def plot_spectrogram(audio_file, loc, t1_sec, t2_sec, geometry=(1, 1, 1)):
fmin = 0
fmax = 1000
frame = 0.0625
window_type = 'hann'
nfft = 0.0853
step = 0.01
channel = 0
chunk = [t1_sec, t2_sec]
graph_spectros = GrapherFactory('SoundPlotter',
title='Spectrograms',
frequency_max=fmax)
sound = Sound(audio_file)
sound.read(channel=channel, chunk=chunk, unit='sec', detrend=True)
# Calculates spectrogram
spectro = Spectrogram(frame,
window_type,
nfft,
step,
sound.waveform_sampling_frequency,
unit='sec')
spectro.compute(sound, dB=True, use_dask=False)
# Crop unused frequencies
spectro.crop(frequency_min=fmin, frequency_max=fmax, inplace=True)
# Plot
graph_spectros.add_data(spectro)
#graph_spectros.add_annotation(loc, panel=0, color='burlywood',label='Detections')
graph_spectros.add_annotation(loc, panel=0, color='peachpuff')
graph_spectros.colormap = 'binary' #'jet'
fig, ax = graph_spectros.show()
if ax.get_geometry() != geometry:
ax.change_geometry(*geometry)
return fig, ax
# for index, row in classes_encoder.iterrows():
# pred_class = [row['label'] if i==row['ID'] else i for i in pred_class]
# # update measuremnets
# data['label_class'] = pred_class
# data['confidence'] = pred_prob
# data_fish = data[data['label_class']=='FS']
# data_noise = data[data['label_class']=='NN']
# classif_fish = copy.deepcopy(measurements)
# classif_fish.data = data_fish
# classif_noise = copy.deepcopy(measurements)
# classif_noise.data = data_noise
# # Plot
graph = GrapherFactory('SoundPlotter', title='Recording', frequency_max=5000)
# graph.add_data(sound)
# #graph.add_annotation(classif_fish, panel=0,color='red', label='Fish', tag=True)
# graph.add_data(spectro1)
# graph.add_data(spectro2)
graph.add_data(spectro2)
# graph.add_data(spectro2)
graph.add_annotation(detections, panel=0,color='red', label='Detections')
# graph.add_annotation(classif_fish, panel=4,color='red', label='Fish', tag=True)
# graph.add_annotation(classif_noise, panel=4,color='blue', label='Noise',tag=True)
# graph.colormap = 'binary'
graph.colormap = 'jet'
graph.show()
# Detector
detector = DetectorFactory('BlobDetector',
use_dask=True,
dask_chunks=(2048, 2000),
kernel_duration=0.1,
kernel_bandwidth=300,
threshold=10,
duration_min=0.05,
bandwidth_min=40)
detections = detector.run(spectro, debug=False)
toc = time.perf_counter()
print(f"Executed in {toc - tic:0.4f} seconds")
# Plot
graph = GrapherFactory('SoundPlotter', title='Recording', frequency_max=1000)
graph.add_data(sound)
graph.add_annotation(detections, panel=0, color='grey', label='Detections')
graph.add_data(spectro)
graph.add_annotation(detections, panel=1, color='black', label='Detections')
graph.colormap = 'binary'
#graph.colormap = 'jet'
graph.show()
## To test the .crop method
#detecSpectro = spectro.crop(time_min=2,time_max=10, inplace=False)
#detecSpectro = spectro.crop(time_max=10, inplace=False)
#detecSpectro = spectro.crop(frequency_min=50, inplace=False)
#detecSpectro = spectro.crop(frequency_max=800,inplace=False)
# detecSpectro = spectro.crop(frequency_min=0,frequency_max=600,time_min=10,time_max=10.3, inplace=False)
# graph = GrapherFactory('SoundPlotter', title='Detection', frequency_max=1000)
def plot_data(audio_files,frame, window_type, nfft, step, fmin, fmax, chunk = None, detections=None, detections_channel=0):
graph_spectros = GrapherFactory('SoundPlotter', title='Spectrograms', frequency_max=fmax)
graph_waveforms = GrapherFactory('SoundPlotter', title='Waveforms')
for audio_file, channel in zip(audio_files['path'], audio_files['channel'] ): # for each channel
# load waveform
sound = Sound(audio_file)
sound.read(channel=channel, chunk=chunk, unit='sec', detrend=True)
# Calculates spectrogram
spectro = Spectrogram(frame, window_type, nfft, step, sound.waveform_sampling_frequency, unit='sec')
spectro.compute(sound, dB=True, use_dask=False)
# Crop unused frequencies
spectro.crop(frequency_min=fmin, frequency_max=fmax, inplace=True)
# Plot
graph_spectros.add_data(spectro, time_offset_sec=chunk[0])
graph_waveforms.add_data(sound, time_offset_sec=chunk[0])
graph_spectros.colormap = 'binary'
if detections:
graph_spectros.add_annotation(detections, panel=detections_channel, color='green',label='Detections')
graph_waveforms.add_annotation(detections, panel=detections_channel, color='green',label='Detections')
if chunk:
graph_spectros.time_min = chunk[0]
graph_spectros.time_max = chunk[1]
graph_waveforms.time_min = chunk[0]
graph_waveforms.time_max = chunk[1]
graph_spectros.show()
graph_waveforms.show()
# detec.data = ovlp
# print(len(detec))
detec.filter_overlap_with(annot,
freq_ovp=freq_ovp,
dur_factor_max=dur_factor_max,
dur_factor_min=dur_factor_min,
ovlp_ratio_min=ovlp_ratio_min,
remove_duplicates=remove_duplicates,
inherit_metadata=inherit_metadata,
filter_deploymentID=filter_deploymentID,
inplace=True
)
print(len(detec))
# # detec.overlap_with(annot)
# toc = time.perf_counter()
# print(f"Executed in {toc - tic:0.4f} seconds")
# Plot
graph = GrapherFactory('SoundPlotter', title='Recording', frequency_max=1000, time_min=20, time_max=200)
graph.add_data(sound)
graph.add_annotation(detec, panel=0, color='green', label='Detections')
graph.add_data(spectro)
graph.add_annotation(annot, panel=1, color='red', label='Annotations')
graph.add_annotation(detec, panel=1, color='green', label='Detections')
graph.colormap = 'binary'
#graph.colormap = 'jet'
graph.show()