def test(self):
view = StickyGraphicsView()
scene = QGraphicsScene(view)
scene.setBackgroundBrush(QBrush(Qt.lightGray, Qt.CrossPattern))
view.setScene(scene)
scene.addRect(QRectF(0, 0, 300, 20), Qt.red,
QBrush(Qt.red, Qt.BDiagPattern))
scene.addRect(QRectF(0, 25, 300, 100))
scene.addRect(QRectF(0, 130, 300, 20), Qt.darkGray,
QBrush(Qt.darkGray, Qt.BDiagPattern))
view.setHeaderSceneRect(QRectF(0, 0, 300, 20))
view.setFooterSceneRect(QRectF(0, 130, 300, 20))
header = view.headerView()
footer = view.footerView()
view.resize(310, 310)
view.grab()
self.assertFalse(header.isVisibleTo(view))
self.assertFalse(footer.isVisibleTo(view))
view.resize(310, 100)
view.verticalScrollBar().setValue(0) # scroll to top
view.grab()
self.assertFalse(header.isVisibleTo(view))
self.assertTrue(footer.isVisibleTo(view))
view.verticalScrollBar().setValue(
view.verticalScrollBar().maximum()) # scroll to bottom
view.grab()
self.assertTrue(header.isVisibleTo(view))
self.assertFalse(footer.isVisibleTo(view))
qWheelScroll(header.viewport(), angleDelta=QPoint(0, -720 * 8))
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()
class OWHierarchicalClustering(widget.OWWidget):
name = "Hierarchical Clustering"
description = "Display a dendrogram of a hierarchical clustering " \
"constructed from the input distance matrix."
icon = "icons/HierarchicalClustering.svg"
priority = 2100
keywords = []
class Inputs:
distances = Input("Distances", 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)
settingsHandler = _DomainContextHandler()
#: Selected linkage
linkage = settings.Setting(1)
#: Index of the selected annotation item (variable, ...)
annotation = settings.ContextSetting("Enumeration")
#: Out-of-context setting for the case when the "Name" option is available
annotation_if_names = settings.Setting("Name")
#: Out-of-context setting for the case with just "Enumerate" and "None"
annotation_if_enumerate = settings.Setting("Enumerate")
#: Selected tree pruning (none/max depth)
pruning = settings.Setting(0)
#: Maximum depth when max depth pruning is selected
max_depth = settings.Setting(10)
#: Selected cluster selection method (none, cut distance, top n)
selection_method = settings.Setting(0)
#: Cut height ratio wrt root height
cut_ratio = settings.Setting(75.0)
#: Number of top clusters to select
top_n = settings.Setting(3)
#: Dendrogram zoom factor
zoom_factor = settings.Setting(0)
autocommit = settings.Setting(True)
graph_name = "scene"
basic_annotations = ["None", "Enumeration"]
class Error(widget.OWWidget.Error):
not_finite_distances = Msg("Some distances are infinite")
#: Stored (manual) selection state (from a saved workflow) to restore.
__pending_selection_restore = None # type: Optional[SelectionState]
def __init__(self):
super().__init__()
self.matrix = None
self.items = None
self.linkmatrix = None
self.root = None
self._displayed_root = None
self.cutoff_height = 0.0
gui.comboBox(self.controlArea,
self,
"linkage",
items=LINKAGE,
box="Linkage",
callback=self._invalidate_clustering)
model = itemmodels.VariableListModel()
model[:] = self.basic_annotations
box = gui.widgetBox(self.controlArea, "Annotations")
self.label_cb = cb = combobox.ComboBoxSearch(
minimumContentsLength=14,
sizeAdjustPolicy=QComboBox.AdjustToMinimumContentsLengthWithIcon)
cb.setModel(model)
cb.setCurrentIndex(cb.findData(self.annotation, Qt.EditRole))
def on_annotation_activated():
self.annotation = cb.currentData(Qt.EditRole)
self._update_labels()
cb.activated.connect(on_annotation_activated)
def on_annotation_changed(value):
cb.setCurrentIndex(cb.findData(value, Qt.EditRole))
self.connect_control("annotation", on_annotation_changed)
box.layout().addWidget(self.label_cb)
box = gui.radioButtons(self.controlArea,
self,
"pruning",
box="Pruning",
callback=self._invalidate_pruning)
grid = QGridLayout()
box.layout().addLayout(grid)
grid.addWidget(gui.appendRadioButton(box, "None", addToLayout=False),
0, 0)
self.max_depth_spin = gui.spin(box,
self,
"max_depth",
minv=1,
maxv=100,
callback=self._invalidate_pruning,
keyboardTracking=False,
addToLayout=False)
grid.addWidget(
gui.appendRadioButton(box, "Max depth:", addToLayout=False), 1, 0)
grid.addWidget(self.max_depth_spin, 1, 1)
self.selection_box = gui.radioButtons(
self.controlArea,
self,
"selection_method",
box="Selection",
callback=self._selection_method_changed)
grid = QGridLayout()
self.selection_box.layout().addLayout(grid)
grid.addWidget(
gui.appendRadioButton(self.selection_box,
"Manual",
addToLayout=False), 0, 0)
grid.addWidget(
gui.appendRadioButton(self.selection_box,
"Height ratio:",
addToLayout=False), 1, 0)
self.cut_ratio_spin = gui.spin(self.selection_box,
self,
"cut_ratio",
0,
100,
step=1e-1,
spinType=float,
callback=self._selection_method_changed,
addToLayout=False)
self.cut_ratio_spin.setSuffix("%")
grid.addWidget(self.cut_ratio_spin, 1, 1)
grid.addWidget(
gui.appendRadioButton(self.selection_box,
"Top N:",
addToLayout=False), 2, 0)
self.top_n_spin = gui.spin(self.selection_box,
self,
"top_n",
1,
20,
callback=self._selection_method_changed,
addToLayout=False)
grid.addWidget(self.top_n_spin, 2, 1)
self.zoom_slider = gui.hSlider(self.controlArea,
self,
"zoom_factor",
box="Zoom",
minValue=-6,
maxValue=3,
step=1,
ticks=True,
createLabel=False,
callback=self.__update_font_scale)
zoom_in = QAction("Zoom in",
self,
shortcut=QKeySequence.ZoomIn,
triggered=self.__zoom_in)
zoom_out = QAction("Zoom out",
self,
shortcut=QKeySequence.ZoomOut,
triggered=self.__zoom_out)
zoom_reset = QAction("Reset zoom",
self,
shortcut=QKeySequence(Qt.ControlModifier
| Qt.Key_0),
triggered=self.__zoom_reset)
self.addActions([zoom_in, zoom_out, zoom_reset])
self.controlArea.layout().addStretch()
gui.auto_send(self.buttonsArea, self, "autocommit")
self.scene = QGraphicsScene(self)
self.view = StickyGraphicsView(
self.scene,
horizontalScrollBarPolicy=Qt.ScrollBarAlwaysOff,
verticalScrollBarPolicy=Qt.ScrollBarAlwaysOn,
alignment=Qt.AlignLeft | Qt.AlignVCenter)
self.mainArea.layout().setSpacing(1)
self.mainArea.layout().addWidget(self.view)
def axis_view(orientation):
ax = AxisItem(orientation=orientation, maxTickLength=7)
ax.mousePressed.connect(self._activate_cut_line)
ax.mouseMoved.connect(self._activate_cut_line)
ax.mouseReleased.connect(self._activate_cut_line)
ax.setRange(1.0, 0.0)
return ax
self.top_axis = axis_view("top")
self.bottom_axis = axis_view("bottom")
self._main_graphics = QGraphicsWidget()
scenelayout = QGraphicsGridLayout()
scenelayout.setHorizontalSpacing(10)
scenelayout.setVerticalSpacing(10)
self._main_graphics.setLayout(scenelayout)
self.scene.addItem(self._main_graphics)
self.dendrogram = DendrogramWidget()
self.dendrogram.setSizePolicy(QSizePolicy.MinimumExpanding,
QSizePolicy.MinimumExpanding)
self.dendrogram.selectionChanged.connect(self._invalidate_output)
self.dendrogram.selectionEdited.connect(self._selection_edited)
self.labels = TextListWidget()
self.labels.setSizePolicy(QSizePolicy.Minimum, QSizePolicy.Preferred)
self.labels.setAlignment(Qt.AlignLeft)
self.labels.setMaximumWidth(200)
scenelayout.addItem(self.top_axis,
0,
0,
alignment=Qt.AlignLeft | Qt.AlignVCenter)
scenelayout.addItem(self.dendrogram,
1,
0,
alignment=Qt.AlignLeft | Qt.AlignVCenter)
scenelayout.addItem(self.labels,
1,
1,
alignment=Qt.AlignLeft | Qt.AlignVCenter)
scenelayout.addItem(self.bottom_axis,
2,
0,
alignment=Qt.AlignLeft | Qt.AlignVCenter)
self.view.viewport().installEventFilter(self)
self._main_graphics.installEventFilter(self)
self.top_axis.setZValue(self.dendrogram.zValue() + 10)
self.bottom_axis.setZValue(self.dendrogram.zValue() + 10)
self.cut_line = SliderLine(self.top_axis, orientation=Qt.Horizontal)
self.cut_line.valueChanged.connect(self._dendrogram_slider_changed)
self.dendrogram.geometryChanged.connect(self._dendrogram_geom_changed)
self._set_cut_line_visible(self.selection_method == 1)
self.__update_font_scale()
@Inputs.distances
def set_distances(self, matrix):
if self.__pending_selection_restore is not None:
selection_state = self.__pending_selection_restore
else:
# save the current selection to (possibly) restore later
selection_state = self._save_selection()
self.error()
self.Error.clear()
if matrix is not None:
N, _ = matrix.shape
if N < 2:
self.error("Empty distance matrix")
matrix = None
if matrix is not None:
if not np.all(np.isfinite(matrix)):
self.Error.not_finite_distances()
matrix = None
self.matrix = matrix
if matrix is not None:
self._set_items(matrix.row_items, matrix.axis)
else:
self._set_items(None)
self._invalidate_clustering()
# Can now attempt to restore session state from a saved workflow.
if self.root and selection_state is not None:
self._restore_selection(selection_state)
self.__pending_selection_restore = None
self.commit.now()
def _set_items(self, items, axis=1):
self.closeContext()
self.items = items
model = self.label_cb.model()
if len(model) == 3:
self.annotation_if_names = self.annotation
elif len(model) == 2:
self.annotation_if_enumerate = self.annotation
if isinstance(items, Orange.data.Table) and axis:
model[:] = chain(
self.basic_annotations, [model.Separator],
items.domain.class_vars, items.domain.metas,
[model.Separator] if
(items.domain.class_vars or items.domain.metas) and next(
filter_visible(items.domain.attributes), False) else [],
filter_visible(items.domain.attributes))
if items.domain.class_vars:
self.annotation = items.domain.class_vars[0]
else:
self.annotation = "Enumeration"
self.openContext(items.domain)
else:
name_option = bool(
items is not None
and (not axis or isinstance(items, list) and all(
isinstance(var, Orange.data.Variable) for var in items)))
model[:] = self.basic_annotations + ["Name"] * name_option
self.annotation = self.annotation_if_names if name_option \
else self.annotation_if_enumerate
def _clear_plot(self):
self.dendrogram.set_root(None)
self.labels.setItems([])
def _set_displayed_root(self, root):
self._clear_plot()
self._displayed_root = root
self.dendrogram.set_root(root)
self._update_labels()
self._main_graphics.resize(
self._main_graphics.size().width(),
self._main_graphics.sizeHint(Qt.PreferredSize).height())
self._main_graphics.layout().activate()
def _update(self):
self._clear_plot()
distances = self.matrix
if distances is not None:
method = LINKAGE[self.linkage].lower()
Z = dist_matrix_linkage(distances, linkage=method)
tree = tree_from_linkage(Z)
self.linkmatrix = Z
self.root = tree
self.top_axis.setRange(tree.value.height, 0.0)
self.bottom_axis.setRange(tree.value.height, 0.0)
if self.pruning:
self._set_displayed_root(prune(tree, level=self.max_depth))
else:
self._set_displayed_root(tree)
else:
self.linkmatrix = None
self.root = None
self._set_displayed_root(None)
self._apply_selection()
def _update_labels(self):
labels = []
if self.root and self._displayed_root:
indices = [leaf.value.index for leaf in leaves(self.root)]
if self.annotation == "None":
labels = []
elif self.annotation == "Enumeration":
labels = [str(i + 1) for i in indices]
elif self.annotation == "Name":
attr = self.matrix.row_items.domain.attributes
labels = [str(attr[i]) for i in indices]
elif isinstance(self.annotation, Orange.data.Variable):
col_data, _ = self.items.get_column_view(self.annotation)
labels = [self.annotation.str_val(val) for val in col_data]
labels = [labels[idx] for idx in indices]
else:
labels = []
if labels and self._displayed_root is not self.root:
joined = leaves(self._displayed_root)
labels = [
", ".join(labels[leaf.value.first:leaf.value.last])
for leaf in joined
]
self.labels.setItems(labels)
self.labels.setMinimumWidth(1 if labels else -1)
def _restore_selection(self, state):
# type: (SelectionState) -> bool
"""
Restore the (manual) node selection state.
Return True if successful; False otherwise.
"""
linkmatrix = self.linkmatrix
if self.selection_method == 0 and self.root:
selected, linksaved = state
linkstruct = np.array(linksaved, dtype=float)
selected = set(selected) # type: Set[Tuple[int]]
if not selected:
return False
if linkmatrix.shape[0] != linkstruct.shape[0]:
return False
# check that the linkage matrix structure matches. Use isclose for
# the height column to account for inexact floating point math
# (e.g. summation order in different ?gemm implementations for
# euclidean distances, ...)
if np.any(linkstruct[:, :2] != linkmatrix[:, :2]) or \
not np.all(np.isclose(linkstruct[:, 2], linkstruct[:, 2])):
return False
selection = []
indices = np.array([n.value.index for n in leaves(self.root)],
dtype=int)
# mapping from ranges to display (pruned) nodes
mapping = {
node.value.range: node
for node in postorder(self._displayed_root)
}
for node in postorder(self.root): # type: Tree
r = tuple(indices[node.value.first:node.value.last])
if r in selected:
if node.value.range not in mapping:
# the node was pruned from display and cannot be
# selected
break
selection.append(mapping[node.value.range])
selected.remove(r)
if not selected:
break # found all, nothing more to do
if selection and selected:
# Could not restore all selected nodes (only partial match)
return False
self._set_selected_nodes(selection)
return True
return False
def _set_selected_nodes(self, selection):
# type: (List[Tree]) -> None
"""
Set the nodes in `selection` to be the current selected nodes.
The selection nodes must be subtrees of the current `_displayed_root`.
"""
self.dendrogram.selectionChanged.disconnect(self._invalidate_output)
try:
self.dendrogram.set_selected_clusters(selection)
finally:
self.dendrogram.selectionChanged.connect(self._invalidate_output)
def _invalidate_clustering(self):
self._update()
self._update_labels()
self._invalidate_output()
def _invalidate_output(self):
self.commit.deferred()
def _invalidate_pruning(self):
if self.root:
selection = self.dendrogram.selected_nodes()
ranges = [node.value.range for node in selection]
if self.pruning:
self._set_displayed_root(prune(self.root,
level=self.max_depth))
else:
self._set_displayed_root(self.root)
selected = [
node for node in preorder(self._displayed_root)
if node.value.range in ranges
]
self.dendrogram.set_selected_clusters(selected)
self._apply_selection()
@gui.deferred
def commit(self):
items = getattr(self.matrix, "items", self.items)
if not items:
self.Outputs.selected_data.send(None)
self.Outputs.annotated_data.send(None)
return
selection = self.dendrogram.selected_nodes()
selection = sorted(selection, key=lambda c: c.value.first)
indices = [leaf.value.index for leaf in leaves(self.root)]
maps = [
indices[node.value.first:node.value.last] for node in selection
]
selected_indices = list(chain(*maps))
unselected_indices = sorted(
set(range(self.root.value.last)) - set(selected_indices))
if not selected_indices:
self.Outputs.selected_data.send(None)
annotated_data = create_annotated_table(items, []) \
if self.selection_method == 0 and self.matrix.axis else None
self.Outputs.annotated_data.send(annotated_data)
return
selected_data = None
if isinstance(items, Orange.data.Table) and self.matrix.axis == 1:
# Select rows
c = np.zeros(self.matrix.shape[0])
for i, indices in enumerate(maps):
c[indices] = i
c[unselected_indices] = len(maps)
mask = c != len(maps)
data, domain = items, items.domain
attrs = domain.attributes
classes = domain.class_vars
metas = domain.metas
var_name = get_unique_names(domain, "Cluster")
values = [f"C{i + 1}" for i in range(len(maps))]
clust_var = Orange.data.DiscreteVariable(var_name,
values=values + ["Other"])
domain = Orange.data.Domain(attrs, classes, metas + (clust_var, ))
data = items.transform(domain)
with data.unlocked(data.metas):
data.get_column_view(clust_var)[0][:] = c
if selected_indices:
selected_data = data[mask]
clust_var = Orange.data.DiscreteVariable(var_name,
values=values)
selected_data.domain = Domain(attrs, classes,
metas + (clust_var, ))
annotated_data = create_annotated_table(data, selected_indices)
elif isinstance(items, Orange.data.Table) and self.matrix.axis == 0:
# Select columns
attrs = []
for clust, indices in chain(enumerate(maps, start=1),
[(0, unselected_indices)]):
for i in indices:
attr = items.domain[i].copy()
attr.attributes["cluster"] = clust
attrs.append(attr)
domain = Orange.data.Domain(
# len(unselected_indices) can be 0
attrs[:len(attrs) - len(unselected_indices)],
items.domain.class_vars,
items.domain.metas)
selected_data = items.from_table(domain, items)
domain = Orange.data.Domain(attrs, items.domain.class_vars,
items.domain.metas)
annotated_data = items.from_table(domain, items)
self.Outputs.selected_data.send(selected_data)
self.Outputs.annotated_data.send(annotated_data)
def eventFilter(self, obj, event):
if obj is self.view.viewport() and event.type() == QEvent.Resize:
# NOTE: not using viewport.width(), due to 'transient' scroll bars
# (macOS). Viewport covers the whole view, but QGraphicsView still
# scrolls left, right with scroll bar extent (other
# QAbstractScrollArea widgets behave as expected).
w_frame = self.view.frameWidth()
margin = self.view.viewportMargins()
w_scroll = self.view.verticalScrollBar().width()
width = (self.view.width() - w_frame * 2 - margin.left() -
margin.right() - w_scroll)
# layout with new width constraint
self.__layout_main_graphics(width=width)
elif obj is self._main_graphics and \
event.type() == QEvent.LayoutRequest:
# layout preserving the width (vertical re layout)
self.__layout_main_graphics()
return super().eventFilter(obj, event)
@Slot(QPointF)
def _activate_cut_line(self, pos: QPointF):
"""Activate cut line selection an set cut value to `pos.x()`."""
self.selection_method = 1
self.cut_line.setValue(pos.x())
self._selection_method_changed()
def onDeleteWidget(self):
super().onDeleteWidget()
self._clear_plot()
self.dendrogram.clear()
self.dendrogram.deleteLater()
def _dendrogram_geom_changed(self):
pos = self.dendrogram.pos_at_height(self.cutoff_height)
geom = self.dendrogram.geometry()
self._set_slider_value(pos.x(), geom.width())
self.cut_line.setLength(self.bottom_axis.geometry().bottom() -
self.top_axis.geometry().top())
geom = self._main_graphics.geometry()
assert geom.topLeft() == QPointF(0, 0)
def adjustLeft(rect):
rect = QRectF(rect)
rect.setLeft(geom.left())
return rect
margin = 3
self.scene.setSceneRect(geom)
self.view.setSceneRect(geom)
self.view.setHeaderSceneRect(
adjustLeft(self.top_axis.geometry()).adjusted(0, 0, 0, margin))
self.view.setFooterSceneRect(
adjustLeft(self.bottom_axis.geometry()).adjusted(0, -margin, 0, 0))
def _dendrogram_slider_changed(self, value):
p = QPointF(value, 0)
cl_height = self.dendrogram.height_at(p)
self.set_cutoff_height(cl_height)
def _set_slider_value(self, value, span):
with blocked(self.cut_line):
self.cut_line.setRange(0, span)
self.cut_line.setValue(value)
def set_cutoff_height(self, height):
self.cutoff_height = height
if self.root:
self.cut_ratio = 100 * height / self.root.value.height
self.select_max_height(height)
def _set_cut_line_visible(self, visible):
self.cut_line.setVisible(visible)
def select_top_n(self, n):
root = self._displayed_root
if root:
clusters = top_clusters(root, n)
self.dendrogram.set_selected_clusters(clusters)
def select_max_height(self, height):
root = self._displayed_root
if root:
clusters = clusters_at_height(root, height)
self.dendrogram.set_selected_clusters(clusters)
def _selection_method_changed(self):
self._set_cut_line_visible(self.selection_method == 1)
if self.root:
self._apply_selection()
def _apply_selection(self):
if not self.root:
return
if self.selection_method == 0:
pass
elif self.selection_method == 1:
height = self.cut_ratio * self.root.value.height / 100
self.set_cutoff_height(height)
pos = self.dendrogram.pos_at_height(height)
self._set_slider_value(pos.x(), self.dendrogram.size().width())
elif self.selection_method == 2:
self.select_top_n(self.top_n)
def _selection_edited(self):
# Selection was edited by clicking on a cluster in the
# dendrogram view.
self.selection_method = 0
self._selection_method_changed()
self._invalidate_output()
def _save_selection(self):
# Save the current manual node selection state
selection_state = None
if self.selection_method == 0 and self.root:
assert self.linkmatrix is not None
linkmat = [(int(_0), int(_1), _2)
for _0, _1, _2 in self.linkmatrix[:, :3].tolist()]
nodes_ = self.dendrogram.selected_nodes()
# match the display (pruned) nodes back (by ranges)
mapping = {node.value.range: node for node in postorder(self.root)}
nodes = [mapping[node.value.range] for node in nodes_]
indices = [
tuple(node.value.index for node in leaves(node))
for node in nodes
]
if nodes:
selection_state = (indices, linkmat)
return selection_state
def save_state(self):
# type: () -> Dict[str, Any]
"""
Save state for `set_restore_state`
"""
selection = self._save_selection()
res = {"version": (0, 0, 0)}
if selection is not None:
res["selection_state"] = selection
return res
def set_restore_state(self, state):
# type: (Dict[str, Any]) -> bool
"""
Restore session data from a saved state.
Parameters
----------
state : Dict[str, Any]
NOTE
----
This is method called while the instance (self) is being constructed,
even before its `__init__` is called. Consider `self` to be only a
`QObject` at this stage.
"""
if "selection_state" in state:
selection = state["selection_state"]
self.__pending_selection_restore = selection
return True
def __zoom_in(self):
def clip(minval, maxval, val):
return min(max(val, minval), maxval)
self.zoom_factor = clip(self.zoom_slider.minimum(),
self.zoom_slider.maximum(),
self.zoom_factor + 1)
self.__update_font_scale()
def __zoom_out(self):
def clip(minval, maxval, val):
return min(max(val, minval), maxval)
self.zoom_factor = clip(self.zoom_slider.minimum(),
self.zoom_slider.maximum(),
self.zoom_factor - 1)
self.__update_font_scale()
def __zoom_reset(self):
self.zoom_factor = 0
self.__update_font_scale()
def __layout_main_graphics(self, width=-1):
if width < 0:
# Preserve current width.
width = self._main_graphics.size().width()
preferred = self._main_graphics.effectiveSizeHint(Qt.PreferredSize,
constraint=QSizeF(
width, -1))
self._main_graphics.resize(QSizeF(width, preferred.height()))
mw = self._main_graphics.minimumWidth() + 4
self.view.setMinimumWidth(mw + self.view.verticalScrollBar().width())
def __update_font_scale(self):
font = self.scene.font()
factor = (1.25**self.zoom_factor)
font = qfont_scaled(font, factor)
self._main_graphics.setFont(font)
def send_report(self):
annot = self.label_cb.currentText()
if isinstance(self.annotation, str):
annot = annot.lower()
if self.selection_method == 0:
sel = "manual"
elif self.selection_method == 1:
sel = "at {:.1f} of height".format(self.cut_ratio)
else:
sel = "top {} clusters".format(self.top_n)
self.report_items((
("Linkage", LINKAGE[self.linkage].lower()),
("Annotation", annot),
("Prunning", self.pruning != 0
and "{} levels".format(self.max_depth)),
("Selection", sel),
))
self.report_plot()