对测试数据集如何归一化？
测试数据是模拟真实环境，真实环境有可能无法得到所有测试
对数据的归一化也是算法的一部分
(x_test - mean_train) / std_train
要保存训练数据集得到的均值和方差
import numpy as np
from sklearn import datasets
iris = datasets.load_iris()//加载鸢尾花数据集
X = iris.data
y = iris.target
X[:10,:]
运行结果：array([[5.1, 3.5, 1.4, 0.2],
[4.9, 3. , 1.4, 0.2],
[4.7, 3.2, 1.3, 0.2],
[4.6, 3.1, 1.5, 0.2],
[5. , 3.6, 1.4, 0.2],
[5.4, 3.9, 1.7, 0.4],
[4.6, 3.4, 1.4, 0.3],
[5. , 3.4, 1.5, 0.2],
[4.4, 2.9, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1]])
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(iris.data,iris.target,test_size=0.2,random_state=666)
### scikit-learn中的StandScaler
from sklearn.preprocessing import StandardScaler//scaler在数据的预处理过程中做归一化
standardScaler = StandardScaler()
standardScaler.fit(X_train)
standardScaler.mean_//对应特征矩阵四个特征相应的均值
standardScaler.scale_//藐视数据分布范围，这里可以代表方差
standardScaler.transform(X_train)//返回值是对整个矩阵进行归一化后得到的结果
X_train = standardScaler.transform(X_train)
X_train
返回结果：array([[-0.90616043, 0.93246262, -1.30856471, -1.28788802],
[-1.15301457, -0.19551636, -1.30856471, -1.28788802],
[-0.16559799, -0.64670795, 0.22203084, 0.17260355],
[ 0.45153738, 0.70686683, 0.95898425, 1.50032315],
[-0.90616043, -1.32349533, -0.40154513, -0.09294037],
[ 1.43895396, 0.25567524, 0.56216318, 0.30537551],
[ 0.3281103 , -1.09789954, 1.0723617 , 0.30537551],
[ 2.1795164 , -0.19551636, 1.63924894, 1.23477923],
[-0.78273335, 2.2860374 , -1.25187599, -1.42065998],
[ 0.45153738, -2.00028272, 0.44878573, 0.43814747],
[ 1.80923518, -0.42111215, 1.46918276, 0.83646335],
[ 0.69839152, 0.25567524, 0.90229552, 1.50032315],
[ 0.20468323, 0.70686683, 0.44878573, 0.57091943],
[-0.78273335, -0.87230374, 0.10865339, 0.30537551],
[-0.53587921, 1.38365421, -1.25187599, -1.28788802],
[-0.65930628, 1.38365421, -1.25187599, -1.28788802],
[-1.0295875 , 0.93246262, -1.19518726, -0.75680017],
[-1.77014994, -0.42111215, -1.30856471, -1.28788802],
[-0.04217092, -0.87230374, 0.10865339, 0.03983159],
[-0.78273335, 0.70686683, -1.30856471, -1.28788802],
[-1.52329579, 0.70686683, -1.30856471, -1.15511606],
[ 0.82181859, 0.25567524, 0.78891808, 1.10200727],
[-0.16559799, -0.42111215, 0.27871956, 0.17260355],
[ 0.94524567, -0.19551636, 0.39209701, 0.30537551],
[ 0.20468323, -0.42111215, 0.44878573, 0.43814747],
[-1.39986872, 0.25567524, -1.19518726, -1.28788802],
[-1.15301457, 1.15805842, -1.30856471, -1.42065998],
[ 1.06867274, 0.03007944, 1.0723617 , 1.63309511],
[ 0.57496445, -0.87230374, 0.67554063, 0.83646335],
[ 0.3281103 , -0.64670795, 0.56216318, 0.03983159],
[ 0.45153738, -0.64670795, 0.6188519 , 0.83646335],
[-0.16559799, 2.96282478, -1.25187599, -1.0223441 ],
[ 0.57496445, -1.32349533, 0.67554063, 0.43814747],
[ 0.69839152, -0.42111215, 0.33540828, 0.17260355],
[-0.90616043, 1.60925001, -1.02512109, -1.0223441 ],
[ 1.19209981, -0.64670795, 0.6188519 , 0.30537551],
[-0.90616043, 0.93246262, -1.30856471, -1.15511606],
[-1.89357701, -0.19551636, -1.47863088, -1.42065998],
[ 0.08125616, -0.19551636, 0.78891808, 0.83646335],
[ 0.69839152, -0.64670795, 1.0723617 , 1.23477923],
[-0.28902506, -0.64670795, 0.67554063, 1.10200727],
[-0.41245214, -1.54909113, -0.00472406, -0.22571233],
[ 1.31552689, 0.03007944, 0.67554063, 0.43814747],
[ 0.57496445, 0.70686683, 1.0723617 , 1.63309511],
[ 0.82181859, -0.19551636, 1.18573914, 1.36755119],
[-0.16559799, 1.60925001, -1.13849854, -1.15511606],
[ 0.94524567, -0.42111215, 0.50547446, 0.17260355],
[ 1.06867274, 0.48127103, 1.12905042, 1.76586707],
[-1.27644165, -0.19551636, -1.30856471, -1.42065998],
[-1.0295875 , 1.15805842, -1.30856471, -1.28788802],
[ 0.20468323, -0.19551636, 0.6188519 , 0.83646335],
[-1.0295875 , -0.19551636, -1.19518726, -1.28788802],
[ 0.3281103 , -0.19551636, 0.67554063, 0.83646335],
[ 0.69839152, 0.03007944, 1.01567297, 0.83646335],
[-0.90616043, 1.38365421, -1.25187599, -1.0223441 ],
[-0.16559799, -0.19551636, 0.27871956, 0.03983159],
[-1.0295875 , 0.93246262, -1.36525344, -1.15511606],
[-0.90616043, 1.60925001, -1.25187599, -1.15511606],
[-1.52329579, 0.25567524, -1.30856471, -1.28788802],
[-0.53587921, -0.19551636, 0.44878573, 0.43814747],
[ 0.82181859, -0.64670795, 0.50547446, 0.43814747],
[ 0.3281103 , -0.64670795, 0.16534211, 0.17260355],
[-1.27644165, 0.70686683, -1.19518726, -1.28788802],
[-0.90616043, 0.48127103, -1.13849854, -0.88957213],
[-0.04217092, -0.87230374, 0.78891808, 0.96923531],
[-0.28902506, -0.19551636, 0.22203084, 0.17260355],
[ 0.57496445, -0.64670795, 0.78891808, 0.43814747],
[ 1.06867274, 0.48127103, 1.12905042, 1.23477923],
[ 1.68580811, -0.19551636, 1.18573914, 0.57091943],
[ 1.06867274, -0.19551636, 0.8456068 , 1.50032315],
[-1.15301457, 0.03007944, -1.25187599, -1.42065998],
[-1.15301457, -1.32349533, 0.44878573, 0.70369139],
[-0.16559799, -1.32349533, 0.73222935, 1.10200727],
[-1.15301457, -1.54909113, -0.23147896, -0.22571233],
[-0.41245214, -1.54909113, 0.05196466, -0.09294037],
[ 1.06867274, -1.32349533, 1.18573914, 0.83646335],
[ 0.82181859, -0.19551636, 1.01567297, 0.83646335],
[-0.16559799, -1.09789954, -0.11810151, -0.22571233],
[ 0.20468323, -2.00028272, 0.73222935, 0.43814747],
[ 1.06867274, 0.03007944, 0.56216318, 0.43814747],
[-1.15301457, 0.03007944, -1.25187599, -1.28788802],
[ 0.57496445, -1.32349533, 0.73222935, 0.96923531],
[-1.39986872, 0.25567524, -1.36525344, -1.28788802],
[ 0.20468323, -0.87230374, 0.78891808, 0.57091943],
[-0.04217092, -1.09789954, 0.16534211, 0.03983159],
[ 1.31552689, 0.25567524, 1.12905042, 1.50032315],
[-1.77014994, -0.19551636, -1.36525344, -1.28788802],
[ 1.56238103, -0.19551636, 1.24242787, 1.23477923],
[ 1.19209981, 0.25567524, 1.24242787, 1.50032315],
[-0.78273335, 0.93246262, -1.25187599, -1.28788802],
[ 2.54979762, 1.60925001, 1.52587149, 1.10200727],
[ 0.69839152, -0.64670795, 1.0723617 , 1.36755119],
[-0.28902506, -0.42111215, -0.06141278, 0.17260355],
[-0.41245214, 2.51163319, -1.30856471, -1.28788802],
[-1.27644165, -0.19551636, -1.30856471, -1.15511606],
[ 0.57496445, -0.42111215, 1.0723617 , 0.83646335],
[-1.77014994, 0.25567524, -1.36525344, -1.28788802],
[-0.53587921, 1.8348458 , -1.13849854, -1.0223441 ],
[-1.0295875 , 0.70686683, -1.19518726, -1.0223441 ],
[ 1.06867274, -0.19551636, 0.73222935, 0.70369139],
[-0.53587921, 1.8348458 , -1.36525344, -1.0223441 ],
[ 2.30294347, -0.64670795, 1.69593766, 1.10200727],
[-0.28902506, -0.87230374, 0.27871956, 0.17260355],
[ 1.19209981, -0.19551636, 1.01567297, 1.23477923],
[-0.41245214, 0.93246262, -1.36525344, -1.28788802],
[-1.27644165, 0.70686683, -1.02512109, -1.28788802],
[-0.53587921, 0.70686683, -1.13849854, -1.28788802],
[ 2.30294347, 1.60925001, 1.69593766, 1.36755119],
[ 1.31552689, 0.03007944, 0.95898425, 1.23477923],
[-0.28902506, -1.32349533, 0.10865339, -0.09294037],
[-0.90616043, 0.70686683, -1.25187599, -1.28788802],
[-0.90616043, 1.60925001, -1.19518726, -1.28788802],
[ 0.3281103 , -0.42111215, 0.56216318, 0.30537551],
[-0.04217092, 2.0604416 , -1.42194216, -1.28788802],
[-1.0295875 , -2.45147431, -0.11810151, -0.22571233],
[ 0.69839152, 0.25567524, 0.44878573, 0.43814747],
[ 0.3281103 , -0.19551636, 0.50547446, 0.30537551],
[ 0.08125616, 0.25567524, 0.6188519 , 0.83646335],
[ 0.20468323, -2.00028272, 0.16534211, -0.22571233],
[ 1.93266225, -0.64670795, 1.35580532, 0.96923531]])
X_test_standard = standardScaler.transform(X_test)
X_test_standard
返回结果：array([[-0.28902506, -0.19551636, 0.44878573, 0.43814747],
[-0.04217092, -0.64670795, 0.78891808, 1.63309511],
[-1.0295875 , -1.77468693, -0.23147896, -0.22571233],
[-0.04217092, -0.87230374, 0.78891808, 0.96923531],
[-1.52329579, 0.03007944, -1.25187599, -1.28788802],
[-0.41245214, -1.32349533, 0.16534211, 0.17260355],
[-0.16559799, -0.64670795, 0.44878573, 0.17260355],
[ 0.82181859, -0.19551636, 0.8456068 , 1.10200727],
[ 0.57496445, -1.77468693, 0.39209701, 0.17260355],
[-0.41245214, -1.09789954, 0.39209701, 0.03983159],
[ 1.06867274, 0.03007944, 0.39209701, 0.30537551],
[-1.64672287, -1.77468693, -1.36525344, -1.15511606],
[-1.27644165, 0.03007944, -1.19518726, -1.28788802],
[-0.53587921, 0.70686683, -1.25187599, -1.0223441 ],
[ 1.68580811, 1.15805842, 1.35580532, 1.76586707],
[-0.04217092, -0.87230374, 0.22203084, -0.22571233],
[-1.52329579, 1.15805842, -1.53531961, -1.28788802],
[ 1.68580811, 0.25567524, 1.29911659, 0.83646335],
[ 1.31552689, 0.03007944, 0.78891808, 1.50032315],
[ 0.69839152, -0.87230374, 0.90229552, 0.96923531],
[ 0.57496445, 0.48127103, 0.56216318, 0.57091943],
[-1.0295875 , 0.70686683, -1.25187599, -1.28788802],
[ 2.30294347, -1.09789954, 1.80931511, 1.50032315],
[-1.0295875 , 0.48127103, -1.30856471, -1.28788802],
[ 0.45153738, -0.42111215, 0.33540828, 0.17260355],
[ 0.08125616, -0.19551636, 0.27871956, 0.43814747],
[-1.0295875 , 0.25567524, -1.42194216, -1.28788802],
[-0.41245214, -1.77468693, 0.16534211, 0.17260355],
[ 0.57496445, 0.48127103, 1.29911659, 1.76586707],
[ 2.30294347, -0.19551636, 1.35580532, 1.50032315]])
from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(X_train,y_train)
返回结果：KNeighborsClassifier(n_neighbors=3)
knn_clf.score(X_test_standard,y_test)
返回结果：1.0
//测试数据集需要进行归一化处理，如不进行归一化处理，则得到的准确度很低，例如：
knn_clf.score(X_test,y_test)
返回结果：0.3333333333333333
625
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
