def test_tool_tips(self):
scene = GraphicsScene()
view = QGraphicsView(scene)
w = TextListWidget()
text = "A" * 10
w.setItems([text, text])
scene.addItem(w)
view.grab() # ensure w is laid out
wrect = view.mapFromScene(w.mapToScene(
w.contentsRect())).boundingRect()
p = QPoint(wrect.topLeft() + QPoint(5, 5))
ev = QHelpEvent(QHelpEvent.ToolTip, p, view.viewport().mapToGlobal(p))
try:
QApplication.sendEvent(view.viewport(), ev)
self.assertEqual(QToolTip.text(), text)
finally:
QToolTip.hideText()
class OWSilhouettePlot(widget.OWWidget):
name = "Silhouette Plot"
description = "Visually assess cluster quality and " \
"the degree of cluster membership."
icon = "icons/SilhouettePlot.svg"
priority = 300
keywords = []
class Inputs:
data = Input("Data", (Orange.data.Table, Orange.misc.DistMatrix))
class Outputs:
selected_data = Output("Selected Data", Orange.data.Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Orange.data.Table)
replaces = [
"orangecontrib.prototypes.widgets.owsilhouetteplot.OWSilhouettePlot",
"Orange.widgets.unsupervised.owsilhouetteplot.OWSilhouettePlot"
]
settingsHandler = settings.PerfectDomainContextHandler()
#: Distance metric index
distance_idx = settings.Setting(0)
#: Group/cluster variable index
cluster_var_idx = settings.ContextSetting(0)
#: Annotation variable index
annotation_var_idx = settings.ContextSetting(0)
#: Group the (displayed) silhouettes by cluster
group_by_cluster = settings.Setting(True)
#: A fixed size for an instance bar
bar_size = settings.Setting(3)
#: Add silhouette scores to output data
auto_commit = settings.Setting(True)
pending_selection = settings.Setting(None, schema_only=True)
Distances = [("Euclidean", Orange.distance.Euclidean),
("Manhattan", Orange.distance.Manhattan),
("Cosine", Orange.distance.Cosine)]
graph_name = "scene"
class Error(widget.OWWidget.Error):
need_two_clusters = Msg("Need at least two non-empty clusters")
singleton_clusters_all = Msg("All clusters are singletons")
memory_error = Msg("Not enough memory")
value_error = Msg("Distances could not be computed: '{}'")
input_validation_error = Msg("{}")
class Warning(widget.OWWidget.Warning):
missing_cluster_assignment = Msg(
"{} instance{s} omitted (missing cluster assignment)")
nan_distances = Msg("{} instance{s} omitted (undefined distances)")
ignoring_categorical = Msg("Ignoring categorical features")
def __init__(self):
super().__init__()
#: The input data
self.data = None # type: Optional[Orange.data.Table]
#: The input distance matrix (if present)
self.distances = None # type: Optional[Orange.misc.DistMatrix]
#: The effective distance matrix (is self.distances or computed from
#: self.data depending on input)
self._matrix = None # type: Optional[Orange.misc.DistMatrix]
#: An bool mask (size == len(data)) indicating missing group/cluster
#: assignments
self._mask = None # type: Optional[np.ndarray]
#: An array of cluster/group labels for instances with valid group
#: assignment
self._labels = None # type: Optional[np.ndarray]
#: An array of silhouette scores for instances with valid group
#: assignment
self._silhouette = None # type: Optional[np.ndarray]
self._silplot = None # type: Optional[SilhouettePlot]
controllayout = self.controlArea.layout()
assert isinstance(controllayout, QVBoxLayout)
self._distances_gui_box = distbox = gui.widgetBox(
None, "Distance"
)
self._distances_gui_cb = gui.comboBox(
distbox, self, "distance_idx",
items=[name for name, _ in OWSilhouettePlot.Distances],
orientation=Qt.Horizontal, callback=self._invalidate_distances)
controllayout.addWidget(distbox)
box = gui.vBox(self.controlArea, "Cluster Label")
self.cluster_var_cb = gui.comboBox(
box, self, "cluster_var_idx", contentsLength=14,
searchable=True, callback=self._invalidate_scores
)
gui.checkBox(
box, self, "group_by_cluster", "Group by cluster",
callback=self._replot)
self.cluster_var_model = itemmodels.VariableListModel(parent=self)
self.cluster_var_cb.setModel(self.cluster_var_model)
box = gui.vBox(self.controlArea, "Bars")
gui.widgetLabel(box, "Bar width:")
gui.hSlider(
box, self, "bar_size", minValue=1, maxValue=10, step=1,
callback=self._update_bar_size)
gui.widgetLabel(box, "Annotations:")
self.annotation_cb = gui.comboBox(
box, self, "annotation_var_idx", contentsLength=14,
callback=self._update_annotations)
self.annotation_var_model = itemmodels.VariableListModel(parent=self)
self.annotation_var_model[:] = ["None"]
self.annotation_cb.setModel(self.annotation_var_model)
ibox = gui.indentedBox(box, 5)
self.ann_hidden_warning = warning = gui.widgetLabel(
ibox, "(increase the width to show)")
ibox.setFixedWidth(ibox.sizeHint().width())
warning.setVisible(False)
gui.rubber(self.controlArea)
gui.auto_send(self.buttonsArea, self, "auto_commit")
self.scene = GraphicsScene(self)
self.view = StickyGraphicsView(self.scene)
self.view.setRenderHint(QPainter.Antialiasing, True)
self.view.setAlignment(Qt.AlignTop | Qt.AlignLeft)
self.mainArea.layout().addWidget(self.view)
self.settingsAboutToBePacked.connect(self.pack_settings)
def sizeHint(self):
sh = self.controlArea.sizeHint()
return sh.expandedTo(QSize(600, 720))
def pack_settings(self):
if self.data and self._silplot is not None:
self.pending_selection = list(self._silplot.selection())
else:
self.pending_selection = None
@Inputs.data
@check_sql_input
def set_data(self, data: Union[Table, DistMatrix, None]):
"""
Set the input dataset or distance matrix.
"""
self.closeContext()
self.clear()
try:
if isinstance(data, Orange.misc.DistMatrix):
self._set_distances(data)
elif isinstance(data, Orange.data.Table):
self._set_table(data)
else:
self.distances = None
self.data = None
except InputValidationError as err:
self.Error.input_validation_error(err.message)
self.distances = None
self.data = None
def _set_table(self, data: Table):
self._setup_control_models(data.domain)
self.data = data
self.distances = None
def _set_distances(self, distances: DistMatrix):
if isinstance(distances.row_items, Orange.data.Table) and \
distances.axis == 1:
data = distances.row_items
else:
raise ValidationError("Input matrix does not have associated data")
if data is not None:
self._setup_control_models(data.domain)
self.distances = distances
self.data = data
def handleNewSignals(self):
if not self._is_empty():
self._update()
self._replot()
if self.pending_selection is not None and self._silplot is not None:
# If selection contains indices that are too large, the data
# file must had been modified, so we ignore selection
if max(self.pending_selection, default=-1) < len(self.data):
self._silplot.setSelection(np.array(self.pending_selection))
self.pending_selection = None
# Disable/enable the Distances GUI controls if applicable
self._distances_gui_box.setEnabled(self.distances is None)
self.commit.now()
def _setup_control_models(self, domain: Domain):
groupvars = [
v for v in domain.variables + domain.metas
if v.is_discrete and len(v.values) >= 2]
if not groupvars:
raise NoGroupVariable()
self.cluster_var_model[:] = groupvars
if domain.class_var in groupvars:
self.cluster_var_idx = groupvars.index(domain.class_var)
else:
self.cluster_var_idx = 0
annotvars = [var for var in domain.variables + domain.metas
if var.is_string or var.is_discrete]
self.annotation_var_model[:] = ["None"] + annotvars
self.annotation_var_idx = 1 if annotvars else 0
self.openContext(Orange.data.Domain(groupvars))
def _is_empty(self) -> bool:
# Is empty (does not have any input).
return (self.data is None or len(self.data) == 0) \
and self.distances is None
def clear(self):
"""
Clear the widget state.
"""
self.data = None
self.distances = None
self._matrix = None
self._mask = None
self._silhouette = None
self._labels = None
self.cluster_var_model[:] = []
self.annotation_var_model[:] = ["None"]
self._clear_scene()
self.Error.clear()
self.Warning.clear()
def _clear_scene(self):
# Clear the graphics scene and associated objects
self.scene.clear()
self.scene.setSceneRect(QRectF())
self.view.setSceneRect(QRectF())
self.view.setHeaderSceneRect(QRectF())
self.view.setFooterSceneRect(QRectF())
self._silplot = None
def _invalidate_distances(self):
# Invalidate the computed distance matrix and recompute the silhouette.
self._matrix = None
self._invalidate_scores()
def _invalidate_scores(self):
# Invalidate and recompute the current silhouette scores.
self._labels = self._silhouette = self._mask = None
self._update()
self._replot()
if self.data is not None:
self.commit.deferred()
def _ensure_matrix(self):
# ensure self._matrix is computed if necessary
if self._is_empty():
return
if self._matrix is None:
if self.distances is not None:
self._matrix = np.asarray(self.distances)
elif self.data is not None:
data = self.data
_, metric = self.Distances[self.distance_idx]
if not metric.supports_discrete and any(
a.is_discrete for a in data.domain.attributes):
self.Warning.ignoring_categorical()
data = Orange.distance.remove_discrete_features(data)
try:
self._matrix = np.asarray(metric(data))
except MemoryError:
self.Error.memory_error()
return
except ValueError as err:
self.Error.value_error(str(err))
return
else:
assert False, "invalid state"
def _update(self):
# Update/recompute the effective distances and scores as required.
self._clear_messages()
if self._is_empty():
self._reset_all()
return
self._ensure_matrix()
if self._matrix is None:
return
labelvar = self.cluster_var_model[self.cluster_var_idx]
labels, _ = self.data.get_column_view(labelvar)
labels = np.asarray(labels, dtype=float)
cluster_mask = np.isnan(labels)
dist_mask = np.isnan(self._matrix).all(axis=0)
mask = cluster_mask | dist_mask
labels = labels.astype(int)
labels = labels[~mask]
labels_unq = np.unique(labels)
if len(labels_unq) < 2:
self.Error.need_two_clusters()
labels = silhouette = mask = None
elif len(labels_unq) == len(labels):
self.Error.singleton_clusters_all()
labels = silhouette = mask = None
else:
silhouette = sklearn.metrics.silhouette_samples(
self._matrix[~mask, :][:, ~mask], labels, metric="precomputed")
self._mask = mask
self._labels = labels
self._silhouette = silhouette
if mask is not None:
count_missing = np.count_nonzero(cluster_mask)
if count_missing:
self.Warning.missing_cluster_assignment(
count_missing, s="s" if count_missing > 1 else "")
count_nandist = np.count_nonzero(dist_mask)
if count_nandist:
self.Warning.nan_distances(
count_nandist, s="s" if count_nandist > 1 else "")
def _reset_all(self):
self._mask = None
self._silhouette = None
self._labels = None
self._matrix = None
self._clear_scene()
def _clear_messages(self):
self.Error.clear()
self.Warning.clear()
def _set_bar_height(self):
visible = self.bar_size >= 5
self._silplot.setBarHeight(self.bar_size)
self._silplot.setRowNamesVisible(visible)
self.ann_hidden_warning.setVisible(
not visible and self.annotation_var_idx > 0)
def _replot(self):
# Clear and replot/initialize the scene
self._clear_scene()
if self._silhouette is not None and self._labels is not None:
var = self.cluster_var_model[self.cluster_var_idx]
self._silplot = silplot = SilhouettePlot()
self._set_bar_height()
if self.group_by_cluster:
silplot.setScores(self._silhouette, self._labels, var.values,
var.colors)
else:
silplot.setScores(
self._silhouette,
np.zeros(len(self._silhouette), dtype=int),
[""], np.array([[63, 207, 207]])
)
self.scene.addItem(silplot)
self._update_annotations()
silplot.selectionChanged.connect(self.commit.deferred)
silplot.layout().activate()
self._update_scene_rect()
silplot.geometryChanged.connect(self._update_scene_rect)
def _update_bar_size(self):
if self._silplot is not None:
self._set_bar_height()
def _update_annotations(self):
if 0 < self.annotation_var_idx < len(self.annotation_var_model):
annot_var = self.annotation_var_model[self.annotation_var_idx]
else:
annot_var = None
self.ann_hidden_warning.setVisible(
self.bar_size < 5 and annot_var is not None)
if self._silplot is not None:
if annot_var is not None:
column, _ = self.data.get_column_view(annot_var)
if self._mask is not None:
assert column.shape == self._mask.shape
# pylint: disable=invalid-unary-operand-type
column = column[~self._mask]
self._silplot.setRowNames(
[annot_var.str_val(value) for value in column])
else:
self._silplot.setRowNames(None)
def _update_scene_rect(self):
geom = self._silplot.geometry()
self.scene.setSceneRect(geom)
self.view.setSceneRect(geom)
header = self._silplot.topScaleItem()
footer = self._silplot.bottomScaleItem()
def extend_horizontal(rect):
# type: (QRectF) -> QRectF
rect = QRectF(rect)
rect.setLeft(geom.left())
rect.setRight(geom.right())
return rect
margin = 3
if header is not None:
self.view.setHeaderSceneRect(
extend_horizontal(header.geometry().adjusted(0, 0, 0, margin)))
if footer is not None:
self.view.setFooterSceneRect(
extend_horizontal(footer.geometry().adjusted(0, -margin, 0, 0)))
@gui.deferred
def commit(self):
"""
Commit/send the current selection to the output.
"""
selected = indices = data = None
if self.data is not None:
selectedmask = np.full(len(self.data), False, dtype=bool)
if self._silplot is not None:
indices = self._silplot.selection()
assert (np.diff(indices) > 0).all(), "strictly increasing"
if self._mask is not None:
# pylint: disable=invalid-unary-operand-type
indices = np.flatnonzero(~self._mask)[indices]
selectedmask[indices] = True
if self._mask is not None:
scores = np.full(shape=selectedmask.shape,
fill_value=np.nan)
# pylint: disable=invalid-unary-operand-type
scores[~self._mask] = self._silhouette
else:
scores = self._silhouette
var = self.cluster_var_model[self.cluster_var_idx]
domain = self.data.domain
proposed = "Silhouette ({})".format(escape(var.name))
names = [var.name for var in itertools.chain(domain.attributes,
domain.class_vars,
domain.metas)]
unique = get_unique_names(names, proposed)
silhouette_var = Orange.data.ContinuousVariable(unique)
domain = Orange.data.Domain(
domain.attributes,
domain.class_vars,
domain.metas + (silhouette_var, ))
if np.count_nonzero(selectedmask):
selected = self.data.from_table(
domain, self.data, np.flatnonzero(selectedmask))
if selected is not None:
with selected.unlocked(selected.metas):
selected[:, silhouette_var] = np.c_[scores[selectedmask]]
data = self.data.transform(domain)
with data.unlocked(data.metas):
data[:, silhouette_var] = np.c_[scores]
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(create_annotated_table(data, indices))
def send_report(self):
if not len(self.cluster_var_model):
return
self.report_plot()
caption = "Silhouette plot ({} distance), clustered by '{}'".format(
self.Distances[self.distance_idx][0],
self.cluster_var_model[self.cluster_var_idx])
if self.annotation_var_idx and self._silplot.rowNamesVisible():
caption += ", annotated with '{}'".format(
self.annotation_var_model[self.annotation_var_idx])
self.report_caption(caption)
def onDeleteWidget(self):
self.clear()
super().onDeleteWidget()
def __init__(self):
super().__init__()
#: The input data
self.data = None # type: Optional[Orange.data.Table]
#: The input distance matrix (if present)
self.distances = None # type: Optional[Orange.misc.DistMatrix]
#: The effective distance matrix (is self.distances or computed from
#: self.data depending on input)
self._matrix = None # type: Optional[Orange.misc.DistMatrix]
#: An bool mask (size == len(data)) indicating missing group/cluster
#: assignments
self._mask = None # type: Optional[np.ndarray]
#: An array of cluster/group labels for instances with valid group
#: assignment
self._labels = None # type: Optional[np.ndarray]
#: An array of silhouette scores for instances with valid group
#: assignment
self._silhouette = None # type: Optional[np.ndarray]
self._silplot = None # type: Optional[SilhouettePlot]
controllayout = self.controlArea.layout()
assert isinstance(controllayout, QVBoxLayout)
self._distances_gui_box = distbox = gui.widgetBox(
None, "Distance"
)
self._distances_gui_cb = gui.comboBox(
distbox, self, "distance_idx",
items=[name for name, _ in OWSilhouettePlot.Distances],
orientation=Qt.Horizontal, callback=self._invalidate_distances)
controllayout.addWidget(distbox)
box = gui.vBox(self.controlArea, "Cluster Label")
self.cluster_var_cb = gui.comboBox(
box, self, "cluster_var_idx", contentsLength=14,
searchable=True, callback=self._invalidate_scores
)
gui.checkBox(
box, self, "group_by_cluster", "Group by cluster",
callback=self._replot)
self.cluster_var_model = itemmodels.VariableListModel(parent=self)
self.cluster_var_cb.setModel(self.cluster_var_model)
box = gui.vBox(self.controlArea, "Bars")
gui.widgetLabel(box, "Bar width:")
gui.hSlider(
box, self, "bar_size", minValue=1, maxValue=10, step=1,
callback=self._update_bar_size)
gui.widgetLabel(box, "Annotations:")
self.annotation_cb = gui.comboBox(
box, self, "annotation_var_idx", contentsLength=14,
callback=self._update_annotations)
self.annotation_var_model = itemmodels.VariableListModel(parent=self)
self.annotation_var_model[:] = ["None"]
self.annotation_cb.setModel(self.annotation_var_model)
ibox = gui.indentedBox(box, 5)
self.ann_hidden_warning = warning = gui.widgetLabel(
ibox, "(increase the width to show)")
ibox.setFixedWidth(ibox.sizeHint().width())
warning.setVisible(False)
gui.rubber(self.controlArea)
gui.auto_send(self.buttonsArea, self, "auto_commit")
self.scene = GraphicsScene(self)
self.view = StickyGraphicsView(self.scene)
self.view.setRenderHint(QPainter.Antialiasing, True)
self.view.setAlignment(Qt.AlignTop | Qt.AlignLeft)
self.mainArea.layout().addWidget(self.view)
self.settingsAboutToBePacked.connect(self.pack_settings)