# load annotations
annot = Annotation()
annot.from_netcdf(annotation_file)
# load detections
detec = Measurement()
detec.from_netcdf(detection_file)
print(detec)
freq_ovp = True # default True
dur_factor_max = None # default None
dur_factor_min = 0.1 # default None
ovlp_ratio_min = 0.3 # defaulkt None
remove_duplicates = True # dfault - False
inherit_metadata = True # default False
filter_deploymentID = False # default True
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(detec)
detec.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')
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'))
data.dropna(subset=features,
axis=0,
how='any',
thresh=None,
inplace=True)
n2 = len(data)
print('Deleted observations (due to NaNs): ' + str(n1 - n2))
# Classification - predictions
X = data[features]
X = (X - Norm_mean) / Norm_std
pred_class = model.predict(X)
pred_prob = model.predict_proba(X)
pred_prob = pred_prob[range(0, len(pred_class)), pred_class]
# Relabel
for index, row in classes_encoder.iterrows():
pred_class = [
row['label'] if i == row['ID'] else i for i in pred_class
]
# update measurements
data['label_class'] = pred_class
data['confidence'] = pred_prob
# sort detections by ascending start date/time
data.sort_values('time_min_offset',
axis=0,
ascending=True,
inplace=True)
# save result as NetCDF file
print('Saving')
meas.data = data
meas.to_netcdf(os.path.join(outdir, file))