Skip to content

In process_function take nnpdf31_process from PLOTTING_*.yaml #1472

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
Zaharid merged 4 commits into from
Dec 1, 2021
Merged

In process_function take nnpdf31_process from PLOTTING_*.yaml #1472

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3b73e91
read process from PLOTTING_*.yml files instead of hardcoding
RoyStegeman Nov 19, 2021
eccaba1
update process_lookup docstring
RoyStegeman Nov 19, 2021
a434a3d
replace process_lookup with get_info in config.py
RoyStegeman Nov 19, 2021
ed8e00f
use get_info to obtain nnpdf31_process in process_lookup()
RoyStegeman Nov 30, 2021
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
11 changes: 7 additions & 4 deletions validphys2/src/validphys/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,6 @@

from validphys.paramfits.config import ParamfitsConfig

from validphys.theorycovariance.theorycovarianceutils import process_lookup
from validphys.plotoptions import get_info

import validphys.scalevariations
Expand Down Expand Up @@ -763,9 +762,13 @@ def produce_matched_datasets_from_dataspecs(self, dataspecs):

with self.set_context(ns=self._curr_ns.new_child(spec)):
_, data_input = self.parse_from_(None, "data_input", write=False)
names = {
(process_lookup(dsin.name), dsin.name): dsin for dsin in data_input
}

names = {}
for dsin in data_input:
cd = self.produce_commondata(dataset_input=dsin)
proc = get_info(cd).nnpdf31_process
ds = dsin.name
names[(proc, ds)] = dsin

all_names.append(names)
used_set = set.intersection(*(set(d) for d in all_names))
Expand Down
74 changes: 8 additions & 66 deletions validphys2/src/validphys/theorycovariance/theorycovarianceutils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,9 @@
import logging

from reportengine.checks import make_argcheck, check
from validphys.loader import Loader
from validphys.plotoptions import get_info

log = logging.getLogger(__name__)


Expand Down Expand Up @@ -90,72 +93,11 @@ def check_fit_dataset_order_matches_grouped(
"errors when running fits with theory covmat. Datasets should "
f"be ordered by {processed_metadata_group} in the runcard."
)

def process_lookup(name):
"""Produces a dictionary with keys corresponding to dataset names
and values corresponding to process types. Process types are
regrouped into the five categories 'Drell-Yan', 'Top', Jets',
'DIS NC' and 'DIS CC'.


The implementation relies on hardcoding the process type for
each dataset internally. If a dataset is not registered,
'UNKNOWN' is returned.
def process_lookup(name):
"""

process_dictionary = { "ATLASZPT8TEVMDIST": "DY",
"ATLASZPT8TEVYDIST": "DY",
"CMSZDIFF12": "DY",
"ATLAS1JET11": "JETS",
"CMSJETS11": "JETS",
"CDFR2KT": "JETS",
"CMSTOPDIFF8TEVTTRAPNORM": "TOP",
"ATLASTOPDIFF8TEVTRAPNORM": "TOP",
"ATLASTTBARTOT": "TOP",
"CMSTTBARTOT": "TOP",
"DYE605": "DY",
"DYE886P": "DY",
"DYE886R": "DY",
"ATLASWZRAP36PB": "DY",
"ATLASZHIGHMASS49FB": "DY",
"ATLASLOMASSDY11EXT": "DY",
"ATLASWZRAP11": "DY",
"CMSWEASY840PB": "DY",
"CMSWMASY47FB": "DY",
"CMSDY2D11": "DY",
"CMSWMU8TEV": "DY",
"CMSWCHARMRAT": "DY",
"LHCBZ940PB": "DY",
"LHCBZEE2FB": "DY",
"LHCBWZMU7TEV": "DY",
"LHCBWZMU8TEV": "DY",
"D0WEASY": "DY",
"D0WMASY": "DY",
"D0ZRAP": "DY",
"CDFZRAP": "DY",
"H1HERAF2B": "DIS NC",
"HERACOMBCCEM": "DIS CC",
"HERACOMBCCEP": "DIS CC",
"HERACOMBNCEM": "DIS NC",
"HERACOMBNCEP460": "DIS NC",
"HERACOMBNCEP575": "DIS NC",
"HERACOMBNCEP820": "DIS NC",
"HERACOMBNCEP920": "DIS NC",
"HERAF2CHARM": "DIS NC",
"ZEUSHERAF2B": "DIS NC",
"NMCPD": "DIS NC",
"NMC": "DIS NC",
"SLACP": "DIS NC",
"SLACD": "DIS NC",
"BCDMSP": "DIS NC",
"BCDMSD": "DIS NC",
"CHORUSNU": "DIS CC",
"CHORUSNB": "DIS CC",
"NTVNUDMN": "DIS CC",
"NTVNBDMN": "DIS CC" }

proc = process_dictionary.get(name)
if not proc:
log.warn(f'Unknown process type for dataset {name}')
return 'UNKNOWN'
Returns the `nnpdf31_process` of the corresponding dataset.
"""
cd = Loader().check_commondata(setname=name)
proc = get_info(cd).nnpdf31_process
return proc