赞
踩
目录
朴素?
假设:特征与特征之间是相互独立的
朴素 + 贝叶斯
- from sklearn.datasets import load_iris, fetch_20newsgroups
- from sklearn.feature_extraction.text import TfidfVectorizer
- from sklearn.model_selection import train_test_split, GridSearchCV
- from sklearn.naive_bayes import MultinomialNB
- from sklearn.neighbors import KNeighborsClassifier
- from sklearn.preprocessing import StandardScaler
-
- def knn_iris():
- # 用KNN 算法对鸢尾花进行分类
- # 1、获取数据
- iris = load_iris()
- # 2、划分数据集
- x_train,x_test,y_train,y_test = train_test_split(iris.data,iris.target,random_state=6)
- # 3、特征工程 - 标准化
- transfer = StandardScaler()
- x_train = transfer.fit_transform(x_train)
- x_test = transfer.transform(x_test)
- # 4、KNN 算法预估器
- estimator = KNeighborsClassifier(n_neighbors=3)
- estimator.fit(x_train,y_train)
- # 5、模型评估
- # 方法1 :直接比对真实值和预测值
- y_predict = estimator.predict(x_test)
- print("y_predict:\n",y_predict)
- print("直接比对真实值和预测值:\n",y_test == y_predict)
- # 方法2:计算准确率
- score = estimator.score(x_test,y_test)
- print("准确率为:\n",score)
- return None
-
- def knn_iris_gscv():
- # 用KNN 算法对鸢尾花进行分类,添加网格搜索和交叉验证
- # 1、获取数据
- iris = load_iris()
-
- # 2、划分数据集
- x_train,x_test,y_train,y_test = train_test_split(iris.data,iris.target,random_state=6)
-
- # 3、特征工程 - 标准化
- transfer = StandardScaler()
- x_train = transfer.fit_transform(x_train)
- x_test = transfer.transform(x_test)
-
- # 4、KNN 算法预估器
- estimator = KNeighborsClassifier()
- # 加入网格搜索和交叉验证
- # 参数准备
- param_dict = {"n_neighbors":[1,3,5,7,9,11]}
- estimator = GridSearchCV(estimator,param_grid=param_dict,cv=10)
- estimator.fit(x_train,y_train)
-
- # 5、模型评估
- # 方法1 :直接比对真实值和预测值
- y_predict = estimator.predict(x_test)
- print("y_predict:\n",y_predict)
- print("直接比对真实值和预测值:\n",y_test == y_predict)
- # 方法2:计算准确率
- score = estimator.score(x_test,y_test)
- print("准确率为:\n",score)
-
- # 最佳参数:best_params_
- print("最佳参数:\n",estimator.best_params_)
- # 最佳结果:best_score_
- print("最佳结果:\n",estimator.best_score_)
- # 最佳估计值:best_estimator_
- print("最佳估计值:\n",estimator.best_estimator_)
- # 交叉验证结果:cv_results_
- print("交叉验证结果:\n",estimator.cv_results_)
- return None
-
- def nb_news():
- # 用朴素贝叶斯算法对新闻进行分类
- # 1、获取数据
- news = fetch_20newsgroups(subset="all")
- # 2、划分数据集
- x_train,x_test,y_train,y_test = train_test_split(news.data,news.target)
- # 3、特征工程:文本特征抽取-tfidf
- transfer = TfidfVectorizer()
- x_train = transfer.fit_transform(x_train)
- x_test = transfer.transform(x_test)
- # 4、用朴素贝叶斯算法预估器流程
- estimator = MultinomialNB()
- estimator.fit(x_train,y_train)
- # 5、模型评估
- # 方法1 :直接比对真实值和预测值
- y_predict = estimator.predict(x_test)
- print("y_predict:\n", y_predict)
- print("直接比对真实值和预测值:\n", y_test == y_predict)
- # 方法2:计算准确率
- score = estimator.score(x_test, y_test)
- print("准确率为:\n", score)
- return None
-
- if __name__ == "__main__":
- # 代码1 :用KNN算法对鸢尾花进行分类
- # knn_iris()
- # 代码2 :用KNN算法对鸢尾花进行分类,添加网格搜索和交叉验证
- # knn_iris_gscv()
- # 代码3:用朴素贝叶斯算法对新闻进行分类
- nb_news()
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。