update

output/output_article_distribution_0917.py

@@ -135,6 +135,7 @@ second_demands_tag_count = {}
 projects_demands_tag_count = {}
 total_tag_count = {}
 total_tag_count_pro = {}
+temp_null_count = 0
 for redis_count,spark_res in enumerate(sql_res):
     # if redis_count >= 50:break
     second_demands = []
@@ -174,6 +175,8 @@ for redis_count,spark_res in enumerate(sql_res):
 
     if 0 <= total_tractate_content_num < 10:
         bulk_dict[0][1] += 1
+        if not second_demands and projects:
+            temp_null_count += 1
         if second_demands:
             for tag in second_demands:
                 if tag in total_tag_count:
@@ -203,6 +206,7 @@ for redis_count,spark_res in enumerate(sql_res):
 
     if redis_count % 5000 == 0:
         print(redis_count,bulk_dict)
+        print(temp_null_count)
         # print(second_demands_tag_count,projects_demands_tag_count)
 print(total_tag_count)
 print(total_tag_count_pro)