上传文件至 /

260423 43(2).py

@@ -0,0 +1,100 @@
+import jieba
+import math
+
+print("=" * 50)
+print("实战：jieba分词 + TF-IDF完整流程")
+print("=" * 50)
+
+def simple_tfidf_tokenized(docs, stopwords=None):
+    """
+    结合分词的TF-IDF实现
+    参数:
+        docs: 原始文档列表
+        stopwords: 停用词集合
+    返回:
+        vocab, tfidf_matrix
+    """
+
+    tokenized = []
+    for doc in docs:
+        words = jieba.cut(doc)
+        if stopwords:
+            words = [w for w in words if w not in stopwords and len(w) > 1]
+        else:
+            words = [w for w in words if len(w) > 1]
+        tokenized.append(words)
+
+    vocab_set = set()
+    for doc in tokenized:
+        vocab_set.update(doc)
+    vocab = sorted(list(vocab_set))
+
+    n_docs = len(tokenized)
+    tf_matrix = []
+    df_dict = {word: 0 for word in vocab}
+    
+    for doc in tokenized:
+        vec = [0] * len(vocab)
+        for word in doc:
+            if word in vocab:
+                idx = vocab.index(word)
+                vec[idx] += 1
+        tf_matrix.append(vec)
+
+    for vec in tf_matrix:
+        for j, count in enumerate(vec):
+            if count > 0:
+                word = vocab[j]
+                df_dict[word] += 1
+
+    idf = []
+    for word in vocab:
+        df = df_dict[word]
+        idf_j = math.log(n_docs / (df + 1)) + 1
+        idf.append(idf_j)
+
+    tfidf = []
+    for vec in tf_matrix:
+        tfidf_vec = [vec[i] * idf[i] for i in range(len(vec))]
+        tfidf.append(tfidf_vec)
+    
+    return vocab, tfidf, tokenized
+
+docs = [
+    "Python是一门很棒的编程语言",
+    "人工智能是未来的发展方向",
+    "深度学习是机器学习的一个分支",
+    "Python和Java都是很流行的编程语言"
+]
+
+stopwords = set(["的", "是", "一个", "很", "和", "在", "了"])
+
+vocab, tfidf_matrix, tokenized = simple_tfidf_tokenized(docs, stopwords)
+
+print("文档集合：")
+for i, doc in enumerate(docs):
+    print(f"  Doc{i+1}: {doc}")
+print()
+
+print(f"分词结果：")
+for i, words in enumerate(tokenized):
+    print(f"  Doc{i+1}: {' / '.join(words)}")
+print()
+
+print(f"词表（共{len(vocab)}个词）:")
+print(f"  {vocab}")
+print()
+
+print("TF-IDF矩阵：")
+for i, vec in enumerate(tfidf_matrix):
+    nonzero = [(vocab[j], round(vec[j], 4)) for j in range(len(vec)) if vec[j] > 0]
+    print(f"  Doc{i+1}: {nonzero}")
+
+print()
+
+print("每个文档最重要的词（TF-IDF值最高）：")
+for i, vec in enumerate(tfidf_matrix):
+    max_idx = max(range(len(vec)), key=lambda j: vec[j])
+    max_score = vec[max_idx]
+    if max_score > 0:
+        print(f"  Doc{i+1}: '{vocab[max_idx]}' (TF-IDF={max_score:.4f})")

260423 43.py

@@ -0,0 +1,23 @@
+documents=[
+    "Python是编程语言",
+    "Java是编程语言",
+    "Python Python Python"
+]
+word_list=[]
+for doc in documents:
+    words=doc.split()
+    for word in words:
+        if word not in word_list:
+            word_list.append(word)
+vocab=sorted(word_list)
+print("词变：",vocab)
+bow_vectors=[]
+for doc in documents:
+    words=doc.split()
+    vector=[words.count(word) for word in vocab]
+    bow_vectors.append(vector)
+for i,vec in enumerate(bow_vectors):
+    print(f"Doc{i+1}的向量表示:{vec}")
+
+#两个缺点：忽略词序与语义关系
+         #词汇维度爆炸与稀疏性