def divide_run(kdst, folder_out):
xbins = np.linspace(-200, 200, 21)
ybins = np.linspace(-200, 200, 21)
xcenters = (xbins[1:] + xbins[:-1]) / 2
ycenters = (ybins[1:] + ybins[:-1]) / 2
binstable = pd.DataFrame({'x': xcenters, 'y': ycenters})
kdst = kdst.assign(xbin=pd.cut(kdst.X, xbins, labels=xcenters),
ybin=pd.cut(kdst.Y, ybins, labels=ycenters))
fout = fname.split('/')[-1].replace('kdst', 'kdst_chunked')
fout = folder_out + fout
groups = kdst.groupby(['xbin', 'ybin'])
with tb.open_file(fout, 'w') as h5out:
df_writer(h5out, binstable, 'BINS', 'BinInfo')
for ind, group in groups:
x, y = ind
groupname = 'KDST'
xindx = np.digitize(x, xbins) - 1
yindx = np.digitize(y, ybins) - 1
tablename = f'b_{xindx}_{yindx}'
df_writer(h5out, group, groupname, tablename)
xcenters = (xbins[1:] + xbins[:-1]) / 2
ycenters = (ybins[1:] + ybins[:-1]) / 2
data = data.assign(xbin=pd.cut(data.X, xbins, labels=xcenters),
ybin=pd.cut(data.Y, ybins, labels=ycenters))
#correct columns
ecols = [f'E_{i}' for i in range(12)] + ['S2e']
for col in ecols:
data[col] = data[col] * np.exp(data.Z / data['lt']) / data['e0cen']
#find mean and std of gaussians
means = data.groupby(['xbin',
'ybin']).apply(mean_and_std).reset_index()
mp_chunk.append(means)
fullmap = pd.concat(mp_chunk, ignore_index=True)
with tb.open_file(fout, 'w') as tab:
df_writer(tab, fullmap, 'LT', 'LightTable')
fnames_tp = fnames
runs = re.findall('\d+', fnames_tp[0])[0]
rune = re.findall('\d+', fnames_tp[-1])[0]
fout = folder_out + 'runs_' + runs + '_' + rune + '.h5'
mp_chunk = []
for tbname in tablenames:
data = load_dsts(fnames_tp, 'KDST', tbname)
xbin, ybin = data.xbin.unique()[0], data.ybin.unique()[0]
xbins = np.linspace(xbin - 10, xbin + 10, 21) #1mm bins
ybins = np.linspace(ybin - 10, ybin + 10, 21)
xcenters = (xbins[1:] + xbins[:-1]) / 2
ycenters = (ybins[1:] + ybins[:-1]) / 2
data = data.assign(xbin=pd.cut(data.X, xbins, labels=xcenters),
ybin=pd.cut(data.Y, ybins, labels=ycenters))
augmentation = parameters.augmentation)
if action == 'predict':
gen = predict_gen(data_path = parameters.predict_file,
label_type = parameters.labeltype,
net = net,
batch_size = parameters.predict_batch,
nevents = parameters.nevents_predict)
coorname = ['xbin', 'ybin', 'zbin']
output_name = parameters.out_file
if parameters.labeltype == LabelType.Segmentation:
tname = 'VoxelsPred'
else:
tname = 'EventPred'
with tb.open_file(output_name, 'w') as h5out:
for dct in gen:
if 'coords' in dct:
coords = dct.pop('coords')
#unpack coords and add them to dictionary
dct.update({coorname[i]:coords[:, i] for i in range(3)})
predictions = dct.pop('predictions')
#unpack predictions and add them back to dictionary
dct.update({f'class_{i}':predictions[:, i] for i in range(predictions.shape[1])})
#create pandas dataframe and save to output file
df = pd.DataFrame(dct)
df_writer(h5out, df, 'DATASET', tname, columns_to_index=['dataset_id'])
index_tables(output_name)
'nbins_y': config.nbins_y,
'min_z': min_z,
'max_z': max_z,
'nbins_z': config.nbins_z,
'Rmax': config.Rmax
}).to_frame().T
return eventInfo, binsInfo, hits
if __name__ == "__main__":
config = configure(sys.argv).as_namespace
filesin = glob(os.path.expandvars(config.files_in))
start_id = 0
for f in filesin:
eventInfo, binsInfo, hits = get_MCtables(f, config, start_id)
start_id += len(eventInfo)
with tb.open_file(os.path.expandvars(config.file_out), 'w') as h5out:
dio.df_writer(h5out,
eventInfo,
'DATASET',
'EventsInfo',
columns_to_index=['dataset_id'],
str_col_length=64)
dio.df_writer(h5out, binsInfo, 'DATASET', 'BinsInfo')
dio.df_writer(h5out,
hits,
'DATASET',
'Voxels',
columns_to_index=['dataset_id'])
"xmax", "ymax", "zmax", "rmax", "xb1", "yb1", "zb1", "eb1", "xb2",
"yb2", "zb2", "eb2", "ovlp_e"
]
data = namedtuple("data", columns) # auxiliar namedtuple
paolina_algorithm = track_blob_info_creator_extractor(**paolina_params)
out_df = pd.DataFrame(columns=columns)
try:
DECO = pd.read_hdf(in_filename, "DECO/Events")
except KeyError:
# save empty file
with tb.open_file(out_filename, "w") as h5out:
df_writer(h5out, out_df, group_name="tracks", table_name="events")
index_tables(out_filename)
sys.exit()
for (event, peak), deco in DECO.groupby(["event", "npeak"]):
# pre-proccess
deco.loc[:, "time"] = 0
deco.loc[:, "Ec"] = deco["E"]
deco.loc[:, "Ep"] = deco["E"]
deco.loc[:, ("Q", "Xrms", "Yrms", "nsipm")] = np.nan
# Paolina
hitc = hits_from_df(deco)[event]
df, voxels, track_hitc, out_of_map = paolina_algorithm(hitc)