df_data = pd.read_parquet('df/data_dataset')
#df_data = uproot.open('../data/AnalysisResults.root')['LambdaTree'].arrays(library="pd")
# df_data = df_data.append(df_data_r, ignore_index=True)
df_data_cent = df_data.query(
f'matter {split_ineq_sign} and centrality > {cent_bins[0]} and centrality < {cent_bins[1]} and pt > 0.5 and pt < 3 and ct > {ct_bins[0]} and ct < {ct_bins[1]} and tpcClV0Pi > 69 and tpcClV0Pr > 69 and radius > 3'
)
del df_data
data_y_score = model_hdl.predict(df_data_cent)
df_data_cent['model_output'] = data_y_score
df_data_cent = df_data_cent.query(
f'model_output > {score_eff_arrays_dict[bin][len(eff_array)-1]}'
)
df_data_cent.to_parquet(f'df/{bin}.parquet.gzip',
compression='gzip')
else:
df_data = TreeHandler()
df_data.get_handler_from_large_file(
DATA_PATH,
"LambdaTree",
preselection=
f'matter {split_ineq_sign} and centrality > {cent_bins[0]} and centrality < {cent_bins[1]} and pt > 0.5 and pt < 3 and ct > {ct_bins[0]} and ct < {ct_bins[1]}',
max_workers=8)
df_data.apply_model_handler(model_hdl)
df_data.apply_preselections(
f'model_output > {score_eff_arrays_dict[bin][len(eff_array)-1]}'
)
df_data.write_df_to_parquet_files(bin, "df/")
data_tree_handler = TreeHandler()
data_tree_handler.set_data_frame(df_data_cent)
del df_data_cent
data_tree_handler.slice_data_frame(
'ct',
list(zip(CT_BINS[i_cent_bins][:-1], CT_BINS[i_cent_bins][1:])))
model_hdl_array = np.empty((len(CT_BINS[i_cent_bins]) - 1, ),
dtype=object)
for i_ct_bins in range(len(CT_BINS[i_cent_bins]) - 1):
bin = f'{split}_{cent_bins[0]}_{cent_bins[1]}_{CT_BINS[i_cent_bins][i_ct_bins]}_{CT_BINS[i_cent_bins][i_ct_bins+1]}'
model_hdl_array[i_ct_bins] = ModelHandler()
if OPTIMIZED:
model_hdl_array[i_ct_bins].load_model_handler(
f'models/{bin}_optimized_trained')
else:
model_hdl_array[i_ct_bins].load_model_handler(
f'models/{bin}_trained')
data_tree_handler.apply_model_handler(list(model_hdl_array))
eff_array = np.arange(0.10, 0.91, 0.01)
for i_ct_bins in range(len(CT_BINS[i_cent_bins]) - 1):
bin = f'{split}_{cent_bins[0]}_{cent_bins[1]}_{CT_BINS[i_cent_bins][i_ct_bins]}_{CT_BINS[i_cent_bins][i_ct_bins+1]}'
slice = data_tree_handler.get_slice(i_ct_bins)
slice.query(
f'model_output > {score_eff_arrays_dict[bin][len(eff_array)-1]}'
)
slice.to_parquet(f'df/{bin}', compression='gzip')