|
机器学习基础（4）：朴素贝叶斯算法（附python代码和详细注释）
夏羽菲:
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
def naivebayes():
"""
朴素贝叶斯进行文本分类
:return: None
"""
news = fetch_20newsgroups(subset="all")
# 对数据集进行划分
x_train, x_test, y_train, y_test = train_test_split(news.data, news.target, test_size=0.25)
# 对数据集进行特征抽取
tf = TfidfVectorizer()
x_train = tf.fit_transform(x_train)
# 打印特征名称（如果有需要的话）
# print(tf.get_feature_names())
x_test = tf.transform(x_test)
# 进行朴素贝叶斯算法
mlt = MultinomialNB(alpha=1.0)
mlt.fit(x_train, y_train)
# 打印训练数据的稀疏表示（如果有需要的话）
# print(x_train.toarray())
y_predict = mlt.predict(x_test)
print("预测的文章类别为：", y_predict)
# 获得准确率
print("准确率为：", mlt.score(x_test, y_test))
print("每个类别的精确率和召回率", classification_report(y_test, y_predict, target_names=news.target_names))
return None
if __name__ == "__main__":
naivebayes()
|