csv_dataset.py 10.1 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
#!/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


Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
13
class CSVBaseSampleLoader(metaclass=ABCMeta):
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
    """
    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
41
    def __init__(self, data_loader, dataset_original_directory="", extension=""):
42
43
        self.data_loader = data_loader
        self.extension = extension
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
44
        self.dataset_original_directory = dataset_original_directory
45
46
47
48
49
50
51
52
53
54
55
        self.excluding_attributes = ["_data", "load", "key"]

    @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
56
57
58
    def convert_samples_to_samplesets(
        self, samples, group_by_subject=True, references=None
    ):
59
60
61
        pass


Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
62
class CSVToSampleLoader(CSVBaseSampleLoader):
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
    """
    Simple mechanism to convert CSV files in the format below to either a list of
    :any:`bob.pipelines.DelayedSample` or :any:`bob.pipelines.SampleSet`
    """

    def __call__(self, filename):
        def check_header(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."
                )

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

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

            check_header(header)
            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
92
        kwargs = dict([[h, r] for h, r in zip(header[2:], row[2:])])
93
        return DelayedSample(
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
94
            functools.partial(self.data_loader, os.path.join(self.dataset_original_directory, path+self.extension)),
95
96
97
98
99
            key=path,
            subject=subject,
            **kwargs,
        )

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
100
101
102
    def convert_samples_to_samplesets(
        self, samples, group_by_subject=True, references=None
    ):
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
        def get_attribute_from_sample(sample):
            return dict(
                [
                    [attribute, sample.__dict__[attribute]]
                    for attribute in list(sample.__dict__.keys())
                    if attribute not in self.excluding_attributes
                ]
            )

        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(
                        [s], **get_attribute_from_sample(s)
                    )
                sample_sets[s.subject].append(s)
            return list(sample_sets.values())

        else:
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
125
            return [SampleSet([s], **get_attribute_from_sample(s), references=references) for s in samples]
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


class CSVDatasetDevEval:
    """
    Generic filelist dataset for :any:`bob.bio.base.pipelines.VanillaBiometrics` pipeline.
    Check :ref:`vanilla_biometrics_features` for more details about the Vanilla Biometrics Dataset
    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
    for enrollment (:ref:`bob.bio.base.pipelines.vanilla_biometrics.abstract_classes.Database.references`) and
    probing (:ref:`bob.bio.base.pipelines.vanilla_biometrics.abstract_classes.Database.probes`).
    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
       ...

    
    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.
    
    Finally, the content of the file `my_dataset/my_protocol/train.csv` is used in the case a protocol
    contains data for training (:ref:`bob.bio.base.pipelines.vanilla_biometrics.abstract_classes.Database.background_model_samples`)

    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
197
198
199
200
201
202
203
          The name of the protocol

        csv_to_sample_loader:


    """

    def __init__(
        self,
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
204
205
        dataset_protocol_path,
        protocol_name,
206
        csv_to_sample_loader=CSVToSampleLoader(
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
207
            data_loader=bob.io.base.load, dataset_original_directory="", extension=""
208
209
210
211
        ),
    ):
        def get_paths():

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
212
213
            if not os.path.exists(dataset_protocol_path):
                raise ValueError(f"The path `{dataset_protocol_path}` was not found")
214
215

            # TODO: Unzip file if dataset path is a zip
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
216
            protocol_path = os.path.join(dataset_protocol_path, protocol_name)
217
            if not os.path.exists(protocol_path):
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
218
                raise ValueError(f"The protocol `{protocol_name}` was not found")
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

            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"]

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
284
285
286
    def _get_subjects_from_samplesets(self, sample_sets):
        return list(set([s.subject for s in sample_sets]))

287
288
    def _get_samplesets(self, group="dev", purpose="enroll", group_by_subject=False):

Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
289
        fetching_probes = False
290
291
292
        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
293
            fetching_probes = True
294
295
296
297
298
            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
299
300
301
302
303
304
305
        references = None
        if fetching_probes:
            references = self._get_subjects_from_samplesets(
                self.references(group=group)
            )

        samples = self.csv_to_sample_loader(self.__dict__[cache_label])
306
307

        sample_sets = self.csv_to_sample_loader.convert_samples_to_samplesets(
Tiago de Freitas Pereira's avatar
Tiago de Freitas Pereira committed
308
            samples, group_by_subject=group_by_subject, references=references
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
        )

        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
        )