上传文件至 /

44龙再飞.py

@@ -1,31 +1,79 @@
 
 text = "Hello"
 print([ord(c) for c in text])
+
+
+text_cn = "你好"
+print([ord(c) for c in text_cn])
 print(chr(65))
 
 import numpy as np
-A = np.array([3, 4])
+
-B = np.array([1, 2])
+v1 = np.array([3])
-print(A + B)
+v2 = np.array([2, 3])
-print(2 * A)
+v3 = np.array([1, 2, 3])
-print(np.linalg.norm(A))
+print(v1, v2, v3)
-A = np.array([1, 2, 3])
+
-B = np.array([4, 5, 6])
+a = np.array([1, 2, 3])
-print(np.dot(A, B))
+b = np.array([4, 5, 6])
-cos = np.dot(A,B)/(np.linalg.norm(A)*np.linalg.norm(B))
+print("加法:", a + b)
-print(cos)
+
-A2 = np.array([1,0])
+
-B2 = np.array([0,1])
+print("数乘:", a * 2)
-print(np.dot(A2,B2)/(np.linalg.norm(A2)*np.linalg.norm(B2)))
+
+v = np.array([3, 4])
+print("长度:", np.linalg.norm(v))
+
+
+print("点积:", np.dot(a, b))
+print("点积(@):", a @ b)
+
+def cosine_similarity(a, b)
+    dot = np.dot(a, b),
+    norm_a = np.linalg.norm(a)
+    norm_b = np.linalg.norm(b)
+    return dot / (norm_a * norm_b)
+
+
+a1 = np.array([1,2,3])
+b1 = np.array([2,4,6])
+a2 = np.array([1,0])
+b2 = np.array([0,1])
+print("相似度1:", cosine_similarity(a1, b1))
+print("相似度2:", cosine_similarity(a2, b2))
+
+cat = np.array([0.9, 0.9, 0.8])
+dog = np.array([0.8, 0.9, 0.8])
+apple = np.array([0.1, 0.3, 0.0])
+print("猫vs狗:", cosine_similarity(cat, dog))
+print("猫vs苹果:", cosine_similarity(cat, apple))
+
 from sklearn.feature_extraction.text import CountVectorizer
-docs = ["Python 是 编程 语言","Java 是 编程 语言","Python Python Python"]
+docs = [
-vec = CountVectorizer()
+    "Python 是 编程 语言",
-print(vec.fit_transform(docs).toarray())
+    "Java 是 编程 语言",
-print(vec.get_feature_names_out())
+]
+vectorizer = CountVectorizer()
+bow = vectorizer.fit_transform(docs)
+print("词表:", vectorizer.get_feature_names_out())
+print("BoW矩阵:\n", bow.toarray())
 
 from sklearn.feature_extraction.text import TfidfVectorizer
-docs = ["Python 编程","Java 编程","Python Python"]
+docs_tfidf = [
+    "Python 编程 语言",
+    "Python Python Python",
+    "Java 编程 语言",
+]
 tfidf = TfidfVectorizer()
-matrix = tfidf.fit_transform(docs)
+tfidf_matrix = tfidf.fit_transform(docs_tfidf)
 print("词表:", tfidf.get_feature_names_out())
-print("矩阵:\n", matrix.toarray())
+print("TF-IDF矩阵:\n", tfidf_matrix.toarray())
+
+word_vectors = {
+    "猫": [0.9, 0.1, 0.2],
+    "狗": [0.8, 0.3, 0.1],
+    "苹果": [0.1, 0.2, 0.9],
+    "Python": [0.1, 0.0, 0.9],
+    "Java": [0.1, 0.0, 0.85],
+}
+print("猫vs狗:", cosine_similarity(word_vectors["猫"], word_vectors["狗"]))