Reimplement ATLAS_Z0_7TEV_36PB Dataset

nnpdf_data/nnpdf_data/commondata/ATLAS_Z0_7TEV_36PB/data.yaml

@@ -0,0 +1,9 @@
+data_central:
+- 1.31687349e+05
+- 1.31860528e+05
+- 1.28162647e+05
+- 1.20440901e+05
+- 1.15490019e+05
+- 1.07228362e+05
+- 9.39037660e+04
+- 5.43782060e+04

nnpdf_data/nnpdf_data/commondata/ATLAS_Z0_7TEV_36PB/filter.py

@@ -0,0 +1,100 @@
+"""
+When running `python filter.py` the relevant data yaml
+file will be created in the `nnpdf_data/commondata/ATLAS_WPWM_7TEV_46FB` directory.
+"""
+
+import yaml
+from filter_utils import get_data_values, get_kinematics, get_systematics
+
+from nnpdf_data.filter_utils.utils import prettify_float
+
+yaml.add_representer(float, prettify_float)
+
+
+def filter_ATLAS_Z0_7TEV_36FB_data_kinematic():
+    """
+    This function writes the systematics to yaml files.
+    """
+
+    central_values = get_data_values()
+
+    kin = get_kinematics()
+
+    data_central_yaml = {"data_central": central_values}
+
+    kinematics_yaml = {"bins": kin}
+
+    # write central values and kinematics to yaml file
+    with open("data.yaml", "w") as file:
+        yaml.dump(data_central_yaml, file, sort_keys=False)
+
+    with open("kinematics.yaml", "w") as file:
+        yaml.dump(kinematics_yaml, file, sort_keys=False)
+
+
+def filter_ATLAS_Z0_7TEV_36FB_systematics():
+    """
+    This function writes the systematics to a yaml file.
+    """
+
+    with open("metadata.yaml", "r") as file:
+        metadata = yaml.safe_load(file)
+
+    systematics = get_systematics()
+
+    # error definition
+    error_definitions = {}
+    errors = []
+    counter_1 = 1
+    counter_2 = 0
+    for sys in systematics:
+        if sys[0]['name'] == 'stat':
+            error_definitions[sys[0]['name']] = {
+                "description": "Uncorrelated statistical uncertainties",
+                "treatment": "ADD",
+                "type": "UNCORR",
+            }
+
+        elif sys[0]['name'] == 'uncor':
+            error_definitions[sys[0]['name']] = {
+                "description": f"Sys uncertainty idx: {counter_1}",
+                "treatment": "MULT",
+                "type": "UNCORR",
+            }
+            counter_1 += 1
+
+        elif sys[0]['name'] == 'atlaslumi10':
+            error_definitions[sys[0]['name']] = {
+                "description": f"Sys uncertainty idx: {counter_1}",
+                "treatment": "MULT",
+                "type": "ATLASLUMI10",
+            }
+            counter_1 += 1
+
+        else:
+            error_definitions[sys[0]['name']] = {
+                "description": f"Sys uncertainty idx: {counter_1}",
+                "treatment": "MULT",
+                "type": f"ATLASWZRAP36PB_{counter_2}",
+            }
+            counter_1 += 1
+            counter_2 += 1
+
+    for i in range(metadata['implemented_observables'][0]['ndata']):
+        error_value = {}
+
+        for sys in systematics:
+            error_value[sys[0]['name']] = float(sys[0]['values'][i])
+
+        errors.append(error_value)
+
+    uncertainties_yaml = {"definitions": error_definitions, "bins": errors}
+
+    # write uncertainties
+    with open(f"uncertainties.yaml", 'w') as file:
+        yaml.dump(uncertainties_yaml, file, sort_keys=False)
+
+
+if __name__ == "__main__":
+    filter_ATLAS_Z0_7TEV_36FB_data_kinematic()
+    filter_ATLAS_Z0_7TEV_36FB_systematics()

nnpdf_data/nnpdf_data/commondata/ATLAS_Z0_7TEV_36PB/filter_utils.py

@@ -0,0 +1,90 @@
+"""
+This module contains helper functions that are used to extract the data values 
+from the rawdata files.
+"""
+
+import yaml
+import pandas as pd
+import numpy as np
+
+
+def get_data_values():
+    """
+    returns the central data values in the form of a list.
+    """
+
+    data_central = []
+
+    hepdata_table = f"rawdata/HEPData-ins928289-v1-Table_1.yaml"
+
+    with open(hepdata_table, 'r') as file:
+        input = yaml.safe_load(file)
+
+    values = input['dependent_variables'][0]['values']
+
+    for value in values:
+        # store data central and convert the units and apply the correction factor
+        data_central.append(value['value'] * 1000 * 1.0187)
+
+    return data_central
+
+
+def get_kinematics():
+    """
+    returns the kinematics in the form of a list of dictionaries.
+    """
+    kin = []
+
+    hepdata_table = f"rawdata/HEPData-ins928289-v1-Table_1.yaml"
+
+    with open(hepdata_table, 'r') as file:
+        input = yaml.safe_load(file)
+
+    for i, M in enumerate(input["independent_variables"][0]['values']):
+        kin_value = {
+            'abs_eta': {'min': None, 'mid': (0.5 * (M['low'] + M['high'])), 'max': None},
+            'm_Z2': {'min': None, 'mid': 8315.17839376, 'max': None},
+            'sqrts': {'min': None, 'mid': 7000.0, 'max': None},
+        }
+        kin.append(kin_value)
+
+    return kin
+
+
+def get_systematics_dataframe():
+    """
+    returns the absolute systematic uncertainties in the form of a pandas dataframe.
+    """
+    sys_rawdata_path = "rawdata/ATLAS-36PB_Z.csv"
+
+    abs_unc_df_arr = []
+
+    data_central = get_data_values()
+
+    df = pd.read_csv(sys_rawdata_path)
+
+    # convert (MULT) percentage unc to absolute unc
+    abs_unc_df = (df.T[2:] * data_central).T / 100
+    abs_unc_df_arr.append(abs_unc_df)
+
+    return abs_unc_df
+
+
+def get_systematics():
+    """ """
+    abs_unc_df = get_systematics_dataframe()
+
+    uncertainties = []
+
+    for i, unc_dp in enumerate(abs_unc_df.values.T):
+        name = f"{abs_unc_df.columns[i]}"
+        values = [unc_dp[j] for j in range(len(unc_dp))]
+        uncertainties.append([{"name": name, "values": values}])
+
+    return uncertainties
+
+
+if __name__ == "__main__":
+    get_data_values()
+    get_kinematics()
+    get_systematics()

nnpdf_data/nnpdf_data/commondata/ATLAS_Z0_7TEV_36PB/kinematics.yaml

@@ -0,0 +1,97 @@
+bins:
+- abs_eta:
+    min: null
+    mid: 0.2
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 6.00000000e-01
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 1.0
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 1.4
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 1.8
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 2.2
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 2.60000000e+00
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null
+- abs_eta:
+    min: null
+    mid: 3.2
+    max: null
+  m_Z2:
+    min: null
+    mid: 8.31517839e+03
+    max: null
+  sqrts:
+    min: null
+    mid: 7000.0
+    max: null

nnpdf_data/nnpdf_data/commondata/ATLAS_Z0_7TEV_36PB/metadata.yaml

@@ -1,29 +1,29 @@
 setname: ATLAS_Z0_7TEV_36PB
-version: 1
-version_comment: Port of old commondata
+version: 2
+version_comment: Reimplementation of old commondata
 nnpdf_metadata:
   nnpdf31_process: DY NC
   experiment: ATLAS
 arXiv:
   url: https://arxiv.org/abs/1109.5141
   journal: Phys.Rev. D85 (2012) 072004
 iNSPIRE:
-  url: ''
+  url: 'https://inspirehep.net/literature/928289'
 hepdata:
-  url: ''
-  version: -1
+  url: 'https://www.hepdata.net/record/ins928289'
+  version: 1
 implemented_observables:
 - observable_name: ETA
   observable:
     description: Drell-Yan Rapidity Distribution
     label: ATLAS $Z$ 7 TeV 2010
     units: ''
-  process_type: EWK_RAP
-  tables: []
+  process_type: DY_Z_Y
+  tables: [1]
   npoints: []
   ndata: 8
   plotting:
-    kinematics_override: ewk_rap_sqrt_scale
+    kinematics_override: identity
     dataset_label: ATLAS $Z$ 7 TeV 2010
     x_label: $\left\|\eta/y\right|$
     y_label: $d\sigma/dy$ (fb)
@@ -42,35 +42,36 @@ implemented_observables:
       - $Z$
       - $Z$
       - $Z$
-    plot_x: k1
+    plot_x: abs_eta
   kinematic_coverage:
-  - k1
-  - k2
-  - k3
+  - abs_eta
+  - m_Z2
+  - sqrts
   kinematics:
     variables:
-      k1:
-        description: Variable k1
-        label: k1
+      abs_eta:
+        description: Absolute value of the rapidity of the Z boson
+        label: "$|y|$"
         units: ''
-      k2:
-        description: Variable k2
-        label: k2
-        units: ''
-      k3:
-        description: Variable k3
-        label: k3
-        units: ''
-    file: kinematics_ETA.yaml
+      m_Z2:
+        description: Squared invariant mass of the Z boson
+        label: '$m_Z^2$'
+        units: 'GeV^2'
+      sqrts:
+        description: Square root of the center of mass energy
+        label: r"\sqrt{s}"
+        units: 'GeV'
+    file: kinematics.yaml
   theory:
     conversion_factor: 1.0
     operation: 'null'
     FK_tables:
     - - ATLASWZRAP36PB-ATLAS-arXiv:1109.5141-Z0_eta34
-  data_uncertainties: []
+  data_uncertainties: [uncertainties.yaml]
   variants:
     legacy:
       data_uncertainties:
       - uncertainties_legacy_ETA.yaml
-  data_central: data_legacy_ETA.yaml
+      data_central: data_legacy_ETA.yaml
+  data_central: data.yaml
   ported_from: ATLASZRAP36PB