okstra 0.108.0 → 0.109.0

package/runtime/python/okstra_vendor/networkx/algorithms/assortativity/correlation.py

@@ -0,0 +1,302 @@
+"""Node assortativity coefficients and correlation measures."""
+
+import networkx as nx
+from networkx.algorithms.assortativity.mixing import (
+    attribute_mixing_matrix,
+    degree_mixing_matrix,
+)
+from networkx.algorithms.assortativity.pairs import node_degree_xy
+
+__all__ = [
+    "degree_pearson_correlation_coefficient",
+    "degree_assortativity_coefficient",
+    "attribute_assortativity_coefficient",
+    "numeric_assortativity_coefficient",
+]
+
+
+@nx._dispatchable(edge_attrs="weight")
+def degree_assortativity_coefficient(G, x="out", y="in", weight=None, nodes=None):
+    """Compute degree assortativity of graph.
+
+    Assortativity measures the similarity of connections
+    in the graph with respect to the node degree.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    x: string ('in','out')
+       The degree type for source node (directed graphs only).
+
+    y: string ('in','out')
+       The degree type for target node (directed graphs only).
+
+    weight: string or None, optional (default=None)
+       The edge attribute that holds the numerical value used
+       as a weight.  If None, then each edge has weight 1.
+       The degree is the sum of the edge weights adjacent to the node.
+
+    nodes: list or iterable (optional)
+        Compute degree assortativity only for nodes in container.
+        The default is all nodes.
+
+    Returns
+    -------
+    r : float
+       Assortativity of graph by degree.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(4)
+    >>> r = nx.degree_assortativity_coefficient(G)
+    >>> print(f"{r:3.1f}")
+    -0.5
+
+    See Also
+    --------
+    attribute_assortativity_coefficient
+    numeric_assortativity_coefficient
+    degree_mixing_dict
+    degree_mixing_matrix
+
+    Notes
+    -----
+    This computes Eq. (21) in Ref. [1]_ , where e is the joint
+    probability distribution (mixing matrix) of the degrees.  If G is
+    directed than the matrix e is the joint probability of the
+    user-specified degree type for the source and target.
+
+    References
+    ----------
+    .. [1] M. E. J. Newman, Mixing patterns in networks,
+       Physical Review E, 67 026126, 2003
+    .. [2] Foster, J.G., Foster, D.V., Grassberger, P. & Paczuski, M.
+       Edge direction and the structure of networks, PNAS 107, 10815-20 (2010).
+    """
+    if nodes is None:
+        nodes = G.nodes
+
+    degrees = None
+
+    if G.is_directed():
+        indeg = (
+            {d for _, d in G.in_degree(nodes, weight=weight)}
+            if "in" in (x, y)
+            else set()
+        )
+        outdeg = (
+            {d for _, d in G.out_degree(nodes, weight=weight)}
+            if "out" in (x, y)
+            else set()
+        )
+        degrees = set.union(indeg, outdeg)
+    else:
+        degrees = {d for _, d in G.degree(nodes, weight=weight)}
+
+    mapping = {d: i for i, d in enumerate(degrees)}
+    M = degree_mixing_matrix(G, x=x, y=y, nodes=nodes, weight=weight, mapping=mapping)
+
+    return _numeric_ac(M, mapping=mapping)
+
+
+@nx._dispatchable(edge_attrs="weight")
+def degree_pearson_correlation_coefficient(G, x="out", y="in", weight=None, nodes=None):
+    """Compute degree assortativity of graph.
+
+    Assortativity measures the similarity of connections
+    in the graph with respect to the node degree.
+
+    This is the same as degree_assortativity_coefficient but uses the
+    potentially faster scipy.stats.pearsonr function.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    x: string ('in','out')
+       The degree type for source node (directed graphs only).
+
+    y: string ('in','out')
+       The degree type for target node (directed graphs only).
+
+    weight: string or None, optional (default=None)
+       The edge attribute that holds the numerical value used
+       as a weight.  If None, then each edge has weight 1.
+       The degree is the sum of the edge weights adjacent to the node.
+
+    nodes: list or iterable (optional)
+        Compute pearson correlation of degrees only for specified nodes.
+        The default is all nodes.
+
+    Returns
+    -------
+    r : float
+       Assortativity of graph by degree.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(4)
+    >>> r = nx.degree_pearson_correlation_coefficient(G)
+    >>> print(f"{r:3.1f}")
+    -0.5
+
+    Notes
+    -----
+    This calls scipy.stats.pearsonr.
+
+    References
+    ----------
+    .. [1] M. E. J. Newman, Mixing patterns in networks
+           Physical Review E, 67 026126, 2003
+    .. [2] Foster, J.G., Foster, D.V., Grassberger, P. & Paczuski, M.
+       Edge direction and the structure of networks, PNAS 107, 10815-20 (2010).
+    """
+    import scipy as sp
+
+    xy = node_degree_xy(G, x=x, y=y, nodes=nodes, weight=weight)
+    x, y = zip(*xy)
+    return float(sp.stats.pearsonr(x, y)[0])
+
+
+@nx._dispatchable(node_attrs="attribute")
+def attribute_assortativity_coefficient(G, attribute, nodes=None):
+    """Compute assortativity for node attributes.
+
+    Assortativity measures the similarity of connections
+    in the graph with respect to the given attribute.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    attribute : string
+        Node attribute key
+
+    nodes: list or iterable (optional)
+        Compute attribute assortativity for nodes in container.
+        The default is all nodes.
+
+    Returns
+    -------
+    r: float
+       Assortativity of graph for given attribute
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_nodes_from([0, 1], color="red")
+    >>> G.add_nodes_from([2, 3], color="blue")
+    >>> G.add_edges_from([(0, 1), (2, 3)])
+    >>> print(nx.attribute_assortativity_coefficient(G, "color"))
+    1.0
+
+    Notes
+    -----
+    This computes Eq. (2) in Ref. [1]_ , (trace(M)-sum(M^2))/(1-sum(M^2)),
+    where M is the joint probability distribution (mixing matrix)
+    of the specified attribute.
+
+    References
+    ----------
+    .. [1] M. E. J. Newman, Mixing patterns in networks,
+       Physical Review E, 67 026126, 2003
+    """
+    M = attribute_mixing_matrix(G, attribute, nodes)
+    return attribute_ac(M)
+
+
+@nx._dispatchable(node_attrs="attribute")
+def numeric_assortativity_coefficient(G, attribute, nodes=None):
+    """Compute assortativity for numerical node attributes.
+
+    Assortativity measures the similarity of connections
+    in the graph with respect to the given numeric attribute.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    attribute : string
+        Node attribute key.
+
+    nodes: list or iterable (optional)
+        Compute numeric assortativity only for attributes of nodes in
+        container. The default is all nodes.
+
+    Returns
+    -------
+    r: float
+       Assortativity of graph for given attribute
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_nodes_from([0, 1], size=2)
+    >>> G.add_nodes_from([2, 3], size=3)
+    >>> G.add_edges_from([(0, 1), (2, 3)])
+    >>> print(nx.numeric_assortativity_coefficient(G, "size"))
+    1.0
+
+    Notes
+    -----
+    This computes Eq. (21) in Ref. [1]_ , which is the Pearson correlation
+    coefficient of the specified (scalar valued) attribute across edges.
+
+    References
+    ----------
+    .. [1] M. E. J. Newman, Mixing patterns in networks
+           Physical Review E, 67 026126, 2003
+    """
+    if nodes is None:
+        nodes = G.nodes
+    vals = {G.nodes[n][attribute] for n in nodes}
+    mapping = {d: i for i, d in enumerate(vals)}
+    M = attribute_mixing_matrix(G, attribute, nodes, mapping)
+    return _numeric_ac(M, mapping)
+
+
+def attribute_ac(M):
+    """Compute assortativity for attribute matrix M.
+
+    Parameters
+    ----------
+    M : numpy.ndarray
+        2D ndarray representing the attribute mixing matrix.
+
+    Notes
+    -----
+    This computes Eq. (2) in Ref. [1]_ , (trace(e)-sum(e^2))/(1-sum(e^2)),
+    where e is the joint probability distribution (mixing matrix)
+    of the specified attribute.
+
+    References
+    ----------
+    .. [1] M. E. J. Newman, Mixing patterns in networks,
+       Physical Review E, 67 026126, 2003
+    """
+    if M.sum() != 1.0:
+        M = M / M.sum()
+    s = (M @ M).sum()
+    t = M.trace()
+    r = (t - s) / (1 - s)
+    return float(r)
+
+
+def _numeric_ac(M, mapping):
+    # M is a 2D numpy array
+    # numeric assortativity coefficient, pearsonr
+    import numpy as np
+
+    if M.sum() != 1.0:
+        M = M / M.sum()
+    x = np.array(list(mapping.keys()))
+    y = x  # x and y have the same support
+    idx = list(mapping.values())
+    a = M.sum(axis=0)
+    b = M.sum(axis=1)
+    vara = (a[idx] * x**2).sum() - ((a[idx] * x).sum()) ** 2
+    varb = (b[idx] * y**2).sum() - ((b[idx] * y).sum()) ** 2
+    xy = np.outer(x, y)
+    ab = np.outer(a[idx], b[idx])
+    return float((xy * (M - ab)).sum() / np.sqrt(vara * varb))

package/runtime/python/okstra_vendor/networkx/algorithms/assortativity/mixing.py

@@ -0,0 +1,255 @@
+"""
+Mixing matrices for node attributes and degree.
+"""
+
+import networkx as nx
+from networkx.algorithms.assortativity.pairs import node_attribute_xy, node_degree_xy
+from networkx.utils import dict_to_numpy_array
+
+__all__ = [
+    "attribute_mixing_matrix",
+    "attribute_mixing_dict",
+    "degree_mixing_matrix",
+    "degree_mixing_dict",
+    "mixing_dict",
+]
+
+
+@nx._dispatchable(node_attrs="attribute")
+def attribute_mixing_dict(G, attribute, nodes=None, normalized=False):
+    """Returns dictionary representation of mixing matrix for attribute.
+
+    Parameters
+    ----------
+    G : graph
+       NetworkX graph object.
+
+    attribute : string
+       Node attribute key.
+
+    nodes: list or iterable (optional)
+        Unse nodes in container to build the dict. The default is all nodes.
+
+    normalized : bool (default=False)
+       Return counts if False or probabilities if True.
+
+    Examples
+    --------
+    >>> G = nx.Graph()
+    >>> G.add_nodes_from([0, 1], color="red")
+    >>> G.add_nodes_from([2, 3], color="blue")
+    >>> G.add_edge(1, 3)
+    >>> d = nx.attribute_mixing_dict(G, "color")
+    >>> print(d["red"]["blue"])
+    1
+    >>> print(d["blue"]["red"])  # d symmetric for undirected graphs
+    1
+
+    Returns
+    -------
+    d : dictionary
+       Counts or joint probability of occurrence of attribute pairs.
+    """
+    xy_iter = node_attribute_xy(G, attribute, nodes)
+    return mixing_dict(xy_iter, normalized=normalized)
+
+
+@nx._dispatchable(node_attrs="attribute")
+def attribute_mixing_matrix(G, attribute, nodes=None, mapping=None, normalized=True):
+    """Returns mixing matrix for attribute.
+
+    Parameters
+    ----------
+    G : graph
+       NetworkX graph object.
+
+    attribute : string
+       Node attribute key.
+
+    nodes: list or iterable (optional)
+        Use only nodes in container to build the matrix. The default is
+        all nodes.
+
+    mapping : dictionary, optional
+       Mapping from node attribute to integer index in matrix.
+       If not specified, an arbitrary ordering will be used.
+
+    normalized : bool (default=True)
+       Return counts if False or probabilities if True.
+
+    Returns
+    -------
+    m: numpy array
+       Counts or joint probability of occurrence of attribute pairs.
+
+    Notes
+    -----
+    If each node has a unique attribute value, the unnormalized mixing matrix
+    will be equal to the adjacency matrix. To get a denser mixing matrix,
+    the rounding can be performed to form groups of nodes with equal values.
+    For example, the exact height of persons in cm (180.79155222, 163.9080892,
+    163.30095355, 167.99016217, 168.21590163, ...) can be rounded to (180, 163,
+    163, 168, 168, ...).
+
+    Definitions of attribute mixing matrix vary on whether the matrix
+    should include rows for attribute values that don't arise. Here we
+    do not include such empty-rows. But you can force them to appear
+    by inputting a `mapping` that includes those values.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(3)
+    >>> gender = {0: "male", 1: "female", 2: "female"}
+    >>> nx.set_node_attributes(G, gender, "gender")
+    >>> mapping = {"male": 0, "female": 1}
+    >>> mix_mat = nx.attribute_mixing_matrix(G, "gender", mapping=mapping)
+    >>> mix_mat
+    array([[0.  , 0.25],
+           [0.25, 0.5 ]])
+    """
+    d = attribute_mixing_dict(G, attribute, nodes)
+    a = dict_to_numpy_array(d, mapping=mapping)
+    if normalized:
+        a = a / a.sum()
+    return a
+
+
+@nx._dispatchable(edge_attrs="weight")
+def degree_mixing_dict(G, x="out", y="in", weight=None, nodes=None, normalized=False):
+    """Returns dictionary representation of mixing matrix for degree.
+
+    Parameters
+    ----------
+    G : graph
+        NetworkX graph object.
+
+    x: string ('in','out')
+       The degree type for source node (directed graphs only).
+
+    y: string ('in','out')
+       The degree type for target node (directed graphs only).
+
+    weight: string or None, optional (default=None)
+       The edge attribute that holds the numerical value used
+       as a weight.  If None, then each edge has weight 1.
+       The degree is the sum of the edge weights adjacent to the node.
+
+    normalized : bool (default=False)
+        Return counts if False or probabilities if True.
+
+    Returns
+    -------
+    d: dictionary
+       Counts or joint probability of occurrence of degree pairs.
+    """
+    xy_iter = node_degree_xy(G, x=x, y=y, nodes=nodes, weight=weight)
+    return mixing_dict(xy_iter, normalized=normalized)
+
+
+@nx._dispatchable(edge_attrs="weight")
+def degree_mixing_matrix(
+    G, x="out", y="in", weight=None, nodes=None, normalized=True, mapping=None
+):
+    """Returns mixing matrix for attribute.
+
+    Parameters
+    ----------
+    G : graph
+       NetworkX graph object.
+
+    x: string ('in','out')
+       The degree type for source node (directed graphs only).
+
+    y: string ('in','out')
+       The degree type for target node (directed graphs only).
+
+    nodes: list or iterable (optional)
+        Build the matrix using only nodes in container.
+        The default is all nodes.
+
+    weight: string or None, optional (default=None)
+       The edge attribute that holds the numerical value used
+       as a weight.  If None, then each edge has weight 1.
+       The degree is the sum of the edge weights adjacent to the node.
+
+    normalized : bool (default=True)
+       Return counts if False or probabilities if True.
+
+    mapping : dictionary, optional
+       Mapping from node degree to integer index in matrix.
+       If not specified, an arbitrary ordering will be used.
+
+    Returns
+    -------
+    m: numpy array
+       Counts, or joint probability, of occurrence of node degree.
+
+    Notes
+    -----
+    Definitions of degree mixing matrix vary on whether the matrix
+    should include rows for degree values that don't arise. Here we
+    do not include such empty-rows. But you can force them to appear
+    by inputting a `mapping` that includes those values. See examples.
+
+    Examples
+    --------
+    >>> G = nx.star_graph(3)
+    >>> mix_mat = nx.degree_mixing_matrix(G)
+    >>> mix_mat
+    array([[0. , 0.5],
+           [0.5, 0. ]])
+
+    If you want every possible degree to appear as a row, even if no nodes
+    have that degree, use `mapping` as follows,
+
+    >>> max_degree = max(deg for n, deg in G.degree)
+    >>> mapping = {x: x for x in range(max_degree + 1)}  # identity mapping
+    >>> mix_mat = nx.degree_mixing_matrix(G, mapping=mapping)
+    >>> mix_mat
+    array([[0. , 0. , 0. , 0. ],
+           [0. , 0. , 0. , 0.5],
+           [0. , 0. , 0. , 0. ],
+           [0. , 0.5, 0. , 0. ]])
+    """
+    d = degree_mixing_dict(G, x=x, y=y, nodes=nodes, weight=weight)
+    a = dict_to_numpy_array(d, mapping=mapping)
+    if normalized:
+        a = a / a.sum()
+    return a
+
+
+def mixing_dict(xy, normalized=False):
+    """Returns a dictionary representation of mixing matrix.
+
+    Parameters
+    ----------
+    xy : list or container of two-tuples
+       Pairs of (x,y) items.
+
+    attribute : string
+       Node attribute key
+
+    normalized : bool (default=False)
+       Return counts if False or probabilities if True.
+
+    Returns
+    -------
+    d: dictionary
+       Counts or Joint probability of occurrence of values in xy.
+    """
+    d = {}
+    psum = 0.0
+    for x, y in xy:
+        if x not in d:
+            d[x] = {}
+        if y not in d:
+            d[y] = {}
+        v = d[x].get(y, 0)
+        d[x][y] = v + 1
+        psum += 1
+
+    if normalized:
+        for _, jdict in d.items():
+            for j in jdict:
+                jdict[j] /= psum
+    return d

package/runtime/python/okstra_vendor/networkx/algorithms/assortativity/neighbor_degree.py

@@ -0,0 +1,160 @@
+import networkx as nx
+
+__all__ = ["average_neighbor_degree"]
+
+
+@nx._dispatchable(edge_attrs="weight")
+def average_neighbor_degree(G, source="out", target="out", nodes=None, weight=None):
+    r"""Returns the average degree of the neighborhood of each node.
+
+    In an undirected graph, the neighborhood `N(i)` of node `i` contains the
+    nodes that are connected to `i` by an edge.
+
+    For directed graphs, `N(i)` is defined according to the parameter `source`:
+
+        - if source is 'in', then `N(i)` consists of predecessors of node `i`.
+        - if source is 'out', then `N(i)` consists of successors of node `i`.
+        - if source is 'in+out', then `N(i)` is both predecessors and successors.
+
+    The average neighborhood degree of a node `i` is
+
+    .. math::
+
+        k_{nn,i} = \frac{1}{|N(i)|} \sum_{j \in N(i)} k_j
+
+    where `N(i)` are the neighbors of node `i` and `k_j` is
+    the degree of node `j` which belongs to `N(i)`. For weighted
+    graphs, an analogous measure can be defined [1]_,
+
+    .. math::
+
+        k_{nn,i}^{w} = \frac{1}{s_i} \sum_{j \in N(i)} w_{ij} k_j
+
+    where `s_i` is the weighted degree of node `i`, `w_{ij}`
+    is the weight of the edge that links `i` and `j` and
+    `N(i)` are the neighbors of node `i`.
+
+
+    Parameters
+    ----------
+    G : NetworkX graph
+
+    source : string ("in"|"out"|"in+out"), optional (default="out")
+       Directed graphs only.
+       Use "in"- or "out"-neighbors of source node.
+
+    target : string ("in"|"out"|"in+out"), optional (default="out")
+       Directed graphs only.
+       Use "in"- or "out"-degree for target node.
+
+    nodes : list or iterable, optional (default=G.nodes)
+        Compute neighbor degree only for specified nodes.
+
+    weight : string or None, optional (default=None)
+       The edge attribute that holds the numerical value used as a weight.
+       If None, then each edge has weight 1.
+
+    Returns
+    -------
+    d: dict
+       A dictionary keyed by node to the average degree of its neighbors.
+
+    Raises
+    ------
+    NetworkXError
+        If either `source` or `target` are not one of 'in', 'out', or 'in+out'.
+        If either `source` or `target` is passed for an undirected graph.
+
+    Examples
+    --------
+    >>> G = nx.path_graph(4)
+    >>> G.edges[0, 1]["weight"] = 5
+    >>> G.edges[2, 3]["weight"] = 3
+
+    >>> nx.average_neighbor_degree(G)
+    {0: 2.0, 1: 1.5, 2: 1.5, 3: 2.0}
+    >>> nx.average_neighbor_degree(G, weight="weight")
+    {0: 2.0, 1: 1.1666666666666667, 2: 1.25, 3: 2.0}
+
+    >>> G = nx.DiGraph()
+    >>> nx.add_path(G, [0, 1, 2, 3])
+    >>> nx.average_neighbor_degree(G, source="in", target="in")
+    {0: 0.0, 1: 0.0, 2: 1.0, 3: 1.0}
+
+    >>> nx.average_neighbor_degree(G, source="out", target="out")
+    {0: 1.0, 1: 1.0, 2: 0.0, 3: 0.0}
+
+    See Also
+    --------
+    average_degree_connectivity
+
+    References
+    ----------
+    .. [1] A. Barrat, M. Barthélemy, R. Pastor-Satorras, and A. Vespignani,
+       "The architecture of complex weighted networks".
+       PNAS 101 (11): 3747–3752 (2004).
+    """
+    if G.is_directed():
+        if source == "in":
+            source_degree = G.in_degree
+        elif source == "out":
+            source_degree = G.out_degree
+        elif source == "in+out":
+            source_degree = G.degree
+        else:
+            raise nx.NetworkXError(
+                f"source argument {source} must be 'in', 'out' or 'in+out'"
+            )
+
+        if target == "in":
+            target_degree = G.in_degree
+        elif target == "out":
+            target_degree = G.out_degree
+        elif target == "in+out":
+            target_degree = G.degree
+        else:
+            raise nx.NetworkXError(
+                f"target argument {target} must be 'in', 'out' or 'in+out'"
+            )
+    else:
+        if source != "out" or target != "out":
+            raise nx.NetworkXError(
+                f"source and target arguments are only supported for directed graphs"
+            )
+        source_degree = target_degree = G.degree
+
+    # precompute target degrees -- should *not* be weighted degree
+    t_deg = dict(target_degree())
+
+    # Set up both predecessor and successor neighbor dicts leaving empty if not needed
+    G_P = G_S = {n: {} for n in G}
+    if G.is_directed():
+        # "in" or "in+out" cases: G_P contains predecessors
+        if "in" in source:
+            G_P = G.pred
+        # "out" or "in+out" cases: G_S contains successors
+        if "out" in source:
+            G_S = G.succ
+    else:
+        # undirected leave G_P empty but G_S is the adjacency
+        G_S = G.adj
+
+    # Main loop: Compute average degree of neighbors
+    avg = {}
+    for n, deg in source_degree(nodes, weight=weight):
+        # handle degree zero average
+        if deg == 0:
+            avg[n] = 0.0
+            continue
+
+        # we sum over both G_P and G_S, but one of the two is usually empty.
+        if weight is None:
+            avg[n] = (
+                sum(t_deg[nbr] for nbr in G_S[n]) + sum(t_deg[nbr] for nbr in G_P[n])
+            ) / deg
+        else:
+            avg[n] = (
+                sum(dd.get(weight, 1) * t_deg[nbr] for nbr, dd in G_S[n].items())
+                + sum(dd.get(weight, 1) * t_deg[nbr] for nbr, dd in G_P[n].items())
+            ) / deg
+    return avg