Data pretreatment

Import library



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]])







Binarization

data_bin = pp.Binarizer(threshold=0.5).transform(input_data)

#array([[1., 0., 1.] ,

 [0., 1., 1.],

 [0., 0., 1.],

 [1., 1., 0.]])



Average value

input_data.mean(0) # array([ 1.75, -1.275 , 2.2 ])

input_data.std(0) # array([2.71431391, 4.20022321, 4.69414529])< /span>



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. ])



Zoom

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. ]])



Normalize

#L1 standardization, the sum of absolute values ​​is always in each row Up to 1

data_L1 = pp.normalize(input_data, 'l1')

#array([[ 0.22105263, -0.2, 0.57894737],< /span>

 [-0.2027027, 0.32432432, 0.47297297],

 [0.03571429, -0.56428571, 0.4 ],

 [0.42142857, 0.16428571, -0.41428571]])



#L2 standardization, the sum of squares in each line is always at most 1

data_L2 = pp.normalize(input_data, 'l2')

#array([[ 0.33946114, -0.30713151, 0.88906489],< /span>

 [-0.33325106, 0.53320169, 0.7775858 ],

 [0.05156558, -0.81473612, 0.57753446],

 [0.68706914, 0.26784051, -0.6754239 ]])





Tag data

input_labels = ['red','black','red< span style="color: #800000;">','green','black< /span>',' yellow','white']

test_labels = list(set(input_labels))



#Create and train tag encoder objects

encoder = pp.LabelEncoder()



#label==>data

values ​​= encoder.transform(test_labels)

#array([1, 4, 3, 2, 0] , dtype=int64)



#data==>label

test = np.array([1, 3, 4])

labels = encoder.inverse_transform(test)

#array(['green','white','yellow '], dtype='

Import library



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]])







Binarization

data_bin = pp.Binarizer(threshold=0.5).transform(input_data)

#array([[1., 0., 1.] ,

 [0., 1., 1.],

 [0., 0., 1.],

 [1., 1., 0.]])



Average value

input_data.mean(0) # array([ 1.75, -1.275 , 2.2 ])

input_data.std(0) # array([2.71431391, 4.20022321, 4.69414529])< /span>



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. ])



Zoom

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. ]])



Normalize

#L1 standardization, the sum of absolute values ​​is always in each row Up to 1

data_L1 = pp.normalize(input_data, 'l1')

#array([[ 0.22105263, -0.2, 0.57894737],< /span>

 [-0.2027027, 0.32432432, 0.47297297],

 [0.03571429, -0.56428571, 0.4 ],

 [0.42142857, 0.16428571, -0.41428571]])



#L2 standardization, the sum of squares in each line is always at most 1

data_L2 = pp.normalize(input_data, 'l2')

#array([[ 0.33946114, -0.30713151, 0.88906489],< /span>

 [-0.33325106, 0.53320169, 0.7775858 ],

 [0.05156558, -0.81473612, 0.57753446],

 [0.68706914, 0.26784051, -0.6754239 ]])





Tag data

input_labels = ['red','black','red< span style="color: #800000;">','green','black< /span>',' yellow','white']

test_labels = list(set(input_labels))



#Create and train tag encoder objects

encoder = pp.LabelEncoder()



#label==>data

values ​​= encoder.transform(test_labels)

#array([1, 4, 3, 2, 0] , dtype=int64)



#data==>label

test = np.array([1, 3, 4])

labels = encoder.inverse_transform(test)

#array(['green','white','yellow '], dtype='