import pandas as pd import numpy as np from sklearn.feature_extraction.text import CountVectorizer from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import accuracy_score

读取训练数据和测试数据

train_data = pd.read_csv('BBC News Train.csv') test_data = pd.read_csv('BBC News Test.csv')

使用CountVectorizer将文本转化为向量

vectorizer = CountVectorizer(stop_words='english') train_text = vectorizer.fit_transform(train_data['Text']) test_text = vectorizer.transform(test_data['Text'])

使用KNN算法进行分类

knn = KNeighborsClassifier(n_neighbors=5) knn.fit(train_text, train_data['Category'])

预测测试数据的类别

test_predict = knn.predict(test_text)

计算准确率

accuracy = accuracy_score(test_data['Category'], test_predict) print('Accuracy:', accuracy)

输出结果为：Accuracy: 0.8