Last active
July 14, 2017 16:49
-
-
Save shadiakiki1986/2c293e364563492c65bffdb6122b4e92 to your computer and use it in GitHub Desktop.
sklearn PCA requires normalization
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# modified example of | |
# http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html#sklearn.decomposition.PCA.transform | |
import numpy as np | |
from sklearn.decomposition import PCA | |
# Just the same PCA as the example | |
pca = PCA(n_components=2, svd_solver='full') | |
# same input as example | |
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, -1], [2, -1], [3, -2]]) | |
X | |
array([[-1, -1], | |
[-2, -1], | |
[-3, -2], | |
[ 1, -1], | |
[ 2, -1], | |
[ 3, -2]]) | |
pca.fit_transform(X) | |
array([[ 1. , -0.33333333], | |
[ 2. , -0.33333333], | |
[ 3. , 0.66666667], | |
[-1. , -0.33333333], | |
[-2. , -0.33333333], | |
[-3. , 0.66666667]]) | |
# duplicate the last column | |
X = np.array([[-1, -1, -1], [-2, -1, -1], [-3, -2, -2], [1, -1, -1], [2, -1, -1], [3, -2, -2]]) | |
X | |
array([[-1, -1, -1], | |
[-2, -1, -1], | |
[-3, -2, -2], | |
[ 1, -1, -1], | |
[ 2, -1, -1], | |
[ 3, -2, -2]]) | |
pca.fit_transform(X) | |
array([[ 1. , -0.47140452], | |
[ 2. , -0.47140452], | |
[ 3. , 0.94280904], | |
[-1. , -0.47140452], | |
[-2. , -0.47140452], | |
[-3. , 0.94280904]]) | |
# the above yielded a different answer, even though it scales with the first | |
######################## | |
# add normalization | |
from sklearn import preprocessing | |
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, -1], [2, -1], [3, -2]]) | |
preprocessing.normalize(pca.fit_transform(X), norm='l2', axis=0) | |
array([[ 0.18898224, -0.28867513], | |
[ 0.37796447, -0.28867513], | |
[ 0.56694671, 0.57735027], | |
[-0.18898224, -0.28867513], | |
[-0.37796447, -0.28867513], | |
[-0.56694671, 0.57735027]]) | |
# duplicate last column | |
X = np.array([[-1, -1, -1], [-2, -1, -1], [-3, -2, -2], [1, -1, -1], [2, -1, -1], [3, -2, -2]]) | |
preprocessing.normalize(pca.fit_transform(X), norm='l2', axis=0) | |
array([[ 0.18898224, -0.28867513], | |
[ 0.37796447, -0.28867513], | |
[ 0.56694671, 0.57735027], | |
[-0.18898224, -0.28867513], | |
[-0.37796447, -0.28867513], | |
[-0.56694671, 0.57735027]]) | |
# same answer for duplicated and non-duplicated case | |
###################### | |
# duplicate last column and scale it | |
X = np.array([[-1, -1, -1000], [-2, -1, -1000], [-3, -2, -2000], [1, -1, -1000], [2, -1, -1000], [3, -2, -2000]]) | |
X | |
array([[ -1, -1, -1000], | |
[ -2, -1, -1000], | |
[ -3, -2, -2000], | |
[ 1, -1, -1000], | |
[ 2, -1, -1000], | |
[ 3, -2, -2000]]) | |
preprocessing.normalize(pca.fit_transform(X), norm='l2', axis=0) | |
array([[-0.28867513, 0.18898224], | |
[-0.28867513, 0.37796447], | |
[ 0.57735027, 0.56694671], | |
[-0.28867513, -0.18898224], | |
[-0.28867513, -0.37796447], | |
[ 0.57735027, -0.56694671]]) | |
# for some reason, above columns are swapped | |
# pre-normalize and post-normalize | |
preprocessing.normalize(pca.fit_transform(preprocessing.normalize(X,norm='l2',axis=0)), norm='l2', axis=0) | |
array([[ 0.18898224, -0.28867513], | |
[ 0.37796447, -0.28867513], | |
[ 0.56694671, 0.57735027], | |
[-0.18898224, -0.28867513], | |
[-0.37796447, -0.28867513], | |
[-0.56694671, 0.57735027]]) | |
# got same answer again | |
######################## | |
# add scaling | |
from sklearn import preprocessing | |
min_max_scaler = preprocessing.MinMaxScaler() | |
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, -1], [2, -1], [3, -2]]) | |
min_max_scaler.fit_transform(pca.fit_transform(X)) | |
array([[ 6.66666667e-01, 2.77555756e-16], | |
[ 8.33333333e-01, 0.00000000e+00], | |
[ 1.00000000e+00, 1.00000000e+00], | |
[ 3.33333333e-01, 1.11022302e-16], | |
[ 1.66666667e-01, 1.11022302e-16], | |
[ 0.00000000e+00, 1.00000000e+00]]) | |
# duplicate last column | |
X = np.array([[-1, -1, -1], [-2, -1, -1], [-3, -2, -2], [1, -1, -1], [2, -1, -1], [3, -2, -2]]) | |
min_max_scaler.fit_transform(pca.fit_transform(X)) | |
array([[ 6.66666667e-01, 1.11022302e-16], | |
[ 8.33333333e-01, 0.00000000e+00], | |
[ 1.00000000e+00, 1.00000000e+00], | |
[ 3.33333333e-01, 5.55111512e-17], | |
[ 1.66666667e-01, 5.55111512e-17], | |
[ 0.00000000e+00, 1.00000000e+00]]) | |
# almost same answer for duplicated and non-duplicated case | |
# pre and post scaling | |
min_max_scaler.fit_transform(pca.fit_transform(min_max_scaler.fit_transform(X))) | |
array([[ 1.11022302e-16, 6.66666667e-01], | |
[ 0.00000000e+00, 8.33333333e-01], | |
[ 1.00000000e+00, 1.00000000e+00], | |
[ 1.11022302e-16, 3.33333333e-01], | |
[ 1.11022302e-16, 1.66666667e-01], | |
[ 1.00000000e+00, 0.00000000e+00]]) | |
# change in order of columns, but same answer roughly |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment