def test_save():
# Empty content
ListDictContainer(
{}).save(filename=os.path.join(tempfile.gettempdir(), 'saved.yaml'))
# Content
data = [
{
'key1': 100,
'key2': 402.2,
},
{
'key1': 200,
'key2': 302.2,
},
{
'key1': 300,
'key2': 202.3,
},
{
'key1': 400,
'key2': 101.2,
},
]
d = ListDictContainer(data,
filename=os.path.join(tempfile.gettempdir(),
'saved.yaml')).save().load()
nose.tools.assert_list_equal(d, data)
d = ListDictContainer(data,
filename=os.path.join(tempfile.gettempdir(),
'saved.csv')).save().load(
fields=['key1', 'key2'])
nose.tools.assert_list_equal(d, data)
d = ListDictContainer(
data, filename=os.path.join(tempfile.gettempdir(), 'saved.csv')).save(
fields=['key1', 'key2']).load(fields=['key1', 'key2'])
nose.tools.assert_list_equal(d, data)
d = ListDictContainer(
data, filename=os.path.join(tempfile.gettempdir(),
'saved.cpickle')).save().load()
nose.tools.assert_list_equal(d, data)
def test_container():
data = ListDictContainer([
{
'key1': 100,
'key2': 400,
},
{
'key1': 200,
'key2': 300,
},
{
'key1': 300,
'key2': 200,
},
{
'key1': 400,
'key2': 100,
},
])
column = data.get_field(field_name='key1')
nose.tools.eq_(column, [100, 200, 300, 400])
column = data.get_field(field_name='key2')
nose.tools.eq_(column, [400, 300, 200, 100])
nose.tools.eq_(data.search(key='key1', value=100), {
'key1': 100,
'key2': 400
})
nose.tools.eq_(data.search(key='key1', value=123), None)
def parse(self, recipe):
"""Parse feature vector recipe
Overall format: [block #1];[block #2];[block #3];...
Block formats:
- [label (string)]=full vector
- [label (string)]=[start index (int)]-[end index (int)] => default stream and vector [start:end]
- [label (string)]=[stream (int or string)]:[start index (int)]-[end index (int)] => specified stream and vector [start:end]
- [label (string)]=1,2,3,4,5 => vector [1,2,3,4,4]
- [label (string)]=0 => specified stream and full vector
Parameters
----------
recipe : str
Feature recipe
Returns
-------
data : dict
Feature recipe structure
"""
if isinstance(recipe, six.string_types):
data = []
labels = recipe.split(self.delimiters['block'])
for label in labels:
label = label.strip()
if label:
detail_parts = label.split(self.delimiters['detail'])
label = detail_parts[0].strip()
# Default values, used when only extractor is defined e.g. [extractor (string)]; [extractor (string)]
vector_index_structure = {
'stream': self.default_stream,
'selection': False,
'full': True,
}
# Inspect recipe further
if len(detail_parts) == 2:
main_index_parts = detail_parts[1].split(
self.delimiters['dimension'])
vector_indexing_string = detail_parts[1]
if len(main_index_parts) > 1:
# Channel has been defined,
# e.g. [extractor (string)]=[channel (int)]:[start index (int)]-[end index (int)]
vector_index_structure['stream'] = int(
main_index_parts[0])
vector_indexing_string = main_index_parts[1]
vector_indexing = vector_indexing_string.split(
self.delimiters['segment'])
if len(vector_indexing) > 1:
vector_index_structure['start'] = int(
vector_indexing[0].strip())
vector_index_structure['stop'] = int(
vector_indexing[1].strip()) + 1
vector_index_structure['full'] = False
vector_index_structure['selection'] = False
else:
vector_indexing = vector_indexing_string.split(
self.delimiters['vector'])
if len(vector_indexing) > 1:
a = list(map(int, vector_indexing))
vector_index_structure['full'] = False
vector_index_structure['selection'] = True
vector_index_structure['vector'] = a
else:
vector_index_structure['stream'] = int(
vector_indexing[0])
vector_index_structure['full'] = True
vector_index_structure['selection'] = False
current_data = {
'label': label,
'vector-index': vector_index_structure,
}
else:
current_data = {
'label': label,
}
data.append(current_data)
from dcase_util.containers import ListDictContainer
return ListDictContainer(data)
else:
return recipe
def prepare(self):
"""Prepare dataset for the usage.
Returns
-------
self
"""
if not self.meta_container.exists():
scene_label = 'home'
evaluation_chunks = ListDictContainer(
filename=os.path.join(self.local_path, 'chime_home',
'evaluation_chunks_refined.csv')).load(
fields=['id', 'filename', 'set_id'])
audio_files = {}
for item in dcase_cross_val_data:
audio_filename = os.path.join(
'chime_home', 'chunks',
item['filename'] + self.sample_mode + '.wav')
annotation_filename = os.path.join('chime_home', 'chunks',
item['filename'] + '.csv')
if audio_filename not in audio_files:
audio_files[audio_filename] = {
'audio': audio_filename,
'meta': annotation_filename
}
meta_data = MetaDataContainer()
for audio_filename, data in iteritems(audio_files):
current_meta_data = DictContainer(filename=os.path.join(
self.local_path, data['meta'])).load()
tags = []
for i, tag in enumerate(current_meta_data['majorityvote']):
if tag != 'S' and tag != 'U':
tags.append(self.tagcode_to_taglabel(tag))
name = os.path.split(audio_filename)[1]
segment_name = name[0:name.find('_chunk')]
chunk_name = name[name.find('_chunk') + 1:].split('.')[0]
item = MetaDataItem({
'filename': audio_filename,
'scene_label': scene_label,
'tags': ';'.join(tags) + ';',
'identifier': segment_name
})
self.process_meta_item(item=item, absolute_path=False)
meta_data.append(item)
# Save meta
meta_data.save(filename=self.meta_file)
# Load meta and cross validation
self.load()
all_folds_found = True
train_filename = self.evaluation_setup_filename(setup_part='train')
test_filename = self.evaluation_setup_filename(setup_part='test')
eval_filename = self.evaluation_setup_filename(setup_part='evaluate')
if not os.path.isfile(train_filename):
all_folds_found = False
if not os.path.isfile(test_filename):
all_folds_found = False
if not os.path.isfile(eval_filename):
all_folds_found = False
if not all_folds_found:
Path().makedirs(path=self.evaluation_setup_path)
# Train
train_filename = self.evaluation_setup_filename(setup_part='train')
train_meta = MetaDataContainer(filename=train_filename)
for filename in self.train_files():
train_meta.append(self.file_meta(filename)[0])
train_meta.save()
# Test
test_filename = self.evaluation_setup_filename(setup_part='test')
test_meta = MetaDataContainer(filename=test_filename)
for filename in self.test_files():
test_meta.append(
MetaDataItem(
{'filename':
self.absolute_to_relative_path(filename)}))
test_meta.save()
# Evaluate
eval_filename = self.evaluation_setup_filename(
setup_part='evaluate')
eval_meta = MetaDataContainer(filename=eval_filename)
for filename in self.test_files():
eval_meta.append(self.file_meta(filename)[0])
eval_meta.save()
# Load meta and cross validation
self.load()
return self
def prepare(self):
"""Prepare dataset for the usage.
Returns
-------
self
"""
if not self.meta_container.exists():
scene_label = 'home'
dcase_cross_val_data = ListDictContainer(filename=os.path.join(
self.local_path, 'chime_home',
'development_chunks_refined_crossval_dcase2016.csv')).load(
fields=['id', 'filename', 'set_id'])
audio_files = {}
for item in dcase_cross_val_data:
audio_filename = os.path.join(
'chime_home', 'chunks',
item['filename'] + self.sample_mode + '.wav')
annotation_filename = os.path.join('chime_home', 'chunks',
item['filename'] + '.csv')
if audio_filename not in audio_files:
audio_files[audio_filename] = {
'audio': audio_filename,
'meta': annotation_filename
}
meta_data = MetaDataContainer()
for audio_filename, data in iteritems(audio_files):
current_meta_data = DictContainer(filename=os.path.join(
self.local_path, data['meta'])).load()
tags = []
for i, tag in enumerate(current_meta_data['majorityvote']):
if tag != 'S' and tag != 'U':
tags.append(self.tagcode_to_taglabel(tag))
name = os.path.split(audio_filename)[1]
segment_name = name[0:name.find('_chunk')]
chunk_name = name[name.find('_chunk') + 1:].split('.')[0]
item = MetaDataItem({
'filename': audio_filename,
'scene_label': scene_label,
'tags': ';'.join(tags) + ';',
'identifier': segment_name
})
self.process_meta_item(item=item, absolute_path=False)
meta_data.append(item)
# Save meta
meta_data.save(filename=self.meta_file)
# Load meta and cross validation
self.load()
all_folds_found = True
for fold in range(1, self.crossvalidation_folds + 1):
train_filename = self.evaluation_setup_filename(setup_part='train',
fold=fold)
test_filename = self.evaluation_setup_filename(setup_part='test',
fold=fold)
eval_filename = self.evaluation_setup_filename(
setup_part='evaluate', fold=fold)
if not os.path.isfile(train_filename):
all_folds_found = False
if not os.path.isfile(test_filename):
all_folds_found = False
if not os.path.isfile(eval_filename):
all_folds_found = False
if not all_folds_found:
Path().makedirs(path=self.evaluation_setup_path)
dcase_crossval = {
1: [],
2: [],
3: [],
4: [],
5: [],
}
dcase_cross_val_data = ListDictContainer(filename=os.path.join(
self.local_path, 'chime_home',
'development_chunks_refined_crossval_dcase2016.csv')).load(
fields=['id', 'filename', 'set_id'])
for item in dcase_cross_val_data:
dcase_crossval[int(item['set_id']) + 1].append(
self.relative_to_absolute_path(
os.path.join(
'chime_home', 'chunks',
item['filename'] + self.sample_mode + '.wav')))
for fold in range(1, self.crossvalidation_folds + 1):
# Collect training and testing files
train_files = []
for f in range(1, self.crossvalidation_folds + 1):
if f is not fold:
train_files += dcase_crossval[f]
test_files = dcase_crossval[fold]
# Create meta containers and save them
# Train
train_filename = self.evaluation_setup_filename(
setup_part='train', fold=fold)
train_meta = MetaDataContainer(filename=train_filename)
for filename in train_files:
item = self.file_meta(filename)[0]
self.process_meta_item(item=item, absolute_path=False)
train_meta.append(item)
train_meta.save()
# Test
test_filename = self.evaluation_setup_filename(
setup_part='test', fold=fold)
test_meta = MetaDataContainer(filename=test_filename)
for filename in test_files:
item = MetaDataItem(
{'filename': self.absolute_to_relative_path(filename)})
test_meta.append(item)
test_meta.save()
# Evaluate
eval_filename = self.evaluation_setup_filename(
setup_part='evaluate', fold=fold)
eval_meta = MetaDataContainer(filename=eval_filename)
for filename in test_files:
item = self.file_meta(filename)[0]
self.process_meta_item(item=item, absolute_path=False)
eval_meta.append(item)
eval_meta.save()
# Load meta and cross validation
self.load()
return self
def extract_packages(self):
"""Extract the dataset packages
Raises
------
IOError
Local package was not found.
Returns
-------
self
"""
# Make sure evaluation_setup directory exists
Path().makedirs(
path=os.path.join(self.local_path, self.evaluation_setup_folder))
log = FancyLogger()
item_access_log_filename = os.path.join(self.local_path,
'item_access_error.log.csv')
if 'audio' in self.included_content_types or self.included_content_types == [
'all'
]: # mean process audio
log.title("Download_data")
log.info(
"Once database is downloaded, do not forget to check your missing_files"
)
non_existing_videos = pandas.DataFrame(
columns=["filename", "error"])
log.line("check files exist or download data")
# Collect file ids
for package in self.package_list:
if package.get('content_type') == "meta":
base_filepath = os.path.splitext(
package.get('filename').split('/')[-1])[0]
if 'train' in package.get('filename'):
result_audio_directory = os.path.join(
self.local_path, 'dataset/audio/train',
base_filepath)
else:
result_audio_directory = os.path.join(
self.local_path, 'dataset/audio/test')
missing_files = download(package.get('filename'),
result_audio_directory,
n_jobs=3)
if not missing_files.empty:
non_existing_videos = non_existing_videos.append(
missing_files, ignore_index=True)
# Save list of non-accessible videos
ListDictContainer(non_existing_videos.to_dict(orient="records"),
filename=item_access_log_filename).save(
fields=['filename', 'error'])
# Evaluation setup filenames
train_filename_fold1 = self.evaluation_setup_filename(
setup_part='train', fold=1, file_extension='csv')
test_filename_fold1 = self.evaluation_setup_filename(
setup_part='test', fold=1, file_extension='csv')
train_filename_fold2 = self.evaluation_setup_filename(
setup_part='train', fold=2, file_extension='csv')
test_filename_fold2 = self.evaluation_setup_filename(
setup_part='test', fold=2, file_extension='csv')
evaluate_filename = self.evaluation_setup_filename(
setup_part='evaluate', fold=2, file_extension='csv')
# Check that evaluation setup exists
evaluation_setup_exists = True
if not os.path.isfile(train_filename_fold1) or not os.path.isfile(test_filename_fold1) \
or not os.path.isfile(train_filename_fold2) or not os.path.isfile(test_filename_fold2) \
or not os.path.isfile(evaluate_filename) or not self.meta_container.exists():
evaluation_setup_exists = False
if not evaluation_setup_exists:
# Evaluation setup was not found, generate one
item_access_log_filename = os.path.join(
self.local_path, 'item_access_error.log.csv')
non_existing_videos = ListDictContainer().load(
filename=item_access_log_filename,
delimiter=',').get_field_unique('filename')
train_meta_weak_fold1 = MetaDataContainer()
audio_path = 'dataset/audio/train/weak'
for item in MetaDataContainer().load(os.path.join(
self.local_path, 'dataset/metadata/train/'
'weak.csv'),
fields=["filename", "tags"],
csv_header=True):
if item.filename not in non_existing_videos:
if not item.filename.endswith(
self.default_audio_extension):
item.filename = os.path.join(
audio_path,
os.path.splitext(item.filename)[0] + '.' +
self.default_audio_extension)
else:
item.filename = Path(path=item.filename).modify(
path_base=audio_path)
# Only collect items which exists if audio present
if 'audio' in self.included_content_types or 'all' in self.included_content_types:
if os.path.isfile(
os.path.join(self.local_path, item.filename)):
train_meta_weak_fold1.append(item)
else:
train_meta_weak_fold1.append(item)
train_meta_weak_fold1.save(filename=train_filename_fold1,
csv_header=True,
file_format="CSV")
test_meta_unlabel_fold1 = MetaDataContainer()
audio_path = 'dataset/audio/train/unlabel_in_domain'
for item in MetaDataContainer().load(os.path.join(
self.local_path, 'dataset/metadata/train/'
'unlabel_in_domain.csv'),
csv_header=True):
if item.filename not in non_existing_videos:
# If not the right extension, change it
if not item.filename.endswith(
self.default_audio_extension):
item.filename = os.path.join(
audio_path,
os.path.splitext(item.filename)[0] + '.' +
self.default_audio_extension)
else:
item.filename = Path(path=item.filename).modify(
path_base=audio_path)
# Only collect items which exists if audio present
if 'audio' in self.included_content_types or 'all' in self.included_content_types:
if os.path.isfile(
os.path.join(self.local_path, item.filename)):
test_meta_unlabel_fold1.append(item)
else:
test_meta_unlabel_fold1.append(item)
test_meta_unlabel_fold1.save(filename=test_filename_fold1,
csv_header=True,
file_format="CSV")
# Fold 2 train is all the data used in fold 1
train_meta_weak_fold2 = MetaDataContainer()
train_meta_weak_fold2 += MetaDataContainer().load(
train_filename_fold1, csv_header=True, file_format="CSV")
for item in MetaDataContainer().load(test_filename_fold1,
csv_header=True,
file_format="CSV"):
item.tags = []
train_meta_weak_fold2.append(item)
train_meta_weak_fold2.save(filename=train_filename_fold2,
csv_header=True)
# Evaluate meta is the groundtruth file with test annotations test.csv
evaluate_meta = MetaDataContainer()
audio_path = 'dataset/audio/test'
for item in MetaDataContainer().load(os.path.join(
self.local_path, 'dataset/metadata/test/test.csv'),
csv_header=True):
if item.filename not in non_existing_videos:
if not item.filename.endswith(
self.default_audio_extension):
item.filename = os.path.join(
audio_path,
os.path.splitext(item.filename)[0] + '.' +
self.default_audio_extension)
else:
item.filename = Path(path=item.filename).modify(
path_base=audio_path)
# Only collect items which exists
if 'audio' in self.included_content_types or 'all' in self.included_content_types:
if os.path.isfile(
os.path.join(self.local_path, item.filename)):
evaluate_meta.append(item)
else:
evaluate_meta.append(item)
evaluate_meta.save(filename=evaluate_filename,
csv_header=True,
file_format="CSV")
# Test meta is filenames of evaluation, labels will be predicted
test_meta_strong_fold2 = MetaDataContainer()
for filename in evaluate_meta.unique_files:
test_meta_strong_fold2.append(
MetaDataItem({'filename': filename}))
test_meta_strong_fold2.save(filename=test_filename_fold2,
csv_header=True,
file_format="CSV")
# meta_data is the default meta container containing all files of the dataset
meta_data = MetaDataContainer()
meta_data += MetaDataContainer().load(train_filename_fold1,
csv_header=True,
file_format="CSV")
meta_data += MetaDataContainer().load(test_filename_fold1,
csv_header=True,
file_format="CSV")
meta_data += MetaDataContainer().load(test_filename_fold2,
csv_header=True,
file_format="CSV")
# Save meta
meta_data.save(filename=self.meta_file)
log.foot()
return self
def prepare(self):
"""Prepare dataset for the usage.
Returns
-------
self
"""
if is_jupyter():
from tqdm import tqdm_notebook as tqdm
else:
from tqdm import tqdm
# Make sure audio directory exists
Path().makedirs(path=os.path.join(self.local_path, 'audio'))
# Make sure evaluation_setup directory exists
Path().makedirs(
path=os.path.join(self.local_path, self.evaluation_setup_folder))
if 'audio' in self.included_content_types:
# Collect file ids
files = []
files += ListDictContainer(filename=os.path.join(
self.local_path, 'testing_set.csv')).load(
fields=['query_id', 'segment_start', 'segment_end'])
files += ListDictContainer(filename=os.path.join(
self.local_path, 'training_set.csv')).load(
fields=['query_id', 'segment_start', 'segment_end'])
file_progress = tqdm(files,
desc="{0: <25s}".format('Files'),
file=sys.stdout,
leave=False,
disable=self.disable_progress_bar,
ascii=self.use_ascii_progress_bar)
non_existing_videos = {}
# Load list of already identified non-accessible videos
item_access_log_filename = os.path.join(
self.local_path, 'item_access_error.log.csv')
if os.path.isfile(item_access_log_filename):
for item in ListDictContainer(
filename=item_access_log_filename).load(
fields=['query_id', 'error']):
non_existing_videos[item['query_id']] = item
# Check that audio files exists
for file_data in file_progress:
audio_filename = os.path.join(
self.local_path, 'audio',
'Y{query_id}_{segment_start}_{segment_end}.{extension}'.
format(query_id=file_data['query_id'],
segment_start=file_data['segment_start'],
segment_end=file_data['segment_end'],
extension=self.default_audio_extension))
# Download segment if it does not exists
if not os.path.isfile(audio_filename) and file_data[
'query_id'] not in non_existing_videos:
try:
AudioContainer().load_from_youtube(
query_id=file_data['query_id'],
start=file_data['segment_start'],
stop=file_data['segment_end']).save(
filename=audio_filename)
except IOError as e:
non_existing_videos[file_data['query_id']] = {
'error': str(e.message).replace('\n', ' '),
'query_id': file_data['query_id']
}
# Save list of non-accessible videos
ListDictContainer(list(non_existing_videos.values()),
filename=item_access_log_filename).save(
fields=['query_id', 'error'])
# Evaluation setup filenames
train_filename = self.evaluation_setup_filename(setup_part='train',
fold=1,
scene_label='youtube',
file_extension='txt')
test_filename = self.evaluation_setup_filename(setup_part='test',
fold=1,
scene_label='youtube',
file_extension='txt')
evaluate_filename = self.evaluation_setup_filename(
setup_part='evaluate',
fold=1,
scene_label='youtube',
file_extension='txt')
# Check that evaluation setup exists
evaluation_setup_exists = True
if not os.path.isfile(train_filename) or not os.path.isfile(
test_filename) or not os.path.isfile(evaluate_filename):
evaluation_setup_exists = False
if not evaluation_setup_exists:
# Evaluation setup was not found, generate one
fold = 1
train_meta = MetaDataContainer()
for item in MetaDataContainer().load(
os.path.join(self.local_path,
'groundtruth_weak_label_training_set.csv')):
if not item.filename.endswith(self.default_audio_extension):
item.filename = os.path.join(
'audio', 'Y' + os.path.splitext(item.filename)[0] +
'.' + self.default_audio_extension)
# Set scene label
item.scene_label = 'youtube'
# Translate event onset and offset, weak labels
item.offset -= item.onset
item.onset -= item.onset
# Only collect items which exists if audio present
if 'audio' in self.included_content_types:
if os.path.isfile(
os.path.join(self.local_path, item.filename)):
train_meta.append(item)
else:
train_meta.append(item)
train_meta.save(
filename=self.evaluation_setup_filename(setup_part='train',
fold=fold,
scene_label='youtube',
file_extension='txt'))
evaluate_meta = MetaDataContainer()
for item in MetaDataContainer().load(
os.path.join(self.local_path,
'groundtruth_strong_label_testing_set.csv')):
if not item.filename.endswith(self.default_audio_extension):
item.filename = os.path.join(
'audio', 'Y' + os.path.splitext(item.filename)[0] +
'.' + self.default_audio_extension)
# Set scene label
item.scene_label = 'youtube'
# Only collect items which exists
if 'audio' in self.included_content_types:
if os.path.isfile(
os.path.join(self.local_path, item.filename)):
evaluate_meta.append(item)
else:
evaluate_meta.append(item)
evaluate_meta.save(
filename=self.evaluation_setup_filename(setup_part='evaluate',
fold=fold,
scene_label='youtube',
file_extension='txt'))
test_meta = MetaDataContainer()
for item in evaluate_meta:
test_meta.append(MetaDataItem({'filename': item.filename}))
test_meta.save(
filename=self.evaluation_setup_filename(setup_part='test',
fold=fold,
scene_label='youtube',
file_extension='txt'))
# Load meta and cross validation
self.load()
if not self.meta_container.exists():
fold = 1
meta_data = MetaDataContainer()
meta_data += MetaDataContainer().load(
self.evaluation_setup_filename(setup_part='train',
fold=fold,
scene_label='youtube',
file_extension='txt'))
meta_data += MetaDataContainer().load(
self.evaluation_setup_filename(setup_part='evaluate',
fold=fold,
scene_label='youtube',
file_extension='txt'))
# Save meta
meta_data.save(filename=self.meta_file)
# Load meta and cross validation
self.load()
return self
def test_load_wrong_type():
with dcase_util.utils.DisableLogger():
ListDictContainer().load(
filename=os.path.join(tempfile.gettempdir(), 'wrong.cpickle'))
def test_load_not_found2():
with dcase_util.utils.DisableLogger():
ListDictContainer().load(
filename=os.path.join(tempfile.gettempdir(), 'wrong.txt'))