Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[ENH] Louvain show number of clusters #3572

Merged
merged 3 commits into from
Feb 2, 2019
Merged

[ENH] Louvain show number of clusters #3572

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b20aa02
OwLouvain: Use double quotes consistently
pavlin-policar Feb 2, 2019
37c041e
OwLouvain: Display number of cluster in UI
pavlin-policar Feb 2, 2019
40762e2
OwLouvain: Don't catch programming errors
pavlin-policar Feb 2, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 47 additions & 38 deletions Orange/widgets/unsupervised/owlouvainclustering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
from AnyQt.QtCore import (
Qt, QObject, QTimer, pyqtSignal as Signal, pyqtSlot as Slot
)
from AnyQt.QtWidgets import QSlider, QCheckBox, QWidget
from AnyQt.QtWidgets import QSlider, QCheckBox, QWidget, QLabel

from Orange.clustering.louvain import table_to_knn_graph, Louvain
from Orange.data import Table, DiscreteVariable
Expand Down Expand Up @@ -40,26 +40,26 @@
_DEFAULT_K_NEIGHBORS = 30


METRICS = [('Euclidean', 'l2'), ('Manhattan', 'l1')]
METRICS = [("Euclidean", "l2"), ("Manhattan", "l1")]


class OWLouvainClustering(widget.OWWidget):
name = 'Louvain Clustering'
description = 'Detects communities in a network of nearest neighbors.'
icon = 'icons/LouvainClustering.svg'
name = "Louvain Clustering"
description = "Detects communities in a network of nearest neighbors."
icon = "icons/LouvainClustering.svg"
priority = 2110

want_main_area = False

settingsHandler = DomainContextHandler()

class Inputs:
data = Input('Data', Table, default=True)
data = Input("Data", Table, default=True)

if Graph is not None:
class Outputs:
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table, default=True)
graph = Output('Network', Graph)
graph = Output("Network", Graph)
else:
class Outputs:
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table, default=True)
Expand All @@ -75,8 +75,7 @@ class Information(widget.OWWidget.Information):
modified = Msg("Press commit to recompute clusters and send new data")

class Error(widget.OWWidget.Error):
empty_dataset = Msg('No features in data')
general_error = Msg('Error occured during clustering\n{}')
empty_dataset = Msg("No features in data")

def __init__(self):
super().__init__()
Expand All @@ -98,40 +97,44 @@ def __init__(self):
self.__commit_timer = QTimer(self, singleShot=True)
self.__commit_timer.timeout.connect(self.commit)

pca_box = gui.vBox(self.controlArea, 'PCA Preprocessing')
# Set up UI
info_box = gui.vBox(self.controlArea, "Info")
self.info_label = gui.widgetLabel(info_box, "No data on input.") # type: QLabel

pca_box = gui.vBox(self.controlArea, "PCA Preprocessing")
self.apply_pca_cbx = gui.checkBox(
pca_box, self, 'apply_pca', label='Apply PCA preprocessing',
pca_box, self, "apply_pca", label="Apply PCA preprocessing",
callback=self._invalidate_graph,
) # type: QCheckBox
self.pca_components_slider = gui.hSlider(
pca_box, self, 'pca_components', label='Components: ', minValue=2,
pca_box, self, "pca_components", label="Components: ", minValue=2,
maxValue=_MAX_PCA_COMPONENTS,
callback=self._invalidate_pca_projection, tracking=False
) # type: QSlider

graph_box = gui.vBox(self.controlArea, 'Graph parameters')
graph_box = gui.vBox(self.controlArea, "Graph parameters")
self.metric_combo = gui.comboBox(
graph_box, self, 'metric_idx', label='Distance metric',
graph_box, self, "metric_idx", label="Distance metric",
items=[m[0] for m in METRICS], callback=self._invalidate_graph,
orientation=Qt.Horizontal,
) # type: gui.OrangeComboBox
self.k_neighbors_spin = gui.spin(
graph_box, self, 'k_neighbors', minv=1, maxv=_MAX_K_NEIGBOURS,
label='k neighbors', controlWidth=80, alignment=Qt.AlignRight,
graph_box, self, "k_neighbors", minv=1, maxv=_MAX_K_NEIGBOURS,
label="k neighbors", controlWidth=80, alignment=Qt.AlignRight,
callback=self._invalidate_graph,
) # type: gui.SpinBoxWFocusOut
self.resolution_spin = gui.hSlider(
graph_box, self, 'resolution', minValue=0, maxValue=5., step=1e-1,
label='Resolution', intOnly=False, labelFormat='%.1f',
graph_box, self, "resolution", minValue=0, maxValue=5., step=1e-1,
label="Resolution", intOnly=False, labelFormat="%.1f",
callback=self._invalidate_partition, tracking=False,
) # type: QSlider
self.resolution_spin.parent().setToolTip(
'The resolution parameter affects the number of clusters to find. '
'Smaller values tend to produce more clusters and larger values '
'retrieve less clusters.'
"The resolution parameter affects the number of clusters to find. "
"Smaller values tend to produce more clusters and larger values "
"retrieve less clusters."
)
self.apply_button = gui.auto_commit(
self.controlArea, self, 'auto_commit', 'Apply', box=None,
self.controlArea, self, "auto_commit", "Apply", box=None,
commit=lambda: self.commit(),
callback=lambda: self._on_auto_commit_changed(),
) # type: QWidget
Expand Down Expand Up @@ -248,6 +251,7 @@ def commit(self):
run_on_graph, graph, resolution=self.resolution, state=state
)

self.info_label.setText("Running...")
self.__set_state_busy()
self.__start_task(task, state)

Expand All @@ -269,7 +273,7 @@ def __set_partial_results(self, result):

@Slot(object)
def __on_done(self, future):
# type: (Future['Results']) -> None
# type: (Future["Results"]) -> None
assert future.done()
assert self.__task is not None
assert self.__task.future is future
Expand All @@ -278,12 +282,9 @@ def __on_done(self, future):
task.deleteLater()

self.__set_state_ready()
try:
result = future.result()
except Exception as err: # pylint: disable=broad-except
self.Error.general_error(str(err), exc_info=True)
else:
self.__set_results(result)

result = future.result()
self.__set_results(result)

@Slot(str)
def setStatusMessage(self, text):
Expand Down Expand Up @@ -330,7 +331,7 @@ def __cancel_task(self, wait=True):
w.done.connect(state.deleteLater)

def __set_results(self, results):
# type: ('Results') -> None
# type: ("Results") -> None
# NOTE: All of these have already been set by __set_partial_results,
# we double check that they are aliases
if results.pca_projection is not None:
Expand All @@ -346,6 +347,11 @@ def __set_results(self, results):
assert results.resolution == self.resolution
assert self.partition is results.partition
self.partition = results.partition

# Display the number of found clusters in the UI
num_clusters = len(np.unique(self.partition))
self.info_label.setText("%d clusters found." % num_clusters)

self._send_data()

def _send_data(self):
Expand All @@ -359,8 +365,8 @@ def _send_data(self):
new_partition = list(map(index_map.get, self.partition))

cluster_var = DiscreteVariable(
get_unique_names(domain, 'Cluster'),
values=['C%d' % (i + 1) for i, _ in enumerate(np.unique(new_partition))]
get_unique_names(domain, "Cluster"),
values=["C%d" % (i + 1) for i, _ in enumerate(np.unique(new_partition))]
)

new_domain = add_columns(domain, metas=[cluster_var])
Expand Down Expand Up @@ -406,6 +412,8 @@ def set_data(self, data):
self.k_neighbors_spin.setMaximum(min(_MAX_K_NEIGBOURS, len(data) - 1))
self.k_neighbors_spin.setValue(min(_DEFAULT_K_NEIGHBORS, len(data) - 1))

self.info_label.setText("Clustering not yet run.")

self.commit()

def clear(self):
Expand All @@ -416,6 +424,7 @@ def clear(self):
self.partition = None
self.Error.clear()
self.Information.modified.clear()
self.info_label.setText("No data on input.")

def onDeleteWidget(self):
self.__cancel_task(wait=True)
Expand All @@ -427,13 +436,13 @@ def onDeleteWidget(self):
def send_report(self):
pca = report.bool_str(self.apply_pca)
if self.apply_pca:
pca += report.plural(', {number} component{s}', self.pca_components)
pca += report.plural(", {number} component{s}", self.pca_components)

self.report_items((
('PCA preprocessing', pca),
('Metric', METRICS[self.metric_idx][0]),
('k neighbors', self.k_neighbors),
('Resolution', self.resolution),
("PCA preprocessing", pca),
("Metric", METRICS[self.metric_idx][0]),
("k neighbors", self.k_neighbors),
("Resolution", self.resolution),
))


Expand Down Expand Up @@ -614,5 +623,5 @@ def run_on_graph(graph, resolution, state):
return res


if __name__ == '__main__': # pragma: no cover
if __name__ == "__main__": # pragma: no cover
WidgetPreview(OWLouvainClustering).run(Table("iris"))