def test_audio_to_observations(uiowa_root, onset_root, workspace):
audio_file = os.path.join(
uiowa_root, "theremin.music.uiowa.edu/sound files/MIS/Brass/tuba"
"/Tuba.ff.C3C4.aiff")
assert os.path.exists(audio_file)
index = "uiowa78fae0a0"
onsets_file = os.path.join(onset_root, 'uiowa', "{}.csv".format(index))
assert os.path.exists(onsets_file)
output_dir = os.path.join(workspace, 'notes_tmp')
utils.create_directory(output_dir)
fext = 'flac'
observations = SC.audio_to_observations(
index, audio_file, onsets_file, output_dir, file_ext=fext,
instrument='Tuba', dataset='uiowa')
onset_df = pd.read_csv(onsets_file)
assert len(observations) == len(onset_df)
coll = model.Collection(observations, output_dir)
assert coll.validate(verbose=True)
for obs in coll.values():
obs.instrument == 'Tuba'
assert len(set([obs.index for obs in observations])) == len(observations)
def segment_many(index, audio_files, mode, output_directory,
num_cpus=-1, verbose=0):
"""Segment a collection of audio files.
Parameters
----------
audio_files : array_like
Collection of audio filepaths.
output_directory : str
Path at which outputs will be written.
num_cpus : int, default=-1
Number of CPUs to use for parallel downloads; -1 for all.
verbose : int, default=0
Verbosity level for parallel computation.
Returns
-------
output_paths : list
Filepaths of generated output, or None for failures.
"""
utils.create_directory(output_directory)
pool = Parallel(n_jobs=num_cpus, verbose=verbose)
fx = delayed(segment_one)
return pool(fx(idx, afile, mode, output_directory)
for idx, afile in zip(index, audio_files))
def segment_many(index,
audio_files,
mode,
output_directory,
num_cpus=-1,
verbose=0):
"""Segment a collection of audio files.
Parameters
----------
audio_files : array_like
Collection of audio filepaths.
output_directory : str
Path at which outputs will be written.
num_cpus : int, default=-1
Number of CPUs to use for parallel downloads; -1 for all.
verbose : int, default=0
Verbosity level for parallel computation.
Returns
-------
output_paths : list
Filepaths of generated output, or None for failures.
"""
utils.create_directory(output_directory)
pool = Parallel(n_jobs=num_cpus, verbose=verbose)
fx = delayed(segment_one)
return pool(
fx(idx, afile, mode, output_directory)
for idx, afile in zip(index, audio_files))
def test_audio_collection_to_observations_no_onsets(uiowa_root, workspace):
audio_file = os.path.join(
uiowa_root, "theremin.music.uiowa.edu/sound files/MIS/Brass/tuba"
"/Tuba.ff.C3C4.aiff")
assert os.path.exists(audio_file)
index = "uiowa78fae0a0"
output_dir = os.path.join(workspace, 'notes_tmp')
utils.create_directory(output_dir)
rec = dict(audio_file=audio_file, onsets_file=None,
instrument="Tuba", dataset='uiowa', dynamic='ff')
seg_index = pd.DataFrame.from_records([rec], index=[index])
seg_file = os.path.join(workspace, 'seg_index.csv')
seg_index.to_csv(seg_file)
assert SC.audio_collection_to_observations(
seg_file, 'empty_note_index.csv', output_dir)
def segment_many(index,
audio_files,
mode,
output_directory,
num_cpus=-1,
verbose=0):
"""Segment a collection of audio files.
Parameters
----------
index : array_like
Index values for the audio files; must be unique!
audio_files : array_like
Collection of audio filepaths.
output_directory : str
Path at which outputs will be written.
num_cpus : int, default=-1
Number of CPUs to use for parallel downloads; -1 for all.
verbose : int, default=0
Verbosity level for parallel computation.
Returns
-------
output_paths : list
Filepaths of generated output, or None for failures.
"""
if len(set(index)) < len(index):
raise ValueError("All index values must be unique.")
logger.info("beginning segmenting {} files with mode={}"
"".format(len(index), mode))
utils.create_directory(output_directory)
pool = Parallel(n_jobs=num_cpus, verbose=verbose)
fx = delayed(segment_one)
return pool(
fx(idx, afile, mode, output_directory)
for idx, afile in zip(index, audio_files))
def segment_many(index, audio_files, mode, output_directory,
num_cpus=-1, verbose=0):
"""Segment a collection of audio files.
Parameters
----------
index : array_like
Index values for the audio files; must be unique!
audio_files : array_like
Collection of audio filepaths.
output_directory : str
Path at which outputs will be written.
num_cpus : int, default=-1
Number of CPUs to use for parallel downloads; -1 for all.
verbose : int, default=0
Verbosity level for parallel computation.
Returns
-------
output_paths : list
Filepaths of generated output, or None for failures.
"""
if len(set(index)) < len(index):
raise ValueError("All index values must be unique.")
logger.info("beginning segmenting {} files with mode={}"
"".format(len(index), mode))
utils.create_directory(output_directory)
pool = Parallel(n_jobs=num_cpus, verbose=verbose)
fx = delayed(segment_one)
return pool(fx(idx, afile, mode, output_directory)
for idx, afile in zip(index, audio_files))
def audio_collection_to_observations(segment_index_file, note_index_file,
note_audio_dir, limit_n_files=None,
note_duration=None):
"""
Parameters
----------
segment_index_file : str
Input file containing all pointers to audio files and
onsets files.
note_index_file: str
Path to the output index file which will contain pointers
to the output note audio, and the metadata relating to it.
note_audio_dir : str
Path to store the resulting audio file.
Returns
-------
success : bool
True if the method completed as expected.
"""
logger.info("Begin audio collection segmentation")
logger.debug("Loading segment index")
segment_df = pd.read_csv(segment_index_file, index_col=0)
logger.debug("loaded {} records.".format(len(segment_df)))
if segment_df.empty:
logger.warning(utils.colorize(
"No data available in {}; exiting.".format(segment_index_file),
color='red'))
# Here, we sys.exit 0 so the makefile will continue to build
# other datasets, even if this one
return True
# Drop rows that do not have onsets_files.
segment_df = segment_df.loc[segment_df.onsets_file.dropna().index]
utils.create_directory(note_audio_dir)
count = 0
observations = []
for idx, row in segment_df.iterrows():
if pd.isnull(row.onsets_file):
logger.warning("No onset file for {} [{}]; moving on.".format(
row.audio_file, row.dataset))
continue
observations += audio_to_observations(
idx, row.audio_file, row.onsets_file, note_audio_dir,
file_ext='flac', dataset=row.dataset, instrument=row.instrument,
dynamic=row.dynamic, note_duration=note_duration)
logger.debug("Generated {} observations ({} of {}).".format(
len(observations), (count + 1), len(segment_df)))
if PRINT_PROGRESS:
print("Progress: {:0.1f}% ({} of {})\r".format(
(((count + 1) / float(len(segment_df))) * 100.),
(count + 1), len(segment_df)), end='')
sys.stdout.flush()
count += 1
if limit_n_files and count >= limit_n_files:
break
if PRINT_PROGRESS:
print()
collection = model.Collection(observations)
collection.to_dataframe().to_csv(note_index_file)
logger.debug("Wrote note index to {} with {} records".format(
note_index_file, len(collection)))
logger.info("Completed audio collection segmentation")
return os.path.exists(note_index_file)