def test_dataset_stats():
stats = pipeline("dataset-stats")
outputs = stats("cora")
outputs = outputs[0]
assert len(outputs) == 6
assert tuple(outputs) == ("cora", 2708, 10484, 1433, 7, 140)
def test_oagbert():
oagbert = pipeline("oagbert", model="oagbert-test", load_weights=False)
outputs = oagbert("CogDL is developed by KEG, Tsinghua.")
assert len(outputs) == 2
assert tuple(outputs[0].shape) == (1, 14, 32)
assert tuple(outputs[1].shape) == (1, 32)
def test_gen_emb():
generator = pipeline("generate-emb", model="prone")
edge_index = np.array([[0, 1], [0, 2], [0, 3], [1, 2], [2, 3]])
outputs = generator(edge_index)
assert tuple(outputs.shape) == (4, 4)
edge_weight = np.array([0.1, 0.3, 1.0, 0.8, 0.5])
outputs = generator(edge_index, edge_weight)
assert tuple(outputs.shape) == (4, 4)
generator = pipeline("generate-emb",
model="dgi",
num_features=8,
hidden_size=10,
cpu=True)
outputs = generator(edge_index, x=np.random.randn(4, 8))
assert tuple(outputs.shape) == (4, 10)
def test_recommendation():
data = np.array([[0, 0], [0, 1], [0, 2], [1, 1], [1, 3], [1, 4], [2, 4],
[2, 5], [2, 6]])
rec = pipeline("recommendation",
model="lightgcn",
data=data,
max_epoch=2,
evaluate_interval=1000,
cpu=True)
ret = rec([0], topk=3)
assert len(ret[0]) == 3
def test_gen_emb():
generator = pipeline("generate-emb", model="prone")
edge_index = np.array([[0, 1], [0, 2], [0, 3], [1, 2], [2, 3], [3, 4],
[4, 5], [5, 6], [6, 7]])
outputs = generator(edge_index)
assert tuple(outputs.shape) == (8, 8)
generator = pipeline(
"generate-emb",
model="mvgrl",
no_test=True,
num_features=8,
hidden_size=10,
sample_size=2,
epochs=2,
cpu=True,
)
outputs = generator(edge_index, x=np.random.randn(8, 8))
assert tuple(outputs.shape) == (8, 10)
import numpy as np
from cogdl import pipeline
data = np.array([[0, 0], [0, 1], [0, 2], [1, 1], [1, 3], [1, 4], [2, 4],
[2, 5], [2, 6]])
rec = pipeline("recommendation",
model="lightgcn",
data=data,
epochs=10,
evaluate_interval=1000,
cpu=True)
print(rec([0]))
rec = pipeline("recommendation",
model="lightgcn",
dataset="ali",
epochs=1,
n_negs=1,
evaluate_interval=1000)
print(rec([0]))
import numpy as np
from cogdl import pipeline
# build a pipeline for generating embeddings
# pass model name with its hyper-parameters to this API
generator = pipeline("generate-emb", model="prone")
# generate embedding by an unweighted graph
edge_index = np.array([[0, 1], [0, 2], [0, 3], [1, 2], [2, 3], [3, 4], [4, 5],
[5, 6], [6, 7]])
outputs = generator(edge_index)
print(outputs)
# generate embeddings by a weighted graph
edge_weight = np.array([0.1, 0.3, 1.0, 0.8, 0.5, 0.2, 0.1, 0.5, 2.0])
outputs = generator(edge_index, edge_weight)
print(outputs)
# build a pipeline for generating embeddings using unsupervised GNNs
# pass model name and num_features with its hyper-parameters to this API
generator = pipeline("generate-emb",
model="mvgrl",
no_test=True,
num_features=8,
hidden_size=4)
outputs = generator(edge_index, x=np.random.randn(8, 8))
print(outputs)
import numpy as np
from cogdl import pipeline
# build a pipeline for generating embeddings
# pass model name with its hyper-parameters to this API
generator = pipeline("generate-emb", model="prone")
# generate embedding by an unweighted graph
edge_index = np.array([[0, 1], [0, 2], [0, 3], [1, 2], [2, 3]])
outputs = generator(edge_index)
print(outputs)
# generate embeddings by a weighted graph
edge_weight = np.array([0.1, 0.3, 1.0, 0.8, 0.5])
outputs = generator(edge_index, edge_weight)
print(outputs)
# build a pipeline for generating embeddings using unsupervised GNNs
# pass model name and num_features with its hyper-parameters to this API
generator = pipeline("generate-emb",
model="dgi",
num_features=8,
hidden_size=4)
outputs = generator(edge_index, x=np.random.randn(4, 8))
print(outputs)
def test_dataset_visual():
visual = pipeline("dataset-visual")
outputs = visual("cora", seed=0, depth=3)
assert len(outputs) == 71
def load_model():
global model
model = pipeline("generate-emb", model="prone")
from cogdl import pipeline
# print the statistics of datasets
stats = pipeline("dataset-stats")
stats(["cora", "citeseer"])
# visualize k-hop neighbors of seed in the dataset
visual = pipeline("dataset-visual")
visual("cora", seed=0, depth=3)
# load OAGBert model and perform inference
oagbert = pipeline("oagbert")
outputs = oagbert([
"CogDL is developed by KEG, Tsinghua.",
"OAGBert is developed by KEG, Tsinghua."
])