def tierpsy_plate_summary_augmented(fname,
is_manual_index=False,
delta_time=1 / 3,
**fold_args):
fps = read_fps(fname)
data_in = read_data(fname, is_manual_index)
if data_in is None:
return
timeseries_data, blob_features = data_in
fold_index = augment_data(timeseries_data, fps=fps, **fold_args)
all_summary = []
for i_fold, ind_fold in enumerate(fold_index):
timeseries_data_r = timeseries_data[ind_fold].reset_index(drop=True)
blob_features_r = blob_features[ind_fold].reset_index(drop=True)
plate_feats = get_summary_stats(timeseries_data_r, fps,
blob_features_r, delta_time)
plate_feats = pd.DataFrame(plate_feats).T
plate_feats.insert(0, 'i_fold', i_fold)
all_summary.append(plate_feats)
all_summary = pd.concat(all_summary, ignore_index=True)
return all_summary
def tierpsy_plate_summary_augmented(fname,
filter_params,
time_windows,
time_units,
only_abs_ventral=False,
selected_feat=None,
is_manual_index=False,
delta_time=1 / 3,
**fold_args):
fps = read_fps(fname)
data_in = read_data(fname, filter_params, time_windows, time_units, fps,
is_manual_index)
if data_in is None:
return [pd.DataFrame() for iwin in range(len(time_windows))]
timeseries_data, blob_features = data_in
# initialize list of summaries for all time windows
all_summaries_list = []
# loop over time windows
for iwin, window in enumerate(time_windows):
if timeseries_data[iwin].empty:
all_summary = pd.DataFrame([])
else:
fold_index = augment_data(timeseries_data[iwin],
fps=fps,
**fold_args)
# initialize list of augmented plate summaries for given time window
all_summary = []
# loop over folds
for i_fold, ind_fold in enumerate(fold_index):
timeseries_data_r = timeseries_data[iwin][
ind_fold].reset_index(drop=True)
blob_features_r = blob_features[iwin][ind_fold].reset_index(
drop=True)
plate_feats = get_summary_stats(
timeseries_data_r,
fps,
blob_features_r,
delta_time,
only_abs_ventral=only_abs_ventral,
selected_feat=selected_feat)
plate_feats['n_skeletons'] = count_skeletons(timeseries_data_r)
plate_feats = pd.DataFrame(plate_feats).T
plate_feats.insert(0, 'i_fold', i_fold)
all_summary.append(plate_feats)
# concatenate all folds in given time window into one dataframe
all_summary = pd.concat(all_summary, ignore_index=True, sort=False)
# add dataframe to the list of summaries for all time windows
all_summaries_list.append(all_summary)
return all_summaries_list
def ow_plate_summary_augmented(fname, **fold_args):
#NOTE: I will only augment the timeseries features.
#It is not trivial to include the event features sampling over time.
fps = read_fps(fname)
with pd.HDFStore(fname, 'r') as fid:
features_timeseries = fid['/features_timeseries']
fold_index = augment_data(features_timeseries, fps=fps, **fold_args)
valid_order = None
wStats = WormStats()
all_summary = []
for i_fold, ind_fold in enumerate(fold_index):
timeseries_data_r = features_timeseries[ind_fold].reset_index(drop=True)
all_feats = {}
for cc in timeseries_data_r:
all_feats[cc] = timeseries_data_r[cc].values
exp_feats = wStats.getWormStats(all_feats, np.nanmean)
exp_feats = pd.DataFrame(exp_feats)
if valid_order is None:
#only calculate this the first time...
valid_order = [x for x in exp_feats.columns if x not in wStats.extra_fields]
exp_feats = exp_feats.loc[:, valid_order]
exp_feats.insert(0, 'i_fold', i_fold)
all_summary.append(exp_feats)
all_summary = pd.concat(all_summary, ignore_index=True)
return all_summary