def read_nml(self,
f: IO,
attrs: Optional[Dict[str, Any]] = None) -> 'core.TreeNeuron':
"""Read .nml buffer into a TreeNeuron.
NML files are XML files containing a single neuron.
Parameters
----------
f : IO
Readable buffer.
attrs : dict | None
Arbitrary attributes to include in the TreeNeuron.
Returns
-------
core.TreeNeuron
"""
if isinstance(f, bytes):
f = f.decode()
f = io.StringIO(f)
root = ET.parse(f).getroot()
# Copy the attributes dict
for element in root:
if element.tag == 'thing':
nodes = pd.DataFrame.from_records(
[n.attrib for n in element[0]])
edges = pd.DataFrame.from_records(
[n.attrib for n in element[1]])
edges = edges.astype(self._dtypes['node_id'])
nodes.rename({'id': 'node_id'}, axis=1, inplace=True)
nodes = nodes.astype({
k: v
for k, v in self._dtypes.items() if k in nodes.columns
})
G = nx.Graph()
G.add_edges_from(edges.values)
tree = nx.bfs_tree(G, list(G.nodes)[0])
edges = pd.DataFrame(list(tree.edges), columns=['source', 'target'])
nodes['parent_id'] = edges.set_index('target').reindex(
nodes.node_id.values).source.values
nodes['parent_id'] = nodes.parent_id.fillna(-1).astype(
self._dtypes['node_id'])
nodes.sort_values('node_id', inplace=True)
return core.TreeNeuron(
nodes,
**(self._make_attributes({
'name': 'NML',
'origin': 'nml'
}, attrs)))
def import_dataset(
name: str,
sample_class: Type[Sample],
features: IO,
content: IO,
user: User = None,
ensure_incomplete=True,
) -> Tuple[Dataset, int]:
if not user:
try:
user = db.query(User).first()
except NoResultFound:
raise ValueError(
"To import a dataset, there must be at least one user in the system "
"(for creating the association between samples and labels)"
)
if isinstance(features, Path):
feature_file = features.open("r")
df = pd.read_csv(feature_file).set_index("ID")
feature_file.close()
elif isinstance(features, SpooledTemporaryFile):
features.rollover()
df = pd.read_csv(features._file).set_index("ID")
else:
raise ValueError(
"The features argument must be either a Path or FileStorage")
try:
if isinstance(content, SpooledTemporaryFile):
content.rollover()
zip_file = ZipFile(content._file, "r")
else:
zip_file = ZipFile(content, "r")
except AttributeError:
raise ValueError(
"The content argument must be either a Path or FileStorage")
feature_df = df.drop(["LABEL"], axis=1)
dataset = Dataset(
name=name,
features=feature_df.to_csv(),
feature_names=",".join(feature_df.columns),
)
all_labels = {
label_name: Label(name=label_name, dataset=dataset)
for label_name in df["LABEL"].unique()
}
db.add_all(all_labels.values())
db.commit()
total, samples, associations = len(df.index), [], []
for index, (identifier, label_name) in enumerate(df["LABEL"].iteritems()):
content = zip_file.read(f"{int(identifier)}.raw")
sample = sample_class()
sample.dataset = dataset
# get type of content and convert to text if needed
content_type = sample_class.content.property.columns[0].type
if isinstance(content_type, Text):
content = content.decode('utf-8')
sample.content = content
samples.append(sample)
if label_name and label_name in all_labels:
associations.append(
Association(sample=sample,
label=all_labels[label_name], user=user)
)
if index % 1000 == 0:
logger.info(
"{:.2f}% imported ({}/{})".format((index /
total) * 100, index, total)
)
db.add_all(samples)
db.commit()
db.add_all(associations)
db.commit()
samples = []
associations = []
logger.info("Done importing dataset {}".format(dataset))
db.add_all(samples)
db.commit()
db.add_all(associations)
db.commit()
number_of_samples = db.query(Sample).filter(
Sample.dataset == dataset).count()
if ensure_incomplete:
number_of_associations = (
db.query(Association.sample_id)
.join(Association.sample)
.filter(Sample.dataset == dataset)
.count()
)
if number_of_samples == number_of_associations:
logger.info(f"{dataset} is already complete. Thinning it out!")
sample_ids = (
db.query(Association.sample_id)
.join(Association.sample)
.filter(Sample.dataset == dataset)
.all()
)
flat_sample_ids = list(map(int, np.array(sample_ids)[:, 0]))
to_delete = flat_sample_ids[::3]
# Dirty; Use a raw query because otherwise SQLAlchemy unsuccessfully tries to synchronise the
# current session
db.execute(
f'DELETE FROM association WHERE sample_id IN ({",".join(map(str, to_delete))})'
)
db.commit()
return dataset, number_of_samples
