from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(cancer.data,
cancer.target,
random_state=1)
print(X_train.shape)
print(X_test.shape)
输出：
(426, 30)
(143, 30)
from sklearn.preprocessing import MinMaxScaler
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(cancer.data,
cancer.target,
random_state=1)
scaler = MinMaxScaler()
#导入实现预处理的类，并将其实例化
scaler.fit(X_train)
#用fit方法拟合缩放器（scaler）
# transform data
X_train_scaled = scaler.transform(X_train)
MinMaxScaler(copy=True,feature_range=(0,1))
#缩放10倍
# print dataset properties before and after scaling
print("transformed shape: {}".format(X_train_scaled.shape))
print("per-feature minimum before scaling:\n {}".format(X_train.min(axis=0)))
print("per-feature maximum before scaling:\n {}".format(X_train.max(axis=0)))
print("per-feature minimum after scaling:\n {}".format(
X_train_scaled.min(axis=0)))
print("per-feature maximum after scaling:\n {}".format(
X_train_scaled.max(axis=0)))
输出：
transformed shape: (426, 30)
per-feature minimum before scaling:
[6.981e+00 9.710e+00 4.379e+01 1.435e+02 5.263e-02 1.938e-02 0.000e+00
0.000e+00 1.060e-01 5.024e-02 1.153e-01 3.602e-01 7.570e-01 6.802e+00
1.713e-03 2.252e-03 0.000e+00 0.000e+00 9.539e-03 8.948e-04 7.930e+00
1.202e+01 5.041e+01 1.852e+02 7.117e-02 2.729e-02 0.000e+00 0.000e+00
1.566e-01 5.521e-02]
per-feature maximum before scaling:
[2.811e+01 3.928e+01 1.885e+02 2.501e+03 1.634e-01 2.867e-01 4.268e-01
2.012e-01 3.040e-01 9.575e-02 2.873e+00 4.885e+00 2.198e+01 5.422e+02
3.113e-02 1.354e-01 3.960e-01 5.279e-02 6.146e-02 2.984e-02 3.604e+01
4.954e+01 2.512e+02 4.254e+03 2.226e-01 9.379e-01 1.170e+00 2.910e-01
5.774e-01 1.486e-01]
per-feature minimum after scaling:
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.
0. 0. 0. 0. 0. 0.]
per-feature maximum after scaling:
[1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.
1. 1. 1. 1. 1. 1.]
from sklearn.preprocessing import MinMaxScaler
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(cancer.data,
cancer.target,
random_state=1)
scaler = MinMaxScaler()
scaler.fit(X_train)
# transform test data
X_test_scaled = scaler.transform(X_test)
# print test data properties after scaling
print("per-feature minimum after scaling:\n{}".format(X_test_scaled.min(axis=0)))
print("per-feature maximum after scaling:\n{}".format(X_test_scaled.max(axis=0)))
输出：
per-feature minimum after scaling:
[ 0.0336031 0.0226581 0.03144219 0.01141039 0.14128374 0.04406704
0. 0. 0.1540404 -0.00615249 -0.00137796 0.00594501
0.00430665 0.00079567 0.03919502 0.0112206 0. 0.
-0.03191387 0.00664013 0.02660975 0.05810235 0.02031974 0.00943767
0.1094235 0.02637792 0. 0. -0.00023764 -0.00182032]
per-feature maximum after scaling:
[0.9578778 0.81501522 0.95577362 0.89353128 0.81132075 1.21958701
0.87956888 0.9333996 0.93232323 1.0371347 0.42669616 0.49765736
0.44117231 0.28371044 0.48703131 0.73863671 0.76717172 0.62928585
1.33685792 0.39057253 0.89612238 0.79317697 0.84859804 0.74488793
0.9154725 1.13188961 1.07008547 0.92371134 1.20532319 1.63068851]
from sklearn.datasets import make_blobs
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import mglearn
# make synthetic data
X, _ = make_blobs(n_samples=50, centers=5, random_state=4, cluster_std=2)
# split it into training and test sets
X_train, X_test = train_test_split(X, random_state=5, test_size=.1)
# plot the training and test sets
fig, axes = plt.subplots(1, 3, figsize=(13, 4))
axes[0].scatter(X_train[:, 0], X_train[:, 1],
c=mglearn.cm2(0), label="Training set", s=60)
axes[0].scatter(X_test[:, 0], X_test[:, 1], marker='^',
c=mglearn.cm2(1), label="Test set", s=60)
axes[0].legend(loc='upper left')
axes[0].set_title("Original Data")
# scale the data using MinMaxScaler
scaler = MinMaxScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
# visualize the properly scaled data
axes[1].scatter(X_train_scaled[:, 0], X_train_scaled[:, 1],
c=mglearn.cm2(0), label="Training set", s=60)
axes[1].scatter(X_test_scaled[:, 0], X_test_scaled[:, 1], marker='^',
c=mglearn.cm2(1), label="Test set", s=60)
axes[1].set_title("Scaled Data")
# rescale the test set separately
# so test set min is 0 and test set max is 1
# DO NOT DO THIS! For illustration purposes only.
test_scaler = MinMaxScaler()
test_scaler.fit(X_test)
X_test_scaled_badly = test_scaler.transform(X_test)
# visualize wrongly scaled data
axes[2].scatter(X_train_scaled[:, 0], X_train_scaled[:, 1],
c=mglearn.cm2(0), label="training set", s=60)
axes[2].scatter(X_test_scaled_badly[:, 0], X_test_scaled_badly[:, 1],
marker='^', c=mglearn.cm2(1), label="test set", s=60)
axes[2].set_title("Improperly Scaled Data")
for ax in axes:
ax.set_xlabel("Feature 0")
ax.set_ylabel("Feature 1")
fig.tight_layout()
plt.show()
输出：
#
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(cancer.data,
cancer.target,
random_state=0)
scaler = StandardScaler()
# calling fit and transform in sequence (using method chaining)
X_scaled = scaler.fit(X_train).transform(X_train)
# same result, but more efficient computation
X_scaled_d = scaler.fit_transform(X_train)
svm = SVC(C=100)
svm.fit(X_train, y_train)
print("Test set accuracy: {:.2f}".format(svm.score(X_test, y_test)))
输出：
0.94
