Remove instances of extra covmat_to_artunc

Author: andrpie

nnpdf_data/nnpdf_data/commondata/DYE906_Z0_120GEV_DW/filter.py

@@ -5,9 +5,8 @@
 import pandas as pd
 import yaml
 
-from nnpdf_data.filter_utils.correlations import covmat_to_artunc
 from nnpdf_data.filter_utils.hera_utils import commondata
-from nnpdf_data.filter_utils.utils import prettify_float
+from nnpdf_data.filter_utils.utils import prettify_float, covmat_to_artunc
 
 yaml.add_representer(float, prettify_float)
 

nnpdf_data/nnpdf_data/commondata/LHCB_Z0J_13TEV_2022/filter.py

@@ -47,40 +47,6 @@
 
 # Utility functions
 # ________________________________________________________
-def OuterDecomposition(matrix):
-    r"""Compute the single value decomposition of the matrix A.
-
-    Returns the set of vector \sigma_{i}^{(k)} defined as
-
-        \sigma_{i}^{(k)} = v_{i}^{(k)} * \lambda^{(k)},
-
-    where v_{i}^{(k)} is the k-th eigenvector of the matrix A
-    associated to the k-th eigenvalue \lambda^{(k)}. The vectors
-    \sigma_{i}^{(k)} are defined such that
-
-        A_{ij} = \sum_{k=1}^{dim(A)} \sigma_{i}^{(k)} \sigma_{j}^{(k)}.
-
-    If A is a correlation matrix, for each data point i there will be
-    an associated vector \sigma_{i} = (sigma_{i}^{(1)}, ... , sigma_{i}^{(dim(A))}).
-
-    Parameters
-    ----------
-    A: the matrix to be decomposed.
-
-    Returns
-    -------
-    sigma: A matrix containing the set of vectors whose outer product reconstruct the original matrix.
-            The matrix has two indices sigma[i,k] - the first one refers to the component of the k-th
-            eigenvector, whereas the other one selects the eigenvalue.
-    """
-    eigenvalues, eigenvectors = np.linalg.eig(matrix)
-    sigma = np.zeros_like(matrix, dtype=float)
-    for i in range(np.size(eigenvalues)):
-        for j in range(np.size(eigenvalues)):
-            sigma[i][j] = eigenvectors[i][j] * np.sqrt(eigenvalues[j])
-    return sigma
-
-
 def ExtractCorrelation(yaml_file, N):
     """Convert a list of values into a matrix
 

nnpdf_data/nnpdf_data/commondata/LHCB_Z0_13TEV_2022/filter.py

@@ -45,40 +45,6 @@
 
 # Utility functions
 # ________________________________________________________
-def OuterDecomposition(matrix):
-    r"""Compute the single value decomposition of the matrix A.
-
-    Returns the set of vector \sigma_{i}^{(k)} defined as
-
-        \sigma_{i}^{(k)} = v_{i}^{(k)} * \lambda^{(k)},
-
-    where v_{i}^{(k)} is the k-th eigenvector of the matrix A
-    associated to the k-th eigenvalue \lambda^{(k)}. The vectors
-    \sigma_{i}^{(k)} are defined such that
-
-        A_{ij} = \sum_{k=1}^{dim(A)} \sigma_{i}^{(k)} \sigma_{j}^{(k)}.
-
-    If A is a correlation matrix, for each data point i there will be
-    an associated vector \sigma_{i} = (sigma_{i}^{(1)}, ... , sigma_{i}^{(dim(A))}).
-
-    Parameters
-    ----------
-    A: the matrix to be decomposed.
-
-    Returns
-    -------
-    sigma: A matrix containing the set of vectors whose outer product reconstruct the original matrix.
-            The matrix has two indices sigma[i,k] - the first one refers to the component of the k-th
-            eigenvector, whereas the other one selects the eigenvalue.
-    """
-    eigenvalues, eigenvectors = np.linalg.eig(matrix)
-    sigma = np.zeros_like(matrix, dtype=float)
-    for i in range(np.size(eigenvalues)):
-        for j in range(np.size(eigenvalues)):
-            sigma[i][j] = eigenvectors[i][j] * np.sqrt(eigenvalues[j])
-    return sigma
-
-
 def ExtractCorrelation(yaml_file, N):
     """Convert a list of values into a matrix
 

nnpdf_data/nnpdf_data/filter_utils/correlations.py

@@ -1,6 +1,6 @@
 import numpy as np
 from numpy.linalg import eig
-from nnpdf_data.filter_utils.utils import sort_eigenvalues
+from nnpdf_data.filter_utils.utils import covmat_to_artunc
 
 
 def upper_triangular_to_symmetric(ut, dim):
@@ -20,73 +20,3 @@ def compute_covmat(corrmat: np.ndarray, unc: np.ndarray, ndata: int) -> list:
     # multiply by stat err
     cov_mat = np.einsum("i,ij,j->ij", unc, corrmat, unc)
     return covmat_to_artunc(ndata, cov_mat.flatten().tolist())
-
-
-def covmat_to_artunc(ndata, covmat_list, no_of_norm_mat=0):
-    r"""Convert the covariance matrix to a matrix of
-    artificial uncertainties.
-
-    NOTE: This function has been taken from validphys.newcommondata_utils.
-    If those utils get merged in the future, we can replace this.
-
-    Parameters
-    ----------
-    ndata : integer
-        Number of data points
-    covmat_list : list
-        A one dimensional list which contains the elements of
-        the covariance matrix row by row. Since experimental
-        datasets provide these matrices in a list form, this
-        simplifies the implementation for the user.
-    no_of_norm_mat : int
-        Normalized covariance matrices may have an eigenvalue
-        of 0 due to the last data point not being linearly
-        independent. To allow for this, the user should input
-        the number of normalized matrices that are being treated
-        in an instance. For example, if a single covariance matrix
-        of a normalized distribution is being processed, the input
-        would be 1. If a covariance matrix contains pertains to
-        3 normalized datasets (i.e. cross covmat for 3
-        distributions), the input would be 3. The default value is
-        0 for when the covariance matrix pertains to an absolute
-        distribution.
-
-    Returns
-    -------
-    artunc : list
-        A two dimensional matrix (given as a list of lists)
-        which contains artificial uncertainties to be added
-        to the commondata. i^th row (or list) contains the
-        artificial uncertainties of the i^th data point.
-
-    """
-    epsilon = -0.0000000001
-    neg_eval_count = 0
-    psd_check = True
-    covmat = np.zeros((ndata, ndata))
-    artunc = np.zeros((ndata, ndata))
-    for i in range(len(covmat_list)):
-        a = i // ndata
-        b = i % ndata
-        covmat[a][b] = covmat_list[i]
-    eigval, eigvec = eig(covmat)
-    eigval, eigvec = sort_eigenvalues(eigval, eigvec)
-    for j in range(len(eigval)):
-        if eigval[j] < epsilon:
-            psd_check = False
-        elif eigval[j] > epsilon and eigval[j] <= 0:
-            neg_eval_count = neg_eval_count + 1
-            if neg_eval_count == (no_of_norm_mat + 1):
-                psd_check = False
-        elif eigval[j] > 0:
-            continue
-    if psd_check == False:
-        raise ValueError("The covariance matrix is not positive-semidefinite")
-    else:
-        for i in range(ndata):
-            for j in range(ndata):
-                if eigval[j] < 0:
-                    continue
-                else:
-                    artunc[i][j] = eigvec[i][j] * np.sqrt(eigval[j])
-    return artunc.tolist()