数据预处理

导入库

import numpy as np
from sklearn import preprocessing as pp

input_data = np.array([[2.1, -1.9, 5.5], 
                      [-1.5, 2.4, 3.5],
                      [0.5, -7.9, 5.6],
                      [5.9, 2.3, -5.8]])
  


二值化
data_bin = pp.Binarizer(threshold=0.5).transform(input_data)
#array([[1., 0., 1.],
       [0., 1., 1.],
       [0., 0., 1.],
       [1., 1., 0.]])

平均去值
input_data.mean(0) #  array([ 1.75 , -1.275,  2.2  ])
input_data.std(0) #  array([2.71431391, 4.20022321, 4.69414529])

data_scale = pp.scale(input_data)

data_scale.mean(0) # array([1.11022302e-16, 0.00000000e+00, 0.00000000e+00])
data_scale.std(0) # array([1., 1., 1.])

缩放
data_minmax = pp.MinMaxScaler(feature_range=(0, 1)).fit_transform(input_data)
#array([[0.48648649, 0.58252427, 0.99122807],
       [0.        , 1.        , 0.81578947],
       [0.27027027, 0.        , 1.        ],
       [1.        , 0.99029126, 0.        ]])

正常化
#L1标准化，绝对值的总和在每行中总是最多为1
data_L1 = pp.normalize(input_data, 'l1')
#array([[ 0.22105263, -0.2       ,  0.57894737],
       [-0.2027027 ,  0.32432432,  0.47297297],
       [ 0.03571429, -0.56428571,  0.4       ],
       [ 0.42142857,  0.16428571, -0.41428571]])

#L2标准化，每一行中的平方和总是最多为1
data_L2 = pp.normalize(input_data, 'l2')
#array([[ 0.33946114, -0.30713151,  0.88906489],
       [-0.33325106,  0.53320169,  0.7775858 ],
       [ 0.05156558, -0.81473612,  0.57753446],
       [ 0.68706914,  0.26784051, -0.6754239 ]])
              

标记数据
input_labels = ['red','black','red','green','black','yellow','white']
test_labels = list(set(input_labels))

#创建和训练标签编码器对象
encoder = pp.LabelEncoder()

#标签==>数据
values = encoder.transform(test_labels)
#array([1, 4, 3, 2, 0], dtype=int64)

#数据==>标签
test = np.array([1, 3, 4])
labels = encoder.inverse_transform(test)
#array(['green', 'white', 'yellow'], dtype='<U6')

 

转载于:https://www.cnblogs.com/hichens/p/11222205.html