from warnings import warn

import numpy as np

import scipy.sparse
import scipy.sparse.csgraph

from sklearn.manifold import SpectralEmbedding
from sklearn.metrics import pairwise_distances
from sklearn.metrics.pairwise import _VALID_METRICS as SKLEARN_PAIRWISE_VALID_METRICS

from umap.distances import pairwise_special_metric, SPECIAL_METRICS
from umap.sparse import SPARSE_SPECIAL_METRICS, sparse_named_distances


def component_layout(
    data,
    n_components,
    component_labels,
    dim,
    random_state,
    metric="euclidean",
    metric_kwds={},
):
    """Provide a layout relating the separate connected components. This is done
    by taking the centroid of each component and then performing a spectral embedding
    of the centroids.

    Parameters
    ----------
    data: array of shape (n_samples, n_features)
        The source data -- required so we can generate centroids for each
        connected component of the graph.

    n_components: int
        The number of distinct components to be layed out.

    component_labels: array of shape (n_samples)
        For each vertex in the graph the label of the component to
        which the vertex belongs.

    dim: int
        The chosen embedding dimension.

    metric: string or callable (optional, default 'euclidean')
        The metric used to measure distances among the source data points.

    metric_kwds: dict (optional, default {})
        Keyword arguments to be passed to the metric function.
        If metric is 'precomputed', 'linkage' keyword can be used to specify
        'average', 'complete', or 'single' linkage. Default is 'average'

    Returns
    -------
    component_embedding: array of shape (n_components, dim)
        The ``dim``-dimensional embedding of the ``n_components``-many
        connected components.
    """
    if data is None:
        # We don't have data to work with; just guess
        return np.random.random(size=(n_components, dim)) * 10.0

    component_centroids = np.empty((n_components, data.shape[1]), dtype=np.float64)

    if metric == "precomputed":
        # cannot compute centroids from precomputed distances
        # instead, compute centroid distances using linkage
        distance_matrix = np.zeros((n_components, n_components), dtype=np.float64)
        linkage = metric_kwds.get("linkage", "average")
        if linkage == "average":
            linkage = np.mean
        elif linkage == "complete":
            linkage = np.max
        elif linkage == "single":
            linkage = np.min
        else:
            raise ValueError(
                "Unrecognized linkage '%s'. Please choose from "
                "'average', 'complete', or 'single'" % linkage
            )
        for c_i in range(n_components):
            dm_i = data[component_labels == c_i]
            for c_j in range(c_i + 1, n_components):
                dist = linkage(dm_i[:, component_labels == c_j])
                distance_matrix[c_i, c_j] = dist
                distance_matrix[c_j, c_i] = dist
    else:
        for label in range(n_components):
            component_centroids[label] = data[component_labels == label].mean(axis=0)

        if scipy.sparse.isspmatrix(component_centroids):
            warn(
                "Forcing component centroids to dense; if you are running out of "
                "memory then consider increasing n_neighbors."
            )
            component_centroids = component_centroids.toarray()

        if metric in SPECIAL_METRICS:
            distance_matrix = pairwise_special_metric(
                component_centroids,
                metric=metric,
                kwds=metric_kwds,
            )
        elif metric in SPARSE_SPECIAL_METRICS:
            distance_matrix = pairwise_special_metric(
                component_centroids,
                metric=SPARSE_SPECIAL_METRICS[metric],
                kwds=metric_kwds,
            )
        else:
            if callable(metric) and scipy.sparse.isspmatrix(data):
                function_to_name_mapping = {
                    sparse_named_distances[k]: k
                    for k in set(SKLEARN_PAIRWISE_VALID_METRICS)
                    & set(sparse_named_distances.keys())
                }
                try:
                    metric_name = function_to_name_mapping[metric]
                except KeyError:
                    raise NotImplementedError(
                        "Multicomponent layout for custom "
                        "sparse metrics is not implemented at "
                        "this time."
                    )
                distance_matrix = pairwise_distances(
                    component_centroids, metric=metric_name, **metric_kwds
                )
            else:
                distance_matrix = pairwise_distances(
                    component_centroids, metric=metric, **metric_kwds
                )

    affinity_matrix = np.exp(-(distance_matrix ** 2))

    component_embedding = SpectralEmbedding(
        n_components=dim, affinity="precomputed", random_state=random_state
    ).fit_transform(affinity_matrix)
    component_embedding /= component_embedding.max()

    return component_embedding


def multi_component_layout(
    data,
    graph,
    n_components,
    component_labels,
    dim,
    random_state,
    metric="euclidean",
    metric_kwds={},
):
    """Specialised layout algorithm for dealing with graphs with many connected components.
    This will first fid relative positions for the components by spectrally embedding
    their centroids, then spectrally embed each individual connected component positioning
    them according to the centroid embeddings. This provides a decent embedding of each
    component while placing the components in good relative positions to one another.

    Parameters
    ----------
    data: array of shape (n_samples, n_features)
        The source data -- required so we can generate centroids for each
        connected component of the graph.

    graph: sparse matrix
        The adjacency matrix of the graph to be emebdded.

    n_components: int
        The number of distinct components to be layed out.

    component_labels: array of shape (n_samples)
        For each vertex in the graph the label of the component to
        which the vertex belongs.

    dim: int
        The chosen embedding dimension.

    metric: string or callable (optional, default 'euclidean')
        The metric used to measure distances among the source data points.

    metric_kwds: dict (optional, default {})
        Keyword arguments to be passed to the metric function.


    Returns
    -------
    embedding: array of shape (n_samples, dim)
        The initial embedding of ``graph``.
    """

    result = np.empty((graph.shape[0], dim), dtype=np.float32)

    if n_components > 2 * dim:
        meta_embedding = component_layout(
            data,
            n_components,
            component_labels,
            dim,
            random_state,
            metric=metric,
            metric_kwds=metric_kwds,
        )
    else:
        k = int(np.ceil(n_components / 2.0))
        base = np.hstack([np.eye(k), np.zeros((k, dim - k))])
        meta_embedding = np.vstack([base, -base])[:n_components]

    for label in range(n_components):
        component_graph = graph.tocsr()[component_labels == label, :].tocsc()
        component_graph = component_graph[:, component_labels == label].tocoo()

        distances = pairwise_distances([meta_embedding[label]], meta_embedding)
        data_range = distances[distances > 0.0].min() / 2.0

        if component_graph.shape[0] < 2 * dim or component_graph.shape[0] <= dim + 1:
            result[component_labels == label] = (
                random_state.uniform(
                    low=-data_range,
                    high=data_range,
                    size=(component_graph.shape[0], dim),
                )
                + meta_embedding[label]
            )
            continue

        diag_data = np.asarray(component_graph.sum(axis=0))
        # standard Laplacian
        # D = scipy.sparse.spdiags(diag_data, 0, graph.shape[0], graph.shape[0])
        # L = D - graph
        # Normalized Laplacian
        I = scipy.sparse.identity(component_graph.shape[0], dtype=np.float64)
        D = scipy.sparse.spdiags(
            1.0 / np.sqrt(diag_data),
            0,
            component_graph.shape[0],
            component_graph.shape[0],
        )
        L = I - D * component_graph * D

        k = dim + 1
        num_lanczos_vectors = max(2 * k + 1, int(np.sqrt(component_graph.shape[0])))
        try:
            eigenvalues, eigenvectors = scipy.sparse.linalg.eigsh(
                L,
                k,
                which="SM",
                ncv=num_lanczos_vectors,
                tol=1e-4,
                v0=np.ones(L.shape[0]),
                maxiter=graph.shape[0] * 5,
            )
            order = np.argsort(eigenvalues)[1:k]
            component_embedding = eigenvectors[:, order]
            expansion = data_range / np.max(np.abs(component_embedding))
            component_embedding *= expansion
            result[component_labels == label] = (
                component_embedding + meta_embedding[label]
            )
        except scipy.sparse.linalg.ArpackError:
            warn(
                "WARNING: spectral initialisation failed! The eigenvector solver\n"
                "failed. This is likely due to too small an eigengap. Consider\n"
                "adding some noise or jitter to your data.\n\n"
                "Falling back to random initialisation!"
            )
            result[component_labels == label] = (
                random_state.uniform(
                    low=-data_range,
                    high=data_range,
                    size=(component_graph.shape[0], dim),
                )
                + meta_embedding[label]
            )

    return result


def spectral_layout(data, graph, dim, random_state, metric="euclidean", metric_kwds={}):
    """Given a graph compute the spectral embedding of the graph. This is
    simply the eigenvectors of the laplacian of the graph. Here we use the
    normalized laplacian.

    Parameters
    ----------
    data: array of shape (n_samples, n_features)
        The source data

    graph: sparse matrix
        The (weighted) adjacency matrix of the graph as a sparse matrix.

    dim: int
        The dimension of the space into which to embed.

    random_state: numpy RandomState or equivalent
        A state capable being used as a numpy random state.

    Returns
    -------
    embedding: array of shape (n_vertices, dim)
        The spectral embedding of the graph.
    """
    n_samples = graph.shape[0]
    n_components, labels = scipy.sparse.csgraph.connected_components(graph)

    if n_components > 1:
        return multi_component_layout(
            data,
            graph,
            n_components,
            labels,
            dim,
            random_state,
            metric=metric,
            metric_kwds=metric_kwds,
        )

    diag_data = np.asarray(graph.sum(axis=0))
    # standard Laplacian
    # D = scipy.sparse.spdiags(diag_data, 0, graph.shape[0], graph.shape[0])
    # L = D - graph
    # Normalized Laplacian
    I = scipy.sparse.identity(graph.shape[0], dtype=np.float64)
    D = scipy.sparse.spdiags(
        1.0 / np.sqrt(diag_data), 0, graph.shape[0], graph.shape[0]
    )
    L = I - D * graph * D

    k = dim + 1
    num_lanczos_vectors = max(2 * k + 1, int(np.sqrt(graph.shape[0])))
    try:
        if L.shape[0] < 2000000:
            eigenvalues, eigenvectors = scipy.sparse.linalg.eigsh(
                L,
                k,
                which="SM",
                ncv=num_lanczos_vectors,
                tol=1e-4,
                v0=np.ones(L.shape[0]),
                maxiter=graph.shape[0] * 5,
            )
        else:
            eigenvalues, eigenvectors = scipy.sparse.linalg.lobpcg(
                L, random_state.normal(size=(L.shape[0], k)), largest=False, tol=1e-8
            )
        order = np.argsort(eigenvalues)[1:k]
        return eigenvectors[:, order]
    except scipy.sparse.linalg.ArpackError:
        warn(
            "WARNING: spectral initialisation failed! The eigenvector solver\n"
            "failed. This is likely due to too small an eigengap. Consider\n"
            "adding some noise or jitter to your data.\n\n"
            "Falling back to random initialisation!"
        )
        return random_state.uniform(low=-10.0, high=10.0, size=(graph.shape[0], dim))