Merge pull request #2329 from NNPDF/fix_commondata

scarlehoff · web-flow · commit cea84fc3a69d · 2025-06-10T10:14:12.000+02:00
Fix commondata
diff --git a/nnpdf_data/nnpdf_data/commondata/CMS_2JET_7TEV/rawdata/dijet_corr.dat b/nnpdf_data/nnpdf_data/commondata/CMS_2JET_7TEV/rawdata/dijet_corr.dat
@@ -73,4 +73,4 @@ Statistical correlation of the measured cross section between the mass bins in t
 2231 2659  0.00  0.01  0.00 -0.13  1.00 -0.15 -0.01  0.01
 2659 3147  0.00  0.00  0.01 -0.01 -0.15  1.00 -0.28  0.00
 3147 3704  0.00  0.00  0.00  0.02 -0.01 -0.28  1.00 -0.12
-3704 5058  0.00  0.00  0.00  0.00  0.01  0.00 -0.12  1.00s
+3704 5058  0.00  0.00  0.00  0.00  0.01  0.00 -0.12  1.00
diff --git a/nnpdf_data/nnpdf_data/commondata/JLABE06_NC_3GEV_EN/filter.py b/nnpdf_data/nnpdf_data/commondata/JLABE06_NC_3GEV_EN/filter.py
@@ -12,7 +12,7 @@
 def read_data(fnames):
     df = pd.DataFrame()
     for fname in fnames:
-        with open(fname, "r") as file:
+        with open(fname) as file:
             # Get the data as string
             data = file.read()
 
@@ -26,7 +26,7 @@ def read_data(fnames):
             last_section[0] = "x A_1 A_stat A_sys G G_stat G_sys"
 
             # Convert the modified section into a Pandas DataFrame
-            df_temp = pd.read_csv(StringIO('\n'.join(last_section)), delim_whitespace=True)
+            df_temp = pd.read_csv(StringIO('\n'.join(last_section)), sep=r'\s+')
 
             # Set the Q^2 and y value
             df_temp["Q2"] = "3.08"
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_DY_7TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_DY_7TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_DY_8TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_DY_8TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_WPWM_7TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_WPWM_7TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_WPWM_8TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_WPWM_8TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_13TEV/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_13TEV/filter.py
@@ -80,7 +80,7 @@ def get_kinematics(hepdata: dict, bin_index: list) -> list:
 
     kinematics = []
     for idx in bin_index:
-        ymin, ymax = [float(i) for i in rapbins[idx]['value'].split("-")]
+        ymin, ymax = (float(i) for i in rapbins[idx]['value'].split("-"))
         kin_value = {
             "y": {"min": ymin, "mid": 0.5 * (ymin + ymax), "max": ymax},
             "m_Z2": {"min": None, "mid": MZ_VALUE**2, "max": None},
@@ -159,7 +159,7 @@ def read_corrmatrix(nb_datapoints: int, state: str) -> np.ndarray:
     corrmat = pd.read_csv(
         f"./rawdata/corrmat{MAP_STATE[state]}.corr",
         names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        sep=r'\s+',
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_7TEV_DIELECTRON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_7TEV_DIELECTRON/filter.py
@@ -148,9 +148,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_7TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_7TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_8TEV_DIELECTRON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_8TEV_DIELECTRON/filter.py
@@ -144,9 +144,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_8TEV_MUON/filter.py b/nnpdf_data/nnpdf_data/commondata/LHCB_Z0_8TEV_MUON/filter.py
@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:
 
     """
     corrmat = pd.read_csv(
-        "./rawdata/corrmat.corr",
-        names=[f'{i}' for i in range(nb_datapoints)],
-        delim_whitespace=True,
+        "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'
     )
     corrmat = corrmat.iloc[:, :].values
 
diff --git a/nnpdf_data/nnpdf_data/filter_utils/poldata_utils.py b/nnpdf_data/nnpdf_data/filter_utils/poldata_utils.py
@@ -54,7 +54,7 @@ def read_txt_data(path_txt: Path) -> pd.DataFrame:
     """
     colnames = ["x", "Q2", "abs"]
     return pd.read_csv(
-        path_txt, delim_whitespace=True, names=colnames, usecols=[i for i in range(len(colnames))]
+        path_txt, sep=r'\s+', names=colnames, usecols=[i for i in range(len(colnames))]
     )
 
 

Original file line number	Diff line number	Diff line change
`@@ -162,9 +162,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:`
`162`	`162`
`163`	`163`	`"""`
`164`	`164`	`corrmat = pd.read_csv(`
`165`		`- "./rawdata/corrmat.corr",`
`166`		`- names=[f'{i}' for i in range(nb_datapoints)],`
`167`		`- delim_whitespace=True,`
	`165`	`+ "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'`
`168`	`166`	`)`
`169`	`167`	`corrmat = corrmat.iloc[:, :].values`
`170`	`168`
Original file line number	Diff line number	Diff line change
`@@ -148,9 +148,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:`
`148`	`148`
`149`	`149`	`"""`
`150`	`150`	`corrmat = pd.read_csv(`
`151`		`- "./rawdata/corrmat.corr",`
`152`		`- names=[f'{i}' for i in range(nb_datapoints)],`
`153`		`- delim_whitespace=True,`
	`151`	`+ "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'`
`154`	`152`	`)`
`155`	`153`	`corrmat = corrmat.iloc[:, :].values`
`156`	`154`
Original file line number	Diff line number	Diff line change
`@@ -144,9 +144,7 @@ def read_corrmatrix(nb_datapoints: int) -> np.ndarray:`
`144`	`144`
`145`	`145`	`"""`
`146`	`146`	`corrmat = pd.read_csv(`
`147`		`- "./rawdata/corrmat.corr",`
`148`		`- names=[f'{i}' for i in range(nb_datapoints)],`
`149`		`- delim_whitespace=True,`
	`147`	`+ "./rawdata/corrmat.corr", names=[f'{i}' for i in range(nb_datapoints)], sep=r'\s+'`
`150`	`148`	`)`
`151`	`149`	`corrmat = corrmat.iloc[:, :].values`
`152`	`150`