nnpdf 4.1.0__py3-none-any.whl → 4.1.1__py3-none-any.whl

nnpdf_data/commondata/CMS_TTBAR_13TEV_35P9FB-1_TOT/data.yaml

@@ -0,0 +1,2 @@
+data_central:
+- 803

nnpdf_data/commondata/CMS_TTBAR_13TEV_35P9FB-1_TOT/kinematics.yaml

@@ -0,0 +1,13 @@
+bins:
+- zero:
+    min: null
+    mid: 0
+    max: null
+  m_t2:
+    min: null
+    mid: 29756.25
+    max: null
+  sqrts:
+    min: null
+    mid: 13000
+    max: null

nnpdf_data/commondata/CMS_TTBAR_13TEV_35P9FB-1_TOT/metadata.yaml

@@ -0,0 +1,51 @@
+setname: CMS_TTBAR_13TEV_35P9FB-1_TOT
+nnpdf_metadata:
+  nnpdf31_process: TOP
+  experiment: CMS
+arXiv:
+  url: https://arxiv.org/abs/1812.10505
+iNSPIRE:
+  url: https://inspirehep.net/literature/1711626
+hepdata:
+  url: NA
+  version:
+version: 1
+version_comment: "This data set supersedes CMS_TTBAR_13TEV_TOT"
+implemented_observables:
+- observable:
+    description: total cross section of ttBar
+    label: $\sigma_{t\bar{t}}$
+    units: $pb$
+  observable_name: X-SEC
+  process_type: INC
+  ndata: 1
+  tables: []
+  kinematics:
+    variables:
+      zero:
+        description: ''
+        label: $$
+        units: ''
+      m_t2:
+        description: mass of top quark squared
+        label: $m_{t}^2$
+        units: $GeV^2$
+      sqrts:
+        description: center of mass energy
+        label: $\sqrt{s}$
+        units: $GeV$
+    file: kinematics.yaml
+  data_central: data.yaml
+  data_uncertainties:
+  - uncertainties.yaml
+  kinematic_coverage:
+  - zero
+  - m_t2
+  - sqrts
+  plotting:
+    dataset_label: CMS 13 TeV $\sigma_{t\bar{t}}$
+    plot_x: sqrts
+    y_label: '$\sigma_{t\bar{t}}$ ($pb$)'
+  theory:
+    FK_tables:
+    - - CMS_TTBAR_13TEV_TOT_X-SEC

nnpdf_data/commondata/CMS_TTBAR_13TEV_35P9FB-1_TOT/uncertainties.yaml

@@ -0,0 +1,17 @@
+definitions:
+  stat:
+    description: total statistical uncertainty
+    treatment: ADD
+    type: UNCORR
+  sys:
+    description: total systematic uncertainty
+    treatment: MULT
+    type: CORR
+  lumi:
+    description: luminosity uncertainty
+    treatment: MULT
+    type: CMSLUMI16
+bins:
+- stat: 2
+  sys: 25
+  lumi: 20

nnpdf_data/commondata/CMS_TTBAR_5TEV_TOT/metadata.yaml

@@ -43,7 +43,7 @@ implemented_observables:
   - m_t2
   - sqrts
   plotting:
-    dataset_label: CMS 5 TeV $\sigma_{t\bar{t}}$
+    dataset_label: CMS 5.02 TeV $\sigma_{t\bar{t}}$
     plot_x: sqrts
     y_label: '$\sigma_{t\bar{t}}$ ($pb$)'
   theory:

nnpdf_data/commondata/NNPDF_POS_2P24GEV/metadata.yaml

@@ -916,3 +916,63 @@ implemented_observables:
     - - NNPDF_POS_ANTI_UP
     - - NNPDF_POS_ANTI_DUP
   data_uncertainties: []
+- observable_name: F2C-CCP
+  observable:
+    description: Deep Inelastic Scattering
+    label: 'positivity dataset: CC DIS $\bar{c}$ structure function $F_2^{W^+,c}$'
+    units: ''
+  process_type: POS_DIS
+  tables: []
+  npoints: []
+  ndata: 20
+  plotting:
+    dataset_label: 'positivity dataset: CC DIS $\bar{c}$ structure function $F_2^{W^+,c}$'
+    plot_x: x
+  kinematic_coverage:
+  - x
+  - Q2
+  kinematics:
+    variables:
+      x:
+        description: Bjorken x
+        label: x
+        units: ''
+      Q2:
+        description: Factorization Scale
+        label: Q2
+        units: ''
+    file: kinematics_F2C.yaml
+  theory:
+    FK_tables:
+    - - NNPDF_POS_F2C_CCP_40
+  data_uncertainties: []
+- observable_name: F2C-CCE
+  observable:
+    description: Deep Inelastic Scattering
+    label: 'positivity dataset: DIS $c$ structure function $F_2^{W^-,c}$'
+    units: ''
+  process_type: POS_DIS
+  tables: []
+  npoints: []
+  ndata: 20
+  plotting:
+    dataset_label: 'positivity dataset: DIS $c$ structure function $F_2^{W^-,c}$'
+    plot_x: x
+  kinematic_coverage:
+  - x
+  - Q2
+  kinematics:
+    variables:
+      x:
+        description: Bjorken x
+        label: x
+        units: ''
+      Q2:
+        description: Factorization Scale
+        label: Q2
+        units: ''
+    file: kinematics_F2C.yaml
+  theory:
+    FK_tables:
+    - - NNPDF_POS_F2C_CCE_40
+  data_uncertainties: []

nnpdf_data/commondata/dataset_names.yml

@@ -85,7 +85,12 @@ ATLAS_2JET_7TEV_R06:
 CMS_1JET_8TEV:
   dataset: CMS_1JET_8TEV_PTY
   variant: legacy
-CMS_2JET_7TEV: CMS_2JET_7TEV_M12Y
+CMS_2JET_7TEV:
+  dataset: CMS_2JET_7TEV_M12-Y
+  variant: legacy
+CMS_2JET_7TEV_M12Y:
+  dataset: CMS_2JET_7TEV_M12-Y
+  variant: legacy
 HERACOMBCCEM:
   dataset: HERA_CC_318GEV_EM-SIGMARED
   variant: legacy

nnpdf_data/theory_cards/41000010.yaml

@@ -0,0 +1,42 @@
+ID: 41_000_010
+Comments: NNPDF4.1 NNLO QCD-only (xir,xif) = (0.5, 1)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+IterEv: 60
+XIR: 0.5
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

nnpdf_data/theory_cards/41000011.yaml

@@ -0,0 +1,43 @@
+ID: 41_000_011
+Comments: NNPDF4.1 NNLO QCD-only (xir, xif) = (1, 0.5)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+ModSV: expanded
+IterEv: 60
+XIR: 1.0
+XIF: 0.5
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

nnpdf_data/theory_cards/41000012.yaml

@@ -0,0 +1,43 @@
+ID: 41_000_012
+Comments: NNPDF4.1 NNLO QCD-only (xir, xif) = (0.5, 0.5)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+ModSV: expanded
+IterEv: 60
+XIR: 0.5
+XIF: 0.5
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

nnpdf_data/theory_cards/41000013.yaml

@@ -0,0 +1,42 @@
+ID: 41_000_013
+Comments: NNPDF4.1 NNLO QCD-only (xir, xif) = (2, 1)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+IterEv: 60
+XIR: 2.0
+XIF: 1.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

nnpdf_data/theory_cards/41000014.yaml

@@ -0,0 +1,43 @@
+ID: 41_000_014
+Comments: NNPDF4.1 NNLO QCD-only (xir, xif) = (1, 2)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+ModSV: expanded
+IterEv: 60
+XIR: 1.0
+XIF: 2.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

nnpdf_data/theory_cards/41000015.yaml

@@ -0,0 +1,43 @@
+ID: 41_000_015
+Comments: NNPDF4.1 NNLO QCD-only (xir, xif) = (2, 2)
+PTO: 2
+FNS: FONLL-C
+DAMP: 0
+IC: 1
+Q0: 1.65
+ModEv: EXA
+ModSV: expanded
+IterEv: 60
+XIR: 2.0
+XIF: 2.0
+NfFF: 5
+QED: 0
+HQ: POLE
+mc: 1.502
+Qmc: 1.502
+kcThr: 1.0
+mb: 4.936
+Qmb: 4.936
+kbThr: 1.0
+mt: 172.5
+Qmt: 172.5
+ktThr: 1.0
+CKM:
+- 0.97367
+- 0.22431
+- 3.82e-3
+- 0.221
+- 0.975
+- 41.1e-3
+- 8.6e-3
+- 41.5e-3
+- 1.010
+MZ: 91.1880
+MW: 80.3692
+GF: 1.1663788e-5
+SIN2TW: 0.22348
+TMC: 1
+MP: 0.938
+Qref: 91.1880
+alphas: 0.118
+alphaqed: 0.0075700

validphys/_version.py

@@ -1 +1 @@
-__version__ = "4.1.0"
+__version__ = "4.1.1"

validphys/config.py

@@ -911,9 +911,9 @@ class CoreConfig(configparser.Config):
         from validphys import n3fit_data
 
         if diagonal_basis:
-            return n3fit_data._diagonal_masks
+            return n3fit_data.diagonal_masks
         else:
-            return n3fit_data._standard_masks
+            return n3fit_data.standard_masks
 
     @configparser.explicit_node
     def produce_covariance_matrix(self, use_pdferr: bool = False):
@@ -1304,16 +1304,26 @@ class CoreConfig(configparser.Config):
                 thcovmat_present = False
 
         if use_thcovmat_if_present and thcovmat_present:
-            # Expected path of theory covmat hardcoded
-            covmat_path = (
-                fit.path / "tables" / "datacuts_theory_theorycovmatconfig_theory_covmat_custom.csv"
-            )
-            # All possible valid files
+            tables_path = fit.path / "tables"
+            theorycovmatconfig = fit.as_input()["theorycovmatconfig"]
+            user_covmat_path = theorycovmatconfig.get("user_covmat_path", None)
+            point_prescriptions = theorycovmatconfig.get("point_prescriptions", None)
+
+            generic_name = "datacuts_theory_theorycovmatconfig_theory_covmat_custom.csv"
+            if user_covmat_path is not None:
+                # User covmat + point prescriptions
+                if point_prescriptions is not None and point_prescriptions != []:
+                  generic_name = "datacuts_theory_theorycovmatconfig_total_theory_covmat.csv"
+                # Only user covmat
+                else:
+                    generic_name = "datacuts_theory_theorycovmatconfig_user_covmat.csv"
+            covmat_path = tables_path / generic_name
             if not covmat_path.exists():
                 raise ConfigError(
                     "Fit appeared to use theory covmat in fit but the file was not at the "
                     f"usual location: {covmat_path}."
                 )
+            logging.info(f"Using theory covmat in fit: {covmat_path}")
             fit_theory_covmat = ThCovMatSpec(covmat_path)
         else:
             fit_theory_covmat = None
@@ -1411,8 +1421,20 @@ class CoreConfig(configparser.Config):
         """
         Returns a tuple of AddedFilterRule objects. Rules are immutable after parsing.
         AddedFilterRule objects inherit from FilterRule objects.
+        It checks if the rules are unique, i.e. if there are no
+        multiple filters for the same dataset or process with the
+        same fields (`reason` is not used in the comparison).
         """
-        return tuple(AddedFilterRule(**rule) for rule in rules) if rules else None
+        if rules is not None:
+            unique_rules = set(AddedFilterRule(**rule) for rule in rules)
+            if len(unique_rules) != len(rules):
+                raise RuleProcessingError(
+                    "Detected repeated filter rules. Please, make sure that "
+                    " rules are not repeated in the runcard."
+                )
+            return tuple(unique_rules)
+        else:
+            return None
 
     def parse_drop_internal_rules(self, drop_internal_rules: (list, type(None)) = None):
         """Turns drop_internal_rules into a tuple for internal caching."""
@@ -1444,7 +1466,6 @@ class CoreConfig(configparser.Config):
         ``drop_internal_rules``: tuple(dataset names)
             Drop internal dataset-specific rules, it is applied before ``added_filter_rules``
         """
-
         theory_parameters = theoryid.get_description()
 
         if filter_rules is None:
@@ -1476,7 +1497,6 @@ class CoreConfig(configparser.Config):
 
         if added_filter_rules:
             for i, rule in enumerate(added_filter_rules):
-
                 try:
                     rule_list.append(
                         Rule(

validphys/convolution.py

@@ -174,6 +174,7 @@ def _predictions(dataset, pdf, fkfunc):
     return opfunc(*all_predictions)
 
 
+@functools.cache
 def predictions(dataset, pdf):
     """ "Compute theory predictions for a given PDF and dataset. Information
     regading the dataset, on cuts, CFactors and combinations of FKTables is
@@ -225,6 +226,7 @@ def predictions(dataset, pdf):
     return _predictions(dataset, pdf, fk_predictions)
 
 
+@functools.cache
 def central_predictions(
     dataset: validphys.core.DataSetSpec, pdf: validphys.core.PDF
 ) -> pd.DataFrame:
@@ -370,15 +372,28 @@ def _gv_hadron_predictions(loaded_fk, gv1func, gv2func=None):
     # possible x1-x2 combinations (f1, f2, x1, x2)
     luminosity = np.einsum("ijk, ijl->ijkl", expanded_gv1, expanded_gv2)
 
-    def appl(df):
-        # x1 and x2 are encoded as the first and second index levels.
-        xx1 = df.index.get_level_values(1)
-        xx2 = df.index.get_level_values(2)
-        # take the active combinations from the luminosity tensor
-        partial_lumi = luminosity[..., xx1, xx2]
-        return pd.Series(np.einsum("ijk,kj->i", partial_lumi, df.values))
-
-    return sigma.groupby(level=0).apply(appl)
+    if loaded_fk.legacy:
+        # Old FkTables are singled out since they are not always sorted in x1/x2 so matching the
+        # FkTable with the PDF grids (gv1/gv2) is done by means of dataframes, which is slow.
+        # The gv1/gv2 grids are arrays of shape (replicas, flavours<14>, xarray)
+        # the expanded gv1/gv2 instead are shaped according to the channels (which will match)
+        # therefore the luminosity is an array of shape (replicas, channels, x1, x2)
+        def appl(df):
+            # x1 and x2 are encoded as the first and second index levels.
+            xx1 = df.index.get_level_values(1)
+            xx2 = df.index.get_level_values(2)
+            # take the active combinations from the luminosity tensor
+            partial_lumi = luminosity[..., xx1, xx2]
+            return pd.Series(np.einsum("ijk,kj->i", partial_lumi, df.values))
+
+        return sigma.groupby(level=0).apply(appl)
+
+    # Pineappl FkTables are sorted and can be treated as numpy arrays
+    lx = len(xgrid)
+    lc = len(fl1)
+    fktab = sigma.values.reshape(-1, lx, lx, lc)
+    ret = np.einsum("rcab, nabc->nr", luminosity, fktab)
+    return pd.DataFrame(ret, index=loaded_fk.data_index)
 
 
 def _gv_dis_predictions(loaded_fk, gvfunc):
@@ -394,12 +409,20 @@ def _gv_dis_predictions(loaded_fk, gvfunc):
     if sigma.empty:
         return pd.DataFrame(columns=range(gv.shape[0]))
 
-    def appl(df):
-        # x is encoded as the first index level.
-        xind = df.index.get_level_values(1)
-        return pd.Series(np.einsum("ijk,kj->i", gv[:, :, xind], df.values))
+    if loaded_fk.legacy:
+        # Old FkTable are not necessarily sorted in x and need to be treated as dataframes
+        # See comment in `_gv_hadron_predictions` for more details
+        def appl(df):
+            # x is encoded as the first index level.
+            xind = df.index.get_level_values(1)
+            return pd.Series(np.einsum("ijk,kj->i", gv[:, :, xind], df.values))
+
+        return sigma.groupby(level=0).apply(appl)
 
-    return sigma.groupby(level=0).apply(appl)
+    lx = len(xgrid)
+    fktab = sigma.values.reshape(-1, lx, len(fm))
+    ret = np.einsum("rfa, naf->nr", gv, fktab)
+    return pd.DataFrame(ret, index=loaded_fk.data_index)
 
 
 def hadron_predictions(loaded_fk, pdf):

validphys/coredata.py

@@ -57,6 +57,13 @@ class FKTableData:
         The most common use-case is when a total cross section is used
         as a normalization table for a differential cross section,
         in legacy code (<= NNPDF4.0) both fktables would be cut using the differential index.
+
+    data_index: pd.Series
+        index of the data points
+
+    legacy: bool
+        If False, this corresponds to an FkTable read from the old applgrid interface.
+        Deprecated and support will be dropped during the 4.1.X series of tags.
     """
 
     hadronic: bool
@@ -64,9 +71,11 @@ class FKTableData:
     ndata: int
     xgrid: np.ndarray
     sigma: pd.DataFrame
+    data_index: pd.Series
     convolution_types: Optional[tuple[str]] = None
     metadata: dict = dataclasses.field(default_factory=dict, repr=False)
     protected: bool = False
+    legacy: bool = False
 
     def with_cfactor(self, cfactor):
         """Returns a copy of the FKTableData object with cfactors applied to the fktable"""
@@ -124,11 +133,12 @@ class FKTableData:
         newndata = len(cuts)
         try:
             newsigma = self.sigma.loc[cuts]
+            newdata_idx = self.data_index.loc[cuts]
         except KeyError as e:
             # This will be an ugly erorr msg, but it should be scary anyway
             log.error(f"Problem applying cuts to {self.metadata}")
             raise e
-        return dataclasses.replace(self, ndata=newndata, sigma=newsigma)
+        return dataclasses.replace(self, ndata=newndata, sigma=newsigma, data_index=newdata_idx)
 
     @property
     def luminosity_mapping(self):
@@ -169,8 +179,8 @@ class FKTableData:
         # Make the dataframe into a dense numpy array
 
         # First get the data index out of the way
-        # this is necessary because cuts/shifts and for performance reasons
-        # otherwise we will be putting things in a numpy array in very awkward orders
+        # this is necessary because cuts/shifts and because old fktables are not necessarily ordered
+        # in addition, for performance reason, we want to order the np array as (ndata, basis, x1, x2)
         ns = self.sigma.unstack(level=("data",), fill_value=0)
         x1 = ns.index.get_level_values(0)
 
@@ -245,5 +255,5 @@ class CFactorData:
     """
 
     description: str
-    central_value: np.array
-    uncertainty: np.array
+    central_value: np.ndarray
+    uncertainty: np.ndarray