csv_dataset.py 16.1 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :


import os
from bob.pipelines import Sample, DelayedSample, SampleSet
import csv
import bob.io.base
import functools
from abc import ABCMeta, abstractmethod
11
12
import numpy as np
import itertools
13
import logging
14

15
logger = logging.getLogger(__name__)
16

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
17
class CSVBaseSampleLoader(metaclass=ABCMeta):
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
    """
    Convert CSV files in the format below to either a list of
    :any:`bob.pipelines.DelayedSample` or :any:`bob.pipelines.SampleSet`

    .. code-block:: text

       PATH,SUBJECT
       path_1,subject_1
       path_2,subject_2
       path_i,subject_j
       ...

    .. note::
       This class should be extended

    Parameters
    ----------

        data_loader:
            A python function that can be called parameterlessly, to load the
            sample in question from whatever medium

        extension:
            The file extension

    """

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
45
    def __init__(self, data_loader, dataset_original_directory="", extension=""):
46
47
        self.data_loader = data_loader
        self.extension = extension
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
48
        self.dataset_original_directory = dataset_original_directory
49
50
51
52
53
54
55
56
57
58

    @abstractmethod
    def __call__(self, filename):
        pass

    @abstractmethod
    def convert_row_to_sample(self, row, header):
        pass

    @abstractmethod
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
59
60
61
    def convert_samples_to_samplesets(
        self, samples, group_by_subject=True, references=None
    ):
62
63
64
        pass


Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
65
class CSVToSampleLoader(CSVBaseSampleLoader):
66
67
68
69
70
    """
    Simple mechanism to convert CSV files in the format below to either a list of
    :any:`bob.pipelines.DelayedSample` or :any:`bob.pipelines.SampleSet`
    """

71
72
73
74
75
76
77
    def check_header(self, header):
        """
        A header should have at least "SUBJECT" AND "PATH"
        """
        header = [h.lower() for h in header]
        if not "subject" in header:
            raise ValueError("The field `subject` is not available in your dataset.")
78

79
80
81
82
        if not "path" in header:
            raise ValueError("The field `path` is not available in your dataset.")

    def __call__(self, filename):
83
84
85
86
87

        with open(filename) as cf:
            reader = csv.reader(cf)
            header = next(reader)

88
            self.check_header(header)
89
90
91
92
93
            return [self.convert_row_to_sample(row, header) for row in reader]

    def convert_row_to_sample(self, row, header):
        path = row[0]
        subject = row[1]
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
94
        kwargs = dict([[h, r] for h, r in zip(header[2:], row[2:])])
95
        return DelayedSample(
96
97
98
99
            functools.partial(
                self.data_loader,
                os.path.join(self.dataset_original_directory, path + self.extension),
            ),
100
101
102
103
104
            key=path,
            subject=subject,
            **kwargs,
        )

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
105
106
107
    def convert_samples_to_samplesets(
        self, samples, group_by_subject=True, references=None
    ):
108
109
110
111
112
113
114
        if group_by_subject:

            # Grouping sample sets
            sample_sets = dict()
            for s in samples:
                if s.subject not in sample_sets:
                    sample_sets[s.subject] = SampleSet(
115
                        [s], parent=s, references=references
116
                    )
117
118
                else:
                    sample_sets[s.subject].append(s)
119
120
121
            return list(sample_sets.values())

        else:
122
            return [
123
                SampleSet([s], parent=s, references=references)
124
125
                for s in samples
            ]
126
127
128
129


class CSVDatasetDevEval:
    """
130
131
    Generic filelist dataset for :any:` bob.bio.base.pipelines.vanilla_biometrics.VanillaBiometricsPipeline` pipeline.
    Check :any:`vanilla_biometrics_features` for more details about the Vanilla Biometrics Dataset
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
    interface.

    To create a new dataset, you need to provide a directory structure similar to the one below:

    .. code-block:: text

       my_dataset/
       my_dataset/my_protocol/
       my_dataset/my_protocol/train.csv
       my_dataset/my_protocol/train.csv/dev_enroll.csv
       my_dataset/my_protocol/train.csv/dev_probe.csv
       my_dataset/my_protocol/train.csv/eval_enroll.csv
       my_dataset/my_protocol/train.csv/eval_probe.csv
       ...


    In the above directory structure, inside of `my_dataset` should contain the directories with all
    evaluation protocols this dataset might have.
    Inside of the `my_protocol` directory should contain at least two csv files:

     - dev_enroll.csv
     - dev_probe.csv


    Those csv files should contain in each row i-) the path to raw data and ii-) the subject label
157
158
    for enrollment (:any:`bob.bio.base.pipelines.vanilla_biometrics.Database.references`) and
    probing (:any:`bob.bio.base.pipelines.vanilla_biometrics.Database.probes`).
159
160
161
162
163
164
165
166
167
168
    The structure of each CSV file should be as below:

    .. code-block:: text

       PATH,SUBJECT
       path_1,subject_1
       path_2,subject_2
       path_i,subject_j
       ...

169

170
171
172
173
174
175
176
177
178
179
180
181
182
183
    You might want to ship metadata within your Samples (e.g gender, age, annotation, ...)
    To do so is simple, just do as below:

    .. code-block:: text

       PATH,SUBJECT,METADATA_1,METADATA_2,METADATA_k
       path_1,subject_1,A,B,C
       path_2,subject_2,A,B,1
       path_i,subject_j,2,3,4
       ...


    The files `my_dataset/my_protocol/train.csv/eval_enroll.csv` and `my_dataset/my_protocol/train.csv/eval_probe.csv`
    are optional and it is used in case a protocol contains data for evaluation.
184

185
    Finally, the content of the file `my_dataset/my_protocol/train.csv` is used in the case a protocol
186
    contains data for training (`bob.bio.base.pipelines.vanilla_biometrics.Database.background_model_samples`)
187
188
189
190
191
192
193

    Parameters
    ----------

        dataset_path: str
          Absolute path of the dataset protocol description

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
194
        protocol_na,e: str
195
196
          The name of the protocol

197
198
        csv_to_sample_loader: :any:`bob.bio.base.database.CSVBaseSampleLoader`
            Base class that whose objective is to generate :any:`bob.pipelines.Sample`
199
            and/or :any:`bob.pipelines.SampleSet` from csv rows
200
201
202
203
204

    """

    def __init__(
        self,
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
205
206
        dataset_protocol_path,
        protocol_name,
207
        csv_to_sample_loader=CSVToSampleLoader(
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
208
            data_loader=bob.io.base.load, dataset_original_directory="", extension=""
209
210
211
212
        ),
    ):
        def get_paths():

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
213
214
            if not os.path.exists(dataset_protocol_path):
                raise ValueError(f"The path `{dataset_protocol_path}` was not found")
215
216

            # TODO: Unzip file if dataset path is a zip
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
217
            protocol_path = os.path.join(dataset_protocol_path, protocol_name)
218
            if not os.path.exists(protocol_path):
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
219
                raise ValueError(f"The protocol `{protocol_name}` was not found")
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

            train_csv = os.path.join(protocol_path, "train.csv")
            dev_enroll_csv = os.path.join(protocol_path, "dev_enroll.csv")
            dev_probe_csv = os.path.join(protocol_path, "dev_probe.csv")
            eval_enroll_csv = os.path.join(protocol_path, "eval_enroll.csv")
            eval_probe_csv = os.path.join(protocol_path, "eval_probe.csv")

            # The minimum required is to have `dev_enroll_csv` and `dev_probe_csv`
            train_csv = train_csv if os.path.exists(train_csv) else None

            # Eval
            eval_enroll_csv = (
                eval_enroll_csv if os.path.exists(eval_enroll_csv) else None
            )
            eval_probe_csv = eval_probe_csv if os.path.exists(eval_probe_csv) else None

            # Dev
            if not os.path.exists(dev_enroll_csv):
                raise ValueError(
                    f"The file `{dev_enroll_csv}` is required and it was not found"
                )

            if not os.path.exists(dev_probe_csv):
                raise ValueError(
                    f"The file `{dev_probe_csv}` is required and it was not found"
                )

            return (
                train_csv,
                dev_enroll_csv,
                dev_probe_csv,
                eval_enroll_csv,
                eval_probe_csv,
            )

        (
            self.train_csv,
            self.dev_enroll_csv,
            self.dev_probe_csv,
            self.eval_enroll_csv,
            self.eval_probe_csv,
        ) = get_paths()

        def get_dict_cache():
            cache = dict()
            cache["train"] = None
            cache["dev_enroll_csv"] = None
            cache["dev_probe_csv"] = None
            cache["eval_enroll_csv"] = None
            cache["eval_probe_csv"] = None
            return cache

        self.cache = get_dict_cache()
        self.csv_to_sample_loader = csv_to_sample_loader

    def background_model_samples(self):

        self.cache["train"] = (
            self.csv_to_sample_loader(self.train_csv)
            if self.cache["train"] is None
            else self.cache["train"]
        )

        return self.cache["train"]

    def _get_samplesets(self, group="dev", purpose="enroll", group_by_subject=False):

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
287
        fetching_probes = False
288
289
290
        if purpose == "enroll":
            cache_label = "dev_enroll_csv" if group == "dev" else "eval_enroll_csv"
        else:
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
291
            fetching_probes = True
292
293
294
295
296
            cache_label = "dev_probe_csv" if group == "dev" else "eval_probe_csv"

        if self.cache[cache_label] is not None:
            return self.cache[cache_label]

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
297
298
        references = None
        if fetching_probes:
299
            references = list(set([s.subject for s in self.references(group=group)]))
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
300
301

        samples = self.csv_to_sample_loader(self.__dict__[cache_label])
302
303

        sample_sets = self.csv_to_sample_loader.convert_samples_to_samplesets(
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
304
            samples, group_by_subject=group_by_subject, references=references
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
        )

        self.cache[cache_label] = sample_sets

        return self.cache[cache_label]

    def references(self, group="dev"):
        return self._get_samplesets(
            group=group, purpose="enroll", group_by_subject=True
        )

    def probes(self, group="dev"):
        return self._get_samplesets(
            group=group, purpose="probe", group_by_subject=False
        )
320

321
322
323
324
325
326
327
328
329
330
331
332
333
334
    def all_samples(self, groups=None):
        """
        Reads and returns all the samples in `groups`.

        Parameters
        ----------
        groups: list or None
            Groups to consider, or all groups if `None` is given.
        """
        # Get train samples (background_model_samples returns a list of samples)
        samples = self.background_model_samples()

        # Get enroll and probe samples
        groups = ["dev", "eval"] if not groups else groups
335
        if "eval" in groups and (not self.eval_enroll_csv or not self.eval_probe_csv):
336
            logger.warning("'eval' requested, but dataset has no 'eval' group.")
337
            groups.remove("eval")
338
339
340
        for group in groups:
            for purpose in ("enroll", "probe"):
                label = f"{group}_{purpose}_csv"
341
                samples = samples + self.csv_to_sample_loader(self.__dict__[label])
342
343
        return samples

344
345
346

class CSVDatasetCrossValidation:
    """
347
    Generic filelist dataset for :any:`bob.bio.base.pipelines.vanilla_biometrics.VanillaBiometricsPipeline` pipeline that
348
349
    handles **CROSS VALIDATION**.

350
    Check :any:`vanilla_biometrics_features` for more details about the Vanilla Biometrics Dataset
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
    interface.


    This interface will take one `csv_file` as input and split into i-) data for training and
    ii-) data for testing.
    The data for testing will be further split in data for enrollment and data for probing.
    The input CSV file should be casted in the following format:

    .. code-block:: text

       PATH,SUBJECT
       path_1,subject_1
       path_2,subject_2
       path_i,subject_j
       ...

    Parameters
    ----------

    csv_file_name: str
      CSV file containing all the samples from your database

    random_state: int
      Pseudo-random number generator seed

    test_size: float
      Percentage of the subjects used for testing

    samples_for_enrollment: float
      Number of samples used for enrollment

382
383
    csv_to_sample_loader: :any:`bob.bio.base.database.CSVBaseSampleLoader`
        Base class that whose objective is to generate :any:`bob.pipelines.Sample`
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
        and/or :any:`bob.pipelines.SampleSet` from csv rows

    """

    def __init__(
        self,
        csv_file_name="metadata.csv",
        random_state=0,
        test_size=0.8,
        samples_for_enrollment=1,
        csv_to_sample_loader=CSVToSampleLoader(
            data_loader=bob.io.base.load, dataset_original_directory="", extension=""
        ),
    ):
        def get_dict_cache():
            cache = dict()
            cache["train"] = None
            cache["dev_enroll_csv"] = None
            cache["dev_probe_csv"] = None
            return cache

        self.random_state = random_state
        self.cache = get_dict_cache()
        self.csv_to_sample_loader = csv_to_sample_loader
        self.csv_file_name = csv_file_name
        self.samples_for_enrollment = samples_for_enrollment
        self.test_size = test_size

        if self.test_size < 0 and self.test_size > 1:
            raise ValueError(
                f"`test_size` should be between 0 and 1. {test_size} is provided"
            )

    def _do_cross_validation(self):

        # Shuffling samples by subject
        samples_by_subject = group_samples_by_subject(
            self.csv_to_sample_loader(self.csv_file_name)
        )
        subjects = list(samples_by_subject.keys())
        np.random.seed(self.random_state)
        np.random.shuffle(subjects)

        # Getting the training data
        n_samples_for_training = len(subjects) - int(self.test_size * len(subjects))
        self.cache["train"] = list(
            itertools.chain(
                *[samples_by_subject[s] for s in subjects[0:n_samples_for_training]]
            )
        )

        # Splitting enroll and probe
        self.cache["dev_enroll_csv"] = []
        self.cache["dev_probe_csv"] = []
        for s in subjects[n_samples_for_training:]:
            samples = samples_by_subject[s]
            if len(samples) < self.samples_for_enrollment:
                raise ValueError(
                    f"Not enough samples ({len(samples)}) for enrollment for the subject {s}"
                )

            # Enrollment samples
            self.cache["dev_enroll_csv"].append(
                self.csv_to_sample_loader.convert_samples_to_samplesets(
                    samples[0 : self.samples_for_enrollment]
                )[0]
            )

            self.cache[
                "dev_probe_csv"
            ] += self.csv_to_sample_loader.convert_samples_to_samplesets(
                samples[self.samples_for_enrollment :],
                group_by_subject=False,
                references=subjects[n_samples_for_training:],
            )

    def _load_from_cache(self, cache_key):
        if self.cache[cache_key] is None:
            self._do_cross_validation()
        return self.cache[cache_key]

    def background_model_samples(self):
        return self._load_from_cache("train")

    def references(self, group="dev"):
        return self._load_from_cache("dev_enroll_csv")

    def probes(self, group="dev"):
        return self._load_from_cache("dev_probe_csv")

474
475
476
477
478
479
480
481
482
483
484
485
486
    def all_samples(self, groups=None):
        """
        Reads and returns all the samples in `groups`.

        Parameters
        ----------
        groups: list or None
            Groups to consider, or all groups if `None` is given.
        """
        # Get train samples (background_model_samples returns a list of samples)
        samples = self.background_model_samples()

        # Get enroll and probe samples
487
488
489
490
        groups = ["dev"] if not groups else groups
        if "eval" in groups:
            logger.info("'eval' requested but there is no 'eval' group defined.")
            groups.remove("eval")
491
        for group in groups:
492
493
            samples = samples+ [s for s_set in self.references(group) for s in s_set]
            samples = samples+ [s for s_set in self.probes(group) for s in s_set]
494
495
        return samples

496
497
498
499
500
501
502
503
504
505

def group_samples_by_subject(samples):

    # Grouping sample sets
    samples_by_subject = dict()
    for s in samples:
        if s.subject not in samples_by_subject:
            samples_by_subject[s.subject] = []
        samples_by_subject[s.subject].append(s)
    return samples_by_subject