deployment_file = r'C:\Users\xavier.mouy\Documents\PhD\Projects\Dectector\datasets\UVIC_mill-bay_2019\deployment_info.csv'
data_dir = r'C:\Users\xavier.mouy\Documents\PhD\Projects\Dectector\datasets\UVIC_mill-bay_2019\audio_data'
# load meta data
operator_name = platform.uname().node
dep_info = DeploymentInfo()
dep_info.read(deployment_file)
#list files
files = ecosound.core.tools.list_files(indir,
ext,
recursive=False,
case_sensitive=True)
for idx, file in enumerate(files):
print(str(idx) + r'/' + str(len(files)) + ': ' + file)
meas = Measurement()
meas.from_netcdf(file)
meas.insert_metadata(deployment_file)
file_name = os.path.splitext(os.path.basename(file))[0]
meas.insert_values(
operator_name=platform.uname().node,
audio_file_name=os.path.splitext(os.path.basename(file_name))[0],
audio_file_dir=data_dir,
audio_file_extension='.wav',
audio_file_start_date=ecosound.core.tools.filename_to_datetime(
file_name)[0])
meas.to_netcdf(os.path.join(outdir, file_name + '.nc'))
""" # Define input and output files annot_file = r'C:\Users\xavier.mouy\Documents\PhD\Projects\Dectector\results\dataset_annotations_only.nc' noise_file = r'C:\Users\xavier.mouy\Documents\PhD\Projects\Dectector\results\Noise_dataset' outfile=r'C:\Users\xavier.mouy\Documents\PhD\Projects\Dectector\results\dataset_FS-NN_modified_20201105145300.nc' # Load measurements meas_annot = Measurement() meas_annot.from_netcdf(annot_file) meas_noise = Measurement() meas_noise.from_netcdf(noise_file) ## Label noise measurement as 'NN' meas_noise.insert_values(label_class='NN') print(meas_noise.summary()) ## relabel annotations that are not 'FS' as 'NN' print(meas_annot.summary()) meas_annot.data['label_class'].replace(to_replace=['', 'ANT','HS','KW','UN'], value='NN', inplace=True) print(meas_annot.summary()) ## merge the 2 datasets meas_NN_FS = meas_noise + meas_annot print(meas_NN_FS.summary()) ## Save dataset to nc file meas_NN_FS.to_netcdf(outfile)
min_threshold = 0.7
noise_label = 'NN'
# load names of file and start/stop times where false alarms have been manually
# identified
df = pd.read_excel(xls_file, header=None)
for idx in range(0, len(df)):
# file name to load
wav_file_name = df[0][idx]
tmin_sec = df[1][idx]
tmax_sec = df[2][idx]
print(wav_file_name, tmin_sec, tmax_sec)
detec_file_path = os.path.join(in_dir, wav_file_name + '.nc')
# load detection/measurement file
meas = Measurement()
meas.from_netcdf(detec_file_path)
data_df = meas.data
# Only keep fish detections above the given confidence threshold and times
data_df_filt = data_df[(data_df.label_class == fish_label)
& (data_df.confidence >= min_threshold)
& (data_df.time_min_offset >= tmin_sec)
& (data_df.time_max_offset <= tmax_sec)]
data_df_filt.reset_index(inplace=True, drop=True)
meas.data = data_df_filt
# Change fish labels to noise labels
meas.insert_values(label_class=noise_label)
# Save to new nc file
meas.to_netcdf(os.path.join(out_dir, wav_file_name + str(idx)))
print('done')