from sklearn.datasets import load_iris
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier, export_graphviz
def knn_iris():
# 1.加载数据集
iris = load_iris()
# 2.数据划分
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
# 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
# 1.直接比较
y_predict = estimator.predict(x_test)
print("直接比较：n", y_test == y_predict)
# 2.计算准确率
score = estimator.score(x_test, y_test)
print("准确率为：", score)
def knn_iris_gscv():
"""
KNN算法对鸢尾花进行分类：添加网格搜索和交叉验证
:return:
"""
# 加载数据集
iris = load_iris()
# 数据集拆分
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
# 标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 预估器生成模型
estimator = KNeighborsClassifier()
param_list = {"n_neighbors": [1, 3, 5, 7, 9]}
estimator = GridSearchCV(estimator, param_grid=param_list, cv=10)
estimator.fit(x_train, y_train)
# 评估模型
# 1.直接比较模型值
y_predict = estimator.predict(x_test)
print("直接比较：", y_test == y_predict)
# 2.计算准确率
score = estimator.score(x_test, y_test)
print("准确率：", score)
# 最佳参数 best_params
print("最佳参数：", estimator.best_params_)
# 最佳结果
print("最佳结果：", estimator.best_score_)
# 最佳估计器
print("最佳估计器:", estimator.best_estimator_)
# 交叉验证结果
print("交叉验证结果：", estimator.cv_results_)
def nb_demo():
"""
朴素贝叶斯：对新闻进行分类
:return:
"""
# 加载数据集
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)
# 进行文本特征提取
transfer = TfidfVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 生成模型
estimator = MultinomialNB()
estimator.fit(x_train, y_train)
# 模型评估
# 直接比较真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:", y_predict)
print("真实值和预测值：", y_predict == y_test)
# 计算准确率
score = estimator.score(x_test, y_test)
print("准确率：", score)
def decision_iris():
"""
用决策树对鸢尾花进行分类
:return:
"""
# 加载数据
iris = load_iris()
# 数据集划分
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
# 生成模型
estimator = DecisionTreeClassifier(criterion="entropy")
estimator.fit(x_train, y_train)
# 模型评估
# 将真实值和预估值进行比较
y_predict = estimator.predict(x_test)
print("y_predict:", y_predict)
print("真实值和预估值：", y_predict == y_test )
# 计算准确率
score = estimator.score(x_test, y_test)
print("score:", score)
# 可视化树
export_graphviz(estimator, out_file="iris_tree.dot", feature_names=iris.feature_names)
if __name__ == '__main__':
# knn_iris()
# knn_iris_gscv()
# nb_demo()
decision_iris()
