浏览代码

min tokens len

ypv 2 年之前
父节点
当前提交
757e536810
共有 1 个文件被更改,包括 4 次插入3 次删除
  1. 4 3
      plagiat_1.v2.py

+ 4 - 3
plagiat_1.v2.py

@@ -17,12 +17,12 @@ from string import punctuation
 BASE_DIR = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
 # проверяемая директория
 # LECTION_DIR = os.path.join("EASvZI", "Лекции")
-LECTION_DIR = os.path.join("TZI", "Лекции", "ПМ3.1")
+LECTION_DIR = os.path.join("TZI", "Лекции", "ПМ3.2")
 
 # кого проверяем
 who = "Савкин"
 # ссылка для проверки
-url = "http://213.155.192.79:3001/ypv/TZI/raw/master/%d0%9b%d0%b5%d0%ba%d1%86%d0%b8%d0%b8/%d0%9f%d0%9c3.1/4.5.350_%d0%94%d0%be%d1%81%d1%82%d0%be%d0%b8%d0%bd%d1%81%d1%82%d0%b2%d0%b0_%d0%b8_%d0%bd%d0%b5%d0%b4%d0%be%d1%81%d1%82%d0%b0%d1%82%d0%ba%d0%b8_%d1%81%d0%bf%d1%83%d1%82%d0%bd%d0%b8%d0%ba%d0%be%d0%b2%d0%be%d0%b9_%d1%81%d0%b2%d1%8f%d0%b7%d0%b8_Starlink/Chubarov.md"
+url = "http://213.155.192.79:3001/u19-23shapovalov/TZI/raw/031542b6312416287de1830d2c77eb9a103f6ba8/%d0%9b%d0%b5%d0%ba%d1%86%d0%b8%d0%b8/%d0%9f%d0%9c3.2/2.2.300_%d0%a1%d1%82%d1%80%d1%83%d0%ba%d1%82%d1%83%d1%80%d0%b0_%d0%b8_%d1%81%d0%be%d1%81%d1%82%d0%b0%d0%b2_C%d0%9a%d0%a3%d0%94/README.md"
 
 # ------------------------------- / НАСТРОЙКИ ------------
 
@@ -165,8 +165,9 @@ for readme_str in readme_list:
         print(f"количество уникальных слов варианта: {len(set(variant_tokens))}")
 
         # пересечение множеств 
+        min_tokens_len = min([len(set(post_tokens)), len(set(variant_tokens))])
         c = list(set(post_tokens) & set(variant_tokens))
-        ratio = (1 - (len(c) / len(set(post_tokens)))) * 100
+        ratio = (1 - (len(c) / min_tokens_len)) * 100
         print(f"количество совпадающих слов: {len(c)} / {ratio:.2f}%")
         print()