AttributeError: 'csr_matrix' object has no attribute 'A'

[qomhmd]

Just at the start off, I get the error message with this piece of code:
cora_dataset = spektral.datasets.citation.Citation('cora')

[carlschmidt26]

Hi @qomhmd,

based on a similar issue in CellRank (#1222) and the PR (#1214: Use toarray() instead of .A) of @michalk8, I can confirm, that the following code resolved the issue for me in Colab with spektral 1.3.1.

Note, that I have not tested any downstream effects of that single-line change, but I hope this helps you and others.

# When overwriting a method of a class from an external package, you must ensure that all external dependencies used within your new method's definition are explicitly imported into the current scope (your notebook's global scope).
import os
import networkx as nx
import numpy as np
import scipy.sparse as sp
from sklearn.model_selection import train_test_split

from spektral.data import Dataset, Graph
from spektral.utils.io import load_binary

def read(self):
        objects = [_read_file(self.path, self.name, s) for s in self.suffixes]
# >>>>> UPDATE TO RESOLVE THE ERROR: 'csr_matrix' object has no attribute 'A'.
        # objects = [o.A if sp.issparse(o) else o for o in objects]
        objects = [o.toarray() if sp.issparse(o) else o for o in objects]
# >>>>> END OF UPDATE
        x, y, tx, ty, allx, ally, graph, idx_te = objects

        # Public Planetoid splits. This is the default
        idx_tr = np.arange(y.shape[0])
        idx_va = np.arange(y.shape[0], y.shape[0] + 500)
        idx_te = idx_te.astype(int)
        idx_te_sort = np.sort(idx_te)

        # Fix disconnected nodes in Citeseer
        if self.name == "citeseer":
            idx_te_len = idx_te.max() - idx_te.min() + 1
            tx_ext = np.zeros((idx_te_len, x.shape[1]))
            tx_ext[idx_te_sort - idx_te.min(), :] = tx
            tx = tx_ext
            ty_ext = np.zeros((idx_te_len, y.shape[1]))
            ty_ext[idx_te_sort - idx_te.min(), :] = ty
            ty = ty_ext

        x = np.vstack((allx, tx))
        y = np.vstack((ally, ty))
        x[idx_te, :] = x[idx_te_sort, :]
        y[idx_te, :] = y[idx_te_sort, :]

        # Row-normalize the features
        if self.normalize_x:
            print("Pre-processing node features")
            x = _preprocess_features(x)

        if self.random_split:
            # Throw away public splits and compute random ones like Shchur et al.
            indices = np.arange(y.shape[0])
            n_classes = y.shape[1]
            idx_tr, idx_te, _, y_te = train_test_split(
                indices, y, train_size=20 * n_classes, stratify=y
            )
            idx_va, idx_te = train_test_split(
                idx_te, train_size=30 * n_classes, stratify=y_te
            )

        # Adjacency matrix
        a = nx.adjacency_matrix(nx.from_dict_of_lists(graph))  # CSR
        a.setdiag(0)
        a.eliminate_zeros()

        # Train/valid/test masks
        self.mask_tr = _idx_to_mask(idx_tr, y.shape[0])
        self.mask_va = _idx_to_mask(idx_va, y.shape[0])
        self.mask_te = _idx_to_mask(idx_te, y.shape[0])

        return [
            Graph(
                x=x.astype(self.dtype),
                a=a.astype(self.dtype),
                y=y.astype(self.dtype),
            )
        ]

# Re-define the helper functions used by `spektral.datasets.citation.Citation.read`.
def _read_file(path, name, suffix):
    full_fname = os.path.join(path, "ind.{}.{}".format(name, suffix))
    if suffix == "test.index":
        return np.loadtxt(full_fname)

    return load_binary(full_fname)


def _idx_to_mask(idx, l):
    mask = np.zeros(l)
    mask[idx] = 1
    return np.array(mask, dtype=bool)


def _preprocess_features(features):
    rowsum = np.array(features.sum(1))
    r_inv = np.power(rowsum, -1).flatten()
    r_inv[np.isinf(r_inv)] = 0.0
    r_mat_inv = sp.diags(r_inv)
    features = r_mat_inv.dot(features)
    return features

# Overwrite the old `spektral.datasets.citation.Citation.read` method with the newly defined `read` method above. 
spektral.datasets.citation.Citation.read = read