机器学习测试笔记（10）——K邻近算法（下）

# 红酒案例
# 导入sklearn数据集
from sklearn import datasets
def Sklean_wine():
    #导入红酒数据集
    wine_dataset = datasets.load_wine()
    print('红酒数据集中的键：{}'.format(wine_dataset.keys()))

红酒数据：
[[1.423e+01 1.710e+00 2.430e+00 ... 1.040e+00 3.920e+00 1.065e+03]
 [1.320e+01 1.780e+00 2.140e+00 ... 1.050e+00 3.400e+00 1.050e+03]
 [1.316e+01 2.360e+00 2.670e+00 ... 1.030e+00 3.170e+00 1.185e+03]
 ...
 [1.327e+01 4.280e+00 2.260e+00 ... 5.900e-01 1.560e+00 8.350e+02]
 [1.317e+01 2.590e+00 2.370e+00 ... 6.000e-01 1.620e+00 8.400e+02]
 [1.413e+01 4.100e+00 2.740e+00 ... 6.100e-01 1.600e+00 5.600e+02]]

红酒数据描述：.. _wine_dataset:
Wine recognition dataset
------------------------
**Data Set Characteristics:**
    :Number of Instances: 178 (50 in each of three classes)
    :Number of Attributes: 13 numeric, predictive attributes and the class
    :Attribute Information(属性信息):
     - Alcohol
     - Malic acid
     - Ash
    - Alcalinity of ash  
     - Magnesium
    - Total phenols
   - Flavanoids
 - Nonflavanoid phenols
     - Proanthocyanins
    - Color intensity
     - Hue
     - OD280/OD315 of diluted wines
     - Proline
- class:
            - class_0
            - class_1
            - class_2
…

#将数据分为训练集和测试集
    X = wine_dataset['data']
    y = wine_dataset['target']
    #测试集占30%
    X_train,X_test,y_train,y_test = train_test_split(X, y, random_state=0,test_size=0.3)
    # 打印X_train,X_test,y_train,y_test的形态
    print("X_train,的形态:{}".format(X_train.shape))
    print("X_test的形态:{}".format(X_test.shape))
    print("y_train的形态:{}".format(y_train.shape))
    print("y_test的形态:{}".format(y_test.shape))

X_train,的形态:(124, 13)
X_test的形态:(54, 13)
y_train的形态:(124,)
y_test的形态:(54,)

 #导入KNN算法
    knn = KNeighborsClassifier(n_neighbors=1)
    knn.fit(X_train,y_train)
    print('测试数据的得分：{}:\n'.format(knn.score(X_test,y_test)))

#输出计算值
print(knn.predict(X_test))
#输出实际标签
print(y_test)

[0 1 1 0 1 1 0 2 1 1 0 1 0 2 1 1 0 0 1 0 1 0 1 1 0 1 1 1 2 2 0 0 1 0 0 0 2 1 1 1 2 0 1 1 1 2 2 2 2 0 2 1 0 2]
[0 2 1 0 1 1 0 2 1 1 2 2 0 1 2 1 0 0 1 0 1 0 0 1 1 1 1 1 1 2 0 0 1 0 0 0 2 1 1 2 0 0 1 1 1 0 2 1 2 0 2 2 0 2] 

 X_new =  np.array([[25.5,3.14,3.22,18.5,95.8, 0.97, 2.52, 0.67, 1.52, 7.3, 0.98, 2.96, 990]])
    prediction = knn.predict(X_new)
    print('预测的红酒为：{}:\n'.format(wine_dataset['target_names'][prediction]))

def Sklean_iris():
    # 加载数据其中的鸢尾花数据
    iris_dataset = datasets.load_iris()
    print('鸢尾花数据集中的键：{}'.format(iris_dataset.keys()))
    print('鸢尾花数据概况：{}'.format(iris_dataset['data'].shape))
    print('鸢尾花数据：{}:\n'.format(iris_dataset['data']))
    print('鸢尾花数据描述：{}'.format(iris_dataset['DESCR']))
    #将数据分为训练集和测试集
    X = iris_dataset['data']
    y = iris_dataset['target']
    #测试集占30%
    X_train,X_test,y_train,y_test = train_test_split(X, y, random_state=0,test_size=0.3)
    # 打印X_train,X_test,y_train,y_test的形态
    print("X_train,的形态:{}".format(X_train.shape))
    print("X_test的形态:{}".format(X_test.shape))
    print("y_train的形态:{}".format(y_train.shape))
    print("y_test的形态:{}".format(y_test.shape))
    # 定义模型算法为K近邻分类器
    knn = KNeighborsClassifier()
    # 用fit完成训练
    knn.fit(X_train,y_train)
    print('测试数据的得分：{}:\n'.format(knn.score(X_test,y_test)))
    # 将测试数据集x_test运用到训练完成后的knn模型中去
     print(knn.predict(X_test))
    # 输出测试集中的真实结果
    print(y_test)

鸢尾花数据集中的键：dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename'])
鸢尾花数据概况：(150, 4)
鸢尾花数据：
[[5.1 3.5 1.4 0.2]
 [4.9 3.  1.4 0.2]
…
鸢尾花数据集中的键：dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename'])
鸢尾花数据概况：(150, 4)
鸢尾花数据：
[[5.1 3.5 1.4 0.2]
 [4.9 3.  1.4 0.2]
…
鸢尾花数据描述：.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
    :Number of Instances: 150 (50 in each of three classes)
    :Number of Attributes: 4 numeric, predictive attributes and the class
:Attribute Information:
        - sepal length in cm
        - sepal width in cm
        - petal length in cm
        - petal width in cm
        - class:
                - Iris-Setosa
                - Iris-Versicolour
                - Iris-Virginica
X_train,的形态:(105, 4)
X_test的形态:(45, 4)
y_train的形态:(105,)
y_test的形态:(45,)
测试数据的得分：0.9777777777777777:
[2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0 2 1 1 2 0 2 0 0]
[2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0 1 1 1 2 0 2 0 0]

X_new =  np.array([[4.5,3.6,1.3,0.3]])
    prediction = knn.predict(X_new)
    print('预测的鸢尾花为：{}:\n'.format(iris_dataset['target_names'][prediction]))

#交叉验证法
from sklearn import svm
from sklearn.model_selection import cross_val_score
def Sklean_iris_cross_validation():
    iris_dataset = datasets.load_iris()
    X,y = datasets.load_iris(return_X_y=True)
    print(X.shape,X.shape)
    X_train,X_test,y_train,y_test = train_test_split(X, y, test_size=0.4, random_state=0)
    print("X_train,的形态:{}".format(X_train.shape))
    print("X_test的形态:{}".format(X_test.shape))
    print("y_train的形态:{}".format(y_train.shape))
    print("y_test的形态:{}".format(y_test.shape))
    clf = svm.SVC(kernel='linear',C=1).fit(X_train,y_train)
    print('交叉验证法前测试数据的得分：{}:\n'.format(clf.score(X_test,y_test)))
    clf = svm.SVC(kernel='linear',C=1)
    scores = cross_val_score(clf,X,y,cv=5)#实现交叉验证，cv=5:分5组
    print('交叉验证法后测试数据的得分：{}:\n'.format(scores))

(150, 4) (150, 4)
X_train,的形态:(90, 4)
X_test的形态:(60, 4)
y_train的形态:(90,)
y_test的形态:(60,)
交叉验证法前测试数据的得分：0.9666666666666667:
交叉验证法后测试数据的得分：[0.96666667 1.      0.96666667 0.96666667 1.        ]:

 clf.fit(X_train,y_train)
    prediction = clf.predict(X_new)
    print('预测的鸢尾花为：{}:\n'.format(iris_dataset['target_names'][prediction]))