okstra 0.108.0 → 0.109.0

package/runtime/python/okstra_vendor/networkx/algorithms/node_classification.py

@@ -0,0 +1,219 @@
+"""This module provides the functions for node classification problem.
+
+The functions in this module are not imported
+into the top level `networkx` namespace.
+You can access these functions by importing
+the `networkx.algorithms.node_classification` modules,
+then accessing the functions as attributes of `node_classification`.
+For example:
+
+  >>> from networkx.algorithms import node_classification
+  >>> G = nx.path_graph(4)
+  >>> G.edges()
+  EdgeView([(0, 1), (1, 2), (2, 3)])
+  >>> G.nodes[0]["label"] = "A"
+  >>> G.nodes[3]["label"] = "B"
+  >>> node_classification.harmonic_function(G)
+  ['A', 'A', 'B', 'B']
+
+References
+----------
+Zhu, X., Ghahramani, Z., & Lafferty, J. (2003, August).
+Semi-supervised learning using gaussian fields and harmonic functions.
+In ICML (Vol. 3, pp. 912-919).
+"""
+
+import networkx as nx
+
+__all__ = ["harmonic_function", "local_and_global_consistency"]
+
+
+@nx.utils.not_implemented_for("directed")
+@nx._dispatchable(node_attrs="label_name")
+def harmonic_function(G, max_iter=30, label_name="label"):
+    """Node classification by Harmonic function
+
+    Function for computing Harmonic function algorithm by Zhu et al.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+    max_iter : int
+        maximum number of iterations allowed
+    label_name : string
+        name of target labels to predict
+
+    Returns
+    -------
+    predicted : list
+        List of length ``len(G)`` with the predicted labels for each node.
+
+    Raises
+    ------
+    NetworkXError
+        If no nodes in `G` have attribute `label_name`.
+
+    Examples
+    --------
+    >>> from networkx.algorithms import node_classification
+    >>> G = nx.path_graph(4)
+    >>> G.nodes[0]["label"] = "A"
+    >>> G.nodes[3]["label"] = "B"
+    >>> G.nodes(data=True)
+    NodeDataView({0: {'label': 'A'}, 1: {}, 2: {}, 3: {'label': 'B'}})
+    >>> G.edges()
+    EdgeView([(0, 1), (1, 2), (2, 3)])
+    >>> predicted = node_classification.harmonic_function(G)
+    >>> predicted
+    ['A', 'A', 'B', 'B']
+
+    References
+    ----------
+    Zhu, X., Ghahramani, Z., & Lafferty, J. (2003, August).
+    Semi-supervised learning using gaussian fields and harmonic functions.
+    In ICML (Vol. 3, pp. 912-919).
+    """
+    import numpy as np
+    import scipy as sp
+
+    X = nx.to_scipy_sparse_array(G)  # adjacency matrix
+    labels, label_dict = _get_label_info(G, label_name)
+
+    if labels.shape[0] == 0:
+        raise nx.NetworkXError(
+            f"No node on the input graph is labeled by '{label_name}'."
+        )
+
+    n_samples = X.shape[0]
+    n_classes = label_dict.shape[0]
+    F = np.zeros((n_samples, n_classes))
+
+    # Build propagation matrix
+    degrees = X.sum(axis=0)
+    degrees[degrees == 0] = 1  # Avoid division by 0
+    D = sp.sparse.dia_array((1.0 / degrees, 0), shape=(n_samples, n_samples)).tocsr()
+    P = (D @ X).tolil()
+    P[labels[:, 0]] = 0  # labels[:, 0] indicates IDs of labeled nodes
+    # Build base matrix
+    B = np.zeros((n_samples, n_classes))
+    B[labels[:, 0], labels[:, 1]] = 1
+
+    for _ in range(max_iter):
+        F = (P @ F) + B
+
+    return label_dict[np.argmax(F, axis=1)].tolist()
+
+
+@nx.utils.not_implemented_for("directed")
+@nx._dispatchable(node_attrs="label_name")
+def local_and_global_consistency(G, alpha=0.99, max_iter=30, label_name="label"):
+    """Node classification by Local and Global Consistency
+
+    Function for computing Local and global consistency algorithm by Zhou et al.
+
+    Parameters
+    ----------
+    G : NetworkX Graph
+    alpha : float
+        Clamping factor
+    max_iter : int
+        Maximum number of iterations allowed
+    label_name : string
+        Name of target labels to predict
+
+    Returns
+    -------
+    predicted : list
+        List of length ``len(G)`` with the predicted labels for each node.
+
+    Raises
+    ------
+    NetworkXError
+        If no nodes in `G` have attribute `label_name`.
+
+    Examples
+    --------
+    >>> from networkx.algorithms import node_classification
+    >>> G = nx.path_graph(4)
+    >>> G.nodes[0]["label"] = "A"
+    >>> G.nodes[3]["label"] = "B"
+    >>> G.nodes(data=True)
+    NodeDataView({0: {'label': 'A'}, 1: {}, 2: {}, 3: {'label': 'B'}})
+    >>> G.edges()
+    EdgeView([(0, 1), (1, 2), (2, 3)])
+    >>> predicted = node_classification.local_and_global_consistency(G)
+    >>> predicted
+    ['A', 'A', 'B', 'B']
+
+    References
+    ----------
+    Zhou, D., Bousquet, O., Lal, T. N., Weston, J., & Schölkopf, B. (2004).
+    Learning with local and global consistency.
+    Advances in neural information processing systems, 16(16), 321-328.
+    """
+    import numpy as np
+    import scipy as sp
+
+    X = nx.to_scipy_sparse_array(G)  # adjacency matrix
+    labels, label_dict = _get_label_info(G, label_name)
+
+    if labels.shape[0] == 0:
+        raise nx.NetworkXError(
+            f"No node on the input graph is labeled by '{label_name}'."
+        )
+
+    n_samples = X.shape[0]
+    n_classes = label_dict.shape[0]
+    F = np.zeros((n_samples, n_classes))
+
+    # Build propagation matrix
+    degrees = X.sum(axis=0)
+    degrees[degrees == 0] = 1  # Avoid division by 0
+    D2 = sp.sparse.dia_array(
+        (1.0 / np.sqrt(degrees), 0), shape=(n_samples, n_samples)
+    ).tocsr()
+    P = alpha * ((D2 @ X) @ D2)
+    # Build base matrix
+    B = np.zeros((n_samples, n_classes))
+    B[labels[:, 0], labels[:, 1]] = 1 - alpha
+
+    for _ in range(max_iter):
+        F = (P @ F) + B
+
+    return label_dict[np.argmax(F, axis=1)].tolist()
+
+
+def _get_label_info(G, label_name):
+    """Get and return information of labels from the input graph
+
+    Parameters
+    ----------
+    G : Network X graph
+    label_name : string
+        Name of the target label
+
+    Returns
+    -------
+    labels : numpy array, shape = [n_labeled_samples, 2]
+        Array of pairs of labeled node ID and label ID
+    label_dict : numpy array, shape = [n_classes]
+        Array of labels
+        i-th element contains the label corresponding label ID `i`
+    """
+    import numpy as np
+
+    labels = []
+    label_to_id = {}
+    lid = 0
+    for i, n in enumerate(G.nodes(data=True)):
+        if label_name in n[1]:
+            label = n[1][label_name]
+            if label not in label_to_id:
+                label_to_id[label] = lid
+                lid += 1
+            labels.append([i, label_to_id[label]])
+    labels = np.array(labels)
+    label_dict = np.array(
+        [label for label, _ in sorted(label_to_id.items(), key=lambda x: x[1])]
+    )
+    return (labels, label_dict)

package/runtime/python/okstra_vendor/networkx/algorithms/non_randomness.py

@@ -0,0 +1,155 @@
+r"""Computation of graph non-randomness."""
+
+import math
+
+import networkx as nx
+from networkx.utils import not_implemented_for
+
+__all__ = ["non_randomness"]
+
+
+@not_implemented_for("directed")
+@not_implemented_for("multigraph")
+@nx._dispatchable(edge_attrs="weight")
+def non_randomness(G, k=None, weight="weight"):
+    """Compute the non-randomness of a graph.
+
+    The first value $R_G$ is the sum of non-randomness values of all
+    edges within the graph (where the non-randomness of an edge tends to be
+    small when the two nodes linked by that edge are from two different
+    communities).
+
+    The second value $R_G^*$ is a relative measure that indicates
+    to what extent `G` is different from a random graph in terms
+    of probability. The closer it is to 0, the higher the likelihood
+    the graph was generated by an Erdős--Rényi model.
+
+    Parameters
+    ----------
+    G : NetworkX graph
+        Graph must be undirected, connected, and without self-loops.
+
+    k : int or None, optional (default=None)
+        The number of communities in `G`.
+        If `k` is not set, the function uses a default community detection
+        algorithm (:func:`~networkx.algorithms.community.label_propagation_communities`)
+        to set it.
+
+    weight : string or None, optional (default="weight")
+        The name of an edge attribute that holds the numerical value used
+        as a weight. If `None`, then each edge has weight 1, i.e., the graph is
+        binary.
+
+    Returns
+    -------
+    (float, float) tuple
+        The first value is $R_G$, the non-randomness of the graph,
+        the second is $R_G^*$, the relative non-randomness
+        w.r.t. the Erdős--Rényi model.
+
+    Raises
+    ------
+    NetworkXNotImplemented
+        If the input graph is directed or a multigraph.
+
+    NetworkXException
+        If the input graph is not connected.
+
+    NetworkXError
+        If the input graph contains self-loops or has no edges.
+
+    ValueError
+        If `k` is not in $\\{1, \\dots, n-1\\}$, where $n$ is the number of nodes,
+        or if `k` is such that the computed edge probability
+        $p = \\frac{2km}{n(n-k)}$ does not satisfy $0 < p < 1$.
+
+    Examples
+    --------
+    >>> G = nx.karate_club_graph()
+    >>> nr, nr_rd = nx.non_randomness(G, 2)
+    >>> nr, nr_rd = nx.non_randomness(G, 2, "weight")
+
+    When the number of communities `k` is not specified,
+    :func:`~networkx.algorithms.community.label_propagation_communities`
+    is used to compute it.
+    This algorithm can give different results depending on
+    the order of nodes and edges in the graph.
+    For example, while the following graphs are identical,
+    computing the non-randomness of each of them yields different results:
+
+    >>> G1, G2 = nx.Graph(), nx.Graph()
+    >>> G1.add_edges_from([(0, 1), (1, 2), (1, 3), (3, 4)])
+    >>> G2.add_edges_from([(0, 1), (1, 3), (1, 2), (3, 4)])
+    >>> [round(r, 6) for r in nx.non_randomness(G1)]
+    [-1.847759, -5.842437]
+    >>> [round(r, 6) for r in nx.non_randomness(G2)]
+    Traceback (most recent call last):
+     ...
+    ValueError: invalid number of communities for graph with 5 nodes and 4 edges: 2
+
+    This is because the community detection algorithm finds
+    1 community in `G1` and 2 communities in `G2`.
+    This can be resolved by specifying the number of communities `k`:
+
+    >>> [round(r, 6) for r in nx.non_randomness(G2, k=1)]
+    [-1.847759, -5.842437]
+
+    Notes
+    -----
+    If a `weight` argument is passed, this algorithm will use the eigenvalues
+    of the weighted adjacency matrix instead.
+
+    The output of this function corresponds to (4.4) and (4.5) in [1]_.
+    A lower value of $R^*_G$ indicates a more random graph;
+    one can think of $1 - \\Phi(R_G^*)$ as the similarity
+    between the graph and a random graph,
+    where $\\Phi(x)$ is the cumulative distribution function
+    of the standard normal distribution.
+
+    Theorem 2 in [2]_ states that for any graph $G$
+    with $n$ nodes, $m$ edges, and $k$ communities,
+    its non-randomness is bounded below by the non-randomness of an
+    $r$-regular graph (a graph where each node has degree $r$),
+    and bounded above by the non-randomness of an $l$-complete graph
+    (a graph where each community is a clique of $l$ nodes).
+
+    References
+    ----------
+    .. [1] Xiaowei Ying and Xintao Wu,
+           On Randomness Measures for Social Networks,
+           SIAM International Conference on Data Mining. 2009
+           https://doi.org/10.1137/1.9781611972795.61
+    .. [2] Ying, Xiaowei & Wu, Leting & Wu, Xintao. (2012).
+           A Spectrum-Based Framework for Quantifying Randomness of Social Networks.
+           IEEE Transactions on Knowledge and Data Engineering 23(12):1842--1856.
+           https://dl.acm.org/doi/abs/10.1109/TKDE.2010.218
+    """
+    import numpy as np
+
+    # corner case: graph has no edges
+    if nx.is_empty(G):
+        raise nx.NetworkXError("non_randomness not applicable to empty graphs")
+    if not nx.is_connected(G):
+        raise nx.NetworkXException("Non connected graph.")
+    if len(list(nx.selfloop_edges(G))) > 0:
+        raise nx.NetworkXError("Graph must not contain self-loops")
+
+    n = G.number_of_nodes()
+    m = G.number_of_edges()
+
+    if k is None:
+        k = len(tuple(nx.community.label_propagation_communities(G)))
+    if not 1 <= k < n or not 0 < (p := (2 * k * m) / (n * (n - k))) < 1:
+        err = (
+            f"invalid number of communities for graph with {n} nodes and {m} edges: {k}"
+        )
+        raise ValueError(err)
+
+    # eq. 4.4
+    eigenvalues = np.linalg.eigvals(nx.to_numpy_array(G, weight=weight))
+    nr = float(np.real(np.sum(eigenvalues[:k])))
+
+    # eq. 4.5
+    nr_rd = (nr - ((n - 2 * k) * p + k)) / math.sqrt(2 * k * p * (1 - p))
+
+    return nr, nr_rd

package/runtime/python/okstra_vendor/networkx/algorithms/operators/__init__.py

@@ -0,0 +1,4 @@
+from networkx.algorithms.operators.all import *
+from networkx.algorithms.operators.binary import *
+from networkx.algorithms.operators.product import *
+from networkx.algorithms.operators.unary import *

package/runtime/python/okstra_vendor/networkx/algorithms/operators/all.py

@@ -0,0 +1,324 @@
+"""Operations on many graphs."""
+
+from itertools import chain, repeat
+
+import networkx as nx
+
+__all__ = ["union_all", "compose_all", "disjoint_union_all", "intersection_all"]
+
+
+@nx._dispatchable(graphs="[graphs]", preserve_all_attrs=True, returns_graph=True)
+def union_all(graphs, rename=()):
+    """Returns the union of all graphs.
+
+    The graphs must be disjoint, otherwise an exception is raised.
+
+    Parameters
+    ----------
+    graphs : iterable
+       Iterable of NetworkX graphs
+
+    rename : iterable , optional
+       Node names of graphs can be changed by specifying the tuple
+       rename=('G-','H-') (for example).  Node "u" in G is then renamed
+       "G-u" and "v" in H is renamed "H-v". Infinite generators (like itertools.count)
+       are also supported.
+
+    Returns
+    -------
+    U : a graph with the same type as the first graph in list
+
+    Raises
+    ------
+    ValueError
+       If `graphs` is an empty list.
+
+    NetworkXError
+        In case of mixed type graphs, like MultiGraph and Graph, or directed and undirected graphs.
+
+    Notes
+    -----
+    For operating on mixed type graphs, they should be converted to the same type.
+    >>> G = nx.Graph()
+    >>> H = nx.DiGraph()
+    >>> GH = union_all([nx.DiGraph(G), H])
+
+    To force a disjoint union with node relabeling, use
+    disjoint_union_all(G,H) or convert_node_labels_to integers().
+
+    Graph, edge, and node attributes are propagated to the union graph.
+    If a graph attribute is present in multiple graphs, then the value
+    from the last graph in the list with that attribute is used.
+
+    Examples
+    --------
+    >>> G1 = nx.Graph([(1, 2), (2, 3)])
+    >>> G2 = nx.Graph([(4, 5), (5, 6)])
+    >>> result_graph = nx.union_all([G1, G2])
+    >>> result_graph.nodes()
+    NodeView((1, 2, 3, 4, 5, 6))
+    >>> result_graph.edges()
+    EdgeView([(1, 2), (2, 3), (4, 5), (5, 6)])
+
+    See Also
+    --------
+    union
+    disjoint_union_all
+    """
+    R = None
+    seen_nodes = set()
+
+    # rename graph to obtain disjoint node labels
+    def add_prefix(graph, prefix):
+        if prefix is None:
+            return graph
+
+        def label(x):
+            return f"{prefix}{x}"
+
+        return nx.relabel_nodes(graph, label)
+
+    rename = chain(rename, repeat(None))
+    graphs = (add_prefix(G, name) for G, name in zip(graphs, rename))
+
+    for i, G in enumerate(graphs):
+        G_nodes_set = set(G.nodes)
+        if i == 0:
+            # Union is the same type as first graph
+            R = G.__class__()
+        elif G.is_directed() != R.is_directed():
+            raise nx.NetworkXError("All graphs must be directed or undirected.")
+        elif G.is_multigraph() != R.is_multigraph():
+            raise nx.NetworkXError("All graphs must be graphs or multigraphs.")
+        elif not seen_nodes.isdisjoint(G_nodes_set):
+            raise nx.NetworkXError(
+                "The node sets of the graphs are not disjoint.\n"
+                "Use `rename` to specify prefixes for the graphs or use\n"
+                "disjoint_union(G1, G2, ..., GN)."
+            )
+
+        seen_nodes |= G_nodes_set
+        R.graph.update(G.graph)
+        R.add_nodes_from(G.nodes(data=True))
+        R.add_edges_from(
+            G.edges(keys=True, data=True) if G.is_multigraph() else G.edges(data=True)
+        )
+
+    if R is None:
+        raise ValueError("cannot apply union_all to an empty list")
+
+    return R
+
+
+@nx._dispatchable(graphs="[graphs]", preserve_all_attrs=True, returns_graph=True)
+def disjoint_union_all(graphs):
+    """Returns the disjoint union of all graphs.
+
+    This operation forces distinct integer node labels starting with 0
+    for the first graph in the list and numbering consecutively.
+
+    Parameters
+    ----------
+    graphs : iterable
+       Iterable of NetworkX graphs
+
+    Returns
+    -------
+    U : A graph with the same type as the first graph in list
+
+    Raises
+    ------
+    ValueError
+       If `graphs` is an empty list.
+
+    NetworkXError
+        In case of mixed type graphs, like MultiGraph and Graph, or directed and undirected graphs.
+
+    Examples
+    --------
+    >>> G1 = nx.Graph([(1, 2), (2, 3)])
+    >>> G2 = nx.Graph([(4, 5), (5, 6)])
+    >>> U = nx.disjoint_union_all([G1, G2])
+    >>> list(U.nodes())
+    [0, 1, 2, 3, 4, 5]
+    >>> list(U.edges())
+    [(0, 1), (1, 2), (3, 4), (4, 5)]
+
+    Notes
+    -----
+    For operating on mixed type graphs, they should be converted to the same type.
+
+    Graph, edge, and node attributes are propagated to the union graph.
+    If a graph attribute is present in multiple graphs, then the value
+    from the last graph in the list with that attribute is used.
+    """
+
+    def yield_relabeled(graphs):
+        first_label = 0
+        for G in graphs:
+            yield nx.convert_node_labels_to_integers(G, first_label=first_label)
+            first_label += len(G)
+
+    R = union_all(yield_relabeled(graphs))
+
+    return R
+
+
+@nx._dispatchable(graphs="[graphs]", preserve_all_attrs=True, returns_graph=True)
+def compose_all(graphs):
+    """Returns the composition of all graphs.
+
+    Composition is the simple union of the node sets and edge sets.
+    The node sets of the supplied graphs need not be disjoint.
+
+    Parameters
+    ----------
+    graphs : iterable
+       Iterable of NetworkX graphs
+
+    Returns
+    -------
+    C : A graph with the same type as the first graph in list
+
+    Raises
+    ------
+    ValueError
+       If `graphs` is an empty list.
+
+    NetworkXError
+        In case of mixed type graphs, like MultiGraph and Graph, or directed and undirected graphs.
+
+    Examples
+    --------
+    >>> G1 = nx.Graph([(1, 2), (2, 3)])
+    >>> G2 = nx.Graph([(3, 4), (5, 6)])
+    >>> C = nx.compose_all([G1, G2])
+    >>> list(C.nodes())
+    [1, 2, 3, 4, 5, 6]
+    >>> list(C.edges())
+    [(1, 2), (2, 3), (3, 4), (5, 6)]
+
+    Notes
+    -----
+    For operating on mixed type graphs, they should be converted to the same type.
+
+    Graph, edge, and node attributes are propagated to the union graph.
+    If a graph attribute is present in multiple graphs, then the value
+    from the last graph in the list with that attribute is used.
+    """
+    R = None
+
+    # add graph attributes, H attributes take precedent over G attributes
+    for i, G in enumerate(graphs):
+        if i == 0:
+            # create new graph
+            R = G.__class__()
+        elif G.is_directed() != R.is_directed():
+            raise nx.NetworkXError("All graphs must be directed or undirected.")
+        elif G.is_multigraph() != R.is_multigraph():
+            raise nx.NetworkXError("All graphs must be graphs or multigraphs.")
+
+        R.graph.update(G.graph)
+        R.add_nodes_from(G.nodes(data=True))
+        R.add_edges_from(
+            G.edges(keys=True, data=True) if G.is_multigraph() else G.edges(data=True)
+        )
+
+    if R is None:
+        raise ValueError("cannot apply compose_all to an empty list")
+
+    return R
+
+
+@nx._dispatchable(graphs="[graphs]", returns_graph=True)
+def intersection_all(graphs):
+    """Returns a new graph that contains only the nodes and the edges that exist in
+    all graphs.
+
+    Parameters
+    ----------
+    graphs : iterable
+       Iterable of NetworkX graphs
+
+    Returns
+    -------
+    R : A new graph with the same type as the first graph in list
+
+    Raises
+    ------
+    ValueError
+       If `graphs` is an empty list.
+
+    NetworkXError
+        In case of mixed type graphs, like MultiGraph and Graph, or directed and undirected graphs.
+
+    Notes
+    -----
+    For operating on mixed type graphs, they should be converted to the same type.
+
+    Attributes from the graph, nodes, and edges are not copied to the new
+    graph.
+
+    The resulting graph can be updated with attributes if desired.
+    For example, code which adds the minimum attribute for each node across all
+    graphs could work::
+
+        >>> g = nx.Graph()
+        >>> g.add_node(0, capacity=4)
+        >>> g.add_node(1, capacity=3)
+        >>> g.add_edge(0, 1)
+
+        >>> h = g.copy()
+        >>> h.nodes[0]["capacity"] = 2
+
+        >>> gh = nx.intersection_all([g, h])
+
+        >>> new_node_attr = {
+        ...     n: min(*(anyG.nodes[n].get("capacity", float("inf")) for anyG in [g, h]))
+        ...     for n in gh
+        ... }
+        >>> nx.set_node_attributes(gh, new_node_attr, "new_capacity")
+        >>> gh.nodes(data=True)
+        NodeDataView({0: {'new_capacity': 2}, 1: {'new_capacity': 3}})
+
+    Examples
+    --------
+    >>> G1 = nx.Graph([(1, 2), (2, 3)])
+    >>> G2 = nx.Graph([(2, 3), (3, 4)])
+    >>> R = nx.intersection_all([G1, G2])
+    >>> list(R.nodes())
+    [2, 3]
+    >>> list(R.edges())
+    [(2, 3)]
+
+    """
+    R = None
+
+    for i, G in enumerate(graphs):
+        G_nodes_set = set(G.nodes)
+        G_edges_set = set(G.edges)
+        if not G.is_directed():
+            if G.is_multigraph():
+                G_edges_set.update((v, u, k) for u, v, k in list(G_edges_set))
+            else:
+                G_edges_set.update((v, u) for u, v in list(G_edges_set))
+        if i == 0:
+            # create new graph
+            R = G.__class__()
+            node_intersection = G_nodes_set
+            edge_intersection = G_edges_set
+        elif G.is_directed() != R.is_directed():
+            raise nx.NetworkXError("All graphs must be directed or undirected.")
+        elif G.is_multigraph() != R.is_multigraph():
+            raise nx.NetworkXError("All graphs must be graphs or multigraphs.")
+        else:
+            node_intersection &= G_nodes_set
+            edge_intersection &= G_edges_set
+
+    if R is None:
+        raise ValueError("cannot apply intersection_all to an empty list")
+
+    R.add_nodes_from(node_intersection)
+    R.add_edges_from(edge_intersection)
+
+    return R