
+
+            return tags
+        else:
+            return []
+    except:
+        return []
+
 
-    return tags
 
 
 def get_searchworlds_to_tagid():
@@ -50,7 +58,6 @@ def get_searchworlds_to_tagid():
         tag_id = cursor.fetchall()
         db.close()
         searchworlds_to_tagid = {}
-
         for i in tag_id:
             searchworlds_to_tagid[i[1]] = i[0]
 
@@ -73,8 +80,9 @@ def get_queues(device_id,city_id):
     else:
         return []
 
-def tag_boost(cid_str, tag_list=[15,21,22,85,86]):
-    if cid_str is not None or cid_str != "":
+
+def tag_boost(cid_str, tag_list):
+    if cid_str is not None and cid_str != "":
         cids = cid_str.split(",")
         try:
             if len(cids) > 6 and len(tag_list) > 0:
@@ -140,29 +148,33 @@ def to_data_base(df,table_name = "tag_boost_device_diary_queue"):
     pass
 
 
-def make_sample(uid,city_id,native_queue,nearby_queue,megacity_queue,nation_queue):
-    pass
-
 
 if __name__ == "__main__":
-    # users_list = get_esmm_users()
-    # total_samples = list()
-    # name_tag = get_searchworlds_to_tagid()
-    # for i in users_list:
-    #     tag_list = get_user_profile(i[0])
-    #     queues = get_queues(i[0],i[1])
-    #
-    #     native_sort_list = tag_boost(native, tag_score)
-    #     nearby_sort_list = tag_boost(nearby, tag_score)
-    #
-    #     sample = make_sample(uid,city_id,native_queue,nearby_queue,megacity_queue,nation_queue)
-    #     total_samples.append(sample)
-    #
-    # total_samples.todf
+    users_list = get_esmm_users()
+    total_samples = list()
+    name_tag = get_searchworlds_to_tagid()
+    # TODO 把下面的截断改掉
+    for i in users_list[:6]:
+        tag_list = get_user_profile(i[0])
+        queues = get_queues(i[0],i[1])
+        if len(queues) > 0:
+            new_native = tag_boost(queues[0], tag_list)
+            new_nearby = tag_boost(queues[1], tag_list)
+
+            sample = [i[0],i[1],new_native,new_nearby,queues[2],queues[3]]
+            total_samples.append(sample)
+
+    if len(total_samples) > 0:
+        df = pd.DataFrame(total_samples)
+        df = df.rename(columns={0: "device_id", 1: "city_id",2:"native_queue",
+                                3:"nearby_queue",4:"nation_queue",5:", megacity_queue"})
+        print(df.head(6))
     # to_data_base(df)
     # to kv
-    cid_str = "16473983,16296886,16199213,16193883,16419499,16372783,16430184,16617593,16498902,16238415,16214258,15715721,16213338,15349114,14091428,16268804,15485655,16448547,16179842,16685025,16612412,16683132,15646229,16482213,16485831,16436136,16353856,16400696,16193006,16294202,16393228,16716816,16713343,16780702,16107140,16647027,16112786,16503037,16372681,16207971,16179934,16480641,16295094,16204980,16317847,16434907,16117929,15633591,16116818"
-    print(tag_boost(cid_str))
+
+
+    # cid_str = "16473983,16296886,16199213,16193883,16419499,16372783,16430184,16617593,16498902,16238415,16214258,15715721,16213338,15349114,14091428,16268804,15485655,16448547,16179842,16685025,16612412,16683132,15646229,16482213,16485831,16436136,16353856,16400696,16193006,16294202,16393228,16716816,16713343,16780702,16107140,16647027,16112786,16503037,16372681,16207971,16179934,16480641,16295094,16204980,16317847,16434907,16117929,15633591,16116818"
+    # print(tag_boost(cid_str))