1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
"""
Feature agglomeration. Base classes and functions for performing feature
agglomeration.
"""
# Author: V. Michel, A. Gramfort
# License: BSD 3 clause
import numpy as np
from ..base import TransformerMixin
from ..utils import check_array
from ..utils.validation import check_is_fitted
from scipy.sparse import issparse
###############################################################################
# Mixin class for feature agglomeration.
class AgglomerationTransform(TransformerMixin):
"""
A class for feature agglomeration via the transform interface
"""
pooling_func = np.mean
def transform(self, X):
"""
Transform a new matrix using the built clustering
Parameters
----------
X : array-like, shape = [n_samples, n_features] or [n_features]
A M by N array of M observations in N dimensions or a length
M array of M one-dimensional observations.
Returns
-------
Y : array, shape = [n_samples, n_clusters] or [n_clusters]
The pooled values for each feature cluster.
"""
check_is_fitted(self, "labels_")
pooling_func = self.pooling_func
X = check_array(X)
if len(self.labels_) != X.shape[1]:
raise ValueError("X has a different number of features than "
"during fitting.")
if pooling_func == np.mean and not issparse(X):
size = np.bincount(self.labels_)
n_samples = X.shape[0]
# a fast way to compute the mean of grouped features
nX = np.array([np.bincount(self.labels_, X[i, :]) / size
for i in range(n_samples)])
else:
nX = []
for l in np.unique(self.labels_):
nX.append(pooling_func(X[:, self.labels_ == l], axis=1))
nX = np.array(nX).T
return nX
def inverse_transform(self, Xred):
"""
Inverse the transformation.
Return a vector of size nb_features with the values of Xred assigned
to each group of features
Parameters
----------
Xred : array-like, shape=[n_samples, n_clusters] or [n_clusters,]
The values to be assigned to each cluster of samples
Returns
-------
X : array, shape=[n_samples, n_features] or [n_features]
A vector of size n_samples with the values of Xred assigned to
each of the cluster of samples.
"""
check_is_fitted(self, "labels_")
unil, inverse = np.unique(self.labels_, return_inverse=True)
return Xred[..., inverse]
|
