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] PCA widget runs a separate thread #6528

Merged
merged 4 commits into from
Aug 11, 2023
Merged

[ENH] PCA widget runs a separate thread #6528

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b67e3f8
remove ._pca_preprocessors attribute
markotoplak Aug 10, 2023
2dda296
Remove ._pca_projector attribute: prevent inconsistent object reuse
markotoplak Aug 10, 2023
5f63e6f
Run PCA in a separate thread
markotoplak Aug 10, 2023
e94858f
Allow PCA widget to be interrupted during preprocessing
markotoplak Aug 11, 2023
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
48 changes: 33 additions & 15 deletions Orange/widgets/unsupervised/owpca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
from Orange.preprocess import preprocess
from Orange.projection import PCA
from Orange.widgets import widget, gui, settings
from Orange.widgets.utils.concurrent import ConcurrentWidgetMixin
from Orange.widgets.utils.slidergraph import SliderGraph
from Orange.widgets.utils.widgetpreview import WidgetPreview
from Orange.widgets.widget import Input, Output
Expand All @@ -21,7 +22,7 @@
LINE_NAMES = ["component variance", "cumulative variance"]


class OWPCA(widget.OWWidget):
class OWPCA(widget.OWWidget, ConcurrentWidgetMixin):
name = "PCA"
description = "Principal component analysis with a scree-diagram."
icon = "icons/PCA.svg"
Expand Down Expand Up @@ -57,8 +58,9 @@ class Error(widget.OWWidget.Error):

def __init__(self):
super().__init__()
self.data = None
ConcurrentWidgetMixin.__init__(self)
noahnovsak marked this conversation as resolved.
Show resolved Hide resolved

self.data = None
self._pca = None
self._transformed = None
self._variance_ratio = None
Expand Down Expand Up @@ -113,6 +115,7 @@ def __init__(self):

@Inputs.data
def set_data(self, data):
self.cancel()
self.clear_messages()
self.clear()
self.information()
Expand Down Expand Up @@ -141,6 +144,7 @@ def set_data(self, data):
self.fit()

def fit(self):
self.cancel()
self.clear()
self.Warning.trivial_components.clear()
if self.data is None:
Expand All @@ -151,20 +155,34 @@ def fit(self):
projector = self._create_projector()

if not isinstance(data, SqlTable):
pca = projector(data)
variance_ratio = pca.explained_variance_ratio_
cumulative = numpy.cumsum(variance_ratio)

if numpy.isfinite(cumulative[-1]):
self.components_spin.setRange(0, len(cumulative))
self._pca = pca
self._variance_ratio = variance_ratio
self._cumulative = cumulative
self._setup_plot()
else:
self.Warning.trivial_components()
self.start(self._call_projector, data, projector)

@staticmethod
def _call_projector(data: Table, projector, _):
return projector(data)

def on_done(self, result):
pca = result
variance_ratio = pca.explained_variance_ratio_
cumulative = numpy.cumsum(variance_ratio)

if numpy.isfinite(cumulative[-1]):
self.components_spin.setRange(0, len(cumulative))
self._pca = pca
self._variance_ratio = variance_ratio
self._cumulative = cumulative
self._setup_plot()
else:
self.Warning.trivial_components()

self.commit.now()

def on_partial_result(self, result):
pass

self.commit.now()
def onDeleteWidget(self):
self.shutdown()
super().onDeleteWidget()

def clear(self):
self._pca = None
Expand Down
18 changes: 11 additions & 7 deletions Orange/widgets/unsupervised/tests/test_owpca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ def test_constant_data(self):
# Ignore the warning: the test checks whether the widget shows
# Warning.trivial_components when this happens
with np.errstate(invalid="ignore"):
self.send_signal(self.widget.Inputs.data, data)
self.send_signal(self.widget.Inputs.data, data, wait=5000)
self.assertTrue(self.widget.Warning.trivial_components.is_shown())
self.assertIsNone(self.get_output(self.widget.Outputs.transformed_data))
self.assertIsNone(self.get_output(self.widget.Outputs.components))
Expand All @@ -55,12 +55,12 @@ def test_limit_components(self):
X = np.random.RandomState(0).rand(101, 101)
data = Table.from_numpy(None, X)
self.widget.ncomponents = 100
self.send_signal(self.widget.Inputs.data, data)
self.send_signal(self.widget.Inputs.data, data, wait=5000)
tran = self.get_output(self.widget.Outputs.transformed_data)
self.assertEqual(len(tran.domain.attributes), 100)
self.widget.ncomponents = 101 # should not be accesible
with self.assertRaises(IndexError):
self.send_signal(self.widget.Inputs.data, data)
self.widget._setup_plot() # pylint: disable=protected-access

def test_migrate_settings_limits_components(self):
settings = dict(ncomponents=10)
Expand All @@ -83,9 +83,11 @@ def test_variance_shown(self):
self.send_signal(self.widget.Inputs.data, self.iris)
self.widget.maxp = 2
self.widget._setup_plot()
self.wait_until_finished()
var2 = self.widget.variance_covered
self.widget.ncomponents = 3
self.widget._update_selection_component_spin()
self.wait_until_finished()
var3 = self.widget.variance_covered
self.assertGreater(var3, var2)

Expand All @@ -97,10 +99,11 @@ def test_unique_domain_components(self):

def test_variance_attr(self):
self.widget.ncomponents = 2
self.send_signal(self.widget.Inputs.data, self.iris)
self.send_signal(self.widget.Inputs.data, self.iris, wait=5000)
self.wait_until_stop_blocking()
self.widget._variance_ratio = np.array([0.5, 0.25, 0.2, 0.05])
self.widget.commit.now()
self.wait_until_finished()

result = self.get_output(self.widget.Outputs.transformed_data)
pc1, pc2 = result.domain.attributes
Expand Down Expand Up @@ -162,7 +165,7 @@ def test_normalize_data(self, prepare_table):
self.widget.controls.normalize.setChecked(True)
self.assertTrue(self.widget.controls.normalize.isChecked())
with patch.object(preprocess.Normalize, "__call__", wraps=lambda x: x) as normalize:
self.send_signal(self.widget.Inputs.data, data)
self.send_signal(self.widget.Inputs.data, data, wait=5000)
self.wait_until_stop_blocking()
self.assertTrue(self.widget.controls.normalize.isEnabled())
normalize.assert_called_once()
Expand All @@ -171,7 +174,7 @@ def test_normalize_data(self, prepare_table):
self.widget.controls.normalize.setChecked(False)
self.assertFalse(self.widget.controls.normalize.isChecked())
with patch.object(preprocess.Normalize, "__call__", wraps=lambda x: x) as normalize:
self.send_signal(self.widget.Inputs.data, data)
self.send_signal(self.widget.Inputs.data, data, wait=5000)
self.wait_until_stop_blocking()
self.assertTrue(self.widget.controls.normalize.isEnabled())
normalize.assert_not_called()
Expand All @@ -184,13 +187,14 @@ def test_normalization_variance(self, prepare_table):
# Enable normalization
self.widget.controls.normalize.setChecked(True)
self.assertTrue(self.widget.normalize)
self.send_signal(self.widget.Inputs.data, data)
self.send_signal(self.widget.Inputs.data, data, wait=5000)
self.wait_until_stop_blocking()
variance_normalized = self.widget.variance_covered

# Disable normalization
self.widget.controls.normalize.setChecked(False)
self.assertFalse(self.widget.normalize)
self.wait_until_finished()
self.wait_until_stop_blocking()
variance_unnormalized = self.widget.variance_covered

Expand Down