KNN算法对鸢尾花数据集进行分类

#!/usr/bin/python
# coding=utf-8
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV

def knn_demo():
    #KNN算法对鸢尾花数据集进行分类,并用网格化搜索与交叉验证

    #获取数据
    iris = load_iris()

    #划分数据
    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6)

    #特征工程：标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer. transform(x_test)

    #KNN算法预估器，网格化搜索与交叉验证
    estimator = KNeighborsClassifier()

    pram_dict = {"n_neighbors": [1, 3, 5, 7, 9]}
    estimator = GridSearchCV(estimator, param_grid=pram_dict, cv=10)

    estimator.fit(x_train, y_train)

    #模型评估
    #方法一：比对真实值和预测值
    y_predict = estimator.predict(x_test)
    print "y_predict:\n", y_predict
    print "对比真实值和预测值:\n", y_test== y_predict

    #方法二：计算正确率
    score = estimator.score(x_test, y_test)
    print "准确率：\n", score
    print "最佳参数：", estimator.best_params_
    print "最佳结果：", estimator.best_score_
    print "最佳估计器：", estimator.best_estimator_
    print "交叉验证结果：", estimator.cv_results_
    return None

knn_demo()