def _compute_graph(self, progress_callback=None):
if self.graph is None:
self.setStatusMessage('Building graph...')
data = self.pca_projection if self.apply_pca else self.preprocessed_data
self.graph = table_to_knn_graph(
data,
k_neighbors=self.k_neighbors,
metric=METRICS[self.metric_idx][1],
progress_callback=progress_callback,
)
def run_on_data(data, pca_components, k_neighbors, metric, resolution, state):
# type: (Table, Optional[int], int, str, float, TaskState) -> Results
"""
Run the louvain clustering on `data`.
state is used to report progress and partial results. Returns early if
`task.is_interuption_requested()` returns true.
Parameters
----------
data : Table
Data table
pca_components : Optional[int]
If not `None` then the data is first projected onto first
`pca_components` principal components.
k_neighbors : int
Passed to `table_to_knn_graph`
metric : str
Passed to `table_to_knn_graph`
resolution : float
Passed to `Louvain`
state : TaskState
Returns
-------
res : Results
"""
state = state # type: TaskState
res = Results(
pca_components=pca_components,
k_neighbors=k_neighbors,
metric=metric,
resolution=resolution,
)
step = 0
if state.is_interuption_requested():
return res
if pca_components is not None:
steps = 3
state.set_status("Computing PCA...")
pca = PCA(n_components=pca_components, random_state=0)
data = res.pca_projection = pca(data)(data)
assert isinstance(data, Table)
state.set_partial_results(("pca_projection", res.pca_projection))
step += 1
else:
steps = 2
if state.is_interuption_requested():
return res
state.set_progress_value(100. * step / steps)
state.set_status("Building graph...")
def pcallback(val):
state.set_progress_value((100. * step + 100 * val) / steps)
if state.is_interuption_requested():
raise InteruptRequested()
try:
res.graph = graph = table_to_knn_graph(data,
k_neighbors=k_neighbors,
metric=metric,
progress_callback=pcallback)
except InteruptRequested:
return res
state.set_partial_results(("graph", res.graph))
step += 1
state.set_progress_value(100 * step / steps)
state.set_status("Detecting communities...")
if state.is_interuption_requested():
return res
louvain = Louvain(resolution=resolution, random_state=0)
res.partition = louvain.fit_predict(graph)
state.set_partial_results(("partition", res.partition))
return res
def run_on_data(data, pca_components, k_neighbors, metric, resolution, state):
# type: (Table, Optional[int], int, str, float, TaskState) -> Results
"""
Run the louvain clustering on `data`.
state is used to report progress and partial results. Returns early if
`task.is_interuption_requested()` returns true.
Parameters
----------
data : Table
Data table
pca_components : Optional[int]
If not `None` then the data is first projected onto first
`pca_components` principal components.
k_neighbors : int
Passed to `table_to_knn_graph`
metric : str
Passed to `table_to_knn_graph`
resolution : float
Passed to `Louvain`
state : TaskState
Returns
-------
res : Results
"""
state = state # type: TaskState
res = Results(
pca_components=pca_components, k_neighbors=k_neighbors, metric=metric,
resolution=resolution,
)
step = 0
if state.is_interuption_requested():
return res
if pca_components is not None:
steps = 3
state.set_status("Computing PCA...")
pca = PCA(n_components=pca_components, random_state=0)
data = res.pca_projection = pca(data)(data)
assert isinstance(data, Table)
state.set_partial_results(("pca_projection", res.pca_projection))
step += 1
else:
steps = 2
if state.is_interuption_requested():
return res
state.set_progress_value(100. * step / steps)
state.set_status("Building graph...")
def pcallback(val):
state.set_progress_value((100. * step + 100 * val) / steps)
if state.is_interuption_requested():
raise InteruptRequested()
try:
res.graph = graph = table_to_knn_graph(
data, k_neighbors=k_neighbors, metric=metric,
progress_callback=pcallback
)
except InteruptRequested:
return res
state.set_partial_results(("graph", res.graph))
step += 1
state.set_progress_value(100 * step / steps)
state.set_status("Detecting communities...")
if state.is_interuption_requested():
return res
louvain = Louvain(resolution=resolution, random_state=0)
res.partition = louvain.fit_predict(graph)
state.set_partial_results(("partition", res.partition))
return res