Update the code to be compatible with pandas==3

.github/actions/prepare_environment/action.yml

@@ -32,7 +32,7 @@ runs:
       with:
         python-version: ${{ inputs.python-version }}
         use-mamba: true
-        channels: https://packages.nnpdf.science/public,conda-forge
+        channels: conda-forge
         show-channel-urls: true
         auto-update-conda: true
         activate-environment: nnpdf_environment

.github/workflows/fitbot.yml

@@ -12,7 +12,7 @@ env:
   POSTFIT_NREP: 15 # requested minimum replicas for postfit
   # IMPORTANT
   # WHEN CHANGING THE REFERENCE SET, THE NEW REFERENCE MUST BE MANUALLY UPLOADED TO THE SERVER
-  REFERENCE_SET: NNBOT-99108504e-2025-11-22 # reference set for exact results
+  REFERENCE_SET: NNNBOT-1a81255f3-2026-01-27 # reference set for exact results
   STABLE_REFERENCE_SET: NNBOT-99108504e-2025-11-22 # reference set for last tag
   PYTHONHASHSEED: "0"
 

.github/workflows/redo_regressions.yml

@@ -34,7 +34,6 @@ jobs:
         echo "$NETRC_FILE" | base64 --decode > ~/.netrc
         conda config --remove channels defaults
         conda config --append channels conda-forge
-        conda config --prepend channels https://packages.nnpdf.science/public
         conda config --set show_channel_urls true
         conda install lhapdf pandoc
     - name: Install nnpdf with testing and qed extras

nnpdf_data/nnpdf_data/commondata/HERA_CC_318GEV/filter.py

@@ -1,68 +1,69 @@
-from nnpdf_data.filter_utils.hera_utils import commondata #, covmat_is_close
-from pathlib import Path
 from dataclasses import dataclass
-import typing
-from typing import List
-import numpy as np
-import pandas as pd
 from os import PathLike
-import yaml
+from pathlib import Path
+
+import pandas as pd
+
+from nnpdf_data.filter_utils.hera_utils import commondata  # , covmat_is_close
+
 
 @dataclass
 class hera_commondata(commondata):
-   def __init__(self, filename: str | PathLike, dataset_name: str, 
-                process: str):
-      # Read the data.
-      file = Path(filename)
-      df = pd.read_table(file, sep=r"\s+")
+    def __init__(self, filename: str | PathLike, dataset_name: str, process: str):
+        # Read the data.
+        file = Path(filename)
+        df = pd.read_table(file, sep=r"\s+")
 
-      # Kinematic quantieties.
-      self.central_values = df["Sigma"].to_numpy()
-      self.kinematics = df[["x", "Q2", "y"]].to_numpy()
-      self.kinematic_quantities = ["x", "Q2", "y"]
+        # Kinematic quantieties.
+        self.central_values = df["Sigma"].to_numpy()
+        self.kinematics = df[["x", "Q2", "y"]].to_numpy()
+        self.kinematic_quantities = ["x", "Q2", "y"]
 
-      # Statistical uncertainties.
-      statistical_uncertainties = df["stat"].to_numpy()
-      for iunc,unc in enumerate(statistical_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         statistical_uncertainties[iunc] = unc
-      self.statistical_uncertainties = statistical_uncertainties
+        # Statistical uncertainties.
+        statistical_uncertainties = df["stat"].to_numpy(copy=True)
+        for iunc, unc in enumerate(statistical_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            statistical_uncertainties[iunc] = unc
+        self.statistical_uncertainties = statistical_uncertainties
 
-      # Systematic uncertainties.
-      # remove the column containing the total uncertainty excluding 
-      # procedural uncertainties.
-      df = df.drop(columns=["tot_noproc"])
-      sys_uncert_col_names = list(df.columns.values)[5:]
-      self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      for iunc,unc in enumerate(systematic_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         systematic_uncertainties[iunc] = unc
-      self.systematic_uncertainties = systematic_uncertainties
-
-      # All uncertainties are treated as multiplicative.
-      systypes = []
-      for name in sys_uncert_col_names:
-         if(name == "uncor"):
-            systypes.append(("MULT", "UNCORR"))
-         else:
-            systypes.append(("MULT", f"HC_{name}"))
-      self.systypes = systypes
-      self.process = process
-      self.dataset_name = dataset_name
+        # Systematic uncertainties.
+        # remove the column containing the total uncertainty excluding
+        # procedural uncertainties.
+        df = df.drop(columns=["tot_noproc"])
+        sys_uncert_col_names = list(df.columns.values)[5:]
+        self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        for iunc, unc in enumerate(systematic_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            systematic_uncertainties[iunc] = unc
+        self.systematic_uncertainties = systematic_uncertainties
 
-def main():
-   hera_em = hera_commondata("./rawdata/HERA1+2_CCem.dat","HERACOMBCCEM", "DIS_CC")
-   hera_em.write_new_commondata(Path("data_EM-SIGMARED.yaml"),
-                                Path("kinematics_EM-SIGMARED.yaml"),
-                                Path("uncertainties_EM-SIGMARED.yaml"))
-   hera_ep = hera_commondata("./rawdata/HERA1+2_CCep.dat","HERACOMBCCEP", "DIS_CC")
-   hera_ep.write_new_commondata(Path("data_EP-SIGMARED.yaml"),
-                                Path("kinematics_EP-SIGMARED.yaml"),
-                                Path("uncertainties_EP-SIGMARED.yaml"))
+        # All uncertainties are treated as multiplicative.
+        systypes = []
+        for name in sys_uncert_col_names:
+            if name == "uncor":
+                systypes.append(("MULT", "UNCORR"))
+            else:
+                systypes.append(("MULT", f"HC_{name}"))
+        self.systypes = systypes
+        self.process = process
+        self.dataset_name = dataset_name
 
-if __name__ == "__main__":
-   main()
 
+def main():
+    hera_em = hera_commondata("./rawdata/HERA1+2_CCem.dat", "HERACOMBCCEM", "DIS_CC")
+    hera_em.write_new_commondata(
+        Path("data_EM-SIGMARED.yaml"),
+        Path("kinematics_EM-SIGMARED.yaml"),
+        Path("uncertainties_EM-SIGMARED.yaml"),
+    )
+    hera_ep = hera_commondata("./rawdata/HERA1+2_CCep.dat", "HERACOMBCCEP", "DIS_CC")
+    hera_ep.write_new_commondata(
+        Path("data_EP-SIGMARED.yaml"),
+        Path("kinematics_EP-SIGMARED.yaml"),
+        Path("uncertainties_EP-SIGMARED.yaml"),
+    )
 
 
+if __name__ == "__main__":
+    main()

nnpdf_data/nnpdf_data/commondata/HERA_NC_225GEV/filter.py

@@ -1,63 +1,63 @@
-from nnpdf_data.filter_utils.hera_utils import commondata #, covmat_is_close
-from pathlib import Path
 from dataclasses import dataclass
-import typing
-from typing import List
-import numpy as np
-import pandas as pd
 from os import PathLike
-import yaml
+from pathlib import Path
+
+import pandas as pd
+
+from nnpdf_data.filter_utils.hera_utils import commondata  # , covmat_is_close
+
 
 @dataclass
 class hera_commondata(commondata):
-   def __init__(self, filename: str | PathLike, dataset_name: str, 
-                process: str):
-      # Read the data.
-      file = Path(filename)
-      df = pd.read_table(file, sep=r"\s+")
-
-      # Kinematic quantieties.
-      self.central_values = df["Sigma"].to_numpy()
-      self.kinematics = df[["x", "Q2", "y"]].to_numpy()
-      self.kinematic_quantities = ["x", "Q2", "y"]
-
-      # Statistical uncertainties.
-      statistical_uncertainties = df["stat"].to_numpy()
-      for iunc,unc in enumerate(statistical_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         statistical_uncertainties[iunc] = unc
-      self.statistical_uncertainties = statistical_uncertainties
-
-      # Systematic uncertainties.
-      # remove the column containing the total uncertainty excluding 
-      # procedural uncertainties.
-      df = df.drop(columns=["tot_noproc"])
-      sys_uncert_col_names = list(df.columns.values)[5:]
-      self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      for iunc,unc in enumerate(systematic_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         systematic_uncertainties[iunc] = unc
-      self.systematic_uncertainties = systematic_uncertainties
-
-      # All uncertainties are treated as multiplicative.
-      systypes = []
-      for name in sys_uncert_col_names:
-         if(name == "uncor"):
-            systypes.append(("MULT", "UNCORR"))
-         else:
-            systypes.append(("MULT", "HC_" + name))
-      self.systypes = systypes
-      self.process = process
-      self.dataset_name = dataset_name
+    def __init__(self, filename: str | PathLike, dataset_name: str, process: str):
+        # Read the data.
+        file = Path(filename)
+        df = pd.read_table(file, sep=r"\s+")
+
+        # Kinematic quantieties.
+        self.central_values = df["Sigma"].to_numpy()
+        self.kinematics = df[["x", "Q2", "y"]].to_numpy()
+        self.kinematic_quantities = ["x", "Q2", "y"]
+
+        # Statistical uncertainties.
+        statistical_uncertainties = df["stat"].to_numpy(copy=True)
+        for iunc, unc in enumerate(statistical_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            statistical_uncertainties[iunc] = unc
+        self.statistical_uncertainties = statistical_uncertainties
+
+        # Systematic uncertainties.
+        # remove the column containing the total uncertainty excluding
+        # procedural uncertainties.
+        df = df.drop(columns=["tot_noproc"])
+        sys_uncert_col_names = list(df.columns.values)[5:]
+        self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        for iunc, unc in enumerate(systematic_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            systematic_uncertainties[iunc] = unc
+        self.systematic_uncertainties = systematic_uncertainties
+
+        # All uncertainties are treated as multiplicative.
+        systypes = []
+        for name in sys_uncert_col_names:
+            if name == "uncor":
+                systypes.append(("MULT", "UNCORR"))
+            else:
+                systypes.append(("MULT", "HC_" + name))
+        self.systypes = systypes
+        self.process = process
+        self.dataset_name = dataset_name
 
-def main():
-   hera_ep = hera_commondata("./rawdata/HERA1+2_NCep_460.dat","HERACOMBNCEP460", "DIS_NCE")
-   hera_ep.write_new_commondata(Path("data_EP-SIGMARED.yaml"),
-                                Path("kinematics_EP-SIGMARED.yaml"),
-                                Path("uncertainties_EP-SIGMARED.yaml"))
-if __name__ == "__main__":
-   main()
 
+def main():
+    hera_ep = hera_commondata("./rawdata/HERA1+2_NCep_460.dat", "HERACOMBNCEP460", "DIS_NCE")
+    hera_ep.write_new_commondata(
+        Path("data_EP-SIGMARED.yaml"),
+        Path("kinematics_EP-SIGMARED.yaml"),
+        Path("uncertainties_EP-SIGMARED.yaml"),
+    )
 
 
+if __name__ == "__main__":
+    main()

nnpdf_data/nnpdf_data/commondata/HERA_NC_251GEV/filter.py

@@ -1,65 +1,67 @@
-from nnpdf_data.filter_utils.hera_utils import commondata #, covmat_is_close
-from pathlib import Path
 from dataclasses import dataclass
+from os import PathLike
+from pathlib import Path
 import typing
 from typing import List
+
 import numpy as np
 import pandas as pd
-from os import PathLike
 import yaml
 
+from nnpdf_data.filter_utils.hera_utils import commondata  # , covmat_is_close
+
+
 @dataclass
 class hera_commondata(commondata):
-   def __init__(self, filename: str | PathLike, dataset_name: str, 
-                process: str):
-      # Read the data.
-      file = Path(filename)
-      df = pd.read_table(file, sep=r"\s+")
-
-      # Kinematic quantieties.
-      self.central_values = df["Sigma"].to_numpy()
-      self.kinematics = df[["x", "Q2", "y"]].to_numpy()
-      self.kinematic_quantities = ["x", "Q2", "y"]
+    def __init__(self, filename: str | PathLike, dataset_name: str, process: str):
+        # Read the data.
+        file = Path(filename)
+        df = pd.read_table(file, sep=r"\s+")
 
-      # Statistical uncertainties.
-      statistical_uncertainties = df["stat"].to_numpy()
-      for iunc,unc in enumerate(statistical_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         statistical_uncertainties[iunc] = unc
-      self.statistical_uncertainties = statistical_uncertainties
+        # Kinematic quantieties.
+        self.central_values = df["Sigma"].to_numpy()
+        self.kinematics = df[["x", "Q2", "y"]].to_numpy()
+        self.kinematic_quantities = ["x", "Q2", "y"]
 
-      # Systematic uncertainties.
-      # remove the column containing the total uncertainty excluding 
-      # procedural uncertainties.
-      df = df.drop(columns=["tot_noproc"])
-      sys_uncert_col_names = list(df.columns.values)[5:]
-      self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
-      for iunc,unc in enumerate(systematic_uncertainties):
-         unc = self.central_values[iunc]*unc/100
-         systematic_uncertainties[iunc] = unc
-      self.systematic_uncertainties = systematic_uncertainties
-
-      # All uncertainties are treated as multiplicative.
-      systypes = []
-      for name in sys_uncert_col_names:
-         if(name == "uncor"):
-            systypes.append(("MULT", "UNCORR"))
-         else:
-            systypes.append(("MULT", "HC_" + name))
-      self.systypes = systypes
-      self.process = process
-      self.dataset_name = dataset_name
+        # Statistical uncertainties.
+        statistical_uncertainties = df["stat"].to_numpy(copy=True)
+        for iunc, unc in enumerate(statistical_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            statistical_uncertainties[iunc] = unc
+        self.statistical_uncertainties = statistical_uncertainties
 
-def main():
-   hera_ep = hera_commondata("./rawdata/HERA1+2_NCep_575.dat","HERACOMBNCEP575", "DIS_NCE")
-   hera_ep.write_new_commondata(Path("data_EP-SIGMARED.yaml"),
-                                Path("kinematics_EP-SIGMARED.yaml"),
-                                Path("uncertainties_EP-SIGMARED.yaml"))
+        # Systematic uncertainties.
+        # remove the column containing the total uncertainty excluding
+        # procedural uncertainties.
+        df = df.drop(columns=["tot_noproc"])
+        sys_uncert_col_names = list(df.columns.values)[5:]
+        self.systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        systematic_uncertainties = df[sys_uncert_col_names].to_numpy()
+        for iunc, unc in enumerate(systematic_uncertainties):
+            unc = self.central_values[iunc] * unc / 100
+            systematic_uncertainties[iunc] = unc
+        self.systematic_uncertainties = systematic_uncertainties
 
+        # All uncertainties are treated as multiplicative.
+        systypes = []
+        for name in sys_uncert_col_names:
+            if name == "uncor":
+                systypes.append(("MULT", "UNCORR"))
+            else:
+                systypes.append(("MULT", "HC_" + name))
+        self.systypes = systypes
+        self.process = process
+        self.dataset_name = dataset_name
 
-if __name__ == "__main__":
-   main()
 
+def main():
+    hera_ep = hera_commondata("./rawdata/HERA1+2_NCep_575.dat", "HERACOMBNCEP575", "DIS_NCE")
+    hera_ep.write_new_commondata(
+        Path("data_EP-SIGMARED.yaml"),
+        Path("kinematics_EP-SIGMARED.yaml"),
+        Path("uncertainties_EP-SIGMARED.yaml"),
+    )
 
 
+if __name__ == "__main__":
+    main()