Skip to content

Change flagging accordingly to new O2Physics data format #1041

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
qgp merged 1 commit into from
Jul 28, 2025
Merged

Change flagging accordingly to new O2Physics data format #1041

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions machine_learning_hep/data/data_run3/database_ml_parameters_LcToPKPi_CrystalBall.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,23 +82,23 @@ LcpKpi:
#extra:
#fY: log((sqrt(2.28646**2 + (fPt * cosh(fEta))**2) + fPt * sinh(fEta)) / sqrt(2.28646**2 + fPt**2)) #TODO : change mass or make sure Lc mass is updated
tags:
isstd: {var: fFlagMcMatchRec, req: [[1], []], level: mc}
ismcsignal: {var: fFlagMcMatchRec, req: [[1], []], abs: true, level: mc}
ismcbkg: {var: fFlagMcMatchRec, req: [[], [1]], abs: true, level: mc}
ismcprompt: {var: fOriginMcRec, req: [[0], []], level: mc}
ismcfd: {var: fOriginMcRec, req: [[1], []], level: mc}
isstd: {var: fFlagMcMatchRec, req: 17, level: mc}
ismcsignal: {var: fFlagMcMatchRec, req: 17, abs: true, level: mc}
ismcbkg: {var: ismcsignal, req: 0, level: mc}
ismcprompt: {var: fOriginMcRec, req: 1, level: mc}
ismcfd: {var: fOriginMcRec, req: 2, level: mc}
swap: {cand: fCandidateSelFlag, var_swap: fIsCandidateSwapped, vars: [ismcsignal, ismcprompt, ismcfd], level: mc}

gen:
level: mc
trees:
O2hflcpbase: [fIndexHFLCMCCOLLBASES, fPt, fY, fEta, fPhi, fFlagMcMatchGen, fOriginMcGen]
tags:
isstd: {var: fFlagMcMatchGen, req: [[1], []], level: mc}
ismcsignal: {var: fFlagMcMatchGen, req: [[1], []], abs: true, level: mc}
ismcbkg: {var: fFlagMcMatchGen, req: [[], [1]], abs: true, level: mc}
ismcprompt: {var: fOriginMcGen, req: [[0], []], level: mc}
ismcfd: {var: fOriginMcGen, req: [[1], []], level: mc}
isstd: {var: fFlagMcMatchGen, req: 17, level: mc}
ismcsignal: {var: fFlagMcMatchGen, req: 17, abs: true, level: mc}
ismcbkg: {var: ismcsignal, req: 0, level: mc}
ismcprompt: {var: fOriginMcGen, req: 1, level: mc}
ismcfd: {var: fOriginMcGen, req: 2, level: mc}
#extra:
#fY: log((sqrt(2.28646**2 + (fPt * cosh(fEta))**2) + fPt * sinh(fEta)) / sqrt(2.28646**2 + fPt**2)) #TODO : change mass or make sure Lc mass is updated

Expand Down
25 changes: 15 additions & 10 deletions machine_learning_hep/processer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,6 @@
import uproot
from pandas.api.types import is_numeric_dtype

from .bitwise import tag_bit_df
from .io import dump_yaml_from_dict
from .logger import get_logger
from .utilities import (
Expand Down Expand Up @@ -217,8 +216,8 @@ def __init__(
# Potentially mask certain values (e.g. nsigma TOF of -999)
self.p_mask_values = datap["ml"].get("mask_values", None)

self.bins_skimming = np.array(list(zip(self.lpt_anbinmin, self.lpt_anbinmax)), "d")
self.bins_analysis = np.array(list(zip(self.lpt_finbinmin, self.lpt_finbinmax)), "d")
self.bins_skimming = np.array(list(zip(self.lpt_anbinmin, self.lpt_anbinmax, strict=False)), "d")
self.bins_analysis = np.array(list(zip(self.lpt_finbinmin, self.lpt_finbinmax, strict=False)), "d")
bin_matching = [
[ptrange[0] <= bin[0] and ptrange[1] >= bin[1] for ptrange in self.bins_skimming].index(True)
for bin in self.bins_analysis
Expand Down Expand Up @@ -251,7 +250,7 @@ def __init__(
for ipt in range(self.p_nptfinbins):
mlsel_multi = [
f"y_test_prob{self.p_modelname}{label.replace('-', '_')} {comp} {probcut}"
for label, comp, probcut in zip(self.class_labels, comps, self.lpt_probcutfin[ipt])
for label, comp, probcut in zip(self.class_labels, comps, self.lpt_probcutfin[ipt], strict=False)
]
self.l_selml.append(" and ".join(mlsel_multi))

Expand Down Expand Up @@ -375,7 +374,7 @@ def dfread(rdir, trees, cols, idx_name=None):
cols = [cols]
# if all(type(var) is str for var in vars): vars = [vars]
df = None
for tree, col in zip([rdir[name] for name in trees], cols):
for tree, col in zip([rdir[name] for name in trees], cols, strict=False):
try:
data = tree.arrays(expressions=col, library="np")
dfnew = pd.DataFrame(columns=col, data=data)
Expand All @@ -396,7 +395,7 @@ def dfread(rdir, trees, cols, idx_name=None):

def dfappend(name: str, dfa):
"""Append DF row-wise"""
dfs[name] = pd.concat([dfs.get(name, None), dfa])
dfs[name] = pd.concat([dfs.get(name), dfa])

def dfmerge(dfl, dfr, **kwargs):
"""Merge dfl and dfr"""
Expand Down Expand Up @@ -437,7 +436,7 @@ def dfuse(df_spec):
if dfuse(df_spec):
trees = []
cols = []
for tree, spec in zip(df_spec["trees"].keys(), df_spec["trees"].values()):
for tree, spec in zip(df_spec["trees"].keys(), df_spec["trees"].values(), strict=False):
if isinstance(spec, list):
trees.append(tree)
cols.append(spec)
Expand Down Expand Up @@ -467,9 +466,15 @@ def dfuse(df_spec):
self.logger.debug(" %s -> tags", df_name)
for tag, value in df_spec["tags"].items():
if dfuse(value):
dfs[df_name][tag] = np.array(
tag_bit_df(dfs[df_name], value["var"], value["req"], value.get("abs", False)), dtype=int
)
var = dfs[df_name][value["var"]]

if value.get("abs", False):
var = var.abs()

dfs[df_name][tag] = (var == value["req"]).astype(int)

# dfs[df_name][tag] = np.array(
# tag_bit_df(dfs[df_name], value["var"], value["req"], value.get("abs", False)), dtype=int)

if "swap" in df_spec:
self.logger.debug(" %s -> swap", df_name)
Expand Down
Loading