def test_import(project):
am = AnnotationManager(project)
input_annotations = pd.read_csv(
'examples/valid_raw_data/raw_annotations/input.csv')
am.import_annotations(input_annotations)
am.read()
assert am.annotations.shape[0] == input_annotations.shape[
0], "imported annotations length does not match input"
assert all([
os.path.exists(os.path.join(project.path, 'annotations', f))
for f in am.annotations['annotation_filename'].tolist()
]), "some annotations are missing"
errors, warnings = am.validate()
assert len(errors) == 0 and len(
warnings) == 0, "malformed annotations detected"
for dataset in ['eaf', 'textgrid', 'eaf_solis']:
annotations = am.annotations[am.annotations['set'] == dataset]
segments = am.get_segments(annotations)
segments.drop(columns=annotations.columns, inplace=True)
pd.testing.assert_frame_equal(
segments.sort_index(axis=1).sort_values(
segments.columns.tolist()).reset_index(drop=True),
pd.read_csv('tests/truth/{}.csv'.format(dataset)).sort_index(
axis=1).sort_values(
segments.columns.tolist()).reset_index(drop=True),
check_less_precise=True)
def import_annotations(args):
"""convert and import a set of annotations"""
project = ChildProject(args.source)
errors, warnings = project.validate_input_data()
if len(errors) > 0:
print("validation failed, {} error(s) occured".format(len(errors)),
file=sys.stderr)
sys.exit(1)
if args.annotations:
annotations = pd.read_csv(args.annotations)
else:
annotations = pd.DataFrame([{
col.name: getattr(args, col.name)
for col in AnnotationManager.INDEX_COLUMNS if not col.generated
}])
am = AnnotationManager(project)
am.import_annotations(annotations)
errors, warnings = am.validate()
if len(am.errors) > 0:
print("importation completed with {} errors and {} warnings".format(
len(am.errors) + len(errors), len(warnings)),
file=sys.stderr)
print("\n".join(am.errors), file=sys.stderr)
print("\n".join(errors), file=sys.stderr)
print("\n".join(warnings))
def test_rename(project):
am = AnnotationManager(project)
input_annotations = pd.read_csv("examples/valid_raw_data/annotations/input.csv")
am.import_annotations(input_annotations[input_annotations["set"] == "textgrid"])
am.read()
tg_count = am.annotations[am.annotations["set"] == "textgrid"].shape[0]
am.rename_set("textgrid", "renamed")
am.read()
errors, warnings = am.validate()
assert len(errors) == 0 and len(warnings) == 0, "malformed annotations detected"
assert am.annotations[am.annotations["set"] == "textgrid"].shape[0] == 0
assert am.annotations[am.annotations["set"] == "renamed"].shape[0] == tg_count
def test_import(project):
am = AnnotationManager(project)
input_annotations = pd.read_csv("examples/valid_raw_data/annotations/input.csv")
am.import_annotations(input_annotations)
am.read()
assert (
am.annotations.shape[0] == input_annotations.shape[0]
), "imported annotations length does not match input"
assert all(
[
os.path.exists(
os.path.join(
project.path,
"annotations",
a["set"],
"converted",
a["annotation_filename"],
)
)
for a in am.annotations.to_dict(orient="records")
]
), "some annotations are missing"
errors, warnings = am.validate()
assert len(errors) == 0 and len(warnings) == 0, "malformed annotations detected"
errors, warnings = am.read()
assert len(errors) == 0 and len(warnings) == 0, "malformed annotation indexes detected"
for dataset in ["eaf_basic", "textgrid", "eaf_solis"]:
annotations = am.annotations[am.annotations["set"] == dataset]
segments = am.get_segments(annotations)
segments.drop(columns=set(annotations.columns) - {"raw_filename"}, inplace=True)
truth = pd.read_csv("tests/truth/{}.csv".format(dataset))
print(segments)
print(truth)
pd.testing.assert_frame_equal(
standardize_dataframe(segments, set(truth.columns.tolist())),
standardize_dataframe(truth, set(truth.columns.tolist())),
check_less_precise=True,
)
def test_custom_importation(project):
am = AnnotationManager(project)
input = pd.DataFrame(
[
{
"set": "vtc_rttm",
"range_onset": 0,
"range_offset": 4000,
"recording_filename": "sound.wav",
"time_seek": 0,
"raw_filename": "example.rttm",
"format": "custom",
}
]
)
am.import_annotations(input, import_function=custom_function)
am.read()
errors, warnings = am.validate()
assert len(errors) == 0