refacter: Model updated | 중복 코드 함수화

Model/lsa_Similar.py

@@ -7,27 +7,20 @@
 tfidf_vectorizer = TfidfVectorizer()
 komoran = Komoran('STABLE')
 
+def preprocess_text(text):
+    tokens = (komoran.get_plain_text(text)).split(' ')
+    words = [token.split('/')[0] for token in tokens]
+    return ' '.join(words)
+
 def lsa_Similar(contents, answer):
-    test = (komoran.get_plain_text(contents[0])).split(' ')
-    for j in range(len(test)):
-        temp = test[j].split('/')
-        test[j] = temp[0]
-        #print('여기',test)
-    test = ' '.join(test)
-    test2 = (komoran.get_plain_text(answer[0])).split(' ')
-    for j in range(len(test2)):
-        temp = test2[j].split('/')
-        test2[j] = temp[0]
-        #print('여기',test)
-    test2 = ' '.join(test2)
-    tfidf_vectorizer = TfidfVectorizer()
-    tfidf_matrix = tfidf_vectorizer.fit_transform([test, test2])
+    contents_preprocessed = preprocess_text(contents[0])
+    answer_preprocessed = preprocess_text(answer[0])
+
+    tfidf_matrix = tfidf_vectorizer.fit_transform([contents_preprocessed, answer_preprocessed])
 
-    # LSA를 사용하여 차원 축소
     lsa = TruncatedSVD(n_components=2)
     lsa_matrix = lsa.fit_transform(tfidf_matrix)
 
-    # 문장 간 유사도 계산
     similarity_matrix = cosine_similarity(lsa_matrix)
 
     response = {