python中的scaler_python 数据预处理之 MinMaxScaler 可视化体验

from matplotlib.pyplot importas pltfrom sklearn.datasets importmake_blobsfrom sklearn.preprocessing importMinMaxScalerfrom sklearn.model_selection importtrain_test_split#构造数据

X, _ = make_blobs(n_samples=60,

centers=5,

random_state=7,

cluster_std=2)

X_train, X_test=train_test_split(X,

random_state=9,

test_size=0.1)

fig, axes= plt.subplots(nrows=1,

ncols=3,

figsize=(13, 4)

)#绘制未经放缩的数据的训练集和测试集

axes[0].scatter(X_train[:, 0],

X_train[:,1],

c='b',

label='Training set',

s=60)

axes[0].scatter(X_test[:, 0],

X_test[:,1],

marker='^',

c='r',

label='Test set',

s=60)

axes[0].legend(loc=1)

axes[0].set_title('Original Data')#利用 MinMaxScaler 放缩数据

scaler =MinMaxScaler()

scaler.fit(X_train)

X_train_scaled=scaler.transform(X_train)

X_test_scaled=scaler.transform(X_test)#可视化正确放缩的数据

axes[1].scatter(X_train_scaled[:, 0],

X_train_scaled[:,1],

c='b',

label='Training set',

s=60)

axes[1].scatter(X_test_scaled[:, 0],

X_test_scaled[:,1],

marker='^',

c='r',

label='Test set',

s=60)

axes[1].set_title('Scaled Data')#对测试集进行单独放缩

test_scaler =MinMaxScaler()

test_scaler.fit(X_test)

X_test_scaled_badly=test_scaler.transform(X_test)#可视化错误放缩的数据

axes[2].scatter(X_train_scaled[:, 0],

X_train_scaled[:,1],

c='b',

label='Training set',

s=60)

axes[2].scatter(X_test_scaled_badly[:, 0],

X_test_scaled_badly[:,1],

marker='^',

c='r',

label='Test set',

s=60)

axes[2].set_title('Improperly Scaled Data')#为每幅图添加坐标轴标题

for ax inaxes:

ax.set_xlabel('Feature 0')

ax.set_ylabel('Feature 1')

plt.show()