3-2-1 文本数据处理导论

0423+2509165015/2.py

@@ -0,0 +1,10 @@
+sent1 = "猫 抓 老鼠"
+sent2 = "老鼠 抓 猫"
+vocab_sent = sorted(set(sent1.split() + sent2.split()))
+vec1 = [sent1.split().count(word) for word in vocab_sent]
+vec2 = [sent2.split().count(word) for word in vocab_sent]
+print("句子1向量：", vec1)
+print("句子2向量：", vec2)
+print("向量是否相同：", vec1 == vec2)
+large_vocab = [f"word_{i}" for i in range(10000)]
+print(f"大词表维度：{len(large_vocab)}")