#机器学习#朴素贝叶斯

 

 

 

 

 

 

 

 

from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics import classification_report

def naviebayes():
    """
    朴素贝叶斯进行文本分类
    :return: None
    """
    news = fetch_20newsgroups(subset='all')

    # 进行数据分割
    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()

    # 以训练集当中的词的列表进行每篇文章重要性统计['a','b','c','d']
    x_train = tf.fit_transform(x_train)

    print(tf.get_feature_names())

    x_test = tf.transform(x_test)

    # 进行朴素贝叶斯算法的预测
    mlt = MultinomialNB(alpha=1.0)

    print(x_train.toarray())

    mlt.fit(x_train, y_train)

    y_predict = mlt.predict(x_test)

    print("预测的文章类别为：", y_predict)

    # 得出准确率
    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__":
    naviebayes()

缺点：训练集误差大，结果一定不好，不需要调参，由于使用了样本独立性假设，所以样本属性有关联时，其效果也不好

优点：分类效率稳定，对缺失的数据不敏感，算法比较简单，常用于文本分类

分类准确度高，速度快

 

 

 

 

 

 

 

 

 

 

 

 

 # 进行网格搜索
    gc = GridSearchCV(knn, param_grid=param, cv=2)

    gc.fit(x_train, y_train)

    # 预测准确率
    print("在测试集上准确率：", gc.score(x_test, y_test))

    print("在交叉验证当中最好的结果：", gc.best_score_)

    print("选择最好的模型是：", gc.best_estimator_)

    print("每个超参数每次交叉验证的结果：", gc.cv_results_)