nnpdf-data 0.0.1__py3-none-any.whl → 0.0.2__py3-none-any.whl

nnpdf_data/theory_cards/40012009.yaml

@@ -0,0 +1,41 @@
+ID: 40_012_009
+Comments: Same as 40_009_002, but alphas=0.123
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: TRN
+XIR: 1.0
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.51
+Qmc: 1.51
+kcThr: 1.0
+mb: 4.92
+Qmb: 4.92
+kbThr: 1.0
+mt: 175.0
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97428
+- 0.2253
+- 0.00347
+- 0.2252
+- 0.97345
+- 0.041
+- 0.00862
+- 0.0403
+- 0.999152
+MZ: 91.1876
+MW: 80.398
+GF: 1.1663787e-05
+SIN2TW: 0.23126
+TMC: 1
+MP: 0.938
+Qref: 91.2
+alphas: 0.123
+alphaqed: 0.0077553

nnpdf_data/theory_cards/40012010.yaml

@@ -0,0 +1,41 @@
+ID: 40_012_010
+Comments: Same as 40_009_002, but alphas=0.124
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: TRN
+XIR: 1.0
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.51
+Qmc: 1.51
+kcThr: 1.0
+mb: 4.92
+Qmb: 4.92
+kbThr: 1.0
+mt: 175.0
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97428
+- 0.2253
+- 0.00347
+- 0.2252
+- 0.97345
+- 0.041
+- 0.00862
+- 0.0403
+- 0.999152
+MZ: 91.1876
+MW: 80.398
+GF: 1.1663787e-05
+SIN2TW: 0.23126
+TMC: 1
+MP: 0.938
+Qref: 91.2
+alphas: 0.124
+alphaqed: 0.0077553

nnpdf_data/theory_cards/40012011.yaml

@@ -0,0 +1,41 @@
+ID: 40_012_011
+Comments: Same as 40_009_002, but alphas=0.125
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: TRN
+XIR: 1.0
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.51
+Qmc: 1.51
+kcThr: 1.0
+mb: 4.92
+Qmb: 4.92
+kbThr: 1.0
+mt: 175.0
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97428
+- 0.2253
+- 0.00347
+- 0.2252
+- 0.97345
+- 0.041
+- 0.00862
+- 0.0403
+- 0.999152
+MZ: 91.1876
+MW: 80.398
+GF: 1.1663787e-05
+SIN2TW: 0.23126
+TMC: 1
+MP: 0.938
+Qref: 91.2
+alphas: 0.125
+alphaqed: 0.0077553

nnpdf_data/theory_cards/40012012.yaml

@@ -0,0 +1,41 @@
+ID: 40_012_012
+Comments: Same as 40_009_002, but alphas=0.130
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: TRN
+XIR: 1.0
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.51
+Qmc: 1.51
+kcThr: 1.0
+mb: 4.92
+Qmb: 4.92
+kbThr: 1.0
+mt: 175.0
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97428
+- 0.2253
+- 0.00347
+- 0.2252
+- 0.97345
+- 0.041
+- 0.00862
+- 0.0403
+- 0.999152
+MZ: 91.1876
+MW: 80.398
+GF: 1.1663787e-05
+SIN2TW: 0.23126
+TMC: 1
+MP: 0.938
+Qref: 91.2
+alphas: 0.130
+alphaqed: 0.0077553

nnpdf_data/theorydbutils.py

@@ -19,7 +19,7 @@ class TheoryNotFoundInDatabase(Exception):
 
 
 @lru_cache
-def parse_theory_card(theory_card):
+def _parse_theory_card(theory_card):
     """Read the theory card using validobj parsing
     Returns the theory as a dictionary
     """
@@ -27,6 +27,22 @@ def parse_theory_card(theory_card):
     return tcard.asdict()
 
 
+@lru_cache
+def _get_available_theory_cards(path):
+    """Since theoryfile names may contain underscores, the theoryfile name cannot uniquely be
+    determined from the theoryID. Therefore we create a mapping between the theoryid as python
+    int and the corresponding file.
+    """
+    available_theories = {}
+    for theoryfile in path.glob("*.yaml"):
+        tmp_id = int(theoryfile.stem)
+        if tmp_id in available_theories:
+            another = available_theories[tmp_id]
+            raise ValueError(f"Two theory files with same id: {theoryfile} and {another}")
+        available_theories[tmp_id] = theoryfile
+    return available_theories
+
+
 def fetch_theory(theory_database: Path, theoryID: int):
     """Looks in the theory card folder and returns a dictionary of theory info for the
     theory number specified by `theoryID`.
@@ -50,38 +66,23 @@ def fetch_theory(theory_database: Path, theoryID: int):
     >>> theory = fetch_theory(theory_cards, 700)
     """
 
-    available_theories = get_available_theory_cards(theory_database)
+    available_theories = _get_available_theory_cards(theory_database)
     theoryID = int(theoryID)
     try:
         theoryfile = available_theories[theoryID]
     except KeyError as e:
         raise TheoryNotFoundInDatabase(f"Theorycard for theory not found: {e}")
 
-    tdict = parse_theory_card(theoryfile)
+    tdict = _parse_theory_card(theoryfile)
     if tdict["ID"] != theoryID:
         raise ValueError(f"The theory ID in {theoryfile} doesn't correspond with its ID entry")
     return tdict
 
 
-@lru_cache
-def get_available_theory_cards(path):
-    """Since theoryfile names may contain underscores, the theoryfile name cannot uniquely be
-    determined from the theoryID. Therefore we create a mapping between the theoryid as python
-    int and the corresponding file.
-    """
-    available_theories = {}
-    for theoryfile in path.glob("*.yaml"):
-        tmp_id = int(theoryfile.stem)
-        if tmp_id in available_theories:
-            another = available_theories[tmp_id]
-            raise ValueError(f"Two theory files with same id: {theoryfile} and {another}")
-        available_theories[tmp_id] = theoryfile
-    return available_theories
-
-
 def fetch_all(theory_database: Path):
     """Looks in the theory database and returns a dataframe with theory info
-    for all theories
+    for all theories that can be found in the folder ``theory_database``.
+    Every ``.yaml`` file found in the folder will be considered a possible theory.
 
     Parameters
     ----------
@@ -99,9 +100,7 @@ def fetch_all(theory_database: Path):
     >>> from nnpdf_data.theorydbutils import fetch_all
     >>> theory_df = fetch_all(theory_cards)
     """
-    available_theories = get_available_theory_cards(theory_database)
-    theories = []
-    for theory_path in available_theories.values():
-        theories.append(parse_theory_card(theory_path))
+    available_theories = _get_available_theory_cards(theory_database)
+    theories = [fetch_theory(theory_database, thid) for thid in available_theories]
     df = pd.DataFrame(theories)
     return df.set_index(['ID']).sort_index()

nnpdf_data/utils.py

@@ -1,12 +1,10 @@
 import pathlib
 
-try:
-    import ruamel.yaml as yaml
-except ImportError:
-    import ruamel_yaml as yaml
-
+from ruamel.yaml import YAML
 from validobj import ValidationError, parse_input
+import yaml
 
+yaml_rt = YAML(typ="rt")
 try:
     # If libyaml is available, use the C loader
     Loader = yaml.CLoader
@@ -36,14 +34,14 @@ def parse_yaml_inp(input_yaml, spec):
         return parse_input(inp, spec)
     except ValidationError as e:
         current_exc = e
-        # In order to provide a more complete error information, use round_trip_load
+        # In order to provide a more complete error information, use round trip
         # to read the .yaml file again (insetad of using the CLoader)
-        current_inp = yaml.round_trip_load(input_yaml.open("r", encoding="utf-8"))
+        current_inp = yaml_rt.load(input_yaml.open("r", encoding="utf-8"))
         error_text_lines = []
         while current_exc:
             if hasattr(current_exc, 'wrong_field'):
                 wrong_field = current_exc.wrong_field
-                # Mappings compping from ``round_trip_load`` have an
+                # Mappings compping from yaml_rt have an
                 # ``lc`` attribute that gives a tuple of
                 # ``(line_number, column)`` for a given item in
                 # the mapping.

nnpdf_data/validphys_compatibility.py

@@ -9,8 +9,12 @@
 """
 
 import dataclasses
+from functools import cache
+import pathlib
 import typing
 
+import ruamel.yaml as yaml
+
 labeler_functions = []
 
 
@@ -37,3 +41,76 @@ class PlottingOptions:
     normalize: typing.Optional[dict] = None
     # Note that this "PlottingOptions" start already digested, because it actually does nothing!
     already_digested: typing.Optional[bool] = True
+
+
+########## Legacy names compatibility
+# The functions and variables below exist solely for reproducibility of old NNPDF results
+# and no external code or new feature should depend on them as they might be removed at any point
+# with no previous warning
+
+path_vpdata = pathlib.Path(__file__).parent
+path_commondata = path_vpdata / "commondata"
+_path_legacy_mapping = path_commondata / "dataset_names.yml"
+_legacy_to_new_mapping_raw = yaml.YAML().load(_path_legacy_mapping)
+# Convert strings into a dictionary
+legacy_to_new_mapping = {
+    k: ({"dataset": v} if isinstance(v, str) else v) for k, v in _legacy_to_new_mapping_raw.items()
+}
+
+
+@cache
+def legacy_to_new_map(dataset_name, sys=None):
+    """Find the new dataset name and variant corresponding to an old dataset
+    and systematics choice"""
+    if dataset_name not in legacy_to_new_mapping:
+        return dataset_name, None
+
+    new_name = legacy_to_new_mapping[dataset_name]
+    variant = new_name.get("variant")
+    new_name = new_name["dataset"]
+    if sys is not None:
+        if variant is None:
+            raise KeyError(
+                f"I cannot translate the combination of {dataset_name} and sys: {sys}. Please report this."
+            )
+        variant += f"_{sys}"
+
+    return new_name, variant
+
+
+@cache
+def new_to_legacy_map(dataset_name, variant_used):
+    """Loop over the dictionary and find the right dataset.
+
+    Since it is posible to have more than 1 dataset mapped to the same new one,
+    returns a list of everything that matches.
+
+    This function will loop over the entire dictionary of mappings and selects
+    1. All datasets that match exactly what's in the runcard (dataset & variant): exact_matches
+    2. All datasets that match the dataset name: matches
+    If there are any `exact_matches`, it will return only those; otherwise, return all `matches`
+    if there are no `matches` at all, return None
+    """
+
+    matches = []
+    exact_matches = []
+
+    for old_name, new_info in legacy_to_new_mapping.items():
+        new_name = new_info["dataset"]
+        variant = new_info.get("variant")
+
+        if new_name == dataset_name:
+            matches.append(old_name)
+            # if it's a nuclear DIS data promote legacy to be legacy_dw
+            if "_DW_" in old_name and variant_used == "legacy":
+                variant = "legacy_dw"
+
+            if variant_used == variant:
+                exact_matches.append(old_name)
+
+    # If we found exact matches, return those and stop looking
+    if exact_matches:
+        return exact_matches
+    elif matches:
+        return matches
+    return None

{nnpdf_data-0.0.1.dist-info → nnpdf_data-0.0.2.dist-info}/METADATA

@@ -1,8 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: nnpdf_data
-Version: 0.0.1
-Summary: The NNPDF data repository. Beta version.
-Home-page: https://github.com/NNPDF/nnpdf_data
+Version: 0.0.2
+Summary: The NNPDF data repository
 License: GPL-3.0-or-later
 Author: NNPDF Collaboration
 Requires-Python: >=3.9,<4.0
@@ -21,7 +20,7 @@ Provides-Extra: filter
 Requires-Dist: numpy
 Requires-Dist: openpyxl ; extra == "filter"
 Requires-Dist: pandas
-Requires-Dist: ruamel.yaml (<0.18)
+Requires-Dist: ruamel.yaml
 Requires-Dist: scipy ; extra == "filter"
 Requires-Dist: uproot ; extra == "filter"
 Requires-Dist: validobj