def infer_type(x):
"""Infer type of the input `x`.
Parameters:
----------
x: Any python object
Returns:
----------
dtype: string, the converted type of `x`:
1. `graphgallery.floatx()` if `x` is floating
2. `graphgallery.intx()` if `x` is integer
3. `'bool'` if `x` is bool.
"""
# For tensor or variable
if is_th_tensor(x):
if x.dtype.is_floating_point:
return floatx()
elif x.dtype == torch.bool:
return 'bool'
elif 'int' in str(x.dtype):
return intx()
else:
raise RuntimeError(f'Invalid input of `{type(x)}`')
elif is_tf_tensor(x):
if x.dtype.is_floating:
return floatx()
elif x.dtype.is_integer or x.dtype.is_unsigned:
return intx()
elif x.dtype.is_bool:
return 'bool'
else:
raise RuntimeError(f'Invalid input of `{type(x)}`')
if not hasattr(x, 'dtype'):
x = np.asarray(x)
if x.dtype.kind in {'f', 'c'}:
return floatx()
elif x.dtype.kind in {'i', 'u'}:
return intx()
elif x.dtype.kind == 'b':
return 'bool'
elif x.dtype.kind == 'O':
raise RuntimeError(f'Invalid inputs of `{x}`.')
else:
raise RuntimeError(f'Invalid input of `{type(x)}`')
def infer_type(x: Any) -> str:
"""Infer the type of the input 'x'.
Parameters:
----------
x: Any python object
Returns:
----------
dtype: string, the proper data type of 'x':
1. 'graphgallery.floatx()' if 'x' is floating,
2. 'graphgallery.intx()' if 'x' is integer,
3. 'graphgallery.boolx()' if 'x' is boolean.
"""
# For tensor or variable
if pytorch.is_tensor(x):
if x.dtype.is_floating_point:
return gg.floatx()
elif x.dtype == torch.bool:
return gg.boolx()
elif 'int' in str(x.dtype):
return gg.intx()
else:
raise TypeError(f"Invalid type of pytorch Tensor: '{type(x)}'")
elif tensorflow.is_tensor(x):
if x.dtype.is_floating:
return gg.floatx()
elif x.dtype.is_integer or x.dtype.is_unsigned:
return gg.intx()
elif x.dtype.is_bool:
return gg.boolx()
else:
raise TypeError(f"Invalid type of tensorflow Tensor: '{type(x)}'")
_x = x
if not hasattr(_x, 'dtype'):
_x = np.asarray(_x)
if _x.dtype.kind in {'f', 'c'}:
return gg.floatx()
elif _x.dtype.kind in {'i', 'u'}:
return gg.intx()
elif _x.dtype.kind == 'b':
return gg.boolx()
elif _x.dtype.kind == 'O':
raise TypeError(f"Invalid inputs of '{x}'.")
else:
raise TypeError(f"Invalid input of '{type(x).__name__}'.")
def astensor(x, *, dtype=None, device=None, escape=None):
try:
if x is None or (escape is not None and isinstance(x, escape)):
return x
except TypeError:
raise TypeError(f"argument 'escape' must be a type or tuple of types.")
if dtype is None:
dtype = gf.infer_type(x)
if isinstance(dtype, (np.dtype, str)):
dtype = data_type_dict().get(str(dtype), dtype)
elif not isinstance(dtype, torch.dtype):
raise TypeError(
f"argument 'dtype' must be torch.dtype, np.dtype or str, but got {type(dtype)}."
)
if is_tensor(x):
tensor = x.to(dtype)
elif gf.is_tensor(x, backend='tensorflow'):
return astensor(gf.tensoras(x),
dtype=dtype,
device=device,
escape=escape)
elif sp.isspmatrix(x):
if gg.backend() == "dgl_torch":
import dgl
tensor = dgl.from_scipy(x, idtype=getattr(torch, gg.intx()))
elif gg.backend() == "pyg":
edge_index, edge_weight = gf.sparse_adj_to_edge(x)
return (astensor(edge_index,
dtype=gg.intx(),
device=device,
escape=escape),
astensor(edge_weight,
dtype=gg.floatx(),
device=device,
escape=escape))
else:
tensor = sparse_adj_to_sparse_tensor(x, dtype=dtype)
elif any((isinstance(x, (np.ndarray, np.matrix)), gg.is_listlike(x),
gg.is_scalar(x))):
tensor = torch.tensor(x, dtype=dtype, device=device)
else:
raise TypeError(
f"Invalid type of inputs. Allowed data type (Tensor, SparseTensor, Numpy array, Scipy sparse tensor, None), but got {type(x)}."
)
return tensor.to(device)
def __init__(self, in_channels, out_channels,
hiddens=[16],
activations=['relu'],
dropout=0.5,
l2_norm=5e-4,
lr=0.01, use_bias=False):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(), name='attr_matrix')
adj = Input(batch_shape=[None, None], dtype=floatx(),
sparse=True, name='adj_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = GraphConvAttribute(hidden, use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(l2_norm))([h, adj])
h = Dropout(rate=dropout)(h)
h = GraphConvAttribute(out_channels, use_bias=use_bias)([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
hiddens=[32],
activations=['relu'],
dropout=0.5,
l2_norm=5e-4,
lr=0.01,
use_bias=True,
aggregator='mean',
output_normalize=False,
n_samples=[15, 5]):
Agg = _AGG.get(aggregator, None)
if not Agg:
raise ValueError(
f"Invalid value of 'aggregator', allowed values {tuple(_AGG.keys())}, but got '{aggregator}'."
)
_intx = intx()
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='attr_matrix')
nodes = Input(batch_shape=[None], dtype=_intx, name='nodes')
neighbors = [
Input(batch_shape=[None], dtype=_intx, name=f'neighbors_{hop}')
for hop, n_sample in enumerate(n_samples)
]
aggregators = []
for hidden, activation in zip(hiddens, activations):
# you can use `GCNAggregator` instead
aggregators.append(
Agg(hidden,
concat=True,
activation=activation,
use_bias=use_bias,
kernel_regularizer=regularizers.l2(l2_norm)))
aggregators.append(Agg(out_channels, use_bias=use_bias))
h = [tf.nn.embedding_lookup(x, node) for node in [nodes, *neighbors]]
for agg_i, aggregator in enumerate(aggregators):
attribute_shape = h[0].shape[-1]
for hop in range(len(n_samples) - agg_i):
neighbor_shape = [-1, n_samples[hop], attribute_shape]
h[hop] = aggregator(
[h[hop], tf.reshape(h[hop + 1], neighbor_shape)])
if hop != len(n_samples) - 1:
h[hop] = Dropout(rate=dropout)(h[hop])
h.pop()
h = h[0]
if output_normalize:
h = tf.nn.l2_normalize(h, axis=1)
super().__init__(inputs=[x, nodes, *neighbors], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def __init__(self, in_channels, out_channels,
hiddens=[16],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01, order=2, use_bias=False):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(), name='node_attr')
adj = [Input(batch_shape=[None, None],
dtype=floatx(), sparse=True,
name=f'adj_matrix_{i}') for i in range(order + 1)]
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = ChebyConvolution(hidden, order=order, use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Dropout(rate=dropout)(h)
h = ChebyConvolution(out_channels,
order=order, use_bias=use_bias)([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, *adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
def neighbor_sampler(adj_matrix: sp.csr_matrix, max_degree: int = 25,
selfloop: bool = False):
adj_matrix = adj_matrix.tocsr(copy=False)
N = adj_matrix.shape[0]
neighbors_matrix = N * np.ones((N + 1, max_degree), dtype=intx())
for nodeid in range(N):
neighbors = adj_matrix[nodeid].indices
# if not selfloop:
# neighbors = np.setdiff1d(neighbors, [nodeid])
# else:
# neighbors = np.intersect1d(neighbors, [nodeid])
size = neighbors.size
if size == 0:
continue
if size > max_degree:
neighbors = np.random.choice(neighbors, max_degree, replace=False)
elif size < max_degree:
neighbors = np.random.choice(neighbors, max_degree, replace=True)
neighbors_matrix[nodeid] = neighbors
np.random.shuffle(neighbors_matrix.T)
return neighbors_matrix
def asintarr(x, dtype: str = None):
"""Convert `x` to interger Numpy array.
Parameters:
----------
x: Tensor, Scipy sparse matrix,
Numpy array-like, etc.
Returns:
----------
Integer Numpy array with dtype or `graphgallery.intx()`
"""
if dtype is None:
dtype = intx()
if is_tensor(x):
if x.dtype != dtype:
kind = backend().kind
if kind == "T":
x = tf.cast(x, dtype=dtype)
else:
x = x.to(getattr(torch, dtype))
return x
if is_interger_scalar(x):
x = np.asarray([x], dtype=dtype)
elif is_list_like(x) or isinstance(x, (np.ndarray, np.matrix)):
x = np.asarray(x, dtype=dtype)
else:
raise ValueError(
f"Invalid input which should be either array-like or integer scalar, but got {type(x)}."
)
return x
def __init__(self, in_features, out_features,
hids=[16], acts=['relu'], dropout=0.5,
weight_decay=5e-4, lr=0.01, bias=False):
_intx = intx()
_floatx = floatx()
x = Input(batch_shape=[None, in_features],
dtype=_floatx, name='node_attr')
edge_index = Input(batch_shape=[None, 2], dtype=_intx,
name='edge_index')
edge_weight = Input(batch_shape=[None], dtype=_floatx,
name='edge_weight')
h = x
for hid, act in zip(hids, acts):
h = GraphEdgeConvolution(hid, use_bias=bias,
activation=act,
kernel_regularizer=regularizers.l2(weight_decay))([h, edge_index, edge_weight])
h = Dropout(rate=dropout)(h)
h = GraphEdgeConvolution(out_features, use_bias=bias)(
[h, edge_index, edge_weight])
super().__init__(inputs=[x, edge_index, edge_weight], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
def infer_type(x)->str:
"""Infer type of the input `x`.
Parameters:
----------
x: tf.Tensor, tf.Variable, Scipy sparse matrix,
Numpy array-like, etc.
Returns:
----------
dtype: string, the converted type of `x`:
1. `graphgallery.floatx()` if `x` is floating
2. `graphgallery.intx()` if `x` is integer
3. `'bool'` if `x` is bool.
"""
# For tensor or variable
if is_tf_tensor(x):
if x.dtype.is_floating:
return floatx()
elif x.dtype.is_integer or x.dtype.is_unsigned:
return intx()
elif x.dtype.is_bool:
return 'bool'
else:
raise RuntimeError(f'Invalid input of `{type(x)}`')
if not hasattr(x, 'dtype'):
x = np.asarray(x)
if x.dtype.kind in {'f', 'c'}:
return floatx()
elif x.dtype.kind in {'i', 'u'}:
return intx()
elif x.dtype.kind == 'b':
return 'bool'
elif x.dtype.kind == 'O':
raise RuntimeError(f'Invalid inputs of `{x}`.')
else:
raise RuntimeError(f'Invalid input of `{type(x)}`')
def __init__(self, in_channels, out_channels,
hiddens=[64],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01, kl=5e-4, gamma=1.,
use_bias=False):
_floatx = floatx()
x = Input(batch_shape=[None, in_channels],
dtype=_floatx, name='node_attr')
adj = [Input(batch_shape=[None, None], dtype=_floatx,
sparse=True, name='adj_matrix_1'),
Input(batch_shape=[None, None], dtype=_floatx, sparse=True,
name='adj_matrix_2')]
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
if hiddens:
mean, var = GaussionConvolution_F(hiddens[0], gamma=gamma,
use_bias=use_bias,
activation=activations[0],
kernel_regularizer=regularizers.l2(weight_decay))([h, *adj])
if kl:
KL_divergence = 0.5 * \
tf.reduce_mean(tf.math.square(mean) + var -
tf.math.log(1e-8 + var) - 1, axis=1)
KL_divergence = tf.reduce_sum(KL_divergence)
# KL loss
kl_loss = kl * KL_divergence
# additional layers (usually unnecessay)
for hidden, activation in zip(hiddens[1:], activations[1:]):
mean, var = GaussionConvolution_D(
hidden, gamma=gamma, use_bias=use_bias, activation=activation)([mean, var, *adj])
mean = Dropout(rate=dropout)(mean)
var = Dropout(rate=dropout)(var)
mean, var = GaussionConvolution_D(
out_channels, gamma=gamma, use_bias=use_bias)([mean, var, *adj])
h = Sample()([mean, var])
h = Gather()([h, index])
super().__init__(inputs=[x, *adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
if hiddens and kl:
self.add_loss(kl_loss)
def add_selfloops_edge(edge_index, n_nodes, edge_weight=None, fill_weight=1.0):
diagnal_edge_index = tf.reshape(
tf.repeat(tf.range(n_nodes, dtype=intx()), 2), [n_nodes, 2])
updated_edge_index = tf.concat(
[edge_index, diagnal_edge_index], axis=0)
if edge_weight:
diagnal_edge_weight = tf.cast(
tf.fill([n_nodes], fill_weight), dtype=floatx())
updated_edge_weight = tf.concat(
[edge_weight, diagnal_edge_weight], axis=0)
else:
updated_edge_weight = None
return updated_edge_index, updated_edge_weight
def __init__(self, *, device="cpu", seed=None, name=None, **kwargs):
"""
Parameters:
----------
device: string. optional
The device where the model running on.
seed: interger scalar. optional
Used to create a reproducible sequence of tensors
across multiple calls.
name: string. optional
Specified name for the model. (default: :str: `class name`)
kwargs: other custom keyword arguments.
"""
# if graph is not None and not isinstance(graph, gg.data.BaseGraph):
# raise ValueError(f"Unrecognized graph: {graph}.")
kwargs.pop("self", None)
kwargs.pop("__class__", None)
cfg = gg.CfgNode()
cfg.merge_from_dict(kwargs)
cfg.intx = self.intx = gg.intx()
cfg.floatx = self.floatx = gg.floatx()
cfg.boolx = self.boolx = gg.boolx()
cfg.seed = self.seed = seed
cfg.name = self.name = name or self.__class__.__name__
cfg.device = device
_backend = gg.backend()
cfg.backend = getattr(_backend, "name", None)
if seed:
gf.random_seed(seed, _backend)
self.device = gf.device(device, _backend)
self.data_device = self.device
self.backend = _backend
# data types, default: `float32`,`int32` and `bool`
self._cache = gf.BunchDict()
self.transform = gf.BunchDict()
self._model = None
self._graph = None
self.cfg = cfg
self.setup_cfg()
self.custom_setup()
def __init__(self, *graph, device="cpu:0", seed=None, name=None, **kwargs):
"""
Parameters:
----------
graph: Graph or MultiGraph.
device: string. optional
The device where the model running on.
seed: interger scalar. optional
Used in combination with `tf.random.set_seed` & `np.random.seed`
& `random.seed` to create a reproducible sequence of tensors
across multiple calls.
name: string. optional
Specified name for the model. (default: :str: `class.__name__`)
kwargs: other custom keyword parameters.
"""
graph = parse_graph_inputs(*graph)
_backend = backend()
self.backend = _backend
self.kind = _backend.kind
raise_if_kwargs(kwargs)
if seed is not None:
np.random.seed(seed)
random.seed(seed)
if self.kind == "P":
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
# torch.cuda.manual_seed_all(seed)
else:
tf.random.set_seed(seed)
if name is None:
name = self.__class__.__name__
self.seed = seed
self.name = name
self.graph = graph.copy()
self.device = parse_device(device, self.kind)
# data types, default: `float32` and `int32`
self.floatx = floatx()
self.intx = intx()
def __init__(self,
in_channels,
out_channels,
hiddens=[64],
activations=['relu'],
dropout=0.5,
weight_decay=5e-3,
lr=0.01,
use_bias=False,
K=10):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=floatx(),
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = Dense(hidden,
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))(h)
h = Dropout(dropout)(h)
h = Dense(out_channels,
use_bias=use_bias,
activation=activations[-1],
kernel_regularizer=regularizers.l2(weight_decay))(h)
h = Dropout(dropout)(h)
h = PropConvolution(
K,
use_bias=use_bias,
activation='sigmoid',
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
num_nodes,
hiddens=[16],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01,
use_bias=False):
_floatx = floatx()
x = Input(batch_shape=[None, in_channels],
dtype=_floatx,
name='node_attr')
wavelet = Input(batch_shape=[num_nodes, num_nodes],
dtype=_floatx,
sparse=True,
name='wavelet_matrix')
inverse_wavelet = Input(batch_shape=[num_nodes, num_nodes],
dtype=_floatx,
sparse=True,
name='inverse_wavelet_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = WaveletConvolution(
hidden,
activation=activation,
use_bias=use_bias,
kernel_regularizer=regularizers.l2(weight_decay))(
[h, wavelet, inverse_wavelet])
h = Dropout(rate=dropout)(h)
h = WaveletConvolution(
out_channels, use_bias=use_bias)([h, wavelet, inverse_wavelet])
h = Gather()([h, index])
super().__init__(inputs=[x, wavelet, inverse_wavelet, index],
outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def predict(self, predict_data=None, return_prob=True):
"""
Predict the output probability for the input data.
Note:
----------
You must compile your model before training/testing/predicting.
Use `model.build()`.
Parameters:
----------
predict_data: Numpy 1D array, optional.
The indices of objects to predict.
if None, predict the all objects.
return_prob: bool.
whether to return the probability of prediction.
Return:
----------
The predicted probability of each class for each object,
for node classification task, it has shape
(num_nodes, num_node_classes).
"""
if not self.model:
raise RuntimeError(
'You must compile your model before training/testing/predicting. Use `model.build()`.'
)
if predict_data is None:
predict_data = np.arange(self.graph.num_nodes, dtype=gg.intx())
if not isinstance(predict_data, Sequence):
predict_data = self.predict_sequence(predict_data)
self.predict_data = predict_data
logit = self.predict_step(predict_data)
if return_prob:
logit = softmax(logit)
return logit
def __init__(self,
in_channels,
out_channels,
hiddens=[16],
activations=['relu'],
dropout=0.5,
l2_norm=5e-4,
lr=0.01,
use_bias=False):
_intx = intx()
_floatx = floatx()
x = Input(batch_shape=[None, in_channels],
dtype=_floatx,
name='attr_matrix')
edge_index = Input(batch_shape=[None, 2],
dtype=_intx,
name='edge_index')
edge_weight = Input(batch_shape=[None],
dtype=_floatx,
name='edge_weight')
index = Input(batch_shape=[None], dtype=_intx, name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = GraphEdgeConvolution(
hidden,
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(l2_norm))(
[h, edge_index, edge_weight])
h = Dropout(rate=dropout)(h)
h = GraphEdgeConvolution(
out_channels, use_bias=use_bias)([h, edge_index, edge_weight])
output = Gather()([h, index])
super().__init__(inputs=[x, edge_index, edge_weight, index],
outputs=output)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
hiddens=[16],
n_heads=[8],
activations=['elu'],
dropout=0.6,
weight_decay=5e-4,
lr=0.01,
use_bias=True):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=floatx(),
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, n_head, activation in zip(hiddens, n_heads, activations):
h = GraphAttention(
hidden,
attn_heads=n_head,
reduction='concat',
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay),
attn_kernel_regularizer=regularizers.l2(weight_decay),
)([h, adj])
h = Dropout(rate=dropout)(h)
h = GraphAttention(out_channels,
use_bias=use_bias,
attn_heads=1,
reduction='average')([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def astensor(x, *, dtype=None, device=None, escape=None):
try:
if x is None or (escape is not None and isinstance(x, escape)):
return x
except TypeError:
raise TypeError(f"argument 'escape' must be a type or tuple of types.")
if dtype is None:
dtype = gf.infer_type(x)
elif isinstance(dtype, tf.dtypes.DType):
dtype = dtype.name
elif isinstance(dtype, (np.dtype, str)):
dtype = str(dtype)
else:
raise TypeError(
f"argument 'dtype' must be tf.dtypes.DType, np.dtype or str, but got {type(dtype)}."
)
with tf.device(device):
if is_tensor(x):
if x.dtype != dtype:
return tf.cast(x, dtype=dtype)
return tf.identity(x)
elif gf.is_tensor(x, backend='torch'):
return astensor(gf.tensoras(x),
dtype=dtype,
device=device,
escape=escape)
elif sp.isspmatrix(x):
if gg.backend() == "dgl_tf":
import dgl
return dgl.from_scipy(x, idtype=getattr(tf,
gg.intx())).to(device)
else:
return sparse_adj_to_sparse_tensor(x, dtype=dtype)
elif any((isinstance(x, (np.ndarray, np.matrix)), gg.is_listlike(x),
gg.is_scalar(x))):
return tf.convert_to_tensor(x, dtype=dtype)
else:
raise TypeError(
f"Invalid type of inputs. Allowed data type(Tensor, SparseTensor, Numpy array, Scipy sparse matrix, None), but got {type(x)}."
)
def __init__(self, graph, device="cpu", seed=None, name=None, **kwargs):
"""
Parameters:
----------
graph: Graph or MultiGraph.
device: string. optional
The device where the model running on.
seed: interger scalar. optional
Used in combination with `tf.random.set_seed` & `np.random.seed`
& `random.seed` to create a reproducible sequence of tensors
across multiple calls.
name: string. optional
Specified name for the model. (default: :str: `class.__name__`)
kwargs: other custom keyword arguments.
"""
if not isinstance(graph, gg.data.BaseGraph):
raise ValueError(f"Unrecognized graph: {graph}.")
_backend = gg.backend()
# It currently takes no keyword arguments
gg.utils.raise_error.raise_if_kwargs(kwargs)
if seed:
gf.random_seed(seed, _backend)
if name is None:
name = self.__class__.__name__
self.seed = seed
self.name = name
self.graph = graph.copy()
self.device = gf.device(device, _backend)
self.backend = _backend
# data types, default: `float32`,`int32` and `bool`
self.floatx = gg.floatx()
self.intx = gg.intx()
self.boolx = gg.boolx()
self._cache = gf.BunchDict()
def predict(self, index=None, return_prob=True):
"""
Predict the output probability for the input node index.
Note:
----------
You must compile your model before training/testing/predicting.
Use `model.build()`.
Parameters:
----------
index: Numpy 1D array, optional.
The indices of nodes to predict.
if None, predict the all nodes.
return_prob: bool.
whether to return the probability of prediction.
Return:
----------
The predicted probability of each class for each node,
shape (n_nodes, n_classes).
"""
if not self.model:
raise RuntimeError(
'You must compile your model before training/testing/predicting. Use `model.build()`.'
)
if index is None:
index = np.arange(self.graph.n_nodes, dtype=intx())
else:
index = asintarr(index)
sequence = self.predict_sequence(index)
logit = self.predict_step(sequence)
if return_prob:
logit = softmax(logit)
return logit
def asarray(x: Any, dtype: Optional[str] = None) -> np.ndarray:
"""Convert `x` to interger Numpy array.
Parameters:
----------
x: Tensor, Scipy sparse matrix,
Numpy array-like, etc.
Returns:
----------
Integer Numpy array with dtype or `graphgallery.intx()`
"""
if dtype is None:
dtype = gg.intx()
if gf.is_tensor(x, backend="tensorflow"):
if x.dtype != dtype:
return tf.cast(x, dtype=dtype)
else:
return x
if gf.is_tensor(x, backend="torch"):
if x.dtype != dtype:
return x.to(getattr(torch, dtype))
else:
return x
if gg.is_intscalar(x):
x = np.asarray([x], dtype=dtype)
elif gg.is_listlike(x) or (isinstance(x, np.ndarray) and x.dtype != "O"):
x = np.asarray(x, dtype=dtype)
else:
raise ValueError(
f"Invalid input which should be either array-like or integer scalar, but got {type(x)}."
)
return x
