Fkparser

conda-recipe/meta.yaml

@@ -44,6 +44,7 @@ requirements:
         - sphinx # documentation
         - recommonmark
         - sphinx_rtd_theme
+        - dataclasses # [py==36]
 
 test:
     requires:

doc/sphinx/source/theory/FastInterface.rst

@@ -1,3 +1,5 @@
+.. _fktables:
+
 ============================================================
 Fast Interface (FK tables)
 ============================================================

doc/sphinx/source/vp/index.rst

@@ -14,3 +14,4 @@ vp-guide
    ./nnprofile.md
    ./scripts.md
    ./theorycov/index
+   ./pydataobjs.rst

doc/sphinx/source/vp/pydataobjs.rst

@@ -0,0 +1,29 @@
+.. _pyobjs:
+
+Python based data objects
+=========================
+
+Internal data formats such as PDF sets, CommonData, or :ref:`FKTables
+<fktables>` files are currently accessed through the `libnnpdf` C++ code
+(interfaced trough the SWIG wrappers). However there is a :ref:`project
+<https://github.com/NNPDF/nnpdf/issues?q=label%3Adestroyingc%2B%2B+>` underway
+to make these resources available in terms of standard Python containers
+(particularly numpy arrays and pandas dataframes). The objectives include
+simplifying the codebase, increasing the ease of use and enabling more advanced
+computation and storage strategies.
+
+Loading FKTables
+----------------
+
+Currently only FKTables can be directly without C++ code. This is implemented
+in the :py:mod:`validphys.fkparser` module. For example::
+
+    from validphys.fkparser import load_fktable
+    from validphys.loader import Loader
+    l = Loader()
+    fk = l.check_fktable(setname="ATLASTTBARTOT", theoryID=53, cfac=('QCD',))
+    res = load_fktable(fk)
+
+results in an :py:mod:`validphys.coredata.FKTableData` object containing all the information needed to compute a
+convolution. In particular the ``sigma`` property contains a dataframe
+representing the partonic cross-section (including the cfactors).

validphys2/src/validphys/coredata.py

@@ -0,0 +1,71 @@
+"""
+Data containers backed by Python managed memory (Numpy arrays and Pandas
+dataframes).  This module is intended to substitute large parts of the C++
+wrappers.
+
+"""
+import dataclasses
+import numpy as np
+import pandas as pd
+
+@dataclasses.dataclass(eq=False)
+class FKTableData:
+    """
+    Data contained in an FKTable
+
+    Parameters
+    ----------
+    hadronic : bool
+        Whether a hadronic (two PDFs) or a DIS (one PDF) convolution is needed.
+
+    Q0 : float
+        The scale at which the PDFs should be evaluated (in GeV).
+
+    ndata : int
+        The number of data points in the grid.
+
+    xgrid : array, shape (nx)
+        The points in x at which the PDFs should be evaluated.
+
+    sigma : DataFrame
+        For hadronic data, the columns are the indexes in the ``NfxNf`` list of
+        possible flavour combinations of two PDFs.  The MultiIndex contains
+        three keys, the data index, an index into ``xgrid`` for the first PDF
+        and an idex into ``xgrid`` for the second PDF, indicating if the points in
+        ``x`` where the PDF should be evaluated.
+
+        For DIS data, the columns are indexes in the ``Nf`` list of flavours.
+        The MultiIndex contains two keys, the data index and an index into
+        ``xgrid`` indicating the points in ``x`` where the PDF should be
+        evaluated.
+
+    metadata : dict
+        Other information contained in the FKTable.
+    """
+    hadronic: bool
+    Q0: float
+    ndata: int
+    xgrid: np.array
+    sigma: pd.DataFrame
+    metadata: dict = dataclasses.field(default_factory=dict, repr=False)
+
+@dataclasses.dataclass(eq=False)
+class CFactorData:
+    """
+    Data contained in a CFactor
+
+    Parameters
+    ----------
+
+    description : str
+        Information on how the data was obtained.
+
+    central_value : array, shape(ndata)
+        The value of the cfactor for each data point.
+
+    uncertainty : array, shape(ndata)
+        The absolute uncertainty on the cfactor if available.
+    """
+    description: str
+    central_value: np.array
+    uncertainty: np.array