Merge pull request #2472 from NNPDF/2471-flawed-function

Remove outdated functions

Author: achiefa

validphys2/src/validphys/n3fit_data.py

@@ -705,117 +705,6 @@ def replica_mask(exps_masks, replica, experiments_index, diagonal_basis=True):
     return df_tr, df_vl
 
 
-def replica_validation_mask(exps_tr_masks, replica, experiments_index, diagonal_basis=True):
-    """Save the boolean mask used to split data into training and validation
-    for a given replica as a pandas DataFrame, indexed by
-    :py:func:`validphys.results.experiments_index`. Can be used to reconstruct
-    the training and validation data used in a fit.
-
-    Parameters
-    ----------
-    exps_tr_masks: list[list[np.array]]
-        Result of :py:func:`tr_masks` collected over experiments, which creates
-        the nested structure. The outer list is
-        len(group_dataset_inputs_by_experiment) and the inner-most list has an
-        array for each dataset in that particular experiment - as defined by the
-        metadata. The arrays should be 1-D boolean arrays which can be used as
-        masks.
-    replica: int
-        The index of the replica.
-    experiments_index: pd.MultiIndex
-        Index returned by :py:func:`validphys.results.experiments_index`.
-
-
-    Example
-    -------
-    >>> from validphys.api import API
-    >>> ds_inp = [
-    ...     {'dataset': 'NMC', 'frac': 0.75},
-    ...     {'dataset': 'ATLASTTBARTOT', 'cfac':['QCD'], 'frac': 0.75},
-    ...     {'dataset': 'CMSZDIFF12', 'cfac':('QCD', 'NRM'), 'sys':10, 'frac': 0.75}
-    ... ]
-    >>> API.replica_training_mask(dataset_inputs=ds_inp, replica=1, trvlseed=123, theoryid=162, use_cuts="nocuts", mcseed=None, genrep=False)
-                         replica 1
-    group dataset    id
-    NMC   NMC        0        True
-                    1        True
-                    2       False
-                    3        True
-                    4        True
-    ...                        ...
-    CMS   CMSZDIFF12 45       True
-                    46       True
-                    47       True
-                    48      False
-                    49       True
-
-    [345 rows x 1 columns]
-    """
-
-    all_masks = np.concatenate(
-        [ds_mask for exp_masks in exps_masks for ds_mask.vl_masks in exp_masks]
-    )
-    if diagonal_basis:
-        return pd.DataFrame(
-            all_masks,
-            columns=[f"replica {replica}"],
-            index=[f"eigenmode {i}" for i in range(len(all_masks))],
-        )
-    else:
-        return pd.DataFrame(all_masks, columns=[f"replica {replica}"], index=experiments_index)
-
-
-replicas_mask = collect("replica_mask", ("replicas",))
-
-
-@table
-def training_mask_table(training_mask):
-    """Same as ``training_mask`` but with a table decorator"""
-    return training_mask
-
-
-def training_mask(replicas_mask):
-    """Save the boolean mask used to split data into training and validation
-    for each replica as a pandas DataFrame, indexed by
-    :py:func:`validphys.results.experiments_index`. Can be used to reconstruct
-    the training and validation data used in a fit.
-
-    Parameters
-    ----------
-    replicas_exps_tr_masks: list[list[list[np.array]]]
-        Result of :py:func:`replica_tr_masks` collected over replicas
-
-    Example
-    -------
-    >>> from validphys.api import API
-    >>> from reportengine.namespaces import NSList
-    >>> # create namespace list for collects over replicas.
-    >>> reps = NSList(list(range(1, 4)), nskey="replica")
-    >>> ds_inp = [
-    ...     {'dataset': 'NMC_NC_NOTFIXED_P_EM-SIGMARED', 'variant': 'legacy', 'frac': 0.75},
-    ...     {'dataset': 'ATLAS_TTBAR_7TEV_TOT_X-SEC', 'variant': 'legacy_theory', 'frac': 0.75},
-    ...     {'dataset': 'CMS_Z0J_8TEV_PT-Y', 'cfac':('NRM',), 'frac': 0.75},
-    ... ]
-    >>> API.training_mask(dataset_inputs=ds_inp, nreplica=3, trvlseed=123, theoryid=40_000_000, use_cuts="nocuts", mcseed=None, genrep=False)
-                                                    replica 1  replica 2  replica 3
-        group dataset                       id
-        NMC   NMC_NC_NOTFIXED_P_EM-SIGMARED 0        True      False      False
-                                            1        True       True       True
-                                            2        True      False       True
-                                            3        True       True      False
-                                            4       False       True       True
-        ...                                           ...        ...        ...
-        CMS   CMS_Z0J_8TEV_PT-Y             45       True      False       True
-                                            46       True       True       True
-                                            47       True      False       True
-                                            48       True       True       True
-                                            49       True      False       True
-        [343 rows x 3 columns]
-
-    """
-    return pd.concat(replicas_training_mask, axis=1)
-
-
 def _fitting_lagrange_dict(lambdadataset):
     """Loads a generic lambda dataset, often used for positivity and integrability datasets
     For more information see :py:func:`validphys.n3fit_data_utils.positivity_reader`.