Merge pull request #2154 from NNPDF/sihp-data

Sihp data

doc/sphinx/source/data/dataset-naming-convention.rst

@@ -13,11 +13,11 @@ constructed following this [Backus–Naur form]::
 
   <valid dataset name> ::= <set name> "_" <observable name>
 
-  <experiment> ::= "ATLAS" | "BCDMS" | "CDF" | "CHORUS" | "CMS" | "D0" | "DYE605" | "DYE866" 
+  <experiment> ::= "ATLAS" | "BCDMS" | "CDF" | "CHORUS" | "CMS" | "D0" | "DYE605" | "DYE866"
                 | "DYE906" | "EMC" | "H1" | "HERA" | "LHCB" | "NMC" | "NNPDF" | "NUTEV" | "SLAC"
                 | "ZEUS"
 
-  <process> ::= "1JET" | "2JET" | "CC" | "DY" | "INTEG" | "NC" | "PH" | "POS" | "SINGLETOP" 
+  <process> ::= "1JET" | "2JET" | "CC" | "DY" | "INTEG" | "NC" | "PH" | "POS" | "SHP" | "SINGLETOP"
               | "TTBAR" | "WCHARM" | "WJ" | "WPWM" | "Z0" | "Z0J"
 
   <energy> ::= <integer> <unit> | <integer> "P" <integer> <unit>  | "NOTFIXED"
@@ -91,6 +91,7 @@ Processes
 - `NC`: DIS neutral-current
 - `POS`: auxiliary dataset for positivity constraints; only valid for
   `NNPDF` experiment
+- `SHP`: single hadron production
 - `TTBAR`: top–anti-top production
 - `WM`: production of a single negatively-charged lepton (charged current
   off-shell Drell–Yan)

nnpdf_data/nnpdf_data/commondata/PHENIX-2009_SHP_200GEV_PI0/data.yaml

@@ -0,0 +1,13 @@
+data_central:
+- 0.00051
+- 0.00096
+- 0.00039
+- -0.00023
+- 0.0006
+- 0.0002
+- 0.0013
+- 0.0026
+- -0.0039
+- 0.0096
+- 0.008
+- 0.061

nnpdf_data/nnpdf_data/commondata/PHENIX-2009_SHP_200GEV_PI0/filter.py

@@ -0,0 +1,93 @@
+from pathlib import Path
+
+import pandas as pd
+import yaml
+
+
+def read_data(path_rawdata: str) -> pd.DataFrame:
+    data = yaml.safe_load(Path(path_rawdata).read_text())
+
+    ptvals = data["independent_variables"][0]["values"]
+    asym_obs = data["dependent_variables"][0]["values"]
+
+    concatenated_table = []
+    for i in range(len(ptvals)):
+        # Compute pT mid-value if not given
+        pt_mid = (float(ptvals[i]["high"]) + float(ptvals[i]["low"])) / 2
+        pt_midval = ptvals[i].get("value", pt_mid)
+
+        concatenated_table.append(
+            pd.DataFrame(
+                {
+                    "pT_low": [ptvals[i]["low"]],
+                    "pT": [pt_midval],
+                    "pT_high": [ptvals[i]["high"]],
+                    "asym": [asym_obs[i]["value"]],
+                    "stat_err": [asym_obs[i]["errors"][0]["symerror"]],
+                    "lumi_err": [asym_obs[i]["errors"][1]["symerror"]],
+                    "spol_err": [asym_obs[i]["errors"][2]["symerror"].removesuffix("%")],
+                }
+            )
+        )
+
+    return pd.concat(concatenated_table, ignore_index=True)
+
+
+def dump_data(df_table: pd.DataFrame) -> None:
+    # Dump central data into Yaml file
+    data_central = []
+    for i in range(len(df_table["asym"])):
+        data_central.append(float(df_table.loc[i, "asym"]))
+
+    with open("data.yaml", "w") as file:
+        yaml.dump({"data_central": data_central}, file, sort_keys=False)
+
+    # Dump the kinematics into Yaml file
+    kinematics = []
+    for i in range(len(df_table["asym"])):
+        kin_value = {
+            "pT": {
+                "min": float(df_table.loc[i, "pT_low"]),
+                "mid": float(df_table.loc[i, "pT"]),
+                "max": float(df_table.loc[i, "pT_high"]),
+            },
+            "eta": {"min": -0.35, "mid": 0.0, "max": 0.35},
+        }
+        kinematics.append(kin_value)
+
+    with open("kinematics.yaml", "w") as file:
+        yaml.dump({"bins": kinematics}, file, sort_keys=False)
+
+    # Dump the uncertainties into Yaml file
+    errors = []
+    for i in range(len(df_table)):
+        error_per_bin = {
+            "stat": float(df_table.loc[i, "stat_err"]),
+            "sys_lumi": float(df_table.loc[i, "lumi_err"]),
+            "sys_pol": abs(data_central[i]) * float(df_table.loc[i, "spol_err"]) / 100.0,
+        }
+        errors.append(error_per_bin)
+
+    error_definition = {
+        "stat": {"description": "Statistical uncertainty", "treatment": "ADD", "type": "UNCORR"},
+        "sys_lumi": {
+            "description": "Systematic uncertainties due to luminosity",
+            "treatment": "MULT",
+            "type": "CORR",
+        },
+        "sys_pol": {
+            "description": "Systematic uncertainties due to polarization",
+            "treatment": "MULT",
+            "type": "CORR",
+        },
+    }
+
+    with open("uncertainties.yaml", "w") as file:
+        yaml.dump({"definitions": error_definition, "bins": errors}, file, sort_keys=False)
+
+    return
+
+
+if __name__ == "__main__":
+    df_table = read_data("./rawdata/HEPData-ins1282448-v1-Table_7.yaml")
+    dump_data(df_table=df_table)

nnpdf_data/nnpdf_data/commondata/PHENIX-2009_SHP_200GEV_PI0/kinematics.yaml

@@ -0,0 +1,97 @@
+bins:
+- pT:
+    min: 1.0
+    mid: 1.3
+    max: 1.5
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 1.5
+    mid: 1.75
+    max: 2.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 2.0
+    mid: 2.23
+    max: 2.5
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 2.5
+    mid: 2.72
+    max: 3.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 3.0
+    mid: 3.22
+    max: 3.5
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 3.5
+    mid: 3.72
+    max: 4.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 4.0
+    mid: 4.39
+    max: 5.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 5.0
+    mid: 5.4
+    max: 6.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 6.0
+    mid: 6.41
+    max: 7.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 7.0
+    mid: 7.74
+    max: 9.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 9.0
+    mid: 10.0
+    max: 12.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35
+- pT:
+    min: 12.0
+    mid: 13.1
+    max: 15.0
+  eta:
+    min: -0.35
+    mid: 0.0
+    max: 0.35

nnpdf_data/nnpdf_data/commondata/PHENIX-2009_SHP_200GEV_PI0/metadata.yaml

@@ -0,0 +1,45 @@
+# Generalia
+setname: "PHENIX-2009_SHP_200GEV_PI0"
+
+version: 1
+version_comment: "Initial implementation"
+
+# References
+iNSPIRE:
+  url: "https://inspirehep.net/literature/1282448"
+hepdata:
+  url: "https://www.hepdata.net/record/ins1282448"
+  version: 1
+
+nnpdf_metadata:
+  nnpdf31_process: "SHP" # Single Hadron Production
+  experiment: "PHENIX"
+
+implemented_observables:
+  - observable_name: "ALL"
+    observable:
+      description: "Double helicity asymmetry in inclusive pi^0 production in polarized p+p collisions at sqrt(s)=200 GeV"
+      label: "$A_{LL}$"
+      units: ""
+    process_type: "SHP_ASY"
+    ndata: 12
+    tables: [7]
+    npoints: [12] # List of datapoints per table
+
+    # Plotting information
+    plotting:
+      kinematics_override: identity # TODO
+      dataset_label: "PHENIX ALL"
+      y_label: "$A_{LL}(p_T)$"
+      plot_x: pT
+    kinematic_coverage: [pT, eta]
+
+    kinematics:
+      variables:
+        pT: { description: "Transverse momentum", label: "$p_T$", units: "GeV" }
+        eta: { description: "pi^0 pseudorapidity", label: r"$\eta$", units: "" }
+      file: kinematics.yaml
+
+    data_central: data.yaml
+    data_uncertainties:
+      - uncertainties.yaml

nnpdf_data/nnpdf_data/commondata/PHENIX-2009_SHP_200GEV_PI0/rawdata/HEPData-ins1282448-v1-Table_7.yaml

@@ -0,0 +1,81 @@
+dependent_variables:
+- header: {name: ASYM(LL)}
+  qualifiers:
+  - {name: RE, value: P P --> PI0 < GAMMA GAMMA > X}
+  - {name: SQRT(S), units: GeV, value: '200.0'}
+  values:
+  - errors:
+    - {label: stat, symerror: 0.00085}
+    - {label: 'sys,rel.lumi.', symerror: 0.00035}
+    - {label: 'sys,pol.', symerror: 3.4%}
+    value: 0.00051
+  - errors:
+    - {label: stat, symerror: 0.00055}
+    - {label: 'sys,rel.lumi.', symerror: 0.00033}
+    - {label: 'sys,pol.', symerror: 3.5%}
+    value: 0.00096
+  - errors:
+    - {label: stat, symerror: 0.00058}
+    - {label: 'sys,rel.lumi.', symerror: 0.00034}
+    - {label: 'sys,pol.', symerror: 3.5%}
+    value: 0.00039
+  - errors:
+    - {label: stat, symerror: 0.00074}
+    - {label: 'sys,rel.lumi.', symerror: 0.00036}
+    - {label: 'sys,pol.', symerror: 3.4%}
+    value: -0.00023
+  - errors:
+    - {label: stat, symerror: 0.0011}
+    - {label: 'sys,rel.lumi.', symerror: 0.0004}
+    - {label: 'sys,pol.', symerror: 3.2%}
+    value: 0.0006
+  - errors:
+    - {label: stat, symerror: 0.0015}
+    - {label: 'sys,rel.lumi.', symerror: 0.00041}
+    - {label: 'sys,pol.', symerror: 3.1%}
+    value: 0.0002
+  - errors:
+    - {label: stat, symerror: 0.0018}
+    - {label: 'sys,rel.lumi.', symerror: 0.00043}
+    - {label: 'sys,pol.', symerror: 3.1%}
+    value: 0.0013
+  - errors:
+    - {label: stat, symerror: 0.0035}
+    - {label: 'sys,rel.lumi.', symerror: 0.00045}
+    - {label: 'sys,pol.', symerror: 3.0%}
+    value: 0.0026
+  - errors:
+    - {label: stat, symerror: 0.0061}
+    - {label: 'sys,rel.lumi.', symerror: 0.00045}
+    - {label: 'sys,pol.', symerror: 2.9%}
+    value: -0.0039
+  - errors:
+    - {label: stat, symerror: 0.0085}
+    - {label: 'sys,rel.lumi.', symerror: 0.00045}
+    - {label: 'sys,pol.', symerror: 2.9%}
+    value: 0.0096
+  - errors:
+    - {label: stat, symerror: 0.018}
+    - {label: 'sys,rel.lumi.', symerror: 0.00058}
+    - {label: 'sys,pol.', symerror: 3.3%}
+    value: 0.008
+  - errors:
+    - {label: stat, symerror: 0.069}
+    - {label: 'sys,rel.lumi.', symerror: 0.001}
+    - {label: 'sys,pol.', symerror: 3.0%}
+    value: 0.061
+independent_variables:
+- header: {name: PT(PI0), units: GEV}
+  values:
+  - {high: 1.5, low: 1.0, value: 1.3}
+  - {high: 2.0, low: 1.5}
+  - {high: 2.5, low: 2.0, value: 2.23}
+  - {high: 3.0, low: 2.5, value: 2.72}
+  - {high: 3.5, low: 3.0, value: 3.22}
+  - {high: 4.0, low: 3.5, value: 3.72}
+  - {high: 5.0, low: 4.0, value: 4.39}
+  - {high: 6.0, low: 5.0, value: 5.4}
+  - {high: 7.0, low: 6.0, value: 6.41}
+  - {high: 9.0, low: 7.0, value: 7.74}
+  - {high: 12.0, low: 9.0, value: 10.0}
+  - {high: 15.0, low: 12.0, value: 13.1}