上传文件至 /

2026-04-23 15:58:58 +08:00
parent 3405f5c60d
commit 7a1725c1a3
2 changed files with 111 additions and 0 deletions
--- a/09.py
+++ b/09.py
@@ -0,0 +1,10 @@
+from sklearn.feature_extraction.text import CountVectorizer
+docs = [
+    "Pyhton是编程语言"
+    "Java是编程语言"
+    "Pyhton Python Pyhton"
+]
+vectorizer = CountVectorizer(token_pattern=r"(?u)\b\w+\b")
+X = vectorizer.fit_transform(docs)
+print("词表:",vectorizer.get_feature_names_out())
+print("文档向量:\n",X.toarray())