上传文件至 /

ljh.py

@@ -1,67 +1,21 @@
-
-print("题目1 ")
-
-hello1 = "Hello"  
-hello2 = 'Hello'  
-print("双引号表示:", hello1)
-print("单引号表示:", hello2)
+from sklearn.feature_extraction.text import CountVectorizer
 
 
-print("\n1. 'Hello' 每个字符的ASCII码:")
-for c in hello1:
-    print(f"字符 '{c}' → ASCII: {ord(c)}")
+docs = [
+    "Python 是 编程 语言",
+    "Java 是 编程 语言",
+    "Python Python Python"
+]
 
 
-print("\n2. 验证ASCII码65对应的字符:")
-print(f"chr(65) → {chr(65)}")
+vectorizer = CountVectorizer()
+X = vectorizer.fit_transform(docs)
 
 
-
-import math
+print("词表（Vocabulary）：")
+print(vectorizer.get_feature_names_out())
 
 
-print("\n题目3")
-A = [3, 4]
-B = [1, 2]
-
-
-A_plus_B = [A[0] + B[0], A[1] + B[1]]
-print(f"1. A + B = {A_plus_B}")
-
-
-two_times_A = [2 * A[0], 2 * A[1]]
-print(f"2. 2 × A = {two_times_A}")
-
-
-len_A = math.sqrt(A[0] ** 2 + A[1] ** 2)
-print(f"3. 向量A的长度 = {len_A}")
-
-
-
-print("\n题目4")
-A3 = [1, 2, 3]
-B3 = [4, 5, 6]
-
-
-dot_product = A3[0]*B3[0] + A3[1]*B3[1] + A3[2]*B3[2]
-print(f"1. 点积A·B = {dot_product}")
-
-
-def cosine_similarity(a, b):
-    
-    dot = sum(x*y for x,y in zip(a,b))
-    
-    norm_a = math.sqrt(sum(x*x for x in a))
-    norm_b = math.sqrt(sum(x*x for x in b))
-    
-    return dot / (norm_a * norm_b)
-
-cos_sim = cosine_similarity(A3, B3)
-print(f"2. 余弦相似度 = {cos_sim:.4f}")
-
-
-A_test = [1, 0]
-B_test = [0, 1]
-cos_sim_test = cosine_similarity(A_test, B_test)
-print(f"3. A=[1,0], B=[0,1]的余弦相似度 = {cos_sim_test}")
-print("原因：两个向量正交（垂直），方向完全不同，所以余弦相似度为0")
+print("\n每个文档的BoW向量：")
+for i, doc_vec in enumerate(X.toarray()):
+    print(f"Doc{i+1}: {doc_vec}")