From 727bada1a277c50328be7b80970e1b1c5a51b532 Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Tue, 10 Dec 2024 11:39:45 +0000
Subject: [PATCH 1/9] First commit re-implementation CMS_WCHARM_7TEV

---
 .../commondata/CMS_WCHARM_7TEV/metadata.yaml      | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
index a741e0159d..9286466e5a 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
@@ -1,17 +1,21 @@
 setname: CMS_WCHARM_7TEV
-version: 1
-version_comment: Port of old commondata
+
 nnpdf_metadata:
   nnpdf31_process: DY CC
   experiment: CMS
+
 arXiv:
   url: https://arxiv.org/abs/1310.1138
   journal: JHEP 02 (2014) 013
 iNSPIRE:
-  url: ''
+  url: https://inspirehep.net/literature/1256938
 hepdata:
-  url: ''
-  version: -1
+  url: https://www.hepdata.net/record/ins1256938
+  version: 1
+
+version: 2
+version_comment: Implementation in the new format
+
 implemented_observables:
 - observable_name: WPWM-RATIO
   observable:
@@ -62,6 +66,7 @@ implemented_observables:
       - uncertainties_WPWM-RATIO_sys_10.yaml
   data_central: data_legacy_WPWM-RATIO.yaml
   ported_from: CMSWCHARMRAT
+
 - observable_name: WPWM-TOT
   observable:
     description: Jet Rapidity Distribution

From e4cb7bd32efa66f98f7e3886864e8ffb3584aa70 Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Tue, 10 Dec 2024 14:13:12 +0000
Subject: [PATCH 2/9] Add filter files

---
 .../commondata/CMS_WCHARM_7TEV/filter.py      |  18 ++
 .../CMS_WCHARM_7TEV/filter_utils.py           | 280 ++++++++++++++++++
 .../commondata/CMS_WCHARM_7TEV/metadata.yaml  |  74 ++---
 3 files changed, 327 insertions(+), 45 deletions(-)
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
new file mode 100644
index 0000000000..97444511cb
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
@@ -0,0 +1,18 @@
+'''
+Filter script for CMS_WCHARM_7TEV
+'''
+
+import logging
+
+from filter_utils import Extractor
+import numpy as np
+
+logging.basicConfig(level=logging.INFO, format='[%(levelname)s] %(message)s')
+
+
+if __name__ == "__main__":
+    CMS_WCHARM_TOT = Extractor("./metadata.yaml", "WPWM-TOT", mult_factor=1000)
+    _, _, _ = CMS_WCHARM_TOT.generate_data(variant='default', save_to_yaml=True)
+
+    CMS_WCHARM_RATIO = Extractor("./metadata.yaml", "WPWM-RATIO", mult_factor=1000)
+    _, _, _ = CMS_WCHARM_RATIO.generate_data(variant='default', save_to_yaml=True)
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
new file mode 100644
index 0000000000..78096bafba
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
@@ -0,0 +1,280 @@
+import logging
+
+import numpy as np
+import yaml
+
+from nnpdf_data.filter_utils.utils import prettify_float
+
+yaml.add_representer(float, prettify_float)
+
+SQRTS = 8000
+MW2 = 80.385**2
+CMSLUMI13 = 2.5
+
+# List of systematic uncertainties that shuold
+# be considered uncorrelated
+UNCORR_SYS_UNC = ['UnfoldMCstat', 'UnfoldOtherGen', 'UnfoldReweight']
+ART_LABEL = 'art_corr'
+STAT_LABEL = 'stat_uncorr'
+TABLE_TOKEN = 'Table'
+
+
+class Extractor:
+    """
+    Extracts kinematics, central data, and uncertainties for a given dataset
+
+    Parameters
+    ----------
+    metadata_file: str
+      Path to the metadata file
+    observable: str
+      The name of the observable for which the data is extracted. The name must
+      be listed in the metadata file.
+    """
+
+    def __init__(self, metadata_file, observable, mult_factor=1):
+
+        # Open metadata and select process
+        with open(metadata_file, 'r') as file:
+            metadata = yaml.safe_load(file)
+            self.metadata = next(
+                (
+                    md
+                    for md in metadata["implemented_observables"]
+                    if md['observable_name'] == observable
+                ),
+                None,
+            )
+            if self.metadata is None:
+                raise Exception(f"{observable} is not listed in the metadata file.")
+
+        # Initialise dict of tables
+        self.tables = {}
+        self.observable = observable
+        self.mult_factor = mult_factor
+        self.kin_labels = self.metadata['kinematic_coverage']
+        self.ndata = self.metadata['ndata']
+
+    def __retrieve_table(self, table_id):
+        """
+        Implementation of the lazy loading for the tables. If the table
+        is loaded for the first time, it is stored into an internal
+        container of the class, so that it will not be loaded each time.
+
+        When called, this functions checks if the table has already been stored
+        and, if that is the case, returns the stored table.
+
+        Parameters
+        ----------
+        table_id: int
+          Index that specifies the table
+
+        Return
+        ------
+        The table specified by `table_id`. If not previously loaded, it is also
+        stored into the internal container for future use.
+        """
+        try:
+            table = self.tables[str(table_id)]
+        except KeyError:
+            logging.debug(
+                f'Table {table_id} has not already been used or stored.' f' Storing the table...'
+            )
+            with open(f'./rawdata/{TABLE_TOKEN}{table_id}.yaml', 'r') as tab:
+                tab_dict = yaml.safe_load(tab)
+                self.tables[str(table_id)] = tab_dict
+                table = tab_dict
+        return table
+
+    def __extract_kinematics(self, table: dict):
+        """
+        Extracts the kinematic variables of the single differential
+        distribution given a table.
+
+        For each bin, it computes the max, min, and mid value of the transverse
+        momentum of the boson.
+
+        Parameters
+        ----------
+        table: dict
+          Dictionary containing the bins in the transverse momentum
+        tab_number: int
+          Index to select the range of the second kinematic variable
+
+        Return
+        ------
+        List of bins containing min, max, and mid values for each of the kinematic
+        observables listed in the `kinematic_coverage` of the metadata file.
+
+        """
+        data = table['independent_variables'][0]
+        label = self.kin_labels
+        kinematics = []
+        for bin in data['values']:
+            abs_eta_min = bin['low']
+            abs_eta_max = bin['high']
+            kin_bin = {
+                label[0]: {
+                    'min': abs_eta_min,
+                    'mid': (abs_eta_max + abs_eta_min) / 2,
+                    'max': abs_eta_max,
+                },
+                label[1]: {'min': None, 'mid': MW2, 'max': None},
+            }
+            kinematics.append(kin_bin)
+        return kinematics
+
+    def generate_kinematics(self):
+        """
+        Function that generates the kinematics by looping over all the
+        tables specified in the metadata file. The resulting kinematics
+        is then saved to a yaml file. It relies on the method
+        `__extract_kinematics`.
+        """
+
+        logging.info(f"Generating kinematics for ATLAS_{self.observable}...")
+
+        # Initialise kinematics list
+        kinematics = []
+        ndata = 0
+        table = self.metadata["tables"][0]
+        tab_dict = self.__retrieve_table(table)
+        kin = self.__extract_kinematics(tab_dict)
+        kinematics = np.concatenate([kinematics, kin])
+        ndata += len(kin)
+
+        # Check number of data agrees with metadata
+        try:
+            assert self.metadata['ndata'] is not None
+            assert self.metadata['ndata'] == ndata
+        except AssertionError as e:
+            logging.warning(
+                f"The number of data in the metafile is either wrong or unspecified."
+                f" The correct number is {ndata}. Please, update the metafile."
+            )
+            return
+        return kinematics.tolist()
+
+    def generate_data_and_unc(self, mult_factor=1.0):
+        """
+        Same as `generate_kinematics`, but for central data points.
+        """
+        logging.info(f"Generating central data for CMS_{self.observable}...")
+        dat_central = []
+        stat_unc = []
+        asy_sys_unc = []
+        table = self.metadata['tables'][0]
+        tab_dict = self.__retrieve_table(table)
+
+        # Select data with pT > 25 GeV
+        tab_dict = tab_dict['dependent_variables'][0]['values']
+
+        # Loop over bins
+        for rap_bin in tab_dict:
+            dat_central.append(rap_bin['value'] * mult_factor)
+            stat_unc.append(rap_bin['errors'][0]['symerror'] * mult_factor)
+            asy_sys_unc.append(rap_bin['errors'][1]['symerror'] * mult_factor)
+        return dat_central, stat_unc, asy_sys_unc
+
+    def __build_unc_definitions(self, variant='default'):
+        unc_definitions = {}
+
+        # Statistical uncertainty
+        unc_definitions[STAT_LABEL] = {
+            'description': f'Statistical uncertainty',
+            'treatment': 'ADD',
+            'type': 'UNCORR',
+        }
+
+        if self.observable == 'WPWM-RATIO':
+            unc_definitions['ART_LABEL'] = {
+                'description': f'Correlated systematic uncertainty',
+                'treatment': 'MULT',
+                'type': 'CORR',
+            }
+        elif self.observable == 'WPWM-TOT':
+            for idx in range(self.ndata):
+                unc_definitions[f'{ART_LABEL}_{idx+1}'] = {
+                    'description': f'Correlated systematic uncertainty {idx+1}',
+                    'treatment': 'MULT',
+                    'type': 'CORR',
+                }
+
+        if variant != 'default':
+            raise ValueError(f'The variant {variant} is not implemented yet.')
+
+        return unc_definitions
+
+    def generate_covmat(self, diag_stat_uncs=None):
+        table = self.metadata["tables"][1]
+        tab_dict = self.__retrieve_table(table)
+        matlist = tab_dict['dependent_variables'][0]['values']
+        matlist = [d['value'] for d in matlist]
+        covmat = np.zeros((self.ndata, self.ndata))
+        for i in range(self.ndata):
+            for j in range(self.ndata):
+                covmat[i, j] = matlist[i + self.ndata * j] * diag_stat_uncs[i] * diag_stat_uncs[j]
+        return covmat
+
+    def generate_data(self, variant='default', save_to_yaml=False, path='./'):
+        # Get central data and kinematics
+        central_data, stat_unc, sys_unc = self.generate_data_and_unc(self.mult_factor)
+        kinematics = self.generate_kinematics()
+
+        # Uncertainty definitions
+        unc_definitions = self.__build_unc_definitions(variant=variant)
+        sys_artificial = []  # Initialize vector of artificial uncertainties
+
+        if self.observable == 'WPWM-TOT':
+            covmat = self.generate_covmat(stat_unc)
+            eigvals, eigvecs = np.linalg.eig(covmat)
+            art_unc = np.sqrt(eigvals) * eigvecs
+
+            # Loop over bins
+            for data_idx, data in enumerate(central_data):
+                # Statistical uncertainty
+                unc_dict = {STAT_LABEL: stat_unc[data_idx]}
+                for sys_idx, art_sys in enumerate(art_unc[data_idx, :]):
+                    unc_dict[f'{ART_LABEL}_{sys_idx+1}'] = float(art_sys)
+                sys_artificial.append(unc_dict)
+
+        elif self.observable == 'WPWM-RATIO':
+            for data_idx, data in enumerate(central_data):
+                # Statistical uncertainty
+                unc_dict = {STAT_LABEL: stat_unc[data_idx]}
+                unc_dict[f'{ART_LABEL}'] = sys_unc[data_idx]
+                sys_artificial.append(unc_dict)
+
+        if save_to_yaml:
+            # Save kinematics into file
+            logging.info("Dumping kinematics to file...")
+            kinematics_yaml = {'bins': kinematics}
+            with open(path + self.metadata['kinematics']['file'], 'w') as kin_out_file:
+                yaml.dump(kinematics_yaml, kin_out_file, sort_keys=False)
+            logging.info("Done!")
+
+            # Save central data into file
+            logging.info("Dumping kinematics to file...")
+            dat_central_yaml = {'data_central': central_data}
+            file_name = self.metadata['data_central']
+            with open(path + file_name, 'w') as dat_out_file:
+                yaml.dump(dat_central_yaml, dat_out_file, sort_keys=False)
+            logging.info("Done!")
+
+            # Save unertainties
+            logging.info("Dumping kinematics to file...")
+            uncertainties_yaml = {'definitions': unc_definitions, 'bins': sys_artificial}
+            file_name = (
+                self.metadata['data_uncertainties'][0]
+                if variant == 'default'
+                else self.metadata['variants'][variant]['data_uncertainties'][0]
+            )
+            with open(path + file_name, 'w') as dat_out_file:
+                yaml.dump(uncertainties_yaml, dat_out_file, sort_keys=False)
+            logging.info("Done!")
+            return kinematics, central_data, sys_artificial
+        else:
+            return kinematics, central_data, sys_artificial
+
+    def get_table(self, table_id):
+        return self.__retrieve_table(table_id)
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
index 9286466e5a..2e60beeb07 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/metadata.yaml
@@ -21,42 +21,35 @@ implemented_observables:
   observable:
     description: Jet Rapidity Distribution
     label: CMS $W+c$ ratio
-    units: ''
-  process_type: EWJ_RAP
-  tables: []
-  npoints: []
+    units: '[fb]'
+  process_type: DY_W_ETA
+  tables: [9]
   ndata: 5
   plotting:
     kinematics_override: ewj_rap_sqrt_scale
     dataset_label: CMS $W+c$ ratio
     y_label: $\sigma(W^+ + \bar{c})/\sigma(W^- + c)$
-    plot_x: k1
-  kinematic_coverage:
-  - k1
-  - k2
-  - k3
+    plot_x: abs_eta
+  kinematic_coverage: [abs_eta, m_W2]
   kinematics:
     variables:
-      k1:
-        description: Variable k1
-        label: k1
-        units: ''
-      k2:
-        description: Variable k2
-        label: k2
-        units: ''
-      k3:
-        description: Variable k3
-        label: k3
+      abs_eta:
+        description: Absolute pseudo-rapidity of the Z boson
+        label: $|\eta|$
         units: ''
+      m_W2:
+        description: Mass of the W boson squared
+        label: $m_W^2$
+        units: GeV$^{2}$
     file: kinematics_WPWM-RATIO.yaml
+  data_central: data_WPWM-RATIO.yaml
+  data_uncertainties: [uncertainties_WPWM-RATIO.yaml]
   theory:
     conversion_factor: 1.0
     operation: ratio
     FK_tables:
     - - CMSWCHARMRAT-CMSWCHARM-WpCb-eta4
     - - CMSWCHARMRAT-CMSWCHARM-WmC-eta3
-  data_uncertainties: []
   variants:
     legacy:
       data_uncertainties:
@@ -64,41 +57,34 @@ implemented_observables:
     legacy_10:
       data_uncertainties:
       - uncertainties_WPWM-RATIO_sys_10.yaml
-  data_central: data_legacy_WPWM-RATIO.yaml
   ported_from: CMSWCHARMRAT
 
 - observable_name: WPWM-TOT
   observable:
-    description: Jet Rapidity Distribution
+    description: identity
     label: CMS $W+c$ total
-    units: ''
-  process_type: EWJ_RAP
-  tables: []
-  npoints: []
+    units: '[fb]'
+  process_type: DY_W_ETA
+  tables: [5, 6]
   ndata: 5
   plotting:
-    kinematics_override: ewj_rap_sqrt_scale
+    kinematics_override: identity
     dataset_label: CMS $W+c$ total
     y_label: $d\sigma(W+c)/d|\eta_l|$ (fb)
     plot_x: k1
-  kinematic_coverage:
-  - k1
-  - k2
-  - k3
+  kinematic_coverage: [abs_eta, m_W2]
+  data_uncertainties: [uncertainties_WPWM-TOT.yaml]
+  data_central: data_WPWM-TOT.yaml
   kinematics:
     variables:
-      k1:
-        description: Variable k1
-        label: k1
-        units: ''
-      k2:
-        description: Variable k2
-        label: k2
-        units: ''
-      k3:
-        description: Variable k3
-        label: k3
+      abs_eta:
+        description: Absolute pseudo-rapidity of the Z boson
+        label: $|\eta|$
         units: ''
+      m_W2:
+        description: Mass of the W boson squared
+        label: $m_W^2$
+        units: GeV$^{2}$
     file: kinematics_WPWM-TOT.yaml
   theory:
     conversion_factor: 1.0
@@ -106,7 +92,6 @@ implemented_observables:
     FK_tables:
     - - CMSWCHARM-CMSWCHARM-WmC-eta3
     - - CMSWCHARM-CMSWCHARM-WpCb-eta4
-  data_uncertainties: []
   variants:
     legacy:
       data_uncertainties:
@@ -114,5 +99,4 @@ implemented_observables:
     legacy_10:
       data_uncertainties:
       - uncertainties_WPWM-TOT_sys_10.yaml
-  data_central: data_legacy_WPWM-TOT.yaml
   ported_from: CMSWCHARMTOT

From 962643784f3bf10c61c042da2841eed6eef7c4fb Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Tue, 10 Dec 2024 14:14:11 +0000
Subject: [PATCH 3/9] Add generated files

---
 .../CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml      |  6 ++
 .../CMS_WCHARM_7TEV/data_WPWM-TOT.yaml        |  6 ++
 .../CMS_WCHARM_7TEV/rawdata/Table5.yaml       | 69 ++++++++++++++
 .../CMS_WCHARM_7TEV/rawdata/Table6.yaml       | 91 +++++++++++++++++++
 .../CMS_WCHARM_7TEV/rawdata/Table9.yaml       | 69 ++++++++++++++
 .../uncertainties_WPWM-RATIO.yaml             | 20 ++++
 .../uncertainties_WPWM-TOT.yaml               | 56 ++++++++++++
 7 files changed, 317 insertions(+)
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-TOT.yaml
 create mode 100755 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table5.yaml
 create mode 100755 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table6.yaml
 create mode 100755 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table9.yaml
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
 create mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
new file mode 100644
index 0000000000..4b4660e02d
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
@@ -0,0 +1,6 @@
+data_central:
+- 1.01300000e+03
+- 960.0
+- 897.0
+- 1062.0
+- 776.0
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-TOT.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-TOT.yaml
new file mode 100644
index 0000000000..328dc6c22b
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-TOT.yaml
@@ -0,0 +1,6 @@
+data_central:
+- 68700.0
+- 59900.0
+- 56700.0
+- 44800.0
+- 35100.0
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table5.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table5.yaml
new file mode 100755
index 0000000000..2d329707b5
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table5.yaml
@@ -0,0 +1,69 @@
+dependent_variables:
+- header: {name: D(SIG)/DABS(ETARAP(LEPTON)), units: PB}
+  qualifiers:
+  - {name: ABS(ETARAP(JET)), value: < 2.5}
+  - {name: JETS, value: 'ANTI-KT, R=1'}
+  - {name: PT(JET), units: GEV, value: '> 25'}
+  - {name: PT(LEPTON), units: GEV, value: '> 25'}
+  - {name: RE, value: P P --> W+ < LEPTON+ NU > CHARMBAR X}
+  - {name: RE, value: P P --> W- < LEPTON- NUBAR > CHARM X}
+  - {name: SQRT(S), units: GeV, value: '7000.0'}
+  values:
+  - errors:
+    - {label: stat, symerror: 2.7}
+    - {label: sys, symerror: 4.6}
+    value: 68.7
+  - errors:
+    - {label: stat, symerror: 2.5}
+    - {label: sys, symerror: 4.0}
+    value: 59.9
+  - errors:
+    - {label: stat, symerror: 2.4}
+    - {label: sys, symerror: 3.8}
+    value: 56.7
+  - errors:
+    - {label: stat, symerror: 1.9}
+    - {label: sys, symerror: 3.2}
+    value: 44.8
+  - errors:
+    - {label: stat, symerror: 1.7}
+    - {label: sys, symerror: 2.4}
+    value: 35.1
+- header: {name: D(SIG)/DABS(ETARAP(LEPTON)), units: PB}
+  qualifiers:
+  - {name: ABS(ETARAP(JET)), value: < 2.5}
+  - {name: JETS, value: 'ANTI-KT, R=1'}
+  - {name: PT(JET), units: GEV, value: '> 25'}
+  - {name: PT(LEPTON), units: GEV, value: '> 35'}
+  - {name: RE, value: P P --> W+ < LEPTON+ NU > CHARMBAR X}
+  - {name: RE, value: P P --> W- < LEPTON- NUBAR > CHARM X}
+  - {name: SQRT(S), units: GeV, value: '7000.0'}
+  values:
+  - errors:
+    - {label: stat, symerror: 1.7}
+    - {label: sys, symerror: 3.2}
+    value: 52.3
+  - errors:
+    - {label: stat, symerror: 1.6}
+    - {label: sys, symerror: 3.0}
+    value: 49.2
+  - errors:
+    - {label: stat, symerror: 1.5}
+    - {label: sys, symerror: 2.7}
+    value: 45.5
+  - errors:
+    - {label: stat, symerror: 1.2}
+    - {label: sys, symerror: 2.1}
+    value: 34.2
+  - errors:
+    - {label: stat, symerror: 1.0}
+    - {label: sys, symerror: 1.7}
+    value: 26.6
+independent_variables:
+- header: {name: ABS(ETARAP(LEPTON))}
+  values:
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table6.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table6.yaml
new file mode 100755
index 0000000000..5ea79d8856
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table6.yaml
@@ -0,0 +1,91 @@
+dependent_variables:
+- header: {name: ''}
+  qualifiers:
+  - {name: ABS(ETARAP(JET)), value: < 2.5}
+  - {name: JETS, value: 'ANTI-KT, R=1'}
+  - {name: PT(JET), units: GEV, value: '> 25'}
+  - {name: PT(LEPTON), units: GEV, value: '> 25'}
+  - {name: RE, value: P P --> W+ < LEPTON+ NU > CHARMBAR X}
+  - {name: RE, value: P P --> W- < LEPTON- NUBAR > CHARM X}
+  - {name: SQRT(S), units: GeV, value: '7000.0'}
+  values:
+  - {value: 1.0}
+  - {value: 0.77}
+  - {value: 0.78}
+  - {value: 0.76}
+  - {value: 0.72}
+  - {value: 0.77}
+  - {value: 1.0}
+  - {value: 0.76}
+  - {value: 0.74}
+  - {value: 0.7}
+  - {value: 0.78}
+  - {value: 0.76}
+  - {value: 1.0}
+  - {value: 0.74}
+  - {value: 0.7}
+  - {value: 0.76}
+  - {value: 0.74}
+  - {value: 0.74}
+  - {value: 1.0}
+  - {value: 0.69}
+  - {value: 0.72}
+  - {value: 0.7}
+  - {value: 0.7}
+  - {value: 0.69}
+  - {value: 1.0}
+independent_variables:
+- header: {name: ABS(ETARAP(LEPTON))}
+  values:
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+- header: {name: ABS(ETARAP(LEPTON))}
+  values:
+  - {high: 0.35, low: 0.0}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 0.7, low: 0.35}
+  - {high: 0.7, low: 0.35}
+  - {high: 0.7, low: 0.35}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 1.6, low: 1.1}
+  - {high: 1.6, low: 1.1}
+  - {high: 1.6, low: 1.1}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
+  - {high: 2.1, low: 1.6}
+  - {high: 2.1, low: 1.6}
+  - {high: 2.1, low: 1.6}
+  - {high: 2.1, low: 1.6}
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table9.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table9.yaml
new file mode 100755
index 0000000000..f260ee1f54
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/rawdata/Table9.yaml
@@ -0,0 +1,69 @@
+dependent_variables:
+- header: {name: SIG(W+ CHARMBAR) / SIG(W- CHARM)}
+  qualifiers:
+  - {name: ABS(ETARAP(JET)), value: < 2.5}
+  - {name: JETS, value: 'ANTI-KT, R=1'}
+  - {name: PT(JET), units: GEV, value: '> 25'}
+  - {name: PT(LEPTON), units: GEV, value: '> 25'}
+  - {name: RE(W+ CHARMBAR), value: P P --> W+ < LEPTON+ NU > CHARMBAR X}
+  - {name: RE(W- CHARM), value: P P --> W- < LEPTON- NUBAR > CHARM X}
+  - {name: SQRT(S), units: GeV, value: '7000.0'}
+  values:
+  - errors:
+    - {label: stat, symerror: 0.052}
+    - {label: sys, symerror: 0.005}
+    value: 1.013
+  - errors:
+    - {label: stat, symerror: 0.053}
+    - {label: sys, symerror: 0.005}
+    value: 0.96
+  - errors:
+    - {label: stat, symerror: 0.051}
+    - {label: sys, symerror: 0.008}
+    value: 0.897
+  - errors:
+    - {label: stat, symerror: 0.061}
+    - {label: sys, symerror: 0.014}
+    value: 1.062
+  - errors:
+    - {label: stat, symerror: 0.058}
+    - {label: sys, symerror: 0.016}
+    value: 0.776
+- header: {name: SIG(W+ CHARMBAR) / SIG(W- CHARM)}
+  qualifiers:
+  - {name: ABS(ETARAP(JET)), value: < 2.5}
+  - {name: JETS, value: 'ANTI-KT, R=1'}
+  - {name: PT(JET), units: GEV, value: '> 25'}
+  - {name: PT(LEPTON), units: GEV, value: '> 35'}
+  - {name: RE(W+ CHARMBAR), value: P P --> W+ < LEPTON+ NU > CHARMBAR X}
+  - {name: RE(W- CHARM), value: P P --> W- < LEPTON- NUBAR > CHARM X}
+  - {name: SQRT(S), units: GeV, value: '7000.0'}
+  values:
+  - errors:
+    - {label: stat, symerror: 0.041}
+    - {label: sys, symerror: 0.007}
+    value: 0.993
+  - errors:
+    - {label: stat, symerror: 0.039}
+    - {label: sys, symerror: 0.007}
+    value: 0.977
+  - errors:
+    - {label: stat, symerror: 0.04}
+    - {label: sys, symerror: 0.008}
+    value: 0.927
+  - errors:
+    - {label: stat, symerror: 0.046}
+    - {label: sys, symerror: 0.01}
+    value: 0.948
+  - errors:
+    - {label: stat, symerror: 0.05}
+    - {label: sys, symerror: 0.011}
+    value: 0.784
+independent_variables:
+- header: {name: ABS(ETARAP(LEPTON))}
+  values:
+  - {high: 0.35, low: 0.0}
+  - {high: 0.7, low: 0.35}
+  - {high: 1.1, low: 0.7}
+  - {high: 1.6, low: 1.1}
+  - {high: 2.1, low: 1.6}
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
new file mode 100644
index 0000000000..b3b6336a7f
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
@@ -0,0 +1,20 @@
+definitions:
+  stat_uncorr:
+    description: Statistical uncertainty
+    treatment: ADD
+    type: UNCORR
+  ART_LABEL:
+    description: Correlated systematic uncertainty
+    treatment: MULT
+    type: CORR
+bins:
+- stat_uncorr: 52.0
+  art_corr: 5.0
+- stat_uncorr: 53.0
+  art_corr: 5.0
+- stat_uncorr: 51.0
+  art_corr: 8.0
+- stat_uncorr: 61.0
+  art_corr: 14.0
+- stat_uncorr: 58.0
+  art_corr: 16.0
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml
new file mode 100644
index 0000000000..d53545763f
--- /dev/null
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml
@@ -0,0 +1,56 @@
+definitions:
+  stat_uncorr:
+    description: Statistical uncertainty
+    treatment: ADD
+    type: UNCORR
+  art_corr_1:
+    description: Correlated systematic uncertainty 1
+    treatment: MULT
+    type: CORR
+  art_corr_2:
+    description: Correlated systematic uncertainty 2
+    treatment: MULT
+    type: CORR
+  art_corr_3:
+    description: Correlated systematic uncertainty 3
+    treatment: MULT
+    type: CORR
+  art_corr_4:
+    description: Correlated systematic uncertainty 4
+    treatment: MULT
+    type: CORR
+  art_corr_5:
+    description: Correlated systematic uncertainty 5
+    treatment: MULT
+    type: CORR
+bins:
+- stat_uncorr: 2700.0
+  art_corr_1: -2.50638824e+03
+  art_corr_2: -7.95697332e+02
+  art_corr_3: 5.18818026e+02
+  art_corr_4: 3.24524090e+02
+  art_corr_5: 1.98921572e+01
+- stat_uncorr: 2500.0
+  art_corr_1: -2.26430174e+03
+  art_corr_2: 9.54417285e+02
+  art_corr_3: 3.80750387e+02
+  art_corr_4: 2.58001370e+02
+  art_corr_5: 2.21295434e+01
+- stat_uncorr: 2400.0
+  art_corr_1: -2.16891682e+03
+  art_corr_2: -4.98172990e+01
+  art_corr_3: -9.87453634e+02
+  art_corr_4: 2.78677305e+02
+  art_corr_5: 2.43385786e+01
+- stat_uncorr: 1900.0
+  art_corr_1: -1.64250437e+03
+  art_corr_2: -1.68762567e+01
+  art_corr_3: -1.03617739e+01
+  art_corr_4: -6.53762602e+02
+  art_corr_5: -6.95975341e+02
+- stat_uncorr: 1700.0
+  art_corr_1: -1.39269626e+03
+  art_corr_2: -2.22542263e+01
+  art_corr_3: -2.70634325e+00
+  art_corr_4: -6.66474311e+02
+  art_corr_5: 7.11130479e+02

From a11c031afaf757818fde8e0cf18cea42b76f3e57 Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Tue, 10 Dec 2024 14:18:31 +0000
Subject: [PATCH 4/9] Correct bug

---
 .../CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml      | 10 +--
 .../commondata/CMS_WCHARM_7TEV/filter.py      |  2 +-
 .../kinematics_WPWM-RATIO.yaml                | 72 +++++++------------
 .../CMS_WCHARM_7TEV/kinematics_WPWM-TOT.yaml  | 72 +++++++------------
 .../uncertainties_WPWM-RATIO.yaml             | 20 +++---
 5 files changed, 68 insertions(+), 108 deletions(-)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
index 4b4660e02d..7454c33d79 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_WPWM-RATIO.yaml
@@ -1,6 +1,6 @@
 data_central:
-- 1.01300000e+03
-- 960.0
-- 897.0
-- 1062.0
-- 776.0
+- 1.013
+- 0.96
+- 0.897
+- 1.062
+- 0.776
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
index 97444511cb..365a92a2d3 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
@@ -14,5 +14,5 @@
     CMS_WCHARM_TOT = Extractor("./metadata.yaml", "WPWM-TOT", mult_factor=1000)
     _, _, _ = CMS_WCHARM_TOT.generate_data(variant='default', save_to_yaml=True)
 
-    CMS_WCHARM_RATIO = Extractor("./metadata.yaml", "WPWM-RATIO", mult_factor=1000)
+    CMS_WCHARM_RATIO = Extractor("./metadata.yaml", "WPWM-RATIO", mult_factor=1.0)
     _, _, _ = CMS_WCHARM_RATIO.generate_data(variant='default', save_to_yaml=True)
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-RATIO.yaml
index d56da464e5..b3549529e5 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-RATIO.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-RATIO.yaml
@@ -1,61 +1,41 @@
 bins:
-- k1:
-    min: null
+- abs_eta:
+    min: 0.0
     mid: 0.175
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
-    min: null
-    mid: 7000.0
-    max: null
-- k1:
-    min: null
-    mid: 0.525
-    max: null
-  k2:
+    max: 0.35
+  m_W2:
     min: null
-    mid: 6463.838404
+    mid: 6.46174823e+03
     max: null
-  k3:
+- abs_eta:
+    min: 0.35
+    mid: 5.25000000e-01
+    max: 0.7
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 0.7
     mid: 0.9
-    max: null
-  k2:
+    max: 1.1
+  m_W2:
     min: null
-    mid: 6463.838404
+    mid: 6.46174823e+03
     max: null
-  k3:
-    min: null
-    mid: 7000.0
-    max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 1.1
     mid: 1.35
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
+    max: 1.6
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 1.6
     mid: 1.85
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
+    max: 2.1
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-TOT.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-TOT.yaml
index d56da464e5..b3549529e5 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-TOT.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/kinematics_WPWM-TOT.yaml
@@ -1,61 +1,41 @@
 bins:
-- k1:
-    min: null
+- abs_eta:
+    min: 0.0
     mid: 0.175
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
-    min: null
-    mid: 7000.0
-    max: null
-- k1:
-    min: null
-    mid: 0.525
-    max: null
-  k2:
+    max: 0.35
+  m_W2:
     min: null
-    mid: 6463.838404
+    mid: 6.46174823e+03
     max: null
-  k3:
+- abs_eta:
+    min: 0.35
+    mid: 5.25000000e-01
+    max: 0.7
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 0.7
     mid: 0.9
-    max: null
-  k2:
+    max: 1.1
+  m_W2:
     min: null
-    mid: 6463.838404
+    mid: 6.46174823e+03
     max: null
-  k3:
-    min: null
-    mid: 7000.0
-    max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 1.1
     mid: 1.35
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
+    max: 1.6
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
-- k1:
-    min: null
+- abs_eta:
+    min: 1.6
     mid: 1.85
-    max: null
-  k2:
-    min: null
-    mid: 6463.838404
-    max: null
-  k3:
+    max: 2.1
+  m_W2:
     min: null
-    mid: 7000.0
+    mid: 6.46174823e+03
     max: null
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
index b3b6336a7f..64740a4566 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-RATIO.yaml
@@ -8,13 +8,13 @@ definitions:
     treatment: MULT
     type: CORR
 bins:
-- stat_uncorr: 52.0
-  art_corr: 5.0
-- stat_uncorr: 53.0
-  art_corr: 5.0
-- stat_uncorr: 51.0
-  art_corr: 8.0
-- stat_uncorr: 61.0
-  art_corr: 14.0
-- stat_uncorr: 58.0
-  art_corr: 16.0
+- stat_uncorr: 0.052
+  art_corr: 0.005
+- stat_uncorr: 0.053
+  art_corr: 0.005
+- stat_uncorr: 0.051
+  art_corr: 0.008
+- stat_uncorr: 0.061
+  art_corr: 0.014
+- stat_uncorr: 0.058
+  art_corr: 0.016

From b75c99d98ec539ee293f65fdb64dead79e74c6be Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Tue, 10 Dec 2024 14:32:05 +0000
Subject: [PATCH 5/9] Remove legacy data

---
 .../commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-RATIO.yaml  | 6 ------
 .../commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-TOT.yaml    | 6 ------
 2 files changed, 12 deletions(-)
 delete mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-RATIO.yaml
 delete mode 100644 nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-TOT.yaml

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-RATIO.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-RATIO.yaml
deleted file mode 100644
index 7454c33d79..0000000000
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-RATIO.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-data_central:
-- 1.013
-- 0.96
-- 0.897
-- 1.062
-- 0.776
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-TOT.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-TOT.yaml
deleted file mode 100644
index 328dc6c22b..0000000000
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/data_legacy_WPWM-TOT.yaml
+++ /dev/null
@@ -1,6 +0,0 @@
-data_central:
-- 68700.0
-- 59900.0
-- 56700.0
-- 44800.0
-- 35100.0

From 5a8e2cb44aa936b4a9e8d50474778d970e77cc0f Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Fri, 13 Dec 2024 10:08:18 +0000
Subject: [PATCH 6/9] Change artificial uncertainties from MUL to ADD

---
 .../CMS_WCHARM_7TEV/filter_utils.py           | 10 ++--
 .../uncertainties_WPWM-TOT.yaml               | 60 +++++++++----------
 2 files changed, 36 insertions(+), 34 deletions(-)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
index 78096bafba..e6e33eb232 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
@@ -196,7 +196,7 @@ def __build_unc_definitions(self, variant='default'):
             for idx in range(self.ndata):
                 unc_definitions[f'{ART_LABEL}_{idx+1}'] = {
                     'description': f'Correlated systematic uncertainty {idx+1}',
-                    'treatment': 'MULT',
+                    'treatment': 'ADD',
                     'type': 'CORR',
                 }
 
@@ -205,7 +205,7 @@ def __build_unc_definitions(self, variant='default'):
 
         return unc_definitions
 
-    def generate_covmat(self, diag_stat_uncs=None):
+    def generate_covmat(self, diag_uncs=None):
         table = self.metadata["tables"][1]
         tab_dict = self.__retrieve_table(table)
         matlist = tab_dict['dependent_variables'][0]['values']
@@ -213,7 +213,7 @@ def generate_covmat(self, diag_stat_uncs=None):
         covmat = np.zeros((self.ndata, self.ndata))
         for i in range(self.ndata):
             for j in range(self.ndata):
-                covmat[i, j] = matlist[i + self.ndata * j] * diag_stat_uncs[i] * diag_stat_uncs[j]
+                covmat[i, j] = matlist[i + self.ndata * j] * diag_uncs[i] * diag_uncs[j]
         return covmat
 
     def generate_data(self, variant='default', save_to_yaml=False, path='./'):
@@ -226,7 +226,7 @@ def generate_data(self, variant='default', save_to_yaml=False, path='./'):
         sys_artificial = []  # Initialize vector of artificial uncertainties
 
         if self.observable == 'WPWM-TOT':
-            covmat = self.generate_covmat(stat_unc)
+            covmat = self.generate_covmat(sys_unc)
             eigvals, eigvecs = np.linalg.eig(covmat)
             art_unc = np.sqrt(eigvals) * eigvecs
 
@@ -242,6 +242,8 @@ def generate_data(self, variant='default', save_to_yaml=False, path='./'):
             for data_idx, data in enumerate(central_data):
                 # Statistical uncertainty
                 unc_dict = {STAT_LABEL: stat_unc[data_idx]}
+
+                # Systematic uncertainty
                 unc_dict[f'{ART_LABEL}'] = sys_unc[data_idx]
                 sys_artificial.append(unc_dict)
 
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml
index d53545763f..19e422c314 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/uncertainties_WPWM-TOT.yaml
@@ -5,52 +5,52 @@ definitions:
     type: UNCORR
   art_corr_1:
     description: Correlated systematic uncertainty 1
-    treatment: MULT
+    treatment: ADD
     type: CORR
   art_corr_2:
     description: Correlated systematic uncertainty 2
-    treatment: MULT
+    treatment: ADD
     type: CORR
   art_corr_3:
     description: Correlated systematic uncertainty 3
-    treatment: MULT
+    treatment: ADD
     type: CORR
   art_corr_4:
     description: Correlated systematic uncertainty 4
-    treatment: MULT
+    treatment: ADD
     type: CORR
   art_corr_5:
     description: Correlated systematic uncertainty 5
-    treatment: MULT
+    treatment: ADD
     type: CORR
 bins:
 - stat_uncorr: 2700.0
-  art_corr_1: -2.50638824e+03
-  art_corr_2: -7.95697332e+02
-  art_corr_3: 5.18818026e+02
-  art_corr_4: 3.24524090e+02
-  art_corr_5: 1.98921572e+01
+  art_corr_1: -4.30085960e+03
+  art_corr_2: 1.48958525e+02
+  art_corr_3: -1.49014534e+03
+  art_corr_4: -3.33760715e+02
+  art_corr_5: 5.55417584e+02
 - stat_uncorr: 2500.0
-  art_corr_1: -2.26430174e+03
-  art_corr_2: 9.54417285e+02
-  art_corr_3: 3.80750387e+02
-  art_corr_4: 2.58001370e+02
-  art_corr_5: 2.21295434e+01
+  art_corr_1: -3.61128670e+03
+  art_corr_2: 1.46245103e+02
+  art_corr_3: 1.37172210e+03
+  art_corr_4: -3.95171209e+02
+  art_corr_5: 9.48387525e+02
 - stat_uncorr: 2400.0
-  art_corr_1: -2.16891682e+03
-  art_corr_2: -4.98172990e+01
-  art_corr_3: -9.87453634e+02
-  art_corr_4: 2.78677305e+02
-  art_corr_5: 2.43385786e+01
+  art_corr_1: -3.42032648e+03
+  art_corr_2: 1.58201894e+02
+  art_corr_3: 2.94011007e+02
+  art_corr_4: -5.54441014e+02
+  art_corr_5: -1.52397231e+03
 - stat_uncorr: 1900.0
-  art_corr_1: -1.64250437e+03
-  art_corr_2: -1.68762567e+01
-  art_corr_3: -1.03617739e+01
-  art_corr_4: -6.53762602e+02
-  art_corr_5: -6.95975341e+02
+  art_corr_1: -2.77487954e+03
+  art_corr_2: 3.53874801e+02
+  art_corr_3: 1.26728625e+02
+  art_corr_4: 1.53882437e+03
+  art_corr_5: -1.75429767e+02
 - stat_uncorr: 1700.0
-  art_corr_1: -1.39269626e+03
-  art_corr_2: -2.22542263e+01
-  art_corr_3: -2.70634325e+00
-  art_corr_4: -6.66474311e+02
-  art_corr_5: 7.11130479e+02
+  art_corr_1: -1.94086828e+03
+  art_corr_2: -1.38692811e+03
+  art_corr_3: 5.04690564e+01
+  art_corr_4: 2.51872601e+02
+  art_corr_5: -5.89390783e+01

From 40b42e8b9b16b266d5c2a6e33f9052127839054a Mon Sep 17 00:00:00 2001
From: Amedeo Chiefa <103528316+achiefa@users.noreply.github.com>
Date: Wed, 18 Dec 2024 11:42:51 +0100
Subject: [PATCH 7/9] Remove `save_to_yaml` and variant

---
 .../commondata/CMS_WCHARM_7TEV/filter.py      |  4 +-
 .../CMS_WCHARM_7TEV/filter_utils.py           | 77 ++++++++-----------
 2 files changed, 33 insertions(+), 48 deletions(-)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
index 365a92a2d3..8ce27320c6 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
@@ -12,7 +12,7 @@
 
 if __name__ == "__main__":
     CMS_WCHARM_TOT = Extractor("./metadata.yaml", "WPWM-TOT", mult_factor=1000)
-    _, _, _ = CMS_WCHARM_TOT.generate_data(variant='default', save_to_yaml=True)
+    CMS_WCHARM_TOT.generate_data()
 
     CMS_WCHARM_RATIO = Extractor("./metadata.yaml", "WPWM-RATIO", mult_factor=1.0)
-    _, _, _ = CMS_WCHARM_RATIO.generate_data(variant='default', save_to_yaml=True)
+    CMS_WCHARM_RATIO.generate_data()
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
index e6e33eb232..097d5dc0de 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
@@ -7,13 +7,9 @@
 
 yaml.add_representer(float, prettify_float)
 
-SQRTS = 8000
 MW2 = 80.385**2
 CMSLUMI13 = 2.5
 
-# List of systematic uncertainties that shuold
-# be considered uncorrelated
-UNCORR_SYS_UNC = ['UnfoldMCstat', 'UnfoldOtherGen', 'UnfoldReweight']
 ART_LABEL = 'art_corr'
 STAT_LABEL = 'stat_uncorr'
 TABLE_TOKEN = 'Table'
@@ -98,8 +94,6 @@ def __extract_kinematics(self, table: dict):
         ----------
         table: dict
           Dictionary containing the bins in the transverse momentum
-        tab_number: int
-          Index to select the range of the second kinematic variable
 
         Return
         ------
@@ -176,7 +170,7 @@ def generate_data_and_unc(self, mult_factor=1.0):
             asy_sys_unc.append(rap_bin['errors'][1]['symerror'] * mult_factor)
         return dat_central, stat_unc, asy_sys_unc
 
-    def __build_unc_definitions(self, variant='default'):
+    def __build_unc_definitions(self):
         unc_definitions = {}
 
         # Statistical uncertainty
@@ -200,9 +194,6 @@ def __build_unc_definitions(self, variant='default'):
                     'type': 'CORR',
                 }
 
-        if variant != 'default':
-            raise ValueError(f'The variant {variant} is not implemented yet.')
-
         return unc_definitions
 
     def generate_covmat(self, diag_uncs=None):
@@ -216,13 +207,13 @@ def generate_covmat(self, diag_uncs=None):
                 covmat[i, j] = matlist[i + self.ndata * j] * diag_uncs[i] * diag_uncs[j]
         return covmat
 
-    def generate_data(self, variant='default', save_to_yaml=False, path='./'):
+    def generate_data(self):
         # Get central data and kinematics
         central_data, stat_unc, sys_unc = self.generate_data_and_unc(self.mult_factor)
         kinematics = self.generate_kinematics()
 
         # Uncertainty definitions
-        unc_definitions = self.__build_unc_definitions(variant=variant)
+        unc_definitions = self.__build_unc_definitions()
         sys_artificial = []  # Initialize vector of artificial uncertainties
 
         if self.observable == 'WPWM-TOT':
@@ -246,37 +237,31 @@ def generate_data(self, variant='default', save_to_yaml=False, path='./'):
                 # Systematic uncertainty
                 unc_dict[f'{ART_LABEL}'] = sys_unc[data_idx]
                 sys_artificial.append(unc_dict)
-
-        if save_to_yaml:
-            # Save kinematics into file
-            logging.info("Dumping kinematics to file...")
-            kinematics_yaml = {'bins': kinematics}
-            with open(path + self.metadata['kinematics']['file'], 'w') as kin_out_file:
-                yaml.dump(kinematics_yaml, kin_out_file, sort_keys=False)
-            logging.info("Done!")
-
-            # Save central data into file
-            logging.info("Dumping kinematics to file...")
-            dat_central_yaml = {'data_central': central_data}
-            file_name = self.metadata['data_central']
-            with open(path + file_name, 'w') as dat_out_file:
-                yaml.dump(dat_central_yaml, dat_out_file, sort_keys=False)
-            logging.info("Done!")
-
-            # Save unertainties
-            logging.info("Dumping kinematics to file...")
-            uncertainties_yaml = {'definitions': unc_definitions, 'bins': sys_artificial}
-            file_name = (
-                self.metadata['data_uncertainties'][0]
-                if variant == 'default'
-                else self.metadata['variants'][variant]['data_uncertainties'][0]
-            )
-            with open(path + file_name, 'w') as dat_out_file:
-                yaml.dump(uncertainties_yaml, dat_out_file, sort_keys=False)
-            logging.info("Done!")
-            return kinematics, central_data, sys_artificial
-        else:
-            return kinematics, central_data, sys_artificial
-
-    def get_table(self, table_id):
-        return self.__retrieve_table(table_id)
+        
+        # Local path for yaml files
+        path='./'
+
+        # Save kinematics into file
+        logging.info("Dumping kinematics to file...")
+        kinematics_yaml = {'bins': kinematics}
+        with open(path + self.metadata['kinematics']['file'], 'w') as kin_out_file:
+            yaml.dump(kinematics_yaml, kin_out_file, sort_keys=False)
+        logging.info("Done!")
+
+        # Save central data into file
+        logging.info("Dumping kinematics to file...")
+        dat_central_yaml = {'data_central': central_data}
+        file_name = self.metadata['data_central']
+        with open(path + file_name, 'w') as dat_out_file:
+            yaml.dump(dat_central_yaml, dat_out_file, sort_keys=False)
+        logging.info("Done!")
+
+        # Save unertainties
+        logging.info("Dumping kinematics to file...")
+        uncertainties_yaml = {'definitions': unc_definitions, 'bins': sys_artificial}
+        file_name = (
+            self.metadata['data_uncertainties'][0]
+        )
+        with open(path + file_name, 'w') as dat_out_file:
+            yaml.dump(uncertainties_yaml, dat_out_file, sort_keys=False)
+        logging.info("Done!")

From 21bc618a300664b68e376dd5ad2665e229645ccd Mon Sep 17 00:00:00 2001
From: Amedeo Chiefa <103528316+achiefa@users.noreply.github.com>
Date: Wed, 18 Dec 2024 11:44:48 +0100
Subject: [PATCH 8/9] Add docstring to `generate_data`

---
 .../nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py     | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
index 097d5dc0de..1dbc3e44d5 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
@@ -208,6 +208,10 @@ def generate_covmat(self, diag_uncs=None):
         return covmat
 
     def generate_data(self):
+        '''
+        Collect central data, kinematics, and uncertainties and save them into
+        yaml files.
+        '''
         # Get central data and kinematics
         central_data, stat_unc, sys_unc = self.generate_data_and_unc(self.mult_factor)
         kinematics = self.generate_kinematics()

From bd47a55257be8c3c4db0d82a56f161718fed9185 Mon Sep 17 00:00:00 2001
From: achiefa <amedeochiefa@gmail.com>
Date: Wed, 8 Jan 2025 10:30:17 +0000
Subject: [PATCH 9/9] Clean-up + pre-commit

---
 .../commondata/CMS_WCHARM_7TEV/filter.py      |   7 +-
 .../CMS_WCHARM_7TEV/filter_utils.py           | 233 +++++++++---------
 2 files changed, 115 insertions(+), 125 deletions(-)

diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
index 8ce27320c6..c0604b80d7 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter.py
@@ -3,16 +3,17 @@
 '''
 
 import logging
+import os
 
 from filter_utils import Extractor
-import numpy as np
 
 logging.basicConfig(level=logging.INFO, format='[%(levelname)s] %(message)s')
 
+CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 
 if __name__ == "__main__":
-    CMS_WCHARM_TOT = Extractor("./metadata.yaml", "WPWM-TOT", mult_factor=1000)
+    CMS_WCHARM_TOT = Extractor(f"{CURRENT_DIR}/metadata.yaml", "WPWM-TOT", mult_factor=1000)
     CMS_WCHARM_TOT.generate_data()
 
-    CMS_WCHARM_RATIO = Extractor("./metadata.yaml", "WPWM-RATIO", mult_factor=1.0)
+    CMS_WCHARM_RATIO = Extractor(f"{CURRENT_DIR}/metadata.yaml", "WPWM-RATIO", mult_factor=1.0)
     CMS_WCHARM_RATIO.generate_data()
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
index 1dbc3e44d5..691d251bdd 100644
--- a/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
+++ b/nnpdf_data/nnpdf_data/commondata/CMS_WCHARM_7TEV/filter_utils.py
@@ -1,4 +1,6 @@
+import functools
 import logging
+import os
 
 import numpy as np
 import yaml
@@ -8,28 +10,29 @@
 yaml.add_representer(float, prettify_float)
 
 MW2 = 80.385**2
-CMSLUMI13 = 2.5
 
+CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 ART_LABEL = 'art_corr'
 STAT_LABEL = 'stat_uncorr'
 TABLE_TOKEN = 'Table'
 
 
 class Extractor:
-    """
-    Extracts kinematics, central data, and uncertainties for a given dataset
-
-    Parameters
-    ----------
-    metadata_file: str
-      Path to the metadata file
-    observable: str
-      The name of the observable for which the data is extracted. The name must
-      be listed in the metadata file.
-    """
 
     def __init__(self, metadata_file, observable, mult_factor=1):
-
+        """
+        Parameters
+        ----------
+        metadata_file: str
+            Path to the metadata file
+        observable: str
+            The name of the observable for which the data is extracted. The name
+            must be listed in the metadata file.
+        mult_factor: float
+            Multiplication factor to apply to the central data points. This is
+            useful to convert the data in the metadata file to the desired
+            units.
+        """
         # Open metadata and select process
         with open(metadata_file, 'r') as file:
             metadata = yaml.safe_load(file)
@@ -44,69 +47,51 @@ def __init__(self, metadata_file, observable, mult_factor=1):
             if self.metadata is None:
                 raise Exception(f"{observable} is not listed in the metadata file.")
 
-        # Initialise dict of tables
-        self.tables = {}
         self.observable = observable
         self.mult_factor = mult_factor
-        self.kin_labels = self.metadata['kinematic_coverage']
-        self.ndata = self.metadata['ndata']
 
-    def __retrieve_table(self, table_id):
+    @functools.cache
+    def _retrieve_table(self, table_id):
         """
-        Implementation of the lazy loading for the tables. If the table
-        is loaded for the first time, it is stored into an internal
-        container of the class, so that it will not be loaded each time.
-
-        When called, this functions checks if the table has already been stored
-        and, if that is the case, returns the stored table.
+        Implementation of the loading for the table.
 
         Parameters
         ----------
         table_id: int
-          Index that specifies the table
+          Index that specifies the table.
 
         Return
         ------
-        The table specified by `table_id`. If not previously loaded, it is also
-        stored into the internal container for future use.
+        The table specified by `table_id`.
         """
-        try:
-            table = self.tables[str(table_id)]
-        except KeyError:
-            logging.debug(
-                f'Table {table_id} has not already been used or stored.' f' Storing the table...'
-            )
-            with open(f'./rawdata/{TABLE_TOKEN}{table_id}.yaml', 'r') as tab:
-                tab_dict = yaml.safe_load(tab)
-                self.tables[str(table_id)] = tab_dict
-                table = tab_dict
-        return table
+        with open(f'{CURRENT_DIR}/rawdata/{TABLE_TOKEN}{table_id}.yaml') as tab:
+            tab_dict = yaml.safe_load(tab)
+        return tab_dict
 
-    def __extract_kinematics(self, table: dict):
+    def _generate_kinematics(self):
         """
-        Extracts the kinematic variables of the single differential
-        distribution given a table.
-
-        For each bin, it computes the max, min, and mid value of the transverse
-        momentum of the boson.
-
-        Parameters
-        ----------
-        table: dict
-          Dictionary containing the bins in the transverse momentum
+        The function generates the kinematics by reading and processing it from
+        the referenced table. Kinematics is processed in the format of a list of
+        dictionaries. The keys in each dictionaries specify the label (i.e. name)
+        for the kinematic variables. For this dataset, they are 'abs_eta' and 'm_W2'.
+        The labels are taken from the matadata file. The corresponding values are
+        'min', 'mid', and 'max'.
+
+        For this dataset, 'm_W2' is used in the computation of the (x,Q2)-map and
+        does not have any active role in the fit. For that reason, every bin has the
+        same value. Moreover, only the mid value is used.
+        """
+        logging.info(f"Generating kinematics for CMS_{self.observable}...")
 
-        Return
-        ------
-        List of bins containing min, max, and mid values for each of the kinematic
-        observables listed in the `kinematic_coverage` of the metadata file.
+        table_ID = self.metadata["tables"][0]
+        tab_dict = self._retrieve_table(table_ID)
 
-        """
-        data = table['independent_variables'][0]
-        label = self.kin_labels
+        data = tab_dict['independent_variables'][0]
+        label = self.metadata['kinematic_coverage']
         kinematics = []
-        for bin in data['values']:
-            abs_eta_min = bin['low']
-            abs_eta_max = bin['high']
+        for eta_bin in data['values']:
+            abs_eta_max = eta_bin['high']
+            abs_eta_min = eta_bin['low']
             kin_bin = {
                 label[0]: {
                     'min': abs_eta_min,
@@ -116,61 +101,47 @@ def __extract_kinematics(self, table: dict):
                 label[1]: {'min': None, 'mid': MW2, 'max': None},
             }
             kinematics.append(kin_bin)
-        return kinematics
-
-    def generate_kinematics(self):
-        """
-        Function that generates the kinematics by looping over all the
-        tables specified in the metadata file. The resulting kinematics
-        is then saved to a yaml file. It relies on the method
-        `__extract_kinematics`.
-        """
-
-        logging.info(f"Generating kinematics for ATLAS_{self.observable}...")
-
-        # Initialise kinematics list
-        kinematics = []
-        ndata = 0
-        table = self.metadata["tables"][0]
-        tab_dict = self.__retrieve_table(table)
-        kin = self.__extract_kinematics(tab_dict)
-        kinematics = np.concatenate([kinematics, kin])
-        ndata += len(kin)
 
         # Check number of data agrees with metadata
-        try:
-            assert self.metadata['ndata'] is not None
-            assert self.metadata['ndata'] == ndata
-        except AssertionError as e:
-            logging.warning(
-                f"The number of data in the metafile is either wrong or unspecified."
-                f" The correct number is {ndata}. Please, update the metafile."
+        ndata = len(kinematics)
+        if not self.metadata['ndata'] == ndata:
+            raise ValueError(
+                f"Mismatch in 'ndata': expected {self.metadata['ndata']}, but got {ndata}"
             )
-            return
-        return kinematics.tolist()
+        self.ndata = ndata
+        return kinematics
 
-    def generate_data_and_unc(self, mult_factor=1.0):
+    def _generate_data_and_unc(self):
         """
-        Same as `generate_kinematics`, but for central data points.
+        Return a list with central data points and two additional lists with the corresponding
+        statistical and systematic uncertainties. For this dataset, uncertainties are always
+        symmetric. Uncertainties are given as absolute values.
+
+        Note that, for the total x-sec, the correlation matrix is provided. The corresponding
+        covariance matrix is constructed in `_generate_covmat`.
         """
         logging.info(f"Generating central data for CMS_{self.observable}...")
         dat_central = []
         stat_unc = []
         asy_sys_unc = []
-        table = self.metadata['tables'][0]
-        tab_dict = self.__retrieve_table(table)
+        table_ID = self.metadata['tables'][0]
+        tab_dict = self._retrieve_table(table_ID)
 
         # Select data with pT > 25 GeV
         tab_dict = tab_dict['dependent_variables'][0]['values']
 
         # Loop over bins
         for rap_bin in tab_dict:
-            dat_central.append(rap_bin['value'] * mult_factor)
-            stat_unc.append(rap_bin['errors'][0]['symerror'] * mult_factor)
-            asy_sys_unc.append(rap_bin['errors'][1]['symerror'] * mult_factor)
+            dat_central.append(rap_bin['value'] * self.mult_factor)
+            stat_unc.append(rap_bin['errors'][0]['symerror'] * self.mult_factor)
+            asy_sys_unc.append(rap_bin['errors'][1]['symerror'] * self.mult_factor)
         return dat_central, stat_unc, asy_sys_unc
 
-    def __build_unc_definitions(self):
+    def _build_unc_definitions(self):
+        """
+        Build the dictionary containing the definitions of the uncertainties to be
+        used in the uncertainty data file.
+        """
         unc_definitions = {}
 
         # Statistical uncertainty
@@ -196,9 +167,22 @@ def __build_unc_definitions(self):
 
         return unc_definitions
 
-    def generate_covmat(self, diag_uncs=None):
-        table = self.metadata["tables"][1]
-        tab_dict = self.__retrieve_table(table)
+    def _generate_covmat(self, diag_uncs):
+        """
+        Generate the covariance matrix for the total x-sec. This function requires
+        the diagonal systematic uncertainties as argument. The diagonal uncertainties
+        are used to construct the covariance matrix from the correlation matrix stored
+        in the HepData table.
+
+        Note that such a correlation matrix exists for the total x-sec only, while the
+        ratio observable does not provide this information.
+        """
+        if not self.observable == 'WPWM-TOT':
+            raise ValueError(
+                "The construction of the covariance matrix is defined for the total x-sec only."
+            )
+        table_ID = self.metadata["tables"][1]
+        tab_dict = self._retrieve_table(table_ID)
         matlist = tab_dict['dependent_variables'][0]['values']
         matlist = [d['value'] for d in matlist]
         covmat = np.zeros((self.ndata, self.ndata))
@@ -208,64 +192,69 @@ def generate_covmat(self, diag_uncs=None):
         return covmat
 
     def generate_data(self):
-        '''
-        Collect central data, kinematics, and uncertainties and save them into
-        yaml files.
-        '''
+        """
+        The function collects central data, kinematics, and uncertainties ans save them
+        into yaml files.
+
+        The systematic uncertainties are given as percentages relative the central data point.
+        The absolute value of the uncertainty is obtained from the central data point before
+        the shifts are applied.
+        """
         # Get central data and kinematics
-        central_data, stat_unc, sys_unc = self.generate_data_and_unc(self.mult_factor)
-        kinematics = self.generate_kinematics()
+        central_data, stat_unc, sys_unc = self._generate_data_and_unc()
+        kinematics = self._generate_kinematics()
 
         # Uncertainty definitions
-        unc_definitions = self.__build_unc_definitions()
+        unc_definitions = self._build_unc_definitions()
         sys_artificial = []  # Initialize vector of artificial uncertainties
 
         if self.observable == 'WPWM-TOT':
-            covmat = self.generate_covmat(sys_unc)
+            # Generate covmat and perform eigen decomposition
+            covmat = self._generate_covmat(sys_unc)
             eigvals, eigvecs = np.linalg.eig(covmat)
             art_unc = np.sqrt(eigvals) * eigvecs
 
             # Loop over bins
-            for data_idx, data in enumerate(central_data):
+            for data_idx in range(len(central_data)):
                 # Statistical uncertainty
                 unc_dict = {STAT_LABEL: stat_unc[data_idx]}
+
+                # Artificial systematic uncertainties
                 for sys_idx, art_sys in enumerate(art_unc[data_idx, :]):
                     unc_dict[f'{ART_LABEL}_{sys_idx+1}'] = float(art_sys)
+
+                # Append to list
                 sys_artificial.append(unc_dict)
 
         elif self.observable == 'WPWM-RATIO':
-            for data_idx, data in enumerate(central_data):
+            for data_idx in range(len(central_data)):
                 # Statistical uncertainty
                 unc_dict = {STAT_LABEL: stat_unc[data_idx]}
 
                 # Systematic uncertainty
                 unc_dict[f'{ART_LABEL}'] = sys_unc[data_idx]
                 sys_artificial.append(unc_dict)
-        
-        # Local path for yaml files
-        path='./'
 
         # Save kinematics into file
         logging.info("Dumping kinematics to file...")
         kinematics_yaml = {'bins': kinematics}
-        with open(path + self.metadata['kinematics']['file'], 'w') as kin_out_file:
-            yaml.dump(kinematics_yaml, kin_out_file, sort_keys=False)
+        kins_file_name = self.metadata['kinematics']['file']
+        with open(CURRENT_DIR + '/' + kins_file_name, 'w') as file:
+            yaml.dump(kinematics_yaml, file, sort_keys=False)
         logging.info("Done!")
 
         # Save central data into file
         logging.info("Dumping kinematics to file...")
         dat_central_yaml = {'data_central': central_data}
-        file_name = self.metadata['data_central']
-        with open(path + file_name, 'w') as dat_out_file:
-            yaml.dump(dat_central_yaml, dat_out_file, sort_keys=False)
+        data_file_name = self.metadata['data_central']
+        with open(CURRENT_DIR + '/' + data_file_name, 'w') as file:
+            yaml.dump(dat_central_yaml, file, sort_keys=False)
         logging.info("Done!")
 
         # Save unertainties
         logging.info("Dumping kinematics to file...")
         uncertainties_yaml = {'definitions': unc_definitions, 'bins': sys_artificial}
-        file_name = (
-            self.metadata['data_uncertainties'][0]
-        )
-        with open(path + file_name, 'w') as dat_out_file:
-            yaml.dump(uncertainties_yaml, dat_out_file, sort_keys=False)
+        unc_file_name = self.metadata['data_uncertainties'][0]
+        with open(CURRENT_DIR + '/' + unc_file_name, 'w') as file:
+            yaml.dump(uncertainties_yaml, file, sort_keys=False)
         logging.info("Done!")