def batch_find_rois(flist, params_detections, path_audio):
"""
Exports features saved as joblib into a csv file readable by R and other
programs. The joblib file should be computed using the
Parameters:
----------
params_detection: dict
Dictionary with the basic parameters to feed find_rois:
'flims', 'tlen', and 'th'.
path_flist : str
Path to a *.txt file with the list of audio filenames to process
path_audio : str
Path to the place were the dataset of audio files are stored
Returns:
-------
Saves a joblib file to disk. Does not return any variable
"""
# load parameters
flims = params_detections['flims']
tlen = params_detections['tlen']
th = params_detections['th']
detections = list()
for idx, fname in enumerate(flist['fname']):
print(idx + 1, '/', len(flist), fname)
s, fs = sound.load(path_audio + fname)
rois = find_rois_cwt(s, fs, flims, tlen, th)
if not rois.empty:
# filter rois shorter than 25% of tlen
idx_rm = (rois.max_t - rois.min_t) < tlen * 0.25
rois.drop(index=np.where(idx_rm)[0], inplace=True)
rois.reset_index(inplace=True, drop=True)
else:
pass
# save to list
detections.append({'fname': fname, 'rois': rois})
info_detections = {
'detections': detections,
'parameters': params_detections
}
return info_detections
})
#%%
# It is possible to extract Rois directly from the audio waveform without
# computing the spectrogram. This works well if there is no big overlap between
# each acoustic signature and you
# First, we have to define the frequency bandwidth where to find acoustic events
# In our example, there are clearly 3 frequency bandwidths (low : l, medium:m
# and high : h).
# We know that we have mostly short (ie. s) acoustic events in low, med and high
# frequency bandwidths but also a long (ie l) acoustic events in med.
# To extract
df_rois_sh = rois.find_rois_cwt(s,
fs,
flims=[7000, 8000],
tlen=0.2,
th=0.000001)
df_rois_sm = rois.find_rois_cwt(s,
fs,
flims=[3500, 5500],
tlen=0.2,
th=0.000001)
df_rois_lm = rois.find_rois_cwt(s, fs, flims=[2000, 7500], tlen=2, th=0.0001)
df_rois_sl = rois.find_rois_cwt(s,
fs,
flims=[1800, 3000],
tlen=0.2,
th=0.000001)
## concat df
centroid = format_features(centroid, tn, fn)
overlay_centroid(Sxx,
ext,
centroid,
savefig=None,
vmin=-120,
vmax=20,
color='blue',
fig=fig,
ax=ax)
# merge dataframes containing different features into a single dataframe (drop duplicate columns)
features = pd.concat([shape, centroid], axis=0, sort=False).fillna(0)
###=============== Find ROI 1D =================
rois_cr = find_rois_cwt(s, fs, flims=[3000, 8000], tlen=3, th=0.003)
rois_sp = find_rois_cwt(s, fs, flims=[6000, 12000], tlen=0.2, th=0.001)
rois = pd.concat([rois_sp, rois_cr], ignore_index=True)
rois = format_features(rois, tn, fn)
# view bbox
ax, fig = overlay_rois(Sxx, ext, rois, vmin=-120, vmax=20)
# get features: shape, center frequency
shape, params = shape_features(Sxx, resolution='low', rois=rois)
plot_shape(shape.mean(), params)
centroid = centroid_features(Sxx, rois)
centroid = format_features(centroid, tn, fn)
from maad.util import power2dB, plot2D
s, fs = sound.load('../../data/spinetail.wav')
Sxx, tn, fn, ext = sound.spectrogram(s, fs, nperseg=1024, noverlap=512)
Sxx_db = power2dB(Sxx, db_range=100) + 100
plot2D(Sxx_db, **{'extent': ext})
#%%
# Detect the accelerating trill
# -----------------------------
# The accelerating trill is the song of a small neotropical bird, Cranioleuca erythrops. This song can be detected on the recording using the function find_rois_cwt and setting frequency limits flims=(4500,8000) and temporal length of signal tlen=2.
_ = find_rois_cwt(s,
fs,
flims=(4500, 8000),
tlen=2,
th=0,
display=True,
figsize=(13, 6))
#%%
# Detect the fast descending chirp
# --------------------------------
# Alternatively, the fast descending chirp (unknown species) can be segmented in the recording by changing the detection parameters.
df = find_rois_cwt(s,
fs,
flims=(8000, 12000),
tlen=0.1,
th=0.001,
display=True,
def batch_predict_rois(flist, tuned_clfs, params, path_audio_db='./'):
"""
Predict the labels of rois in a list of audio files.
Parameters
----------
flist: pandas DataFrame
list of audio filenames to be analysed. Column name must be 'fname'
tuned_clfs: dict
data structure with tuned classifiers by grid search or random search
params: dict
data structure with the same parameters used to train the classifiers.
Keys to be included: 'sample_rate_wav', 'flims', 'tlen', 'th',
'opt_spec', 'opt_shape_str'
path_audio_db: str, default current directory
path pointing to the directory where the audio files are located.
Note that all files in flist must be in the same directory
Returns
-------
predictions: dict
data structure with name of audio files as keys. Each element in the
dictionary has a DataFrame with predictions for every region interest
found. Predictions are given as probabilities for three different
classifiers, namely Random Forest ('rf'), Adaboost ('adb') and Support
Vector Machines ('svm').
"""
t_start = time.time() # compute processing time
# Load params and variables
clf_svm = tuned_clfs['svm'].best_estimator_
clf_rf = tuned_clfs['rf'].best_estimator_
clf_adb = tuned_clfs['adb'].best_estimator_
flims = params['flims']
tlen = params['tlen']
th = params['th']
opt_spec = params['opt_spec']
opt_shape = opt_shape_presets(params['opt_shape_str'])
sample_rate_std = params['sample_rate_wav']
# Batch: compute rois, features and predict through files
predictions = dict()
for idx, fname in enumerate(flist['fname']):
print(idx+1, '/', len(flist), fname)
# fname = flist['fname'][0]
s, fs = sound.load(path_audio_db+fname)
# Check sampling frequency on file
if fs==sample_rate_std:
pass
else:
print('Warning: sample rate mismatch, resampling audio file to standard',
sample_rate_std, 'Hz')
s = resample(s, fs, sample_rate_std, res_type='kaiser_fast')
fs = sample_rate_std
rois = find_rois_cwt(s, fs, flims, tlen, th)
if rois.empty:
#print('< No detection on file >')
predictions[fname] = -1
else:
# filter rois shorter than 25% of tlen
idx_rm = (rois.max_t - rois.min_t) < tlen*0.25
rois.drop(index=np.where(idx_rm)[0], inplace=True)
rois.reset_index(inplace=True, drop=True)
if rois.empty:
print('< No detection on file >')
predictions[fname] = -1
else:
# compute features
rois_features = compute_rois_features(s, fs, rois, opt_spec, opt_shape, flims)
# predict
X = rois_features.loc[:,rois_features.columns.str.startswith('shp')]
#X['frequency'] = preprocessing.scale(X['frequency']) # new! scale frequency
pred_rf = pd.DataFrame(data=clf_rf.predict_proba(X),
columns=[s + '_rf' for s in clf_rf.classes_.astype('str')])
pred_adb = pd.DataFrame(data=clf_adb.predict_proba(X),
columns=[s + '_adb' for s in clf_adb.classes_.astype('str')])
pred_svm = pd.DataFrame(data=clf_svm.predict_proba(X),
columns=[s + '_svm' for s in clf_svm.classes_.astype('str')])
# save to variable
pred_proba_file = pd.concat([rois, pred_rf, pred_adb, pred_svm], axis=1)
predictions[fname] = pred_proba_file
t_stop = time.time() # compute processing time
print('Batch process completed. Processing time: ', np.round(t_stop - t_start,2),'s')
return predictions
from maad.rois import find_rois_cwt
from maad.util import plot_spectrogram
s, fs = sound.load('../../data/spinetail.wav')
Sxx, tn, fn, ext = sound.spectrogram(s, fs, nperseg=1024, noverlap=512)
plot_spectrogram(Sxx, extent=ext, db_range=60, gain=20, figsize=(4, 10))
#%%
# Detect the bouncy trill
# -----------------------
# The accelerating trill is the song of a small neotropical bird, the Red-faced Spinetail *Cranioleuca erythrops*. This song can be detected on the recording using the function ``find_rois_cwt`` and setting frequency limits ``flims=(4500,8000)`` and temporal length of signal ``tlen=2``. The segmentation results are returned as a dataframe with temporal segmentation given by the function and using the frequency limits defined by the user.
df_trill = find_rois_cwt(s,
fs,
flims=(4500, 8000),
tlen=2,
th=0,
display=True,
figsize=(10, 6))
print(df_trill)
#%%
# Detect the fast descending chirp
# --------------------------------
# Alternatively, the fast descending chirp (unknown species) can be segmented in the recording by changing the detection parameters, ``flims`` and ``tlen``.
df_chirp = find_rois_cwt(s,
fs,
flims=(8000, 12000),
tlen=0.1,
th=0.001,