调优前后knn鸢尾花

def knn_iris():
    # 获取数据
    iris = load_iris()
    # 划分数据集
    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
    # 特征工程:标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.fit_transform(x_test)
    # KNN算法预估器
    estimator = KNeighborsClassifier(n_neighbors=3)
    estimator.fit(x_train, y_train)
    # 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)


def knn_iris_gscv():
    # 添加网格搜索和交叉验证
    # 获取数据
    iris = load_iris()
    # 划分数据集
    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
    # 特征工程:标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.fit_transform(x_test)
    # KNN算法预估器
    estimator = KNeighborsClassifier()  # 不用添加k值了
    # 网格搜索与交叉验证
    # 数据准备
    param_data = {"n_neighbors": [1, 3, 5, 7, 9, 11]}
    estimator = GridSearchCV(estimator, param_grid=param_data, cv=10)

    estimator.fit(x_train, y_train)
    # 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
    print("最佳参数:\n", estimator.best_params_)
    # 最佳结果
    print("最佳结果:\n", estimator.best_score_)
    # 最佳估计器
    print("最佳估计器:\n", estimator.best_estimator_)
    # 交叉验证结果
    print("交叉验证结果:\n", estimator.cv_results_)

标签：knn,iris,predict,train,print,调优,estimator,test,鸢尾花
来源： https://www.cnblogs.com/MatteaTse/p/16393358.html