load.py 8.42 KB
Newer Older
André Anjos's avatar
André Anjos committed
1
2
3
4
5
6
7
8
9
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
# Andre Anjos <andre.anjos@idiap.ch>
# Mon 23 May 2011 16:23:05 CEST

"""A set of utilities to load score files with different formats.
"""

import numpy
10
11
12
13
14
15
16
17
import tarfile
import os

def open_file(filename):
  """Opens the given score file for reading.
  Score files might be raw text files, or a tar-file including a single score file inside.

  Parameters:
18
19
20
21

  filename : str or file-like
    The name of the score file to open, or a file-like object open for reading.
    If a file name is given, the according file might be a raw text file or a (compressed) tar file containing a raw text file.
22
23
24
25

  Returns:
    A read-only file-like object as it would be returned by open().
  """
26
27
28
29
  if not isinstance(filename, str) and hasattr(filename, 'read'):
    # It seems that this is an open file
    return filename

30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
  if not os.path.isfile(filename):
    raise IOError("Score file '%s' does not exist." % filename)
  if not tarfile.is_tarfile(filename):
    return open(filename, 'rt')

  # open the tar file for reading
  tar = tarfile.open(filename, 'r')
  # get the first file in the tar file
  tar_info = tar.next()
  while tar_info is not None and not tar_info.isfile():
    tar_info = tar.next()
  # check that one file was found in the archive
  if tar_info is None:
    raise IOError("The given file is a .tar file, but it does not contain any file.")

  # open the file for reading
  return tar.extractfile(tar_info)

André Anjos's avatar
André Anjos committed
48
49
50
51
52
53

def four_column(filename):
  """Loads a score set from a single file to memory.

  Verifies that all fields are correctly placed and contain valid fields.

54
  Returns a python generator of tuples containing the following fields:
André Anjos's avatar
André Anjos committed
55
56
57
58
59
60
61
62
63
64
65

    [0]
      claimed identity (string)
    [1]
      real identity (string)
    [2]
      test label (string)
    [3]
      score (float)
  """

66
67
  for i, l in enumerate(open_file(filename)):
    if isinstance(l, bytes): l = l.decode('utf-8')
André Anjos's avatar
André Anjos committed
68
69
70
71
72
73
74
75
76
    s = l.strip()
    if len(s) == 0 or s[0] == '#': continue #empty or comment
    field = [k.strip() for k in s.split()]
    if len(field) < 4:
      raise SyntaxError('Line %d of file "%s" is invalid: %s' % (i, filename, l))
    try:
      score = float(field[3])
    except:
      raise SyntaxError('Cannot convert score to float at line %d of file "%s": %s' % (i, filename, l))
77
    yield (field[0], field[1], field[2], score)
André Anjos's avatar
André Anjos committed
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94


def split_four_column(filename):
  """Loads a score set from a single file to memory and splits the scores
  between positives and negatives. The score file has to respect the 4 column
  format as defined in the method four_column().

  This method avoids loading and allocating memory for the strings present in
  the file. We only keep the scores.

  Returns a python tuple (negatives, positives). The values are 1-D blitz
  arrays of float64.
  """

  # split in positives and negatives
  neg = []
  pos = []
95
96
97
98
99
100
  # read four column list line by line
  for (client_id, probe_id, _, score) in four_column(filename):
    if client_id == probe_id:
      pos.append(score)
    else:
      neg.append(score)
André Anjos's avatar
André Anjos committed
101
102
103
104
105

  return (numpy.array(neg, numpy.float64), numpy.array(pos, numpy.float64))

def cmc_four_column(filename):
  """Loads scores to compute CMC curves from a file in four column format.
106
107
108
109
110
111
  The four column file needs to be in the same format as described in the four_column function,
  and the "test label" (column 3) has to contain the test/probe file name.

  This function returns a list of tuples.
  For each probe file, the tuple consists of a list of negative scores and a list of positive scores.
  Usually, the list of positive scores should contain only one element, but more are allowed.
112

113
114
  The result of this function can directly be passed to, e.g., the bob.measure.cmc function.
  """
André Anjos's avatar
André Anjos committed
115
116
117
  # extract positives and negatives
  pos_dict = {}
  neg_dict = {}
118
119
  # read four column list
  for (client_id, probe_id, probe_name, score_str) in four_column(filename):
André Anjos's avatar
André Anjos committed
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
    try:
      score = float(score_str)
      # check in which dict we have to put the score
      if client_id == probe_id:
        correct_dict = pos_dict
      else:
        correct_dict = neg_dict
      # append score
      if probe_name in correct_dict:
        correct_dict[probe_name].append(score)
      else:
        correct_dict[probe_name] = [score]
    except:
      raise SyntaxError("Cannot convert score '%s' to float" % score_str)

  # convert to lists of tuples of ndarrays
  retval = []
  import logging
  logger = logging.getLogger('bob')
  for probe_name in sorted(pos_dict.keys()):
    if probe_name in neg_dict:
      retval.append((numpy.array(neg_dict[probe_name], numpy.float64), numpy.array(pos_dict[probe_name], numpy.float64)))
    else:
      logger.warn('For probe name "%s" there are only positive scores. This probe name is ignored.' % probe_name)
  # test if there are probes for which only negatives exist
  for probe_name in sorted(neg_dict.keys()):
    if not probe_name in pos_dict.keys():
       logger.warn('For probe name "%s" there are only negative scores. This probe name is ignored.' % probe_name)

  return retval

def five_column(filename):
  """Loads a score set from a single file to memory.

  Verifies that all fields are correctly placed and contain valid fields.

156
  Returns a python generator of tuples containing the following fields:
André Anjos's avatar
André Anjos committed
157
158
159
160
161
162
163
164
165
166
167
168
169

    [0]
      claimed identity (string)
    [1]
      model label (string)
    [2]
      real identity (string)
    [3]
      test label (string)
    [4]
      score (float)
  """

170
  for i, l in enumerate(open_file(filename)):
171
    if isinstance(l, bytes): l = l.decode('utf-8')
André Anjos's avatar
André Anjos committed
172
173
174
175
176
177
178
179
180
    s = l.strip()
    if len(s) == 0 or s[0] == '#': continue #empty or comment
    field = [k.strip() for k in s.split()]
    if len(field) < 5:
      raise SyntaxError('Line %d of file "%s" is invalid: %s' % (i, filename, l))
    try:
      score = float(field[4])
    except:
      raise SyntaxError('Cannot convert score to float at line %d of file "%s": %s' % (i, filename, l))
181
    yield (field[0], field[1], field[2], field[3], score)
André Anjos's avatar
André Anjos committed
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197

def split_five_column(filename):
  """Loads a score set from a single file to memory and splits the scores
  between positives and negatives. The score file has to respect the 5 column
  format as defined in the method five_column().

  This method avoids loading and allocating memory for the strings present in
  the file. We only keep the scores.

  Returns a python tuple (negatives, positives). The values are 1-D blitz
  arrays of float64.
  """

  # split in positives and negatives
  neg = []
  pos = []
198
199
200
201
202
203
  # read five column list
  for (client_id, _, probe_id, _, score) in five_column(filename):
    if client_id == probe_id:
      pos.append(score)
    else:
      neg.append(score)
André Anjos's avatar
André Anjos committed
204
205
206
207
208

  return (numpy.array(neg, numpy.float64), numpy.array(pos, numpy.float64))

def cmc_five_column(filename):
  """Loads scores to compute CMC curves from a file in five column format.
209
210
  The four column file needs to be in the same format as described in the five_column function,
  and the "test label" (column 4) has to contain the test/probe file name.
André Anjos's avatar
André Anjos committed
211

212
213
214
  This function returns a list of tuples.
  For each probe file, the tuple consists of a list of negative scores and a list of positive scores.
  Usually, the list of positive scores should contain only one element, but more are allowed.
215

216
  The result of this function can directly be passed to, e.g., the bob.measure.cmc function.
André Anjos's avatar
André Anjos committed
217
  """
218
  # extract positives and negatives
André Anjos's avatar
André Anjos committed
219
220
  pos_dict = {}
  neg_dict = {}
221
222
223
224
225
226
227
228
229
230
231
232
  # read four column list
  for (client_id, _, probe_id, probe_name, score) in five_column(filename):
    # check in which dict we have to put the score
    if client_id == probe_id:
      correct_dict = pos_dict
    else:
      correct_dict = neg_dict
    # append score
    if probe_name in correct_dict:
      correct_dict[probe_name].append(score)
    else:
      correct_dict[probe_name] = [score]
André Anjos's avatar
André Anjos committed
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247

  # convert to lists of tuples of ndarrays
  retval = []
  import logging
  logger = logging.getLogger('bob')
  for probe_name in sorted(pos_dict.keys()):
    if probe_name in neg_dict:
      retval.append((numpy.array(neg_dict[probe_name], numpy.float64), numpy.array(pos_dict[probe_name], numpy.float64)))
    else:
      logger.warn('For probe name "%s" there are only positive scores. This probe name is ignored.' % probe_name)
  # test if there are probes for which only negatives exist
  for probe_name in sorted(neg_dict.keys()):
    if not probe_name in pos_dict.keys():
       logger.warn('For probe name "%s" there are only negative scores. This probe name is ignored.' % probe_name)
  return retval