Add pre-commit

.flake8

+[flake8]
+max-line-length = 80
+ignore = E501,W503,E302,E402,E203

.pre-commit-config.yaml

+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/timothycrosley/isort
+    rev: 5.9.3
+    hooks:
+      - id: isort
+        args: [--settings-path, "pyproject.toml"]
+  - repo: https://github.com/psf/black
+    rev: 21.7b0
+    hooks:
+      - id: black
+  - repo: https://gitlab.com/pycqa/flake8
+    rev: 3.9.2
+    hooks:
+      - id: flake8
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.0.1
+    hooks:
+      - id: check-ast
+      - id: check-case-conflict
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: debug-statements
+      - id: check-added-large-files
+      - id: check-yaml
+        exclude: .*/meta.yaml

MANIFEST.in

@@ -4,4 +4,3 @@ recursive-include bob/pad/face/config/preprocessor/dictionaries *.hdf5
 recursive-include doc *.py *.rst *.ico *.png
 recursive-include bob/pad/face/test/data *.hdf5 *.png
 recursive-include bob/pad/face/config *.xml
-

bob/__init__.py

 # see https://docs.python.org/3/library/pkgutil.html
 from pkgutil import extend_path
+
 __path__ = extend_path(__path__, __name__)

bob/pad/__init__.py

 # see https://docs.python.org/3/library/pkgutil.html
 from pkgutil import extend_path
+
 __path__ = extend_path(__path__, __name__)

bob/pad/face/__init__.py

-from . import extractor, preprocessor, database
+from . import database, extractor, preprocessor  # noqa: F401
 
 
 def get_config():
-    """Returns a string containing the configuration information.
-    """
+    """Returns a string containing the configuration information."""
 
     import bob.extension
+
     return bob.extension.get_config(__name__)
 
 
 # gets sphinx autodoc done right - don't remove it
-__all__ = [_ for _ in dir() if not _.startswith('_')]
+__all__ = [_ for _ in dir() if not _.startswith("_")]

bob/pad/face/config/svm_frames.py

-import bob.pipelines as mario
-from bob.pad.face.transformer import VideoToFrames
 from sklearn.model_selection import GridSearchCV
 from sklearn.pipeline import Pipeline
 from sklearn.svm import SVC
 
+import bob.pipelines as mario
+
+from bob.pad.face.transformer import VideoToFrames
+
 preprocessor = globals().get("preprocessor")
 extractor = globals().get("extractor")
 
@@ -21,7 +23,9 @@ param_grid = [
 
 classifier = GridSearchCV(SVC(), param_grid=param_grid, cv=3)
 classifier = mario.wrap(
-    ["sample"], classifier, fit_extra_arguments=[("y", "is_bonafide")],
+    ["sample"],
+    classifier,
+    fit_extra_arguments=[("y", "is_bonafide")],
 )
 
 

bob/pad/face/database/__init__.py

-from .database import VideoPadSample  # noqa: F401
 from .casiafasd import CasiaFasdPadDatabase
 from .casiasurf import CasiaSurfPadDatabase
+from .database import VideoPadSample  # noqa: F401
 from .maskattack import MaskAttackPadDatabase
+from .oulunpu import OulunpuPadDatabase
 from .replay_attack import ReplayAttackPadDatabase
 from .replay_mobile import ReplayMobilePadDatabase
 from .swan import SwanPadDatabase
-from .oulunpu import OulunpuPadDatabase
 
 
 # gets sphinx autodoc done right - don't remove it
 def __appropriate__(*args):
     """Says object was actually declared here, and not in the import module.
-  Fixing sphinx warnings of not being able to find classes, when path is
-  shortened. Parameters:
+    Fixing sphinx warnings of not being able to find classes, when path is
+    shortened. Parameters:
 
-    *args: An iterable of objects to modify
+      *args: An iterable of objects to modify
 
-  Resolves `Sphinx referencing issues
-  <https://github.com/sphinx-doc/sphinx/issues/3048>`
-  """
+    Resolves `Sphinx referencing issues
+    <https://github.com/sphinx-doc/sphinx/issues/3048>`
+    """
 
     for obj in args:
         obj.__module__ = __name__
@@ -34,4 +34,4 @@ __appropriate__(
     OulunpuPadDatabase,
 )
 
-__all__ = [_ for _ in dir() if not _.startswith('_')]
+__all__ = [_ for _ in dir() if not _.startswith("_")]

bob/pad/face/database/casiasurf.py

 import logging
 import os
+
 from functools import partial
 
+from sklearn.preprocessing import FunctionTransformer
+
 import bob.io.base
+
 from bob.bio.video import VideoLikeContainer
 from bob.extension import rc
 from bob.extension.download import get_file
 from bob.pad.base.database import FileListPadDatabase
 from bob.pipelines import DelayedSample
-from sklearn.preprocessing import FunctionTransformer
 
 logger = logging.getLogger(__name__)
 
@@ -45,7 +48,9 @@ def casia_surf_multistream_load(samples, original_directory, stream_type):
         paths = []
         for mod in mods:
             paths.append(
-                os.path.join(original_directory or "", getattr(sample, mod_to_attr[mod]))
+                os.path.join(
+                    original_directory or "", getattr(sample, mod_to_attr[mod])
+                )
             )
         data = partial(load_multi_stream, mods, paths)
         return DelayedSample(data, parent=sample, annotations=None)
@@ -56,7 +61,9 @@ def casia_surf_multistream_load(samples, original_directory, stream_type):
 def CasiaSurfMultiStreamSample(original_directory, stream_type):
     return FunctionTransformer(
         casia_surf_multistream_load,
-        kw_args=dict(original_directory=original_directory, stream_type=stream_type),
+        kw_args=dict(
+            original_directory=original_directory, stream_type=stream_type
+        ),
     )
 
 

bob/pad/face/database/database.py

-from functools import partial
 import os
-import bob.bio.video
-from bob.bio.base.utils.annotations import read_annotation_file
+
+from functools import partial
+
 from sklearn.preprocessing import FunctionTransformer
+
+from bob.bio.base.utils.annotations import read_annotation_file
 from bob.bio.video import VideoAsArray
 from bob.pipelines import DelayedSample
 
-from ..utils import frames, number_of_frames
 
 def get_no_transform(x):
     return None
 
+
 def delayed_video_load(
     samples,
     original_directory,

bob/pad/face/database/replay_mobile.py

 import logging
 
-import numpy as np
+from sklearn.pipeline import make_pipeline
+
 from bob.extension import rc
 from bob.extension.download import get_file
 from bob.pad.base.database import FileListPadDatabase
 from bob.pad.face.database import VideoPadSample
-from bob.pipelines.transformers import Str_To_Types
-from bob.pipelines.transformers import str_to_bool
-from sklearn.pipeline import make_pipeline
+from bob.pipelines.transformers import Str_To_Types, str_to_bool
 
 logger = logging.getLogger(__name__)
 

bob/pad/face/extractor/__init__.py

-
-
 def __appropriate__(*args):
     """Says object was actually declared here, and not in the import module.
     Fixing sphinx warnings of not being able to find classes, when path is
@@ -19,4 +17,4 @@ def __appropriate__(*args):
 
 
 __appropriate__()
-__all__ = [_ for _ in dir() if not _.startswith('_')]
+__all__ = [_ for _ in dir() if not _.startswith("_")]

bob/pad/face/preprocessor/Patch.py

-from bob.bio.base.annotator.FailSafe import translate_kwargs
+from collections import OrderedDict
+
 from sklearn.base import BaseEstimator, TransformerMixin
-from ..utils import extract_patches
+
+from bob.bio.base.annotator.FailSafe import translate_kwargs
 from bob.bio.video import VideoLikeContainer
-from collections import OrderedDict
+
+from ..utils import extract_patches
 
 
 class ImagePatches(TransformerMixin, BaseEstimator):
@@ -55,7 +58,10 @@ class VideoPatches(TransformerMixin, BaseEstimator):
 
     def transform(self, videos, annotations=None):
         kwargs = translate_kwargs(dict(annotations=annotations), len(videos))
-        return [self.transform_one_video(vid, **kw) for vid, kw in zip(videos, kwargs)]
+        return [
+            self.transform_one_video(vid, **kw)
+            for vid, kw in zip(videos, kwargs)
+        ]
 
     def transform_one_video(self, frames, annotations=None):
         annotations = annotations or {}
@@ -76,7 +82,10 @@ class VideoPatches(TransformerMixin, BaseEstimator):
 
             # extract patches
             patches = extract_patches(
-                preprocessed, self.block_size, self.block_overlap, self.n_random_patches
+                preprocessed,
+                self.block_size,
+                self.block_overlap,
+                self.n_random_patches,
             )
             all_patches.extend(patches)
 

bob/pad/face/preprocessor/__init__.py

@@ -23,4 +23,4 @@ __appropriate__(
     ImagePatches,
     VideoPatches,
 )
-__all__ = [_ for _ in dir() if not _.startswith('_')]
+__all__ = [_ for _ in dir() if not _.startswith("_")]

bob/pad/face/script/statistics.py

 """Gets statistics on the average face size in a video database.
 """
 import logging
+
+from os.path import expanduser
+
 import click
 import numpy as np
-from os.path import expanduser
-from bob.extension.scripts.click_helper import (
-    verbosity_option,
-    ConfigCommand,
-    ResourceOption,
-)
+
 from bob.bio.face.annotator import (
+    BoundingBox,
     bounding_box_from_annotation,
     expected_eye_positions,
-    BoundingBox,
+)
+from bob.extension.scripts.click_helper import (
+    ConfigCommand,
+    ResourceOption,
+    verbosity_option,
 )
 
 logger = logging.getLogger(__name__)
@@ -108,14 +111,20 @@ def statistics(database, output, database_directories_file, **kwargs):
         ):
             click.echo(
                 "min: {}, mean: {}, max: {}, std: {:.1f} for {}".format(
-                    array.min(), int(array.mean()), array.max(), array.std(), name
+                    array.min(),
+                    int(array.mean()),
+                    array.max(),
+                    array.std(),
+                    name,
                 )
             )
         # print the average eye distance assuming bounding boxes are from
         # bob.ip.facedetect or the annotations had eye locations in them
         bbx = BoundingBox((0, 0), face_sizes.mean(axis=0))
         annot = expected_eye_positions(bbx)
-        eye_distance = np.linalg.norm(np.array(annot["reye"]) - np.array(annot["leye"]))
+        eye_distance = np.linalg.norm(
+            np.array(annot["reye"]) - np.array(annot["leye"])
+        )
         click.echo("Average eye locations: {}".format(annot))
         click.echo("Average eye distance: {}".format(int(eye_distance)))
 
@@ -141,7 +150,11 @@ def statistics(database, output, database_directories_file, **kwargs):
         # ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap=cm.viridis)
 
         plt.hist(
-            face_sizes[:, 1], density=True, bins="auto", label=attack_type, alpha=0.5
+            face_sizes[:, 1],
+            density=True,
+            bins="auto",
+            label=attack_type,
+            alpha=0.5,
         )
     if output:
         plt.xlabel("Width of faces")

bob/pad/face/test/dummy/database.py

-import bob.io.base
 import os
-from bob.pipelines import DelayedSample
-from bob.pad.base.pipelines.vanilla_pad.abstract_classes import Database
-from bob.bio.base.database.legacy import check_parameters_for_validity, convert_names_to_lowlevel
-from bob.bio.video import VideoLikeContainer
+
+import bob.io.base
+
 from bob.bio.base.database import AtntBioDatabase
+from bob.bio.base.database.legacy import (
+    check_parameters_for_validity,
+    convert_names_to_lowlevel,
+)
+from bob.bio.video import VideoLikeContainer
+from bob.pad.base.pipelines.vanilla_pad.abstract_classes import Database
+from bob.pipelines import DelayedSample
 
 
 def DummyPadSample(
-    path, original_directory, client_id, key, attack_type, none_annotations=False
+    path,
+    original_directory,
+    client_id,
+    key,
+    attack_type,
+    none_annotations=False,
 ):
     def load():
         file_name = os.path.join(original_directory, path + ".pgm")

bob/pad/face/test/test_block.py

@@ -2,11 +2,19 @@ import numpy
 
 A_org = numpy.array(range(1, 17), "float64").reshape((4, 4))
 A_ans_0_3D = numpy.array(
-    [[[1, 2], [5, 6]], [[3, 4], [7, 8]], [[9, 10], [13, 14]], [[11, 12], [15, 16]]],
+    [
+        [[1, 2], [5, 6]],
+        [[3, 4], [7, 8]],
+        [[9, 10], [13, 14]],
+        [[11, 12], [15, 16]],
+    ],
     "float64",
 )
 A_ans_0_4D = numpy.array(
-    [[[[1, 2], [5, 6]], [[3, 4], [7, 8]]], [[[9, 10], [13, 14]], [[11, 12], [15, 16]]]],
+    [
+        [[[1, 2], [5, 6]], [[3, 4], [7, 8]]],
+        [[[9, 10], [13, 14]], [[11, 12], [15, 16]]],
+    ],
     "float64",
 )
 

bob/pad/face/test/test_databases.py

@@ -2,10 +2,11 @@
 # vim: set fileencoding=utf-8 :
 # Thu May 24 10:41:42 CEST 2012
 
+import numpy as np
+
 from nose.plugins.skip import SkipTest
 
 import bob.bio.base
-import numpy as np
 
 
 def test_replayattack():
@@ -31,10 +32,13 @@ def test_replayattack():
     assert len(database.samples(groups=["train", "dev"])) == 720
     assert len(database.samples(groups=["train"])) == 360
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="real")) == 200
+        len(database.samples(groups=["train", "dev", "eval"], purposes="real"))
+        == 200
     )
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="attack"))
+        len(
+            database.samples(groups=["train", "dev", "eval"], purposes="attack")
+        )
         == 1000
     )
 
@@ -71,10 +75,14 @@ def test_replaymobile():
     assert len(database.samples(groups=["train", "dev"])) == 728
     assert len(database.samples(groups=["train"])) == 312
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="real")) == 390
+        len(database.samples(groups=["train", "dev", "eval"], purposes="real"))
+        == 390
     )
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="attack")) == 640
+        len(
+            database.samples(groups=["train", "dev", "eval"], purposes="attack")
+        )
+        == 640
     )
 
     all_samples = database.sort(database.samples())
@@ -133,11 +141,18 @@ def test_maskattack():
     )
     # all real sequences: 2 sessions, 5 recordings for 17 individuals
     assert (
-        len(maskattack.samples(groups=["train", "dev", "eval"], purposes="real")) == 170
+        len(
+            maskattack.samples(groups=["train", "dev", "eval"], purposes="real")
+        )
+        == 170
     )
     # all attacks: 1 session, 5 recordings for 17 individuals
     assert (
-        len(maskattack.samples(groups=["train", "dev", "eval"], purposes="attack"))
+        len(
+            maskattack.samples(
+                groups=["train", "dev", "eval"], purposes="attack"
+            )
+        )
         == 85
     )
 
@@ -189,11 +204,17 @@ def test_casiasurf_color_protocol():
     assert len(casiasurf.samples(groups=["train"], purposes="attack")) == 20324
     assert len(casiasurf.samples(groups=("dev",), purposes=("real",))) == 2994
     assert len(casiasurf.samples(groups=("dev",), purposes=("attack",))) == 6614
-    assert len(casiasurf.samples(groups=("dev",), purposes=("real", "attack"))) == 9608
+    assert (
+        len(casiasurf.samples(groups=("dev",), purposes=("real", "attack")))
+        == 9608
+    )
     assert len(casiasurf.samples(groups=("eval",), purposes=("real",))) == 17458
-    assert len(casiasurf.samples(groups=("eval",), purposes=("attack",))) == 40252
     assert (
-        len(casiasurf.samples(groups=("eval",), purposes=("real", "attack"))) == 57710
+        len(casiasurf.samples(groups=("eval",), purposes=("attack",))) == 40252
+    )
+    assert (
+        len(casiasurf.samples(groups=("eval",), purposes=("real", "attack")))
+        == 57710
     )
 
 
@@ -234,10 +255,13 @@ def test_swan():
     assert len(database.samples(groups=["train", "dev"])) == 2803
     assert len(database.samples(groups=["train"])) == 2001
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="real")) == 3300
+        len(database.samples(groups=["train", "dev", "eval"], purposes="real"))
+        == 3300
     )
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="attack"))
+        len(
+            database.samples(groups=["train", "dev", "eval"], purposes="attack")
+        )
         == 2502
     )
 
@@ -287,7 +311,10 @@ def test_oulunpu():
         "Protocol_4_6",
     ]
     assert database.groups() == ["dev", "eval", "train"]
-    assert len(database.samples(groups=["train", "dev", "eval"])) == 1200 + 900 + 600
+    assert (
+        len(database.samples(groups=["train", "dev", "eval"]))
+        == 1200 + 900 + 600
+    )
     assert len(database.samples(groups=["train", "dev"])) == 1200 + 900
     assert len(database.samples(groups=["train"])) == 1200
     assert (
@@ -295,7 +322,9 @@ def test_oulunpu():
         == 240 + 180 + 120
     )
     assert (
-        len(database.samples(groups=["train", "dev", "eval"], purposes="attack"))
+        len(
+            database.samples(groups=["train", "dev", "eval"], purposes="attack")
+        )
         == 960 + 720 + 480
     )
 

bob/pad/face/test/test_transformers.py

 import bob.pipelines as mario
+
 from bob.bio.video import VideoLikeContainer
 from bob.pad.face.transformer import VideoToFrames
 

bob/pad/face/test/test_utils.py

-from bob.pad.face.test.dummy.database import DummyDatabase as Database
-from bob.pad.face.utils import yield_faces, scale_face, blocks, frames, number_of_frames
-from nose.tools import raises
-import numpy
 import imageio
+import numpy
+
+from nose.tools import raises
+
+from bob.pad.face.test.dummy.database import DummyDatabase as Database
+from bob.pad.face.utils import (
+    blocks,
+    frames,
+    number_of_frames,
+    scale_face,
+    yield_faces,
+)
 
 
 def get_pad_sample(none_annotations=False):
-    sample = Database(none_annotations=none_annotations).samples(("train", "dev"))[0]
+    sample = Database(none_annotations=none_annotations).samples(
+        ("train", "dev")
+    )[0]
     return sample
 
 
@@ -15,7 +25,9 @@ image = get_pad_sample().data[0]
 
 def test_video_frames():
     # get the path to cockatoo.mp4 from imageio-ffmpeg
-    path = imageio.core.Request("imageio:cockatoo.mp4", "r").get_local_filename()
+    path = imageio.core.Request(
+        "imageio:cockatoo.mp4", "r"
+    ).get_local_filename()
     # read 2 frames
     for i, frame in enumerate(frames(path)):
         assert frame.shape == (3, 720, 1280), frame.shape
@@ -32,7 +44,6 @@ def test_video_frames():
     assert n_frames == 280, n_frames
 
 
-
 def dummy_cropper(frame, annotations=None):
     return frame