def get_feature_timbre_ssd(wav_dir):
audiofile = wav_dir
samplerate, samplewidth, wavedata = audiofile_read(audiofile)
nsamples = wavedata.shape[0]
nchannels = wavedata.shape[1]
print "Successfully read audio file:", audiofile
print samplerate, "Hz,", samplewidth * 8, "bit,", nchannels, "channel(s),", nsamples, "samples"
features = rp_extract(wavedata, # the two-channel wave-data of the audio-file
samplerate=11025, # the samplerate of the audio-file
extract_ssd=True, # <== extract this feature!
transform_db=True, # apply psycho-accoustic transformation
transform_phon=True, # apply psycho-accoustic transformation
transform_sone=True, # apply psycho-accoustic transformation
fluctuation_strength_weighting=True, # apply psycho-accoustic transformation
skip_leadin_fadeout=1, # skip lead-in/fade-out. value = number of segments skipped
step_width=1) #
# plotssd(features['ssd'])
print len(features['ssd'])
return features
def extract_all_files(filelist,
path,
out_file=None,
feature_types=['rp', 'ssd', 'rh'],
label=False,
append=False,
no_extension_check=False,
force_resampling=None,
out_HDF5=False,
log_AudioTypes=True,
log_Errors=True,
verbose=True):
"""
finds all files of a certain type (e.g. .wav and/or .mp3) in a path and all sub-directories in it
extracts selected RP feature types
and saves them into separate CSV feature files (one per feature type)
# filelist: list of files for features to be extracted
# path: absolute path that will be added at beginning of filelist (can be '')
# out_file: output file name stub for feature files to write (if omitted, features will be returned from function)
# feature_types: RP feature types to extract. see rp_extract.py
# label: use subdirectory name as class label
# no_extension_check: does not check file format via extension. means that decoder is called on ALL files.
# force_resampling: force a target sampling rate (provided in Hz) when decoding (works with FFMPEG only!)
# out_HDF5: whether to store as HDF5 file format (otherwise CSV)
"""
ext = feature_types
n = 0 # counting the files being processed
n_extracted = 0 # counting the files that were actually analyzed
err = 0 # counting errors
n_files = len(filelist)
# initialize filelist_extracted and dict containing all accumulated feature arrays
filelist_extracted = []
feat_array = {}
audio_logwriter = None
error_logwriter = None
audio_logwriter_wrote_header = False
start_time = time.time()
if out_file: # only if out_file is specified
if log_AudioTypes:
log_filename = out_file + '.audiotypes.log'
audio_logfile = open(log_filename,
'w') # TODO allow append mode 'a'
audio_logwriter = unicsv.UnicodeCSVWriter(
audio_logfile) #, quoting=csv.QUOTE_ALL)
if log_Errors:
err_log_filename = out_file + '.errors.log'
error_logfile = open(err_log_filename,
'w') # TODO allow append mode 'a'
error_logwriter = unicsv.UnicodeCSVWriter(
error_logfile) #, quoting=csv.QUOTE_ALL)
if out_HDF5:
FeatureWriter = HDF5FeatureWriter()
else:
FeatureWriter = CSVFeatureWriter()
FeatureWriter.open(out_file, ext, append=append)
for fil in filelist: # iterate over all files
try:
if n > 0:
elaps_time = time.time() - start_time
remain_time = elaps_time * n_files / n - elaps_time # n is the number of files done here
else:
remain_time = None
n += 1
if path:
filename = path + os.sep + fil
else:
filename = fil
if verbose:
print '#', n, '/', n_files, '(ETA: ' + timestr(
remain_time) + "):", filename
# read audio file (wav or mp3)
samplerate, samplewidth, data, decoder = audiofile_read(
filename,
verbose=verbose,
include_decoder=True,
no_extension_check=no_extension_check,
force_resampling=force_resampling)
# audio file info
if verbose:
print samplerate, "Hz,", data.shape[
1], "channel(s),", data.shape[0], "samples"
# extract features
# Note: the True/False flags are determined by checking if a feature is listed in 'ext' (see settings above)
feat = rp.rp_extract(
data,
samplerate,
extract_rp=('rp' in ext), # extract Rhythm Patterns features
extract_ssd=(
'ssd' in ext), # extract Statistical Spectrum Descriptor
extract_tssd=(
'tssd' in ext
), # extract temporal Statistical Spectrum Descriptor
extract_rh=('rh' in ext), # extract Rhythm Histogram features
extract_trh=(
'trh'
in ext), # extract temporal Rhythm Histogram features
extract_mvd=(
'mvd' in ext
), # extract Modulation Frequency Variance Descriptor
spectral_masking=True,
transform_db=True,
transform_phon=True,
transform_sone=True,
fluctuation_strength_weighting=True,
skip_leadin_fadeout=1,
step_width=1,
verbose=verbose)
# TODO check if ext and feat.keys are consistent
# WHAT TO USE AS ID (based on filename): 3 choices:
id = fil # rel. filename as from find_files
# id = filename # full filename incl. full path
# id = filename[len(path)+1:] # relative filename only (extracted from path)
if out_file:
# WRITE each feature set to a CSV or HDF5 file
id2 = None
if label:
id2 = id.replace("\\", "/").split("/")[-2].strip()
if out_HDF5 and n_extracted == 0:
# for HDF5 we need to know the vector dimension
# thats why we cannot open the file earlier
FeatureWriter.open(
out_file, ext, feat, append=append
) # append not working for now but possibly in future
FeatureWriter.write_features(id, feat, id2)
else:
# IN MEMORY: add the extracted features for 1 file to the array dict accumulating all files
# TODO: only if we don't have out_file? maybe we want this as a general option
if feat_array == {}: # for first file, initialize empty array with dimension of the feature set
for e in feat.keys():
feat_array[e] = np.empty((0, feat[e].shape[0]))
# store features in array
for e in feat.keys():
feat_array[e] = np.append(
feat_array[e], feat[e].reshape(1, -1), axis=0
) # 1 for horizontal vector, -1 means take original dimension
filelist_extracted.append(id)
n_extracted += 1
# write list of analyzed audio files alongsize audio metadata (kHz, bit, etc.)
if audio_logwriter:
if not audio_logwriter_wrote_header: # write CSV header
log_info = [
"filename", "decoder", "samplerate (kHz)",
"samplewidth (bit)", "n channels", "n samples"
]
audio_logwriter.writerow(log_info)
audio_logwriter_wrote_header = True
log_info = [
filename, decoder, samplerate, samplewidth * 8,
data.shape[1], data.shape[0]
]
audio_logwriter.writerow(log_info)
gc.collect(
) # after every file we do garbage collection, otherwise our memory is used up quickly for some reason
except Exception as e:
print "ERROR analysing file: " + fil + ": " + str(e)
err += 1
if error_logwriter:
error_logwriter.writerow([fil, str(e)])
try:
if out_file: # close all output files
FeatureWriter.close()
if audio_logwriter:
audio_logfile.close()
if error_logwriter:
error_logfile.close()
except Exception as e:
print "ERROR closing the output or log files: " + str(e)
end_time = time.time()
if verbose:
print "FEATURE EXTRACTION FINISHED.", n, "file(s) processed,", n_extracted, "successful. Duration:", timestr(
end_time - start_time)
if err > 0:
print err, "file(s) had ERRORs during feature extraction.",
if log_Errors:
print "See", err_log_filename
else:
print
if out_file:
opt_ext = '.h5' if out_HDF5 else ''
print "Feature file(s):", out_file + "." + str(ext) + opt_ext
if out_file is None:
return filelist_extracted, feat_array
def extract_all_files_in_path(path,out_file,feature_types,audiofile_types=('.wav','.mp3')):
ext = feature_types
# get file list of all files in a path (filtered by audiofile_types)
filelist = find_files(path,audiofile_types,relative_path=True)
n = 0 # counting the files that were actually analyzed
err = 0 # counting errors
n_files = len(filelist)
start_abs = time.time()
files, writer = initialize_feature_files(out_file,ext)
for fil in filelist: # iterate over all files
try:
n += 1
filename = path + os.sep + fil
print '#',n,'/',n_files,':', filename
start = time.time()
# read audio file (wav or mp3)
samplerate, samplewidth, data = audiofile_read(filename)
end = time.time()
print end - start, "sec"
# audio file info
print samplerate, "Hz,", data.shape[1], "channels,", data.shape[0], "samples"
# extract features
# Note: the True/False flags are determined by checking if a feature is listed in 'ext' (see settings above)
start = time.time()
feat = rp.rp_extract(data,
samplerate,
extract_rp = ('rp' in ext), # extract Rhythm Patterns features
extract_ssd = ('ssd' in ext), # extract Statistical Spectrum Descriptor
extract_sh = ('sh' in ext), # extract Statistical Histograms
extract_tssd = ('tssd' in ext), # extract temporal Statistical Spectrum Descriptor
extract_rh = ('rh' in ext), # extract Rhythm Histogram features
extract_trh = ('trh' in ext), # extract temporal Rhythm Histogram features
extract_mvd = ('mvd' in ext), # extract Modulation Frequency Variance Descriptor
spectral_masking=True,
transform_db=True,
transform_phon=True,
transform_sone=True,
fluctuation_strength_weighting=True,
skip_leadin_fadeout=1,
step_width=1)
end = time.time()
print "Features extracted:", feat.keys(), end - start, "sec"
# WRITE each feature set to a CSV
# TODO check if ext and feat.keys are consistent
start = time.time()
# add filename before vector. 3 choices:
id = fil # filename only
# id = filename # full filename incl. full path
# id = filename[len(path)+1:] # relative filename only
write_feature_files(id,feat,writer)
end = time.time()
print "Data written." #, end-start
except:
print "ERROR analysing file: " + fil
err += 1
# close all output files
close_feature_files(files,ext)
end = time.time()
print "FEATURE EXTRACTION FINISHED.", n, "files,", end-start_abs, "sec"
if err > 0:
print err, "files had ERRORs during feature extraction."
def extract_all_files(filelist, path, out_file=None, feature_types=["rp", "ssd", "rh"], verbose=True):
"""
finds all files of a certain type (e.g. .wav and/or .mp3) in a path and all sub-directories in it
extracts selected RP feature types
and saves them into separate CSV feature files (one per feature type)
# filelist: list of files for features to be extracted
# path: absolute path that will be added at beginning of filelist (can be '')
# out_file: output file name stub for feature files to write (if omitted, features will be returned from function)
# feature_types: RP feature types to extract. see rp_extract.py
# audiofile_types: a string or tuple of suffixes to look for file extensions to consider (include the .)
"""
ext = feature_types
n = 0 # counting the files that were actually analyzed
err = 0 # counting errors
n_files = len(filelist)
# initialize filelist_extracted and dict containing all accumulated feature arrays
filelist_extracted = []
feat_array = {}
start_abs = time.time()
if out_file: # only if out_file is specified
files, writer = initialize_feature_files(out_file, ext)
for fil in filelist: # iterate over all files
try:
n += 1
if path:
filename = path + os.sep + fil
else:
filename = fil
# if verbose:
print "#", n, "/", n_files, ":", filename
# read audio file (wav or mp3)
samplerate, samplewidth, data = audiofile_read(filename)
# audio file info
if verbose:
print samplerate, "Hz,", data.shape[1], "channel(s),", data.shape[0], "samples"
# extract features
# Note: the True/False flags are determined by checking if a feature is listed in 'ext' (see settings above)
feat = rp.rp_extract(
data,
samplerate,
extract_rp=("rp" in ext), # extract Rhythm Patterns features
extract_ssd=("ssd" in ext), # extract Statistical Spectrum Descriptor
extract_sh=("sh" in ext), # extract Statistical Histograms
extract_tssd=("tssd" in ext), # extract temporal Statistical Spectrum Descriptor
extract_rh=("rh" in ext), # extract Rhythm Histogram features
extract_trh=("trh" in ext), # extract temporal Rhythm Histogram features
extract_mvd=("mvd" in ext), # extract Modulation Frequency Variance Descriptor
spectral_masking=True,
transform_db=True,
transform_phon=True,
transform_sone=True,
fluctuation_strength_weighting=True,
skip_leadin_fadeout=1,
step_width=1,
verbose=verbose,
)
# TODO check if ext and feat.keys are consistent
# WHAT TO USE AS ID (based on filename): 3 choices:
id = fil # rel. filename as from find_files
# id = filename # full filename incl. full path
# id = filename[len(path)+1:] # relative filename only (extracted from path)
if out_file:
# WRITE each feature set to a CSV
write_feature_files(id, feat, writer)
else:
# IN MEMORY: add the extracted features for 1 file to the array dict accumulating all files
# TODO: only if we dont have out_file? maybe we want this as a general option
if feat_array == {}: # for first file, initialize empty array with dimension of the feature set
for e in feat.keys():
feat_array[e] = np.empty((0, feat[e].shape[0]))
# store features in array
for e in feat.keys():
feat_array[e] = np.append(
feat_array[e], feat[e].reshape(1, -1), axis=0
) # 1 for horizontal vector, -1 means take original dimension
filelist_extracted.append(id)
except Exception as e:
print "ERROR analysing file: " + fil + ": " + str(e)
err += 1
if out_file: # close all output files
close_feature_files(files, ext)
end = time.time()
if verbose:
print "FEATURE EXTRACTION FINISHED. %d file(s), %.2f sec" % (n, end - start_abs)
if err > 0:
print err, "files had ERRORs during feature extraction."
if out_file:
print "Feature file(s):", out_file + ".*", ext
if out_file is None:
return filelist_extracted, feat_array
def extract_all_files(filelist,
path,
out_file=None,
feature_types=['rp', 'ssd', 'rh'],
verbose=True):
"""
finds all files of a certain type (e.g. .wav and/or .mp3) in a path and all sub-directories in it
extracts selected RP feature types
and saves them into separate CSV feature files (one per feature type)
# filelist: list of files for features to be extracted
# path: absolute path that will be added at beginning of filelist (can be '')
# out_file: output file name stub for feature files to write (if omitted, features will be returned from function)
# feature_types: RP feature types to extract. see rp_extract.py
# audiofile_types: a string or tuple of suffixes to look for file extensions to consider (include the .)
"""
ext = feature_types
n = 0 # counting the files that were actually analyzed
err = 0 # counting errors
n_files = len(filelist)
# initialize filelist_extracted and dict containing all accumulated feature arrays
filelist_extracted = []
feat_array = {}
start_abs = time.time()
if out_file: # only if out_file is specified
files, writer = initialize_feature_files(out_file, ext)
for fil in filelist: # iterate over all files
try:
n += 1
if path:
filename = path + os.sep + fil
else:
filename = fil
#if verbose:
print '#', n, '/', n_files, ':', filename
# read audio file (wav or mp3)
samplerate, samplewidth, data = audiofile_read(filename)
# audio file info
if verbose:
print samplerate, "Hz,", data.shape[
1], "channel(s),", data.shape[0], "samples"
# extract features
# Note: the True/False flags are determined by checking if a feature is listed in 'ext' (see settings above)
feat = rp.rp_extract(
data,
samplerate,
extract_rp=('rp' in ext), # extract Rhythm Patterns features
extract_ssd=(
'ssd' in ext), # extract Statistical Spectrum Descriptor
extract_sh=('sh' in ext), # extract Statistical Histograms
extract_tssd=(
'tssd' in ext
), # extract temporal Statistical Spectrum Descriptor
extract_rh=('rh' in ext), # extract Rhythm Histogram features
extract_trh=(
'trh'
in ext), # extract temporal Rhythm Histogram features
extract_mvd=(
'mvd' in ext
), # extract Modulation Frequency Variance Descriptor
spectral_masking=True,
transform_db=True,
transform_phon=True,
transform_sone=True,
fluctuation_strength_weighting=True,
skip_leadin_fadeout=1,
step_width=1,
verbose=verbose)
# TODO check if ext and feat.keys are consistent
# WHAT TO USE AS ID (based on filename): 3 choices:
id = fil # rel. filename as from find_files
# id = filename # full filename incl. full path
# id = filename[len(path)+1:] # relative filename only (extracted from path)
if out_file:
# WRITE each feature set to a CSV
write_feature_files(id, feat, writer)
else:
# IN MEMORY: add the extracted features for 1 file to the array dict accumulating all files
# TODO: only if we dont have out_file? maybe we want this as a general option
if feat_array == {}: # for first file, initialize empty array with dimension of the feature set
for e in feat.keys():
feat_array[e] = np.empty((0, feat[e].shape[0]))
# store features in array
for e in feat.keys():
feat_array[e] = np.append(
feat_array[e], feat[e].reshape(1, -1), axis=0
) # 1 for horizontal vector, -1 means take original dimension
filelist_extracted.append(id)
except Exception as e:
print "ERROR analysing file: " + fil + ": " + str(e)
err += 1
if out_file: # close all output files
close_feature_files(files, ext)
end = time.time()
if verbose:
print "FEATURE EXTRACTION FINISHED. %d file(s), %.2f sec" % (n, end -
start_abs)
if err > 0:
print err, "files had ERRORs during feature extraction."
if out_file: print "Feature file(s):", out_file + ".*", ext
if out_file is None:
return filelist_extracted, feat_array
def get_similar_for_soundcloud_track(self, sc_track_id):
extracted_features = None
tmp_path = tempfile.mktemp(prefix="soundcloud.", suffix=".mp3")
try:
# occasionally, a track has been removed and the stream is no longer available, so we have to catch a 404 error
try:
stream = self.client.get('/tracks/%d/streams' % sc_track_id)
if not hasattr(stream, 'http_mp3_128_url'):
raise Exception("No download URL available!")
mp3_download_url = stream.http_mp3_128_url
urllib.urlretrieve(mp3_download_url, tmp_path)
#tmp_path = "c:/users/schind~1/appdata/local/temp/soundcloud.hziisf.mp3"
(samplerate, samplewidth, wavedata) = ar.mp3_read(tmp_path)
print wavedata.shape, samplerate, tmp_path
extracted_features = rp_extract(
wavedata, # the two-channel wave-data of the audio-file
samplerate, # the samplerate of the audio-file
extract_rp=True, # <== extract this feature!
extract_ssd=True,
extract_tssd=False,
transform_db=True, # apply psycho-accoustic transformation
transform_phon=True, # apply psycho-accoustic transformation
transform_sone=True, # apply psycho-accoustic transformation
fluctuation_strength_weighting=
True, # apply psycho-accoustic transformation
skip_leadin_fadeout=
1, # skip lead-in/fade-out. value = number of segments skipped
step_width=1) #
chroma, mfcc, rmse, spectral_centroid, spectral_bandwidth, spectral_contrast, spectral_rolloff, \
tonnetz, zero_crossing_rate, bpm = self.extract_librosa_features(wavedata, samplerate)
print bpm
sims, nn = self.calc_similar_items(
extracted_features["ssd"], extracted_features["rp"],
chroma, mfcc, rmse, spectral_centroid, spectral_bandwidth,
spectral_contrast, spectral_rolloff, tonnetz,
zero_crossing_rate, bpm)
except HTTPError as e:
if e.response.status_code == 404:
print "Track stream not found (404)! Skipping track."
else:
raise e
except Exception as e:
raise e
finally:
if os.path.exists(tmp_path):
os.remove(tmp_path)
return sims, nn
return True
### MAIN
for filename in os.listdir(filepath):
if not filename.endswith(".mp3"):
continue
else:
allData = {}
samplerate, samplewidth, wavedata = audiofile_read.audiofile_read(filepath + filename)
### extract rp data
RP_EXT_N = 6 # 6 -- since the rp_extract works on 6 sec and we want calculation every 1 sec
for i in range(RP_EXT_N):
featTmp = rp_extract.rp_extract(wavedata[samplerate*i:], samplerate, extract_rp=True,return_segment_features=True,skip_leadin_fadeout=0)
save2data('rp_'+str(i), featTmp['rp']) # <--- this is most of the data
featSum = np.sum(featTmp['rp'],1)
if i == 0:
rpSum = np.zeros(len(featSum)*RP_EXT_N)
rpSum[i:len(featSum)*RP_EXT_N:RP_EXT_N] = featSum
itemindex = np.where(rpSum != 0.0)
rpSum = rpSum[itemindex]
save2data('rp_sum', rpSum)
### calculate sc for each N
rhythm_sc = np.zeros((len(SUMMERY_N),len(rpSum)))
for j,sumN in enumerate(SUMMERY_N):
for i in range(len(rpSum)):
if i < sumN or len(rpSum) - i <= sumN:
