load.py 11.4 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
import tarfile
import os

def open_file(filename):
14 15 16
  """open_file(filename) -> file_like

  Opens the given score file for reading.
17 18
  Score files might be raw text files, or a tar-file including a single score file inside.

19
  **Parameters:**
20

21
  ``filename`` : str or file-like
22 23
    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.
24

25 26 27
  **Returns:**

  ``file_like`` : file-like
28 29
    A read-only file-like object as it would be returned by open().
  """
30 31 32 33
  if not isinstance(filename, str) and hasattr(filename, 'read'):
    # It seems that this is an open file
    return filename

34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
  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
52 53

def four_column(filename):
54 55 56 57 58 59 60 61 62 63 64 65
  """four_column(filename) -> claimed_id, real_id, test_label, score

  Loads a score set from a single file and yield its lines (to avoid loading the score file at once into memory).
  This function verifies that all fields are correctly placed and contain valid fields.
  The score file must contain the following information in each line:

    claimed_id real_id test_label score

  **Parametes:**

  ``filename`` : str or file-like
    The file object that will be opened with :py:func:`open_file` containing the scores.
André Anjos's avatar
André Anjos committed
66

67
  **Yields:**
André Anjos's avatar
André Anjos committed
68

69 70
  ``claimed_id`` : str
    The claimed identity -- the client name of the model that was used in the comparison
André Anjos's avatar
André Anjos committed
71

72 73 74 75 76 77 78 79
  ``real_id`` : str
    The real identity -- the client name of the probe that was used in the comparison

  ``test_label`` : str
    A label of the probe -- usually the probe file name, or the probe id

  ``score`` : float
    The result of the comparison of the model and the probe
André Anjos's avatar
André Anjos committed
80 81
  """

82 83
  for i, l in enumerate(open_file(filename)):
    if isinstance(l, bytes): l = l.decode('utf-8')
André Anjos's avatar
André Anjos committed
84 85 86 87 88 89 90 91 92
    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))
93
    yield (field[0], field[1], field[2], score)
André Anjos's avatar
André Anjos committed
94 95 96


def split_four_column(filename):
97 98 99 100 101
  """split_four_column(filename) -> negatives, positives

  Loads a score set from a single file and splits the scores
  between negatives and positives. The score file has to respect the 4 column
  format as defined in the method :py:func:`four_column`.
André Anjos's avatar
André Anjos committed
102 103 104 105

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

106 107 108 109
  **Parameters:**

  ``filename`` : str or file-like
    The file that will be opened with :py:func:`open_file` containing the scores.
André Anjos's avatar
André Anjos committed
110

111 112 113 114 115 116 117 118
  **Returns:**

  ``negatives`` : array_like(1D, float)
    The list of ``score``'s, for which the ``claimed_id`` and the ``real_id`` differed (see :py:func:`four_column`).

  ``positives`` : array_like(1D, float)
    The list of ``score``'s, for which the ``claimed_id`` and the ``real_id`` are identical (see :py:func:`four_column`).
  """
André Anjos's avatar
André Anjos committed
119 120 121
  # split in positives and negatives
  neg = []
  pos = []
122 123 124 125 126 127
  # 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
128 129 130 131

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

def cmc_four_column(filename):
132 133 134 135 136
  """cmc_four_column(filename) -> cmc_scores

  Loads scores to compute CMC curves from a file in four column format.
  The four column file needs to be in the same format as described in :py:func:`four_column`,
  and the ``test_label`` (column 3) has to contain the test/probe file name or a probe id.
137 138 139 140

  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.
141
  The result of this function can directly be passed to, e.g., the :py:func:`bob.measure.cmc` function.
142 143 144 145 146 147 148 149 150 151

  **Parameters:**

  ``filename`` : str or file-like
    The file that will be opened with :py:func:`open_file` containing the scores.

  **Returns:**

  ``cmc_scores`` : [(array_like(1D, float), array_like(1D, float))]
    A list of tuples, where each tuple contains the ``negative`` and ``positive`` scores for one probe of the database
152
  """
André Anjos's avatar
André Anjos committed
153 154 155
  # extract positives and negatives
  pos_dict = {}
  neg_dict = {}
156 157
  # read four column list
  for (client_id, probe_id, probe_name, score_str) in four_column(filename):
André Anjos's avatar
André Anjos committed
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
    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):
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
  """five_column(filename) -> claimed_id, model_label, real_id, test_label, score

  Loads a score set from a single file and yield its lines (to avoid loading the score file at once into memory).
  This function verifies that all fields are correctly placed and contain valid fields.
  The score file must contain the following information in each line:

    claimed_id model_label real_id test_label score

  **Parametes:**

  ``filename`` : str or file-like
    The file object that will be opened with :py:func:`open_file` containing the scores.

  **Yields:**

  ``claimed_id`` : str
    The claimed identity -- the client name of the model that was used in the comparison

  ``model_label`` : str
    A label for the model -- usually the model file name, or the model id

  ``real_id`` : str
    The real identity -- the client name of the probe that was used in the comparison

  ``test_label`` : str
    A label of the probe -- usually the probe file name, or the probe id

  ``score`` : float
    The result of the comparison of the model and the probe.
André Anjos's avatar
André Anjos committed
219 220
  """

221
  for i, l in enumerate(open_file(filename)):
222
    if isinstance(l, bytes): l = l.decode('utf-8')
André Anjos's avatar
André Anjos committed
223 224 225 226 227 228 229 230 231
    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))
232
    yield (field[0], field[1], field[2], field[3], score)
André Anjos's avatar
André Anjos committed
233 234

def split_five_column(filename):
235 236 237 238 239
  """split_five_column(filename) -> negatives, positives

  Loads a score set from a single file in five column format and splits the scores
  between negatives and positives. The score file has to respect the 4 column
  format as defined in the method :py:func:`five_column`.
André Anjos's avatar
André Anjos committed
240 241 242 243

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

244 245 246 247 248 249 250 251 252 253 254 255
  **Parameters:**

  ``filename`` : str or file-like
    The file that will be opened with :py:func:`open_file` containing the scores.

  **Returns:**

  ``negatives`` : array_like(1D, float)
    The list of ``score``'s, for which the ``claimed_id`` and the ``real_id`` differed (see :py:func:`five_column`).

  ``positives`` : array_like(1D, float)
    The list of ``score``'s, for which the ``claimed_id`` and the ``real_id`` are identical (see :py:func:`five_column`).
André Anjos's avatar
André Anjos committed
256 257 258 259 260
  """

  # split in positives and negatives
  neg = []
  pos = []
261 262 263 264 265 266
  # 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
267 268 269 270

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

def cmc_five_column(filename):
271 272 273 274 275
  """cmc_four_column(filename) -> cmc_scores

  Loads scores to compute CMC curves from a file in five column format.
  The four column file needs to be in the same format as described in :py:func:`five_column`,
  and the ``test_label`` (column 4) has to contain the test/probe file name or a probe id.
André Anjos's avatar
André Anjos committed
276

277 278 279
  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.
280
  The result of this function can directly be passed to, e.g., the :py:func:`bob.measure.cmc` function.
281 282 283 284 285 286 287 288 289 290

  **Parameters:**

  ``filename`` : str or file-like
    The file that will be opened with :py:func:`open_file` containing the scores.

  **Returns:**

  ``cmc_scores`` : [(array_like(1D, float), array_like(1D, float))]
    A list of tuples, where each tuple contains the ``negative`` and ``positive`` scores for one probe of the database
André Anjos's avatar
André Anjos committed
291
  """
292
  # extract positives and negatives
André Anjos's avatar
André Anjos committed
293 294
  pos_dict = {}
  neg_dict = {}
295 296 297 298 299 300 301 302 303 304 305 306
  # 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
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321

  # 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