add test

tensnsorflow/applist.py

@@ -68,25 +68,26 @@ def sort_app():
                 "job": {"智联招聘", "前程无忧", "斗米", "拉勾", "Boss直聘", "猎聘同道", "智联招聘"}
                  }
     df["app_list"] = df["app_list"].apply(json_format)
+    n = df.shape[0]
     for i in category.keys():
         df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 0)
         print(i)
-        print(df[i].value_counts())
+        print(df.loc[df[i]==1].shape[0]/n)
     df = df.drop("app_list",axis=1)
 
-    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
-    print(df.shape)
-    n = 200000
-    for i in range(0,df.shape[0],n):
-        print(i)
-        if i == 0:
-            temp = df.loc[0:n]
-        elif i+n > df.shape[0]:
-            temp = df.loc[i+1:]
-        else:
-            temp = df.loc[i+1:i+n]
-        pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
-        print("insert done")
+    # yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
+    # print(df.shape)
+    # n = 200000
+    # for i in range(0,df.shape[0],n):
+    #     print(i)
+    #     if i == 0:
+    #         temp = df.loc[0:n]
+    #     elif i+n > df.shape[0]:
+    #         temp = df.loc[i+1:]
+    #     else:
+    #         temp = df.loc[i+1:i+n]
+    #     pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
+    #     print("insert done")
 
 
 

tensnsorflow/test.py

@@ -48,7 +48,7 @@ def click():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
     sql = "select d.cid_id,f.level1_ids,f.level2_ids from data_feed_click d left join diary_feat f " \
           "on d.cid_id = f.diary_id where d.device_id = '358035085192742' " \
-          "and d.cid_type = 'diary' and d.stat_date > '2018-12-20'"
+          "and (d.cid_type = 'diary' or d.cid_type = 'diary_video') and d.stat_date > '2018-12-20'"
     df = con_sql(db, sql)
 
     n = df.shape[0]