Create keywords_processor.py

keywords_processor.py

@@ -0,0 +1,10 @@
+import re
+from sklearn.feature_extraction.text import CountVectorizer
+
+def process_keywords(text):
+    """テキストからN-gramを生成してリストとして返す"""
+    text = re.sub(r"[,\\n]+", " ", text)
+    vectorizer = CountVectorizer(ngram_range=(1, 3))
+    X = vectorizer.fit_transform([text])
+    features = vectorizer.get_feature_names_out()
+    return features