forked from scikit-learn/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdict_vectorizer.py
296 lines (241 loc) · 9.94 KB
/
dict_vectorizer.py
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
# Author: Lars Buitinck <[email protected]>
# License: BSD 3 clause
from array import array
from collections import Mapping
from operator import itemgetter
import numpy as np
import scipy.sparse as sp
from ..base import BaseEstimator, TransformerMixin
from ..externals import six
from ..externals.six.moves import xrange
from ..utils import check_array, tosequence
def _tosequence(X):
"""Turn X into a sequence or ndarray, avoiding a copy if possible."""
if isinstance(X, Mapping): # single sample
return [X]
else:
return tosequence(X)
class DictVectorizer(BaseEstimator, TransformerMixin):
"""Transforms lists of feature-value mappings to vectors.
This transformer turns lists of mappings (dict-like objects) of feature
names to feature values into Numpy arrays or scipy.sparse matrices for use
with scikit-learn estimators.
When feature values are strings, this transformer will do a binary one-hot
(aka one-of-K) coding: one boolean-valued feature is constructed for each
of the possible string values that the feature can take on. For instance,
a feature "f" that can take on the values "ham" and "spam" will become two
features in the output, one signifying "f=ham", the other "f=spam".
Features that do not occur in a sample (mapping) will have a zero value
in the resulting array/matrix.
Parameters
----------
dtype : callable, optional
The type of feature values. Passed to Numpy array/scipy.sparse matrix
constructors as the dtype argument.
separator: string, optional
Separator string used when constructing new features for one-hot
coding.
sparse: boolean, optional.
Whether transform should produce scipy.sparse matrices.
True by default.
Attributes
----------
vocabulary_ : dict
A dictionary mapping feature names to feature indices.
feature_names_ : list
A list of length n_features containing the feature names (e.g., "f=ham"
and "f=spam").
Examples
--------
>>> from sklearn.feature_extraction import DictVectorizer
>>> v = DictVectorizer(sparse=False)
>>> D = [{'foo': 1, 'bar': 2}, {'foo': 3, 'baz': 1}]
>>> X = v.fit_transform(D)
>>> X
array([[ 2., 0., 1.],
[ 0., 1., 3.]])
>>> v.inverse_transform(X) == \
[{'bar': 2.0, 'foo': 1.0}, {'baz': 1.0, 'foo': 3.0}]
True
>>> v.transform({'foo': 4, 'unseen_feature': 3})
array([[ 0., 0., 4.]])
See also
--------
FeatureHasher : performs vectorization using only a hash function.
sklearn.preprocessing.OneHotEncoder : handles nominal/categorical features
encoded as columns of integers.
"""
def __init__(self, dtype=np.float64, separator="=", sparse=True):
self.dtype = dtype
self.separator = separator
self.sparse = sparse
def fit(self, X, y=None):
"""Learn a list of feature name -> indices mappings.
Parameters
----------
X : Mapping or iterable over Mappings
Dict(s) or Mapping(s) from feature names (arbitrary Python
objects) to feature values (strings or convertible to dtype).
y : (ignored)
Returns
-------
self
"""
# collect all the possible feature names
feature_names = set()
for x in X:
for f, v in six.iteritems(x):
if isinstance(v, six.string_types):
f = "%s%s%s" % (f, self.separator, v)
feature_names.add(f)
# sort the feature names to define the mapping
feature_names = sorted(feature_names)
self.vocabulary_ = dict((f, i) for i, f in enumerate(feature_names))
self.feature_names_ = feature_names
return self
def fit_transform(self, X, y=None):
"""Learn a list of feature name -> indices mappings and transform X.
Like fit(X) followed by transform(X).
Parameters
----------
X : Mapping or iterable over Mappings
Dict(s) or Mapping(s) from feature names (arbitrary Python
objects) to feature values (strings or convertible to dtype).
y : (ignored)
Returns
-------
Xa : {array, sparse matrix}
Feature vectors; always 2-d.
Notes
-----
Because this method requires two passes over X, it materializes X in
memory.
"""
X = _tosequence(X)
self.fit(X)
return self.transform(X)
def inverse_transform(self, X, dict_type=dict):
"""Transform array or sparse matrix X back to feature mappings.
X must have been produced by this DictVectorizer's transform or
fit_transform method; it may only have passed through transformers
that preserve the number of features and their order.
In the case of one-hot/one-of-K coding, the constructed feature
names and values are returned rather than the original ones.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Sample matrix.
dict_type : callable, optional
Constructor for feature mappings. Must conform to the
collections.Mapping API.
Returns
-------
D : list of dict_type objects, length = n_samples
Feature mappings for the samples in X.
"""
# COO matrix is not subscriptable
X = check_array(X, accept_sparse=['csr', 'csc'])
n_samples = X.shape[0]
names = self.feature_names_
dicts = [dict_type() for _ in xrange(n_samples)]
if sp.issparse(X):
for i, j in zip(*X.nonzero()):
dicts[i][names[j]] = X[i, j]
else:
for i, d in enumerate(dicts):
for j, v in enumerate(X[i, :]):
if v != 0:
d[names[j]] = X[i, j]
return dicts
def transform(self, X, y=None):
"""Transform feature->value dicts to array or sparse matrix.
Named features not encountered during fit or fit_transform will be
silently ignored.
Parameters
----------
X : Mapping or iterable over Mappings, length = n_samples
Dict(s) or Mapping(s) from feature names (arbitrary Python
objects) to feature values (strings or convertible to dtype).
y : (ignored)
Returns
-------
Xa : {array, sparse matrix}
Feature vectors; always 2-d.
"""
# Sanity check: Python's array has no way of explicitly requesting the
# signed 32-bit integers that scipy.sparse needs, so we use the next
# best thing: typecode "i" (int). However, if that gives larger or
# smaller integers than 32-bit ones, np.frombuffer screws up.
assert array("i").itemsize == 4, (
"sizeof(int) != 4 on your platform; please report this at"
" https://github.com/scikit-learn/scikit-learn/issues and"
" include the output from platform.platform() in your bug report")
dtype = self.dtype
vocab = self.vocabulary_
if self.sparse:
X = [X] if isinstance(X, Mapping) else X
indices = array("i")
indptr = array("i", [0])
# XXX we could change values to an array.array as well, but it
# would require (heuristic) conversion of dtype to typecode...
values = []
for x in X:
for f, v in six.iteritems(x):
if isinstance(v, six.string_types):
f = "%s%s%s" % (f, self.separator, v)
v = 1
try:
indices.append(vocab[f])
values.append(dtype(v))
except KeyError:
pass
indptr.append(len(indices))
if len(indptr) == 1:
raise ValueError("Sample sequence X is empty.")
if len(indices) > 0:
# workaround for bug in older NumPy:
# http://projects.scipy.org/numpy/ticket/1943
indices = np.frombuffer(indices, dtype=np.intc)
indptr = np.frombuffer(indptr, dtype=np.intc)
shape = (len(indptr) - 1, len(vocab))
return sp.csr_matrix((values, indices, indptr),
shape=shape, dtype=dtype)
else:
X = _tosequence(X)
Xa = np.zeros((len(X), len(vocab)), dtype=dtype)
for i, x in enumerate(X):
for f, v in six.iteritems(x):
if isinstance(v, six.string_types):
f = "%s%s%s" % (f, self.separator, v)
v = 1
try:
Xa[i, vocab[f]] = dtype(v)
except KeyError:
pass
return Xa
def get_feature_names(self):
"""Returns a list of feature names, ordered by their indices.
If one-of-K coding is applied to categorical features, this will
include the constructed feature names but not the original ones.
"""
return self.feature_names_
def restrict(self, support, indices=False):
"""Restrict the features to those in support.
Parameters
----------
support : array-like
Boolean mask or list of indices (as returned by the get_support
member of feature selectors).
indices : boolean, optional
Whether support is a list of indices.
"""
if not indices:
support = np.where(support)[0]
names = self.feature_names_
new_vocab = {}
for i in support:
new_vocab[names[i]] = len(new_vocab)
self.vocabulary_ = new_vocab
self.feature_names_ = [f for f, i in sorted(six.iteritems(new_vocab),
key=itemgetter(1))]
return self