Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

add a README.md and fix start.sh with a cat command to merge all files

diaryCandidateSet.py

@@ -45,8 +45,9 @@ def get_eachCityDiaryTop2000():
     cityList = get_cityList()
     allCitiesTop2000 = get_allCitiesDiaryTop2000()
     for i in cityList:
-        sql = "select '{0}',cid from data_feed_click " \
-              "where cid_type = 'diary' group by cid order by max(click_count_choice) desc limit 2000".format(i)
+        sql = "select city_id,cid from data_feed_click " \
+              "where cid_type = 'diary' and city_id = '{0}' group by cid " \
+              "order by max(click_count_choice) desc limit 2000".format(i)
         data = con_sql(sql)
         data = data.rename(columns={0: "city_id", 1: "cid"})
         data = filter_cid(data)

predictDiary.py

@@ -73,7 +73,7 @@ def upload_predict(user_profile, instance):
 def wrapper_result(prob, device_id):
     prob = prob.head(500)
     prob.loc[:,"url"] = prob["cid"].apply(lambda x: "http://m.igengmei.com/diary_book/" + str(x[6:]) + '/')
-    prob.to_csv(DIRECTORY_PATH + "result/{}_feed".format(device_id),index= False)
+    prob.to_csv(DIRECTORY_PATH + "result/feed_{}".format(device_id),index= False)
 
 
 def router(device_id):
@@ -86,4 +86,4 @@ def router(device_id):
 
 
 if __name__ == "__main__":
-    router(device_id='358035085192742')
+    router(device_id='EDEE004A-40AC-4ACD-9D3F-D54480EACEE9')