def test_from_data_frame(self):
dframe1 = DictFrame({"x": [0, 1, 2], "y": ["a", "b", "c"]})
pdf = dframe1.todf()
dframe2 = pd_to_dict_frame(pdf)
assert set(pdf.columns) == set(["x", "y"])
assert dframe1 == dframe2
def test_to_data_frame(self):
dframe = DictFrame({
"x": [0, 1, 2],
"y": ["a", "b", "c"],
"embed": np.random.normal(0, 1, (3, 20)),
})
exp_cols = ["x", "y"] + ["embed-{0:d}".format(x) for x in range(20)]
pdf = dframe.todf()
assert set(pdf.columns) == set(exp_cols)
assert issubclass(type(pdf), pd.core.frame.DataFrame)
def test_process_empty_output(self):
fpobj = FrameProcessor()
fpobj.load_annotator(FrameAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=4)
fpobj.process(finput)
assert fpobj.collect("base") == DictFrame()
def test_add(self):
dframe1 = DictFrame({
"x": [0, 1, 2],
"y": ["a", "b", "c"],
"embed": np.random.normal(0, 1, (3, 20)),
})
dframe2 = DictFrame({
"x": [0, 1],
"y": ["a", "b"],
"embed": np.random.normal(0, 1, (2, 20)),
})
dframe3 = dframe1 + dframe2
assert set(dframe3.keys()) == set(["x", "y", "embed"])
assert issubclass(type(dframe3["embed"]), np.ndarray)
assert dframe3.shape == (5, 3)
def test_collect_all(self):
fpobj = FrameProcessor()
fpobj.load_annotator(FrameAnnotator())
fpobj.load_annotator(DiffAnnotator())
finput = FrameInput("test-data/video-clip.mp4", bsize=8)
fpobj.process(finput, max_batch=2)
output = fpobj.collect_all()
assert output["base"] == DictFrame()
assert output["diff"].shape[0] == (2 * 8)
def test_png_resize(self):
dname = tempfile.mkdtemp() # creates directory
fpobj = FrameProcessor()
fpobj.load_annotator(PngAnnotator(output_dir=dname, size=(32, 64)))
finput = FrameInput("test-data/video-clip.mp4", bsize=4)
fpobj.process(finput, max_batch=2)
expected_files = set(["frame-{0:06d}.png".format(x) for x in range(8)])
obj_out = fpobj.collect("png")
assert obj_out == DictFrame()
assert set(os.listdir(dname)) == expected_files
def test_cutoff_ignore(self):
fpobj = FrameProcessor()
fpobj.load_annotator(DiffAnnotator(quantiles=[40]))
finput = FrameInput("test-data/video-clip.mp4", bsize=128)
fpobj.process(finput, max_batch=2)
obj_out = fpobj.collect_all()
ca = CutAggregator(
cut_vals={"h40": 0.2, "q40": 3}, ignore_vals={"avg_value": 70}
)
agg = ca.aggregate(obj_out)
assert agg == DictFrame()
def test_channels(self):
finput = FrameInput("test-data/video-clip.mp4", bsize=1)
batch = get_batch(finput, batch_num=0)
img = batch.get_frames()[0, :, :, :]
face = DictFrame({"top": 0, "bottom": 96, "left": 0, "right": 96})
femb = FaceEmbedVgg2()
femb._iformat = "channels_first"
emb1 = femb.embed(img, face)
femb._iformat = "channels_last"
emb2 = femb.embed(img, face)
assert (emb1 != emb2).any()
def test_bad_length(self):
# check assertion on input
with pytest.raises(AssertionError):
dframe = DictFrame({"x": [0, 1], "y": ["a", "b", "c"]})
# check assertion after the fact
dframe = DictFrame({"x": [0, 1], "y": ["a", "b", "c"]}, check=False)
with pytest.raises(AssertionError):
dframe.verify()
def test_png_image(self):
dname = tempfile.mkdtemp() # creates directory
fpobj = FrameProcessor()
fpobj.load_annotator(PngAnnotator(output_dir=dname))
iobj = ImageInput(input_paths=[
"test-data/img/frame-000076.png",
"test-data/img/frame-000506.png",
])
fpobj.process(iobj, max_batch=2)
# assert that all of the images in the input exist in output
expected_files = set(["frame-000076.png", "frame-000506.png"])
obj_out = fpobj.collect("png")
assert obj_out == DictFrame()
assert set(os.listdir(dname)) == expected_files
# make sure images are the same
img1 = cv2.imread(os.path.join("test-data/img/frame-000076.png"))
img2 = cv2.imread(os.path.join(dname, "frame-000076.png"))
assert np.all(img1 == img2)
def test_scalar_input(self):
dframe = DictFrame({"x": 0, "y": ["a"]})
assert dframe["x"] == [0]
assert dframe["y"] == ["a"]
def test_empty_dict(self):
empty = DictFrame()
assert empty.shape == (0, 0)
