def getFeatureProject(graphJob: signac.Project.Job):
try:
featureProject = signac.get_project(root=graphJob.workspace(),
search=False)
except LookupError:
featureProject = signac.init_project("SyntheticExperimentFeatures",
root=graphJob.workspace(),
workspace="features")
return featureProject
def getSplitProject(featureJob: signac.Project.Job):
try:
splitProject = signac.get_project(root=featureJob.workspace(),
search=False)
except LookupError:
splitProject = signac.init_project("SyntheticExperimentSplits",
root=featureJob.workspace(),
workspace="splits")
return splitProject
def clear_job(job: signac.Project.Job):
workspaceDirObj = Path(job.workspace())
for child in workspaceDirObj.iterdir():
if child.name not in ["signac_statepoint.json", "signac_job_document.json"]:
if child.is_dir():
print(f"Deleting directory {child}")
shutil.rmtree(str(child))
else:
print(f"Deleting {child}")
child.unlink()
def generate_graph(job: signac.Project.Job):
print("Generating graph for job {}".format(job.get_id()))
graphgen.random_state = reset_random_state(job)
if job.sp.method == "mixhop":
generator = graphgen.MixhopGraphGenerator(
job.sp.classRatio, job.sp.heteroClsWeight, heteroWeightsExponent=job.sp.heteroWeightsExponent)
G = generator(job.sp.numNode, job.sp.m, job.sp.m0, job.sp.h)
generator.save_graph(G, job.workspace(), job.sp.graphName)
generator.save_y(G, job.workspace(), job.sp.graphName)
generator.save_nx_graph(G, job.workspace(), job.sp.graphName)
elif job.sp.method == "planetoid":
with job:
dataset = utils.PlanetoidData(job.sp.datasetName, "data_source")
G = dataset.getNXGraph()
generator = graphgen.GraphGenerator(job.sp.numClass)
generator.save_graph(G, job.workspace(), job.sp.graphName)
generator.save_y(G, job.workspace(), job.sp.graphName)
generator.save_nx_graph(G, job.workspace(), job.sp.graphName)
featureProject = utils.signac_tools.getFeatureProject(job)
featureJob = featureProject.open_job({
"feature_type": "unmodified"
}).init()
splitProject = utils.signac_tools.getSplitProject(featureJob)
trainSetSize = dataset.y_all[dataset.train_mask].sum(0)
if len(np.unique(trainSetSize)) == 1:
trainSetSize = "{}c".format(int(trainSetSize[0]))
else:
trainSetSize = int(dataset.train_mask.sum())
splitJob = splitProject.open_job({
"split_config": "{}__{}".format(trainSetSize, int(dataset.test_mask.sum()))
}).init()
elif job.sp.method == "GeomGCN":
with job:
dataset = utils.GeomGCNData(job.sp.datasetName, "data_source")
G = dataset.getNXGraph()
generator = graphgen.GraphGenerator(job.sp.numClass)
generator.save_graph(G, job.workspace(), job.sp.graphName)
generator.save_y(G, job.workspace(), job.sp.graphName)
generator.save_nx_graph(G, job.workspace(), job.sp.graphName)
featureProject = utils.signac_tools.getFeatureProject(job)
featureJob = featureProject.open_job({
"feature_type": "unmodified"
}).init()
output_name = f"{job.sp.graphName}-unmodified.allx.npz"
allx = dataset.features
allx = scipy.sparse.csr_matrix(allx)
scipy.sparse.save_npz(featureJob.fn(output_name), allx)
featureJob.doc["feature_file"] = output_name
featureJob.doc["feature_name"] = f"{job.sp.datasetName}-unmodified"
featureJob.doc["succeeded"] = True
elif job.sp.method == "SparseGraph":
with job:
spgraph = sparsegraph.io.load_dataset(
str(Path("data_source")/job.sp.datasetName))
for command in job.sp.get("preprocess", []):
exec(command)
G = spgraph.getNXGraph()
generator = graphgen.GraphGenerator(job.sp.numClass)
generator.save_graph(G, job.workspace(), job.sp.graphName)
generator.save_y(G, job.workspace(), job.sp.graphName)
generator.save_nx_graph(G, job.workspace(), job.sp.graphName)
featureProject = utils.signac_tools.getFeatureProject(job)
featureJob = featureProject.open_job({
"feature_type": "unmodified"
}).init()
if spgraph.attr_matrix is not None:
# Generate features
output_name = f"{job.sp.graphName}-unmodified.allx.npz"
allx = spgraph.attr_matrix
allx = scipy.sparse.csr_matrix(allx)
scipy.sparse.save_npz(featureJob.fn(output_name), allx)
featureJob.doc["feature_file"] = output_name
featureJob.doc["feature_name"] = f"{job.sp.datasetName}-unmodified"
featureJob.doc["succeeded"] = True
elif job.sp.method == "copy":
graph_path, ally_path, ty_path, test_index_path = map(
lambda x: job.fn("source_graph/{}{}".format(job.sp.source_name, x)), (".graph", ".ally", ".ty", ".test.index"))
graph = pickle.load(open(graph_path, "rb"))
G = nx.from_dict_of_lists(graph)
ally = np.load(ally_path, allow_pickle=True)
ty = np.load(ty_path, allow_pickle=True)
attrs = dict()
for i in range(ally.shape[0]):
color = np.nonzero(ally[i, :])[0] + 1
assert len(color) == 1, print(i, color)
color = color[0]
attrs[i] = {"color": color}
for i, line in enumerate(open(test_index_path, "r")):
node_id = int(line.strip())
color = np.nonzero(ty[i, :])[0] + 1
assert len(color) == 1, print(i, color)
color = color[0]
attrs[node_id] = {"color": color}
assert i == ty.shape[0] - 1
assert len(attrs) == len(G.node)
nx.set_node_attributes(G, attrs)
generator = graphgen.GraphGenerator(job.sp.numClass)
generator.save_graph(G, job.workspace(), job.sp.graphName)
generator.save_y(G, job.workspace(), job.sp.graphName)
generator.save_nx_graph(G, job.workspace(), job.sp.graphName)
else:
raise ValueError("Unknown generation method {}".format(job.sp.method))
def getModelProject(splitJob: signac.Project.Job, modelRoot: str):
projectRoot = Path(splitJob.workspace()) / modelRoot
modelProject = signac.get_project(root=str(projectRoot), search=False)
return modelProject