class OWRadviz(widget.OWWidget):
name = "Radviz"
description = "Radviz"
icon = "icons/Radviz.svg"
priority = 240
class Inputs:
data = Input("Data", Table, default=True)
data_subset = Input("Data Subset", Table)
class Outputs:
selected_data = Output("Selected Data", Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
components = Output("Components", Table)
settings_version = 1
settingsHandler = settings.DomainContextHandler()
variable_state = settings.ContextSetting({})
auto_commit = settings.Setting(True)
graph = settings.SettingProvider(OWRadvizGraph)
vizrank = settings.SettingProvider(RadvizVizRank)
jitter_sizes = [0, 0.1, 0.5, 1.0, 2.0]
ReplotRequest = QEvent.registerEventType()
graph_name = "graph.plot_widget.plotItem"
class Information(widget.OWWidget.Information):
sql_sampled_data = widget.Msg("Data has been sampled")
class Warning(widget.OWWidget.Warning):
no_features = widget.Msg("At least 2 features have to be chosen")
class Error(widget.OWWidget.Error):
sparse_data = widget.Msg("Sparse data is not supported")
no_features = widget.Msg("At least 3 numeric or categorical variables are required")
no_instances = widget.Msg("At least 2 data instances are required")
def __init__(self):
super().__init__()
self.data = None
self.subset_data = None
self._subset_mask = None
self._selection = None # np.array
self.__replot_requested = False
self._new_plotdata()
self.variable_x = ContinuousVariable("radviz-x")
self.variable_y = ContinuousVariable("radviz-y")
box = gui.vBox(self.mainArea, True, margin=0)
self.graph = OWRadvizGraph(self, box, "Plot", view_box=RadvizInteractiveViewBox)
self.graph.hide_axes()
box.layout().addWidget(self.graph.plot_widget)
plot = self.graph.plot_widget
SIZE_POLICY = (QSizePolicy.Minimum, QSizePolicy.Maximum)
self.variables_selection = VariablesSelection()
self.model_selected = VariableListModel(enable_dnd=True)
self.model_other = VariableListModel(enable_dnd=True)
self.variables_selection(self, self.model_selected, self.model_other)
self.vizrank, self.btn_vizrank = RadvizVizRank.add_vizrank(
self.controlArea, self, "Suggest features", self.vizrank_set_attrs)
self.btn_vizrank.setSizePolicy(*SIZE_POLICY)
self.variables_selection.add_remove.layout().addWidget(self.btn_vizrank)
self.viewbox = plot.getViewBox()
self.replot = None
g = self.graph.gui
pp_box = g.point_properties_box(self.controlArea)
pp_box.setSizePolicy(*SIZE_POLICY)
self.models = g.points_models
box = gui.vBox(self.controlArea, "Plot Properties")
box.setSizePolicy(*SIZE_POLICY)
g.add_widget(g.JitterSizeSlider, box)
g.add_widgets([g.ShowLegend, g.ClassDensity, g.LabelOnlySelected], box)
zoom_select = self.graph.box_zoom_select(self.controlArea)
zoom_select.setSizePolicy(*SIZE_POLICY)
self.icons = gui.attributeIconDict
p = self.graph.plot_widget.palette()
self.graph.set_palette(p)
gui.auto_commit(self.controlArea, self, "auto_commit", "Send Selection",
auto_label="Send Automatically")
self.graph.zoom_actions(self)
self._circle = QGraphicsEllipseItem()
self._circle.setRect(QRectF(-1., -1., 2., 2.))
self._circle.setPen(pg.mkPen(QColor(0, 0, 0), width=2))
def resizeEvent(self, event):
self._update_points_labels()
def keyPressEvent(self, event):
super().keyPressEvent(event)
self.graph.update_tooltip(event.modifiers())
def keyReleaseEvent(self, event):
super().keyReleaseEvent(event)
self.graph.update_tooltip(event.modifiers())
def vizrank_set_attrs(self, attrs):
if not attrs:
return
self.variables_selection.display_none()
self.model_selected[:] = attrs[:]
self.model_other[:] = [v for v in self.model_other if v not in attrs]
def _new_plotdata(self):
self.plotdata = namespace(
valid_mask=None,
embedding_coords=None,
points=None,
arcarrows=[],
point_labels=[],
rand=None,
data=None,
)
def update_colors(self):
self._vizrank_color_change()
self.cb_class_density.setEnabled(self.graph.can_draw_density())
def sizeHint(self):
return QSize(800, 500)
def clear(self):
"""
Clear/reset the widget state
"""
self.data = None
self.model_selected.clear()
self.model_other.clear()
self._clear_plot()
def _clear_plot(self):
self._new_plotdata()
self.graph.plot_widget.clear()
def invalidate_plot(self):
"""
Schedule a delayed replot.
"""
if not self.__replot_requested:
self.__replot_requested = True
QApplication.postEvent(self, QEvent(self.ReplotRequest), Qt.LowEventPriority - 10)
def init_attr_values(self):
self.graph.set_domain(self.data)
def _vizrank_color_change(self):
attr_color = self.graph.attr_color
is_enabled = self.data is not None and not self.data.is_sparse() and \
(len(self.model_other) + len(self.model_selected)) > 3 and len(self.data) > 1
self.btn_vizrank.setEnabled(
is_enabled and attr_color is not None
and not np.isnan(self.data.get_column_view(attr_color)[0].astype(float)).all())
self.vizrank.initialize()
@Inputs.data
def set_data(self, data):
"""
Set the input dataset and check if data is valid.
Args:
data (Orange.data.table): data instances
"""
def sql(data):
self.Information.sql_sampled_data.clear()
if isinstance(data, SqlTable):
if data.approx_len() < 4000:
data = Table(data)
else:
self.Information.sql_sampled_data()
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(2000, partial=True)
data = Table(data_sample)
return data
def settings(data):
# get the default encoded state, replacing the position with Inf
state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
state = {key: (source_ind, np.inf) for key, (source_ind, _) in state.items()}
self.openContext(data.domain)
selected_keys = [key
for key, (sind, _) in self.variable_state.items()
if sind == 0]
if set(selected_keys).issubset(set(state.keys())):
pass
# update the defaults state (the encoded state must contain
# all variables in the input domain)
state.update(self.variable_state)
# ... and restore it with saved positions taking precedence over
# the defaults
selected, other = VariablesSelection.decode_var_state(
state, [list(self.model_selected), list(self.model_other)])
return selected, other
def is_sparse(data):
if data.is_sparse():
self.Error.sparse_data()
data = None
return data
def are_features(data):
domain = data.domain
vars = [var for var in chain(domain.class_vars, domain.metas, domain.attributes)
if var.is_primitive()]
if len(vars) < 3:
self.Error.no_features()
data = None
return data
def are_instances(data):
if len(data) < 2:
self.Error.no_instances()
data = None
return data
self.clear_messages()
self.btn_vizrank.setEnabled(False)
self.closeContext()
self.clear()
self.information()
self.Error.clear()
for f in [sql, is_sparse, are_features, are_instances]:
if data is None:
break
data = f(data)
if data is not None:
self.data = data
self.init_attr_values()
domain = data.domain
vars = [v for v in chain(domain.metas, domain.attributes)
if v.is_primitive()]
self.model_selected[:] = vars[:5]
self.model_other[:] = vars[5:] + list(domain.class_vars)
self.model_selected[:], self.model_other[:] = settings(data)
self._selection = np.zeros(len(data), dtype=np.uint8)
self.invalidate_plot()
else:
self.data = None
@Inputs.data_subset
def set_subset_data(self, subset):
"""
Set the supplementary input subset dataset.
Args:
subset (Orange.data.table): subset of data instances
"""
self.subset_data = subset
self._subset_mask = None
self.controls.graph.alpha_value.setEnabled(subset is None)
def handleNewSignals(self):
if self.data is not None:
self._clear_plot()
if self.subset_data is not None and self._subset_mask is None:
dataids = self.data.ids.ravel()
subsetids = np.unique(self.subset_data.ids)
self._subset_mask = np.in1d(
dataids, subsetids, assume_unique=True)
self.setup_plot(reset_view=True)
self.cb_class_density.setEnabled(self.graph.can_draw_density())
else:
self.init_attr_values()
self.graph.new_data(None)
self._vizrank_color_change()
self.commit()
def customEvent(self, event):
if event.type() == OWRadviz.ReplotRequest:
self.__replot_requested = False
self._clear_plot()
self.setup_plot(reset_view=True)
else:
super().customEvent(event)
def closeContext(self):
self.variable_state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
super().closeContext()
def prepare_radviz_data(self, variables):
ec, points, valid_mask = radviz(self.data, variables, self.plotdata.points)
self.plotdata.embedding_coords = ec
self.plotdata.points = points
self.plotdata.valid_mask = valid_mask
def setup_plot(self, reset_view=True):
if self.data is None:
return
self.graph.jitter_continuous = True
self.__replot_requested = False
variables = list(self.model_selected)
if len(variables) < 2:
self.Warning.no_features()
self.graph.new_data(None)
return
self.Warning.clear()
self.prepare_radviz_data(variables)
if self.plotdata.embedding_coords is None:
return
domain = self.data.domain
new_metas = domain.metas + (self.variable_x, self.variable_y)
domain = Domain(attributes=domain.attributes,
class_vars=domain.class_vars,
metas=new_metas)
mask = self.plotdata.valid_mask
array = np.zeros((len(self.data), 2), dtype=np.float)
array[mask] = self.plotdata.embedding_coords
data = self.data.transform(domain)
data[:, self.variable_x] = array[:, 0].reshape(-1, 1)
data[:, self.variable_y] = array[:, 1].reshape(-1, 1)
subset_data = data[self._subset_mask & mask]\
if self._subset_mask is not None and len(self._subset_mask) else None
self.plotdata.data = data
self.graph.new_data(data[mask], subset_data)
if self._selection is not None:
self.graph.selection = self._selection[self.plotdata.valid_mask]
self.graph.update_data(self.variable_x, self.variable_y, reset_view=reset_view)
self.graph.plot_widget.addItem(self._circle)
self.graph.scatterplot_points = ScatterPlotItem(
x=self.plotdata.points[:, 0],
y=self.plotdata.points[:, 1]
)
self._update_points_labels()
self.graph.plot_widget.addItem(self.graph.scatterplot_points)
def randomize_indices(self):
ec = self.plotdata.embedding_coords
self.plotdata.rand = np.random.choice(len(ec), MAX_POINTS, replace=False) \
if len(ec) > MAX_POINTS else None
def manual_move(self):
self.__replot_requested = False
if self.plotdata.rand is not None:
rand = self.plotdata.rand
valid_mask = self.plotdata.valid_mask
data = self.data[valid_mask]
selection = self._selection[valid_mask]
selection = selection[rand]
ec, _, valid_mask = radviz(data, list(self.model_selected), self.plotdata.points)
assert sum(valid_mask) == len(data)
data = data[rand]
ec = ec[rand]
data_x = data.X
data_y = data.Y
data_metas = data.metas
else:
self.prepare_radviz_data(list(self.model_selected))
ec = self.plotdata.embedding_coords
valid_mask = self.plotdata.valid_mask
data_x = self.data.X[valid_mask]
data_y = self.data.Y[valid_mask]
data_metas = self.data.metas[valid_mask]
selection = self._selection[valid_mask]
attributes = (self.variable_x, self.variable_y) + self.data.domain.attributes
domain = Domain(attributes=attributes,
class_vars=self.data.domain.class_vars,
metas=self.data.domain.metas)
data = Table.from_numpy(domain, X=np.hstack((ec, data_x)), Y=data_y, metas=data_metas)
self.graph.new_data(data, None)
self.graph.selection = selection
self.graph.update_data(self.variable_x, self.variable_y, reset_view=True)
self.graph.plot_widget.addItem(self._circle)
self.graph.scatterplot_points = ScatterPlotItem(
x=self.plotdata.points[:, 0], y=self.plotdata.points[:, 1])
self._update_points_labels()
self.graph.plot_widget.addItem(self.graph.scatterplot_points)
def _update_points_labels(self):
if self.plotdata.points is None:
return
for point_label in self.plotdata.point_labels:
self.graph.plot_widget.removeItem(point_label)
self.plotdata.point_labels = []
sx, sy = self.graph.view_box.viewPixelSize()
for row in self.plotdata.points:
ti = TextItem()
metrics = QFontMetrics(ti.textItem.font())
text_width = ((RANGE.width())/2. - np.abs(row[0])) / sx
name = row[2].name
ti.setText(name)
ti.setTextWidth(text_width)
ti.setColor(QColor(0, 0, 0))
br = ti.boundingRect()
width = metrics.width(name) if metrics.width(name) < br.width() else br.width()
width = sx * (width + 5)
height = sy * br.height()
ti.setPos(row[0] - (row[0] < 0) * width, row[1] + (row[1] > 0) * height)
self.plotdata.point_labels.append(ti)
self.graph.plot_widget.addItem(ti)
def _update_jitter(self):
self.invalidate_plot()
def reset_graph_data(self, *_):
if self.data is not None:
self.graph.rescale_data()
self._update_graph()
def _update_graph(self, reset_view=True, **_):
self.graph.zoomStack = []
if self.graph.data is None:
return
self.graph.update_data(self.variable_x, self.variable_y, reset_view=reset_view)
def update_density(self):
self._update_graph(reset_view=True)
def selection_changed(self):
if self.graph.selection is not None:
self._selection[self.plotdata.valid_mask] = self.graph.selection
self.commit()
def prepare_data(self):
pass
def commit(self):
selected = annotated = components = None
graph = self.graph
if self.plotdata.data is not None:
name = self.data.name
data = self.plotdata.data
mask = self.plotdata.valid_mask.astype(int)
mask[mask == 1] = graph.selection if graph.selection is not None \
else [False * len(mask)]
selection = np.array([], dtype=np.uint8) if mask is None else np.flatnonzero(mask)
if len(selection):
selected = data[selection]
selected.name = name + ": selected"
selected.attributes = self.data.attributes
if graph.selection is not None and np.max(graph.selection) > 1:
annotated = create_groups_table(data, mask)
else:
annotated = create_annotated_table(data, selection)
annotated.attributes = self.data.attributes
annotated.name = name + ": annotated"
comp_domain = Domain(
self.plotdata.points[:, 2],
metas=[StringVariable(name='component')])
metas = np.array([["RX"], ["RY"], ["angle"]])
angle = np.arctan2(np.array(self.plotdata.points[:, 1].T, dtype=float),
np.array(self.plotdata.points[:, 0].T, dtype=float))
components = Table.from_numpy(
comp_domain,
X=np.row_stack((self.plotdata.points[:, :2].T, angle)),
metas=metas)
components.name = name + ": components"
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(annotated)
self.Outputs.components.send(components)
def send_report(self):
if self.data is None:
return
def name(var):
return var and var.name
caption = report.render_items_vert((
("Color", name(self.graph.attr_color)),
("Label", name(self.graph.attr_label)),
("Shape", name(self.graph.attr_shape)),
("Size", name(self.graph.attr_size)),
("Jittering", self.graph.jitter_size != 0 and "{} %".format(self.graph.jitter_size))))
self.report_plot()
if caption:
self.report_caption(caption)
class OWLinearProjection(widget.OWWidget):
name = "Linear Projection"
description = "A multi-axis projection of data onto " \
"a two-dimensional plane."
icon = "icons/LinearProjection.svg"
priority = 240
keywords = []
selection_indices = settings.Setting(None, schema_only=True)
class Inputs:
data = Input("Data", Table, default=True)
data_subset = Input("Data Subset", Table)
projection = Input("Projection", Table)
class Outputs:
selected_data = Output("Selected Data", Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
components = Output("Components", Table)
Placement = Enum("Placement",
dict(Circular=0, LDA=1, PCA=2, Projection=3),
type=int,
qualname="OWLinearProjection.Placement")
Component_name = {
Placement.Circular: "C",
Placement.LDA: "LD",
Placement.PCA: "PC"
}
Variable_name = {
Placement.Circular: "circular",
Placement.LDA: "lda",
Placement.PCA: "pca",
Placement.Projection: "projection"
}
jitter_sizes = [0, 0.1, 0.5, 1.0, 2.0]
settings_version = 3
settingsHandler = settings.DomainContextHandler()
variable_state = settings.ContextSetting({})
placement = settings.Setting(Placement.Circular)
radius = settings.Setting(0)
auto_commit = settings.Setting(True)
resolution = 256
graph = settings.SettingProvider(OWLinProjGraph)
ReplotRequest = QEvent.registerEventType()
vizrank = settings.SettingProvider(LinearProjectionVizRank)
graph_name = "graph.plot_widget.plotItem"
class Warning(widget.OWWidget.Warning):
no_cont_features = widget.Msg("Plotting requires numeric features")
not_enough_components = widget.Msg(
"Input projection has less than 2 components")
trivial_components = widget.Msg(
"All components of the PCA are trivial (explain 0 variance). "
"Input data is constant (or near constant).")
class Error(widget.OWWidget.Error):
proj_and_domain_match = widget.Msg(
"Projection and Data domains do not match")
no_valid_data = widget.Msg("No projection due to invalid data")
def __init__(self):
super().__init__()
self.data = None
self.projection = None
self.subset_data = None
self._subset_mask = None
self._selection = None
self.__replot_requested = False
self.n_cont_var = 0
#: Remember the saved state to restore
self.__pending_selection_restore = self.selection_indices
self.selection_indices = None
self.variable_x = None
self.variable_y = None
box = gui.vBox(self.mainArea, True, margin=0)
self.graph = OWLinProjGraph(self,
box,
"Plot",
view_box=LinProjInteractiveViewBox)
box.layout().addWidget(self.graph.plot_widget)
plot = self.graph.plot_widget
SIZE_POLICY = (QSizePolicy.Minimum, QSizePolicy.Maximum)
self.variables_selection = VariablesSelection()
self.model_selected = VariableListModel(enable_dnd=True)
self.model_other = VariableListModel(enable_dnd=True)
self.variables_selection(self, self.model_selected, self.model_other)
self.vizrank, self.btn_vizrank = LinearProjectionVizRank.add_vizrank(
self.controlArea, self, "Suggest Features", self._vizrank)
self.variables_selection.add_remove.layout().addWidget(
self.btn_vizrank)
box = gui.widgetBox(self.controlArea,
"Placement",
sizePolicy=SIZE_POLICY)
self.radio_placement = gui.radioButtonsInBox(
box,
self,
"placement",
btnLabels=[
"Circular Placement", "Linear Discriminant Analysis",
"Principal Component Analysis", "Use input projection"
],
callback=self._change_placement)
self.viewbox = plot.getViewBox()
self.replot = None
g = self.graph.gui
box = g.point_properties_box(self.controlArea)
self.models = g.points_models
g.add_widget(g.JitterSizeSlider, box)
box.setSizePolicy(*SIZE_POLICY)
box = gui.widgetBox(self.controlArea,
"Hide axes",
sizePolicy=SIZE_POLICY)
self.rslider = gui.hSlider(box,
self,
"radius",
minValue=0,
maxValue=100,
step=5,
label="Radius",
createLabel=False,
ticks=True,
callback=self.update_radius)
self.rslider.setTickInterval(0)
self.rslider.setPageStep(10)
box = gui.vBox(self.controlArea, "Plot Properties")
box.setSizePolicy(*SIZE_POLICY)
g.add_widgets([
g.ShowLegend, g.ToolTipShowsAll, g.ClassDensity,
g.LabelOnlySelected
], box)
box = self.graph.box_zoom_select(self.controlArea)
box.setSizePolicy(*SIZE_POLICY)
self.icons = gui.attributeIconDict
p = self.graph.plot_widget.palette()
self.graph.set_palette(p)
gui.auto_commit(self.controlArea,
self,
"auto_commit",
"Send Selection",
auto_label="Send Automatically")
self.graph.zoom_actions(self)
self._new_plotdata()
self._change_placement()
self.graph.jitter_continuous = True
def reset_graph_data(self):
if self.data is not None:
self.graph.rescale_data()
self._update_graph(reset_view=True)
def keyPressEvent(self, event):
super().keyPressEvent(event)
self.graph.update_tooltip(event.modifiers())
def keyReleaseEvent(self, event):
super().keyReleaseEvent(event)
self.graph.update_tooltip(event.modifiers())
def _vizrank(self, attrs):
self.variables_selection.display_none()
self.model_selected[:] = attrs[:]
self.model_other[:] = [
var for var in self.model_other if var not in attrs
]
def _change_placement(self):
placement = self.placement
p_Circular = self.Placement.Circular
p_LDA = self.Placement.LDA
self.variables_selection.set_enabled(placement in [p_Circular, p_LDA])
self._vizrank_color_change()
self.rslider.setEnabled(placement != p_Circular)
self._setup_plot()
self.commit()
def _get_min_radius(self):
return self.radius * np.max(np.linalg.norm(self.plotdata.axes,
axis=1)) / 100 + 1e-5
def update_radius(self):
# Update the anchor/axes visibility
pd = self.plotdata
assert pd is not None
if pd.hidecircle is None:
return
min_radius = self._get_min_radius()
for anchor, item in zip(pd.axes, pd.axisitems):
item.setVisible(np.linalg.norm(anchor) > min_radius)
pd.hidecircle.setRect(
QRectF(-min_radius, -min_radius, 2 * min_radius, 2 * min_radius))
def _new_plotdata(self):
self.plotdata = namespace(valid_mask=None,
embedding_coords=None,
axisitems=[],
axes=[],
variables=[],
data=None,
hidecircle=None)
def _anchor_circle(self, variables):
# minimum visible anchor radius (radius)
min_radius = self._get_min_radius()
axisitems = []
for anchor, var in zip(self.plotdata.axes, variables[:]):
axitem = AnchorItem(
line=QLineF(0, 0, *anchor),
text=var.name,
)
axitem.setVisible(np.linalg.norm(anchor) > min_radius)
axitem.setPen(pg.mkPen((100, 100, 100)))
axitem.setArrowVisible(True)
self.viewbox.addItem(axitem)
axisitems.append(axitem)
self.plotdata.axisitems = axisitems
if self.placement == self.Placement.Circular:
return
hidecircle = QGraphicsEllipseItem()
hidecircle.setRect(
QRectF(-min_radius, -min_radius, 2 * min_radius, 2 * min_radius))
_pen = QPen(Qt.lightGray, 1)
_pen.setCosmetic(True)
hidecircle.setPen(_pen)
self.viewbox.addItem(hidecircle)
self.plotdata.hidecircle = hidecircle
def update_colors(self):
self._vizrank_color_change()
def clear(self):
# Clear/reset the widget state
self.data = None
self.model_selected.clear()
self.model_other.clear()
self._clear_plot()
self.selection_indices = None
def _clear_plot(self):
self.Warning.trivial_components.clear()
for axisitem in self.plotdata.axisitems:
self.viewbox.removeItem(axisitem)
if self.plotdata.hidecircle:
self.viewbox.removeItem(self.plotdata.hidecircle)
self._new_plotdata()
self.graph.hide_axes()
def invalidate_plot(self):
"""
Schedule a delayed replot.
"""
if not self.__replot_requested:
self.__replot_requested = True
QApplication.postEvent(self, QEvent(self.ReplotRequest),
Qt.LowEventPriority - 10)
def init_attr_values(self):
self.graph.set_domain(self.data)
def _vizrank_color_change(self):
is_enabled = False
if self.data is None:
self.btn_vizrank.setToolTip("There is no data.")
return
vars = [
v
for v in chain(self.data.domain.variables, self.data.domain.metas)
if v.is_primitive and v is not self.graph.attr_color
]
self.n_cont_var = len(vars)
if self.placement not in [self.Placement.Circular, self.Placement.LDA]:
msg = "Suggest Features works only for Circular and " \
"Linear Discriminant Analysis Projection"
elif self.graph.attr_color is None:
msg = "Color variable has to be selected"
elif self.graph.attr_color.is_continuous and self.placement == self.Placement.LDA:
msg = "Suggest Features does not work for Linear Discriminant Analysis Projection " \
"when continuous color variable is selected."
elif len(vars) < 3:
msg = "Not enough available continuous variables"
else:
is_enabled = True
msg = ""
self.btn_vizrank.setToolTip(msg)
self.btn_vizrank.setEnabled(is_enabled)
self.vizrank.stop_and_reset(is_enabled)
@Inputs.projection
def set_projection(self, projection):
self.Warning.not_enough_components.clear()
if projection and len(projection) < 2:
self.Warning.not_enough_components()
projection = None
if projection is not None:
self.placement = self.Placement.Projection
self.projection = projection
@Inputs.data
def set_data(self, data):
"""
Set the input dataset.
Args:
data (Orange.data.table): data instances
"""
def sql(data):
if isinstance(data, SqlTable):
if data.approx_len() < 4000:
data = Table(data)
else:
self.information("Data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(2000, partial=True)
data = Table(data_sample)
return data
def settings(data):
# get the default encoded state, replacing the position with Inf
state = VariablesSelection.encode_var_state(
[list(self.model_selected),
list(self.model_other)])
state = {
key: (source_ind, np.inf)
for key, (source_ind, _) in state.items()
}
self.openContext(data.domain)
selected_keys = [
key for key, (sind, _) in self.variable_state.items()
if sind == 0
]
if set(selected_keys).issubset(set(state.keys())):
pass
if self.__pending_selection_restore is not None:
self._selection = np.array(self.__pending_selection_restore,
dtype=int)
self.__pending_selection_restore = None
# update the defaults state (the encoded state must contain
# all variables in the input domain)
state.update(self.variable_state)
# ... and restore it with saved positions taking precedence over
# the defaults
selected, other = VariablesSelection.decode_var_state(
state, [list(self.model_selected),
list(self.model_other)])
return selected, other
self.closeContext()
self.clear()
self.Warning.no_cont_features.clear()
self.information()
data = sql(data)
if data is not None:
domain = data.domain
vars = [
var for var in chain(domain.variables, domain.metas)
if var.is_continuous
]
if not len(vars):
self.Warning.no_cont_features()
data = None
self.data = data
self.init_attr_values()
if data is not None and len(data):
self._initialize(data)
self.model_selected[:], self.model_other[:] = settings(data)
self.vizrank.stop_and_reset()
self.vizrank.attrs = self.data.domain.attributes if self.data is not None else []
def _check_possible_opt(self):
def set_enabled(is_enabled):
for btn in self.radio_placement.buttons:
btn.setEnabled(is_enabled)
self.variables_selection.set_enabled(is_enabled)
p_Circular = self.Placement.Circular
p_LDA = self.Placement.LDA
p_Input = self.Placement.Projection
if self.data:
set_enabled(True)
domain = self.data.domain
if not domain.has_discrete_class or len(
domain.class_var.values) < 2:
self.radio_placement.buttons[p_LDA].setEnabled(False)
if self.placement == p_LDA:
self.placement = p_Circular
if not self.projection:
self.radio_placement.buttons[p_Input].setEnabled(False)
if self.placement == p_Input:
self.placement = p_Circular
self._setup_plot()
else:
self.graph.new_data(None)
self.rslider.setEnabled(False)
set_enabled(False)
self.commit()
@Inputs.data_subset
def set_subset_data(self, subset):
"""
Set the supplementary input subset dataset.
Args:
subset (Orange.data.table): subset of data instances
"""
self.subset_data = subset
self._subset_mask = None
self.controls.graph.alpha_value.setEnabled(subset is None)
def handleNewSignals(self):
if self.data is not None and self.subset_data is not None:
# Update the plot's highlight items
dataids = self.data.ids.ravel()
subsetids = np.unique(self.subset_data.ids)
self._subset_mask = np.in1d(dataids, subsetids, assume_unique=True)
self._check_possible_opt()
self._change_placement()
self.commit()
def customEvent(self, event):
if event.type() == OWLinearProjection.ReplotRequest:
self.__replot_requested = False
self._setup_plot()
self.commit()
else:
super().customEvent(event)
def closeContext(self):
self.variable_state = VariablesSelection.encode_var_state(
[list(self.model_selected),
list(self.model_other)])
super().closeContext()
def _initialize(self, data):
# Initialize the GUI controls from data's domain.
vars = [
v for v in chain(data.domain.metas, data.domain.attributes)
if v.is_continuous
]
self.model_other[:] = vars[3:]
self.model_selected[:] = vars[:3]
def prepare_plot_data(self, variables):
def projection(variables):
if set(self.projection.domain.attributes).issuperset(variables):
axes = self.projection[:2, variables].X
elif set(f.name
for f in self.projection.domain.attributes).issuperset(
f.name for f in variables):
axes = self.projection[:2, [f.name for f in variables]].X
else:
self.Error.proj_and_domain_match()
axes = None
return axes
def get_axes(variables):
self.Error.proj_and_domain_match.clear()
axes = None
if self.placement == self.Placement.Circular:
axes = LinProj.defaultaxes(len(variables))
elif self.placement == self.Placement.LDA:
axes = self._get_lda(self.data, variables)
elif self.placement == self.Placement.Projection and self.projection:
axes = projection(variables)
return axes
coords = [
column_data(self.data, var, dtype=float) for var in variables
]
coords = np.vstack(coords)
p, N = coords.shape
assert N == len(self.data), p == len(variables)
axes = get_axes(variables)
if axes is None:
return None, None, None
assert axes.shape == (2, p)
valid_mask = ~np.isnan(coords).any(axis=0)
coords = coords[:, valid_mask]
X, Y = np.dot(axes, coords)
if X.size and Y.size:
X = normalized(X)
Y = normalized(Y)
return valid_mask, np.stack((X, Y), axis=1), axes.T
def _setup_plot(self):
self._clear_plot()
if self.data is None:
return
self.__replot_requested = False
names = get_unique_names([
v.name
for v in chain(self.data.domain.variables, self.data.domain.metas)
], [
"{}-x".format(self.Variable_name[self.placement]), "{}-y".format(
self.Variable_name[self.placement])
])
self.variable_x = ContinuousVariable(names[0])
self.variable_y = ContinuousVariable(names[1])
if self.placement in [self.Placement.Circular, self.Placement.LDA]:
variables = list(self.model_selected)
elif self.placement == self.Placement.Projection:
variables = self.model_selected[:] + self.model_other[:]
elif self.placement == self.Placement.PCA:
variables = [
var for var in self.data.domain.attributes if var.is_continuous
]
if not variables:
self.graph.new_data(None)
return
if self.placement == self.Placement.PCA:
valid_mask, ec, axes = self._get_pca()
variables = self._pca.orig_domain.attributes
else:
valid_mask, ec, axes = self.prepare_plot_data(variables)
self.plotdata.variables = variables
self.plotdata.valid_mask = valid_mask
self.plotdata.embedding_coords = ec
self.plotdata.axes = axes
if any(e is None for e in (valid_mask, ec, axes)):
return
if not sum(valid_mask):
self.Error.no_valid_data()
self.graph.new_data(None, None)
return
self.Error.no_valid_data.clear()
self._anchor_circle(variables=variables)
self._plot()
def _plot(self):
domain = self.data.domain
new_metas = domain.metas + (self.variable_x, self.variable_y)
domain = Domain(attributes=domain.attributes,
class_vars=domain.class_vars,
metas=new_metas)
valid_mask = self.plotdata.valid_mask
array = np.zeros((len(self.data), 2), dtype=np.float)
array[valid_mask] = self.plotdata.embedding_coords
self.plotdata.data = data = self.data.transform(domain)
data[:, self.variable_x] = array[:, 0].reshape(-1, 1)
data[:, self.variable_y] = array[:, 1].reshape(-1, 1)
subset_data = data[self._subset_mask & valid_mask]\
if self._subset_mask is not None and len(self._subset_mask) else None
self.plotdata.data = data
self.graph.new_data(data[valid_mask], subset_data)
if self._selection is not None:
self.graph.selection = self._selection[valid_mask]
self.graph.update_data(self.variable_x, self.variable_y, False)
def _get_lda(self, data, variables):
domain = Domain(attributes=variables,
class_vars=data.domain.class_vars)
data = data.transform(domain)
lda = LinearDiscriminantAnalysis(solver='eigen', n_components=2)
lda.fit(data.X, data.Y)
scalings = lda.scalings_[:, :2].T
if scalings.shape == (1, 1):
scalings = np.array([[1.], [0.]])
return scalings
def _get_pca(self):
data = self.data
MAX_COMPONENTS = 2
ncomponents = 2
DECOMPOSITIONS = [PCA] # TruncatedSVD
cls = DECOMPOSITIONS[0]
pca_projector = cls(n_components=MAX_COMPONENTS)
pca_projector.component = ncomponents
pca_projector.preprocessors = cls.preprocessors + [Normalize()]
pca = pca_projector(data)
variance_ratio = pca.explained_variance_ratio_
cumulative = np.cumsum(variance_ratio)
self._pca = pca
if not np.isfinite(cumulative[-1]):
self.Warning.trivial_components()
coords = pca(data).X
valid_mask = ~np.isnan(coords).any(axis=1)
# scale axes
max_radius = np.min(
[np.abs(np.min(coords, axis=0)),
np.max(coords, axis=0)])
axes = pca.components_.T.copy()
axes *= max_radius / np.max(np.linalg.norm(axes, axis=1))
return valid_mask, coords, axes
def _update_graph(self, reset_view=False):
self.graph.zoomStack = []
if self.graph.data is None:
return
self.graph.update_data(self.variable_x, self.variable_y, reset_view)
def update_density(self):
self._update_graph(reset_view=False)
def selection_changed(self):
if self.graph.selection is not None:
self._selection = np.zeros(len(self.data), dtype=np.uint8)
self._selection[self.plotdata.valid_mask] = self.graph.selection
self.selection_indices = self._selection.tolist()
else:
self._selection = self.selection_indices = None
self.commit()
def prepare_data(self):
pass
def commit(self):
def prepare_components():
if self.placement in [self.Placement.Circular, self.Placement.LDA]:
attrs = [a for a in self.model_selected[:]]
axes = self.plotdata.axes
elif self.placement == self.Placement.PCA:
axes = self._pca.components_.T
attrs = [a for a in self._pca.orig_domain.attributes]
if self.placement != self.Placement.Projection:
domain = Domain([
ContinuousVariable(a.name, compute_value=lambda _: None)
for a in attrs
],
metas=[StringVariable(name='component')])
metas = np.array([[
"{}{}".format(self.Component_name[self.placement], i + 1)
for i in range(axes.shape[1])
]],
dtype=object).T
components = Table(domain, axes.T, metas=metas)
components.name = 'components'
else:
components = self.projection
return components
selected = annotated = components = None
if self.data is not None and self.plotdata.data is not None:
components = prepare_components()
graph = self.graph
mask = self.plotdata.valid_mask.astype(int)
mask[mask == 1] = graph.selection if graph.selection is not None \
else [False * len(mask)]
selection = np.array(
[], dtype=np.uint8) if mask is None else np.flatnonzero(mask)
name = self.data.name
data = self.plotdata.data
if len(selection):
selected = data[selection]
selected.name = name + ": selected"
selected.attributes = self.data.attributes
if graph.selection is not None and np.max(graph.selection) > 1:
annotated = create_groups_table(data, mask)
else:
annotated = create_annotated_table(data, selection)
annotated.attributes = self.data.attributes
annotated.name = name + ": annotated"
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(annotated)
self.Outputs.components.send(components)
def send_report(self):
if self.data is None:
return
def name(var):
return var and var.name
def projection_name():
name = ("Circular Placement", "Linear Discriminant Analysis",
"Principal Component Analysis", "Input projection")
return name[self.placement]
caption = report.render_items_vert(
(("Projection", projection_name()), ("Color",
name(self.graph.attr_color)),
("Label", name(self.graph.attr_label)),
("Shape", name(self.graph.attr_shape)),
("Size", name(self.graph.attr_size)),
("Jittering", self.graph.jitter_size != 0
and "{} %".format(self.graph.jitter_size))))
self.report_plot()
if caption:
self.report_caption(caption)
@classmethod
def migrate_settings(cls, settings_, version):
if version < 2:
settings_["point_width"] = settings_["point_size"]
if version < 3:
settings_graph = {}
settings_graph["jitter_size"] = settings_["jitter_value"]
settings_graph["point_width"] = settings_["point_width"]
settings_graph["alpha_value"] = settings_["alpha_value"]
settings_graph["class_density"] = settings_["class_density"]
settings_["graph"] = settings_graph
@classmethod
def migrate_context(cls, context, version):
if version < 2:
domain = context.ordered_domain
c_domain = [t for t in context.ordered_domain if t[1] == 2]
d_domain = [t for t in context.ordered_domain if t[1] == 1]
for d, old_val, new_val in ((domain, "color_index", "attr_color"),
(d_domain, "shape_index",
"attr_shape"),
(c_domain, "size_index", "attr_size")):
index = context.values[old_val][0] - 1
context.values[new_val] = (d[index][0], d[index][1] + 100) \
if 0 <= index < len(d) else None
if version < 3:
context.values["graph"] = {
"attr_color": context.values["attr_color"],
"attr_shape": context.values["attr_shape"],
"attr_size": context.values["attr_size"]
}
class OWRadviz(OWProjectionWidget):
name = "Radviz"
description = "Display Radviz projection"
icon = "icons/Radviz.svg"
priority = 241
keywords = ["viz"]
class Inputs:
data = Input("Data", Table, default=True)
data_subset = Input("Data Subset", Table)
class Outputs:
selected_data = Output("Selected Data", Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
components = Output("Components", Table)
settings_version = 2
settingsHandler = settings.DomainContextHandler()
variable_state = settings.ContextSetting({})
auto_commit = settings.Setting(True)
vizrank = settings.SettingProvider(RadvizVizRank)
graph = settings.SettingProvider(OWRadvizGraph)
graph_name = "graph.plot_widget.plotItem"
ReplotRequest = QEvent.registerEventType()
class Information(OWProjectionWidget.Information):
sql_sampled_data = widget.Msg("Data has been sampled")
class Warning(OWProjectionWidget.Warning):
no_features = widget.Msg("At least 2 features have to be chosen")
invalid_embedding = widget.Msg("No projection for selected features")
class Error(OWProjectionWidget.Error):
sparse_data = widget.Msg("Sparse data is not supported")
no_features = widget.Msg(
"At least 3 numeric or categorical variables are required")
no_instances = widget.Msg("At least 2 data instances are required")
def __init__(self):
super().__init__()
self.data = None
self.subset_data = None
self.subset_indices = None
self._embedding_coords = None
self._rand_indices = None
self.__replot_requested = False
self.variable_x = ContinuousVariable("radviz-x")
self.variable_y = ContinuousVariable("radviz-y")
box = gui.vBox(self.mainArea, True, margin=0)
self.graph = OWRadvizGraph(self, box)
box.layout().addWidget(self.graph.plot_widget)
self.variables_selection = VariablesSelection()
self.model_selected = selected = VariableListModel(enable_dnd=True)
self.model_other = other = VariableListModel(enable_dnd=True)
self.variables_selection(self, selected, other, self.controlArea)
self.vizrank, self.btn_vizrank = RadvizVizRank.add_vizrank(
None, self, "Suggest features", self.vizrank_set_attrs)
# Todo: this button introduces some margin at the bottom?!
self.variables_selection.add_remove.layout().addWidget(
self.btn_vizrank)
g = self.graph.gui
g.point_properties_box(self.controlArea)
g.effects_box(self.controlArea)
g.plot_properties_box(self.controlArea)
self.graph.box_zoom_select(self.controlArea)
gui.auto_commit(self.controlArea, self, "auto_commit",
"Send Selection", "Send Automatically")
self.graph.view_box.started.connect(self._randomize_indices)
self.graph.view_box.moved.connect(self._manual_move)
self.graph.view_box.finished.connect(self._finish_manual_move)
def vizrank_set_attrs(self, attrs):
if not attrs:
return
self.variables_selection.display_none()
self.model_selected[:] = attrs[:]
self.model_other[:] = [v for v in self.model_other if v not in attrs]
def update_colors(self):
self._vizrank_color_change()
self.cb_class_density.setEnabled(self.can_draw_density())
def invalidate_plot(self):
"""
Schedule a delayed replot.
"""
if not self.__replot_requested:
self.__replot_requested = True
QApplication.postEvent(self, QEvent(self.ReplotRequest),
Qt.LowEventPriority - 10)
def _vizrank_color_change(self):
is_enabled = self.data is not None and not self.data.is_sparse() and \
len(self.model_other) + len(self.model_selected) > 3 and \
len(self.data[self.valid_data]) > 1 and \
np.all(np.nan_to_num(np.nanstd(self.data.X, 0)) != 0)
self.btn_vizrank.setEnabled(
is_enabled and self.attr_color is not None and not np.isnan(
self.data.get_column_view(
self.attr_color)[0].astype(float)).all())
self.vizrank.initialize()
def clear(self):
self.data = None
self.valid_data = None
self._embedding_coords = None
self._rand_indices = None
self.model_selected.clear()
self.model_other.clear()
self.graph.set_attributes(())
self.graph.set_points(None)
self.graph.update_coordinates()
self.graph.clear()
@Inputs.data
def set_data(self, data):
self.clear_messages()
self.btn_vizrank.setEnabled(False)
self.closeContext()
self.clear()
self.data = data
self._check_data()
self.init_attr_values()
self.openContext(self.data)
if self.data is not None:
self.model_selected[:], self.model_other[:] = self._load_settings()
def _check_data(self):
if self.data is not None:
domain = self.data.domain
if self.data.is_sparse():
self.Error.sparse_data()
self.data = None
elif isinstance(self.data, SqlTable):
if self.data.approx_len() < 4000:
self.data = Table(self.data)
else:
self.Information.sql_sampled_data()
data_sample = self.data.sample_time(1, no_cache=True)
data_sample.download_data(2000, partial=True)
self.data = Table(data_sample)
elif len(self.data) < 2:
self.Error.no_instances()
self.data = None
elif len([
v for v in domain.variables + domain.metas
if v.is_primitive()
]) < 3:
self.Error.no_features()
self.data = None
def _load_settings(self):
domain = self.data.domain
variables = [
v for v in domain.attributes + domain.metas if v.is_primitive()
]
self.model_selected[:] = variables[:5]
self.model_other[:] = variables[5:] + list(domain.class_vars)
state = VariablesSelection.encode_var_state(
[list(self.model_selected),
list(self.model_other)])
state = {key: (ind, np.inf) for key, (ind, _) in state.items()}
state.update(self.variable_state)
return VariablesSelection.decode_var_state(
state, [list(self.model_selected),
list(self.model_other)])
@Inputs.data_subset
def set_subset_data(self, subset):
self.subset_data = subset
self.subset_indices = {e.id for e in subset} \
if subset is not None else {}
self.controls.graph.alpha_value.setEnabled(subset is None)
def handleNewSignals(self):
self.setup_plot()
self._vizrank_color_change()
self.commit()
def get_coordinates_data(self):
ec = self._embedding_coords
if ec is None or np.any(np.isnan(ec)):
return None, None
return ec[:, 0], ec[:, 1]
def get_subset_mask(self):
if self.subset_indices:
return np.array([
ex.id in self.subset_indices
for ex in self.data[self.valid_data]
])
def customEvent(self, event):
if event.type() == OWRadviz.ReplotRequest:
self.__replot_requested = False
self.setup_plot()
else:
super().customEvent(event)
def closeContext(self):
self.variable_state = VariablesSelection.encode_var_state(
[list(self.model_selected),
list(self.model_other)])
super().closeContext()
def setup_plot(self):
if self.data is None:
return
self.__replot_requested = False
self.clear_messages()
if len(self.model_selected) < 2:
self.Warning.no_features()
self.graph.clear()
return
r = radviz(self.data, self.model_selected)
self._embedding_coords = r[0]
self.graph.set_points(r[1])
self.valid_data = r[2]
if self._embedding_coords is None or \
np.any(np.isnan(self._embedding_coords)):
self.Warning.invalid_embedding()
self.graph.reset_graph()
def _randomize_indices(self):
n = len(self._embedding_coords)
if n > MAX_POINTS:
self._rand_indices = np.random.choice(n, MAX_POINTS, replace=False)
self._rand_indices = sorted(self._rand_indices)
def _manual_move(self):
self.__replot_requested = False
res = radviz(self.data, self.model_selected, self.graph.get_points())
self._embedding_coords = res[0]
if self._rand_indices is not None:
# save widget state
selection = self.graph.selection
valid_data = self.valid_data.copy()
data = self.data.copy()
ec = self._embedding_coords.copy()
# plot subset
self.__plot_random_subset(selection)
# restore widget state
self.graph.selection = selection
self.valid_data = valid_data
self.data = data
self._embedding_coords = ec
else:
self.graph.update_coordinates()
def __plot_random_subset(self, selection):
self._embedding_coords = self._embedding_coords[self._rand_indices]
self.data = self.data[self._rand_indices]
self.valid_data = self.valid_data[self._rand_indices]
self.graph.reset_graph()
if selection is not None:
self.graph.selection = selection[self._rand_indices]
self.graph.update_selection_colors()
def _finish_manual_move(self):
if self._rand_indices is not None:
selection = self.graph.selection
self.graph.reset_graph()
if selection is not None:
self.graph.selection = selection
self.graph.select_by_index(self.graph.get_selection())
def selection_changed(self):
self.commit()
def commit(self):
selected = annotated = components = None
if self.data is not None and np.sum(self.valid_data):
name = self.data.name
domain = self.data.domain
metas = domain.metas + (self.variable_x, self.variable_y)
domain = Domain(domain.attributes, domain.class_vars, metas)
embedding_coords = np.zeros((len(self.data), 2), dtype=np.float)
embedding_coords[self.valid_data] = self._embedding_coords
data = self.data.transform(domain)
data[:, self.variable_x] = embedding_coords[:, 0][:, None]
data[:, self.variable_y] = embedding_coords[:, 1][:, None]
selection = self.graph.get_selection()
if len(selection):
selected = data[selection]
selected.name = name + ": selected"
selected.attributes = self.data.attributes
if self.graph.selection is not None and \
np.max(self.graph.selection) > 1:
annotated = create_groups_table(data, self.graph.selection)
else:
annotated = create_annotated_table(data, selection)
annotated.attributes = self.data.attributes
annotated.name = name + ": annotated"
points = self.graph.get_points()
comp_domain = Domain(points[:, 2],
metas=[StringVariable(name='component')])
metas = np.array([["RX"], ["RY"], ["angle"]])
angle = np.arctan2(np.array(points[:, 1].T, dtype=float),
np.array(points[:, 0].T, dtype=float))
components = Table.from_numpy(comp_domain,
X=np.row_stack(
(points[:, :2].T, angle)),
metas=metas)
components.name = name + ": components"
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(annotated)
self.Outputs.components.send(components)
def send_report(self):
if self.data is None:
return
def name(var):
return var and var.name
caption = report.render_items_vert(
(("Color", name(self.attr_color)), ("Label",
name(self.attr_label)),
("Shape", name(self.attr_shape)), ("Size", name(self.attr_size)),
("Jittering", self.graph.jitter_size != 0
and "{} %".format(self.graph.jitter_size))))
self.report_plot()
if caption:
self.report_caption(caption)
@classmethod
def migrate_context(cls, context, version):
if version < 3:
values = context.values
values["attr_color"] = values["graph"]["attr_color"]
values["attr_size"] = values["graph"]["attr_size"]
values["attr_shape"] = values["graph"]["attr_shape"]
values["attr_label"] = values["graph"]["attr_label"]
class OWRadviz(widget.OWWidget):
name = "Radviz"
description = "Radviz"
icon = "icons/Radviz.svg"
priority = 240
class Inputs:
data = Input("Data", Table, default=True)
data_subset = Input("Data Subset", Table)
class Outputs:
selected_data = Output("Selected Data", Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
components = Output("Components", Table)
settings_version = 1
settingsHandler = settings.DomainContextHandler()
variable_state = settings.ContextSetting({})
auto_commit = settings.Setting(True)
graph = settings.SettingProvider(OWRadvizGraph)
vizrank = settings.SettingProvider(RadvizVizRank)
jitter_sizes = [0, 0.1, 0.5, 1.0, 2.0]
ReplotRequest = QEvent.registerEventType()
graph_name = "graph.plot_widget.plotItem"
class Information(widget.OWWidget.Information):
sql_sampled_data = widget.Msg("Data has been sampled")
class Warning(widget.OWWidget.Warning):
no_features = widget.Msg("At least 2 features have to be chosen")
class Error(widget.OWWidget.Error):
sparse_data = widget.Msg("Sparse data is not supported")
no_features = widget.Msg(
"At least 3 numeric or categorical variables are required"
)
no_instances = widget.Msg("At least 2 data instances are required")
def __init__(self):
super().__init__()
self.data = None
self.subset_data = None
self._subset_mask = None
self._selection = None # np.array
self.__replot_requested = False
self._new_plotdata()
self.variable_x = ContinuousVariable("radviz-x")
self.variable_y = ContinuousVariable("radviz-y")
box = gui.vBox(self.mainArea, True, margin=0)
self.graph = OWRadvizGraph(self, box, "Plot", view_box=RadvizInteractiveViewBox)
self.graph.hide_axes()
box.layout().addWidget(self.graph.plot_widget)
plot = self.graph.plot_widget
SIZE_POLICY = (QSizePolicy.Minimum, QSizePolicy.Maximum)
self.variables_selection = VariablesSelection()
self.model_selected = VariableListModel(enable_dnd=True)
self.model_other = VariableListModel(enable_dnd=True)
self.variables_selection(self, self.model_selected, self.model_other)
self.vizrank, self.btn_vizrank = RadvizVizRank.add_vizrank(
self.controlArea, self, "Suggest features", self.vizrank_set_attrs
)
self.btn_vizrank.setSizePolicy(*SIZE_POLICY)
self.variables_selection.add_remove.layout().addWidget(self.btn_vizrank)
self.viewbox = plot.getViewBox()
self.replot = None
g = self.graph.gui
pp_box = g.point_properties_box(self.controlArea)
pp_box.setSizePolicy(*SIZE_POLICY)
self.models = g.points_models
box = gui.vBox(self.controlArea, "Plot Properties")
box.setSizePolicy(*SIZE_POLICY)
g.add_widget(g.JitterSizeSlider, box)
g.add_widgets([g.ShowLegend, g.ClassDensity, g.LabelOnlySelected], box)
zoom_select = self.graph.box_zoom_select(self.controlArea)
zoom_select.setSizePolicy(*SIZE_POLICY)
self.icons = gui.attributeIconDict
p = self.graph.plot_widget.palette()
self.graph.set_palette(p)
gui.auto_commit(
self.controlArea,
self,
"auto_commit",
"Send Selection",
auto_label="Send Automatically",
)
self.graph.zoom_actions(self)
self._circle = QGraphicsEllipseItem()
self._circle.setRect(QRectF(-1.0, -1.0, 2.0, 2.0))
self._circle.setPen(pg.mkPen(QColor(0, 0, 0), width=2))
def resizeEvent(self, event):
self._update_points_labels()
def keyPressEvent(self, event):
super().keyPressEvent(event)
self.graph.update_tooltip(event.modifiers())
def keyReleaseEvent(self, event):
super().keyReleaseEvent(event)
self.graph.update_tooltip(event.modifiers())
def vizrank_set_attrs(self, attrs):
if not attrs:
return
self.variables_selection.display_none()
self.model_selected[:] = attrs[:]
self.model_other[:] = [v for v in self.model_other if v not in attrs]
def _new_plotdata(self):
self.plotdata = namespace(
valid_mask=None,
embedding_coords=None,
points=None,
arcarrows=[],
point_labels=[],
rand=None,
data=None,
)
def update_colors(self):
self._vizrank_color_change()
self.cb_class_density.setEnabled(self.graph.can_draw_density())
def sizeHint(self):
return QSize(800, 500)
def clear(self):
"""
Clear/reset the widget state
"""
self.data = None
self.model_selected.clear()
self.model_other.clear()
self._clear_plot()
def _clear_plot(self):
self._new_plotdata()
self.graph.plot_widget.clear()
def invalidate_plot(self):
"""
Schedule a delayed replot.
"""
if not self.__replot_requested:
self.__replot_requested = True
QApplication.postEvent(
self, QEvent(self.ReplotRequest), Qt.LowEventPriority - 10
)
def init_attr_values(self):
self.graph.set_domain(self.data)
def _vizrank_color_change(self):
attr_color = self.graph.attr_color
is_enabled = (
self.data is not None
and not self.data.is_sparse()
and (len(self.model_other) + len(self.model_selected)) > 3
and len(self.data) > 1
)
self.btn_vizrank.setEnabled(
is_enabled
and attr_color is not None
and not np.isnan(
self.data.get_column_view(attr_color)[0].astype(float)
).all()
)
self.vizrank.initialize()
@Inputs.data
def set_data(self, data):
"""
Set the input dataset and check if data is valid.
Args:
data (Orange.data.table): data instances
"""
def sql(data):
self.Information.sql_sampled_data.clear()
if isinstance(data, SqlTable):
if data.approx_len() < 4000:
data = Table(data)
else:
self.Information.sql_sampled_data()
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(2000, partial=True)
data = Table(data_sample)
return data
def settings(data):
# get the default encoded state, replacing the position with Inf
state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
state = {
key: (source_ind, np.inf) for key, (source_ind, _) in state.items()
}
self.openContext(data.domain)
selected_keys = [
key for key, (sind, _) in self.variable_state.items() if sind == 0
]
if set(selected_keys).issubset(set(state.keys())):
pass
# update the defaults state (the encoded state must contain
# all variables in the input domain)
state.update(self.variable_state)
# ... and restore it with saved positions taking precedence over
# the defaults
selected, other = VariablesSelection.decode_var_state(
state, [list(self.model_selected), list(self.model_other)]
)
return selected, other
def is_sparse(data):
if data.is_sparse():
self.Error.sparse_data()
data = None
return data
def are_features(data):
domain = data.domain
vars = [
var
for var in chain(domain.class_vars, domain.metas, domain.attributes)
if var.is_primitive()
]
if len(vars) < 3:
self.Error.no_features()
data = None
return data
def are_instances(data):
if len(data) < 2:
self.Error.no_instances()
data = None
return data
self.clear_messages()
self.btn_vizrank.setEnabled(False)
self.closeContext()
self.clear()
self.information()
self.Error.clear()
for f in [sql, is_sparse, are_features, are_instances]:
if data is None:
break
data = f(data)
if data is not None:
self.data = data
self.init_attr_values()
domain = data.domain
vars = [
v for v in chain(domain.metas, domain.attributes) if v.is_primitive()
]
self.model_selected[:] = vars[:5]
self.model_other[:] = vars[5:] + list(domain.class_vars)
self.model_selected[:], self.model_other[:] = settings(data)
self._selection = np.zeros(len(data), dtype=np.uint8)
self.invalidate_plot()
else:
self.data = None
@Inputs.data_subset
def set_subset_data(self, subset):
"""
Set the supplementary input subset dataset.
Args:
subset (Orange.data.table): subset of data instances
"""
self.subset_data = subset
self._subset_mask = None
self.controls.graph.alpha_value.setEnabled(subset is None)
def handleNewSignals(self):
if self.data is not None:
self._clear_plot()
if self.subset_data is not None and self._subset_mask is None:
dataids = self.data.ids.ravel()
subsetids = np.unique(self.subset_data.ids)
self._subset_mask = np.in1d(dataids, subsetids, assume_unique=True)
self.setup_plot(reset_view=True)
self.cb_class_density.setEnabled(self.graph.can_draw_density())
else:
self.init_attr_values()
self.graph.new_data(None)
self._vizrank_color_change()
self.commit()
def customEvent(self, event):
if event.type() == OWRadviz.ReplotRequest:
self.__replot_requested = False
self._clear_plot()
self.setup_plot(reset_view=True)
else:
super().customEvent(event)
def closeContext(self):
self.variable_state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
super().closeContext()
def prepare_radviz_data(self, variables):
ec, points, valid_mask = radviz(self.data, variables, self.plotdata.points)
self.plotdata.embedding_coords = ec
self.plotdata.points = points
self.plotdata.valid_mask = valid_mask
def setup_plot(self, reset_view=True):
if self.data is None:
return
self.graph.jitter_continuous = True
self.__replot_requested = False
variables = list(self.model_selected)
if len(variables) < 2:
self.Warning.no_features()
self.graph.new_data(None)
return
self.Warning.clear()
self.prepare_radviz_data(variables)
if self.plotdata.embedding_coords is None:
return
domain = self.data.domain
new_metas = domain.metas + (self.variable_x, self.variable_y)
domain = Domain(
attributes=domain.attributes, class_vars=domain.class_vars, metas=new_metas
)
mask = self.plotdata.valid_mask
array = np.zeros((len(self.data), 2), dtype=np.float)
array[mask] = self.plotdata.embedding_coords
data = self.data.transform(domain)
data[:, self.variable_x] = array[:, 0].reshape(-1, 1)
data[:, self.variable_y] = array[:, 1].reshape(-1, 1)
subset_data = (
data[self._subset_mask & mask]
if self._subset_mask is not None and len(self._subset_mask)
else None
)
self.plotdata.data = data
self.graph.new_data(data[mask], subset_data)
if self._selection is not None:
self.graph.selection = self._selection[self.plotdata.valid_mask]
self.graph.update_data(self.variable_x, self.variable_y, reset_view=reset_view)
self.graph.plot_widget.addItem(self._circle)
self.graph.scatterplot_points = ScatterPlotItem(
x=self.plotdata.points[:, 0], y=self.plotdata.points[:, 1]
)
self._update_points_labels()
self.graph.plot_widget.addItem(self.graph.scatterplot_points)
def randomize_indices(self):
ec = self.plotdata.embedding_coords
self.plotdata.rand = (
np.random.choice(len(ec), MAX_POINTS, replace=False)
if len(ec) > MAX_POINTS
else None
)
def manual_move(self):
self.__replot_requested = False
if self.plotdata.rand is not None:
rand = self.plotdata.rand
valid_mask = self.plotdata.valid_mask
data = self.data[valid_mask]
selection = self._selection[valid_mask]
selection = selection[rand]
ec, _, valid_mask = radviz(
data, list(self.model_selected), self.plotdata.points
)
assert sum(valid_mask) == len(data)
data = data[rand]
ec = ec[rand]
data_x = data.X
data_y = data.Y
data_metas = data.metas
else:
self.prepare_radviz_data(list(self.model_selected))
ec = self.plotdata.embedding_coords
valid_mask = self.plotdata.valid_mask
data_x = self.data.X[valid_mask]
data_y = self.data.Y[valid_mask]
data_metas = self.data.metas[valid_mask]
selection = self._selection[valid_mask]
attributes = (self.variable_x, self.variable_y) + self.data.domain.attributes
domain = Domain(
attributes=attributes,
class_vars=self.data.domain.class_vars,
metas=self.data.domain.metas,
)
data = Table.from_numpy(
domain, X=np.hstack((ec, data_x)), Y=data_y, metas=data_metas
)
self.graph.new_data(data, None)
self.graph.selection = selection
self.graph.update_data(self.variable_x, self.variable_y, reset_view=True)
self.graph.plot_widget.addItem(self._circle)
self.graph.scatterplot_points = ScatterPlotItem(
x=self.plotdata.points[:, 0], y=self.plotdata.points[:, 1]
)
self._update_points_labels()
self.graph.plot_widget.addItem(self.graph.scatterplot_points)
def _update_points_labels(self):
if self.plotdata.points is None:
return
for point_label in self.plotdata.point_labels:
self.graph.plot_widget.removeItem(point_label)
self.plotdata.point_labels = []
sx, sy = self.graph.view_box.viewPixelSize()
for row in self.plotdata.points:
ti = TextItem()
metrics = QFontMetrics(ti.textItem.font())
text_width = ((RANGE.width()) / 2.0 - np.abs(row[0])) / sx
name = row[2].name
ti.setText(name)
ti.setTextWidth(text_width)
ti.setColor(QColor(0, 0, 0))
br = ti.boundingRect()
width = (
metrics.width(name) if metrics.width(name) < br.width() else br.width()
)
width = sx * (width + 5)
height = sy * br.height()
ti.setPos(row[0] - (row[0] < 0) * width, row[1] + (row[1] > 0) * height)
self.plotdata.point_labels.append(ti)
self.graph.plot_widget.addItem(ti)
def _update_jitter(self):
self.invalidate_plot()
def reset_graph_data(self, *_):
if self.data is not None:
self.graph.rescale_data()
self._update_graph()
def _update_graph(self, reset_view=True, **_):
self.graph.zoomStack = []
if self.graph.data is None:
return
self.graph.update_data(self.variable_x, self.variable_y, reset_view=reset_view)
def update_density(self):
self._update_graph(reset_view=True)
def selection_changed(self):
if self.graph.selection is not None:
self._selection[self.plotdata.valid_mask] = self.graph.selection
self.commit()
def prepare_data(self):
pass
def commit(self):
selected = annotated = components = None
graph = self.graph
if self.plotdata.data is not None:
name = self.data.name
data = self.plotdata.data
mask = self.plotdata.valid_mask.astype(int)
mask[mask == 1] = (
graph.selection if graph.selection is not None else [False * len(mask)]
)
selection = (
np.array([], dtype=np.uint8) if mask is None else np.flatnonzero(mask)
)
if len(selection):
selected = data[selection]
selected.name = name + ": selected"
selected.attributes = self.data.attributes
if graph.selection is not None and np.max(graph.selection) > 1:
annotated = create_groups_table(data, mask)
else:
annotated = create_annotated_table(data, selection)
annotated.attributes = self.data.attributes
annotated.name = name + ": annotated"
comp_domain = Domain(
self.plotdata.points[:, 2], metas=[StringVariable(name="component")]
)
metas = np.array([["RX"], ["RY"], ["angle"]])
angle = np.arctan2(
np.array(self.plotdata.points[:, 1].T, dtype=float),
np.array(self.plotdata.points[:, 0].T, dtype=float),
)
components = Table.from_numpy(
comp_domain,
X=np.row_stack((self.plotdata.points[:, :2].T, angle)),
metas=metas,
)
components.name = name + ": components"
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(annotated)
self.Outputs.components.send(components)
def send_report(self):
if self.data is None:
return
def name(var):
return var and var.name
caption = report.render_items_vert(
(
("Color", name(self.graph.attr_color)),
("Label", name(self.graph.attr_label)),
("Shape", name(self.graph.attr_shape)),
("Size", name(self.graph.attr_size)),
(
"Jittering",
self.graph.jitter_size != 0
and "{} %".format(self.graph.jitter_size),
),
)
)
self.report_plot()
if caption:
self.report_caption(caption)
class OWLinearProjection(widget.OWWidget):
name = "Linear Projection"
description = "A multi-axis projection of data onto " \
"a two-dimensional plane."
icon = "icons/LinearProjection.svg"
priority = 240
selection_indices = settings.Setting(None, schema_only=True)
class Inputs:
data = Input("Data", Table, default=True)
data_subset = Input("Data Subset", Table)
projection = Input("Projection", Table)
class Outputs:
selected_data = Output("Selected Data", Table, default=True)
annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
components = Output("Components", Table)
Placement = Enum("Placement",
dict(Circular=0,
LDA=1,
PCA=2,
Projection=3),
type=int,
qualname="OWLinearProjection.Placement")
Component_name = {Placement.Circular: "C", Placement.LDA: "LD", Placement.PCA: "PC"}
Variable_name = {Placement.Circular: "circular",
Placement.LDA: "lda",
Placement.PCA: "pca",
Placement.Projection: "projection"}
jitter_sizes = [0, 0.1, 0.5, 1.0, 2.0]
settings_version = 3
settingsHandler = settings.DomainContextHandler()
variable_state = settings.ContextSetting({})
placement = settings.Setting(Placement.Circular)
radius = settings.Setting(0)
auto_commit = settings.Setting(True)
resolution = 256
graph = settings.SettingProvider(OWLinProjGraph)
ReplotRequest = QEvent.registerEventType()
vizrank = settings.SettingProvider(LinearProjectionVizRank)
graph_name = "graph.plot_widget.plotItem"
class Warning(widget.OWWidget.Warning):
no_cont_features = widget.Msg("Plotting requires numeric features")
not_enough_components = widget.Msg("Input projection has less than 2 components")
trivial_components = widget.Msg(
"All components of the PCA are trivial (explain 0 variance). "
"Input data is constant (or near constant).")
class Error(widget.OWWidget.Error):
proj_and_domain_match = widget.Msg("Projection and Data domains do not match")
no_valid_data = widget.Msg("No projection due to invalid data")
def __init__(self):
super().__init__()
self.data = None
self.projection = None
self.subset_data = None
self._subset_mask = None
self._selection = None
self.__replot_requested = False
self.n_cont_var = 0
#: Remember the saved state to restore
self.__pending_selection_restore = self.selection_indices
self.selection_indices = None
self.variable_x = None
self.variable_y = None
box = gui.vBox(self.mainArea, True, margin=0)
self.graph = OWLinProjGraph(self, box, "Plot", view_box=LinProjInteractiveViewBox)
box.layout().addWidget(self.graph.plot_widget)
plot = self.graph.plot_widget
SIZE_POLICY = (QSizePolicy.Minimum, QSizePolicy.Maximum)
self.variables_selection = VariablesSelection()
self.model_selected = VariableListModel(enable_dnd=True)
self.model_other = VariableListModel(enable_dnd=True)
self.variables_selection(self, self.model_selected, self.model_other)
self.vizrank, self.btn_vizrank = LinearProjectionVizRank.add_vizrank(
self.controlArea, self, "Suggest Features", self._vizrank)
self.variables_selection.add_remove.layout().addWidget(self.btn_vizrank)
box = gui.widgetBox(
self.controlArea, "Placement", sizePolicy=SIZE_POLICY)
self.radio_placement = gui.radioButtonsInBox(
box, self, "placement",
btnLabels=["Circular Placement",
"Linear Discriminant Analysis",
"Principal Component Analysis",
"Use input projection"],
callback=self._change_placement
)
self.viewbox = plot.getViewBox()
self.replot = None
g = self.graph.gui
box = g.point_properties_box(self.controlArea)
self.models = g.points_models
g.add_widget(g.JitterSizeSlider, box)
box.setSizePolicy(*SIZE_POLICY)
box = gui.widgetBox(self.controlArea, "Hide axes", sizePolicy=SIZE_POLICY)
self.rslider = gui.hSlider(
box, self, "radius", minValue=0, maxValue=100,
step=5, label="Radius", createLabel=False, ticks=True,
callback=self.update_radius)
self.rslider.setTickInterval(0)
self.rslider.setPageStep(10)
box = gui.vBox(self.controlArea, "Plot Properties")
box.setSizePolicy(*SIZE_POLICY)
g.add_widgets([g.ShowLegend,
g.ToolTipShowsAll,
g.ClassDensity,
g.LabelOnlySelected], box)
box = self.graph.box_zoom_select(self.controlArea)
box.setSizePolicy(*SIZE_POLICY)
self.icons = gui.attributeIconDict
p = self.graph.plot_widget.palette()
self.graph.set_palette(p)
gui.auto_commit(self.controlArea, self, "auto_commit", "Send Selection",
auto_label="Send Automatically")
self.graph.zoom_actions(self)
self._new_plotdata()
self._change_placement()
self.graph.jitter_continuous = True
def reset_graph_data(self):
if self.data is not None:
self.graph.rescale_data()
self._update_graph(reset_view=True)
def keyPressEvent(self, event):
super().keyPressEvent(event)
self.graph.update_tooltip(event.modifiers())
def keyReleaseEvent(self, event):
super().keyReleaseEvent(event)
self.graph.update_tooltip(event.modifiers())
def _vizrank(self, attrs):
self.variables_selection.display_none()
self.model_selected[:] = attrs[:]
self.model_other[:] = [var for var in self.model_other if var not in attrs]
def _change_placement(self):
placement = self.placement
p_Circular = self.Placement.Circular
p_LDA = self.Placement.LDA
self.variables_selection.set_enabled(placement in [p_Circular, p_LDA])
self._vizrank_color_change()
self.rslider.setEnabled(placement != p_Circular)
self._setup_plot()
self.commit()
def _get_min_radius(self):
return self.radius * np.max(np.linalg.norm(self.plotdata.axes, axis=1)) / 100 + 1e-5
def update_radius(self):
# Update the anchor/axes visibility
pd = self.plotdata
assert pd is not None
if pd.hidecircle is None:
return
min_radius = self._get_min_radius()
for anchor, item in zip(pd.axes, pd.axisitems):
item.setVisible(np.linalg.norm(anchor) > min_radius)
pd.hidecircle.setRect(QRectF(-min_radius, -min_radius, 2 * min_radius, 2 * min_radius))
def _new_plotdata(self):
self.plotdata = namespace(
valid_mask=None,
embedding_coords=None,
axisitems=[],
axes=[],
variables=[],
data=None,
hidecircle=None
)
def _anchor_circle(self, variables):
# minimum visible anchor radius (radius)
min_radius = self._get_min_radius()
axisitems = []
for anchor, var in zip(self.plotdata.axes, variables[:]):
axitem = AnchorItem(line=QLineF(0, 0, *anchor), text=var.name,)
axitem.setVisible(np.linalg.norm(anchor) > min_radius)
axitem.setPen(pg.mkPen((100, 100, 100)))
axitem.setArrowVisible(True)
self.viewbox.addItem(axitem)
axisitems.append(axitem)
self.plotdata.axisitems = axisitems
if self.placement == self.Placement.Circular:
return
hidecircle = QGraphicsEllipseItem()
hidecircle.setRect(QRectF(-min_radius, -min_radius, 2 * min_radius, 2 * min_radius))
_pen = QPen(Qt.lightGray, 1)
_pen.setCosmetic(True)
hidecircle.setPen(_pen)
self.viewbox.addItem(hidecircle)
self.plotdata.hidecircle = hidecircle
def update_colors(self):
self._vizrank_color_change()
def clear(self):
# Clear/reset the widget state
self.data = None
self.model_selected.clear()
self.model_other.clear()
self._clear_plot()
self.selection_indices = None
def _clear_plot(self):
self.Warning.trivial_components.clear()
for axisitem in self.plotdata.axisitems:
self.viewbox.removeItem(axisitem)
if self.plotdata.hidecircle:
self.viewbox.removeItem(self.plotdata.hidecircle)
self._new_plotdata()
self.graph.hide_axes()
def invalidate_plot(self):
"""
Schedule a delayed replot.
"""
if not self.__replot_requested:
self.__replot_requested = True
QApplication.postEvent(self, QEvent(self.ReplotRequest), Qt.LowEventPriority - 10)
def init_attr_values(self):
self.graph.set_domain(self.data)
def _vizrank_color_change(self):
is_enabled = False
if self.data is None:
self.btn_vizrank.setToolTip("There is no data.")
return
vars = [v for v in chain(self.data.domain.variables, self.data.domain.metas) if
v.is_primitive and v is not self.graph.attr_color]
self.n_cont_var = len(vars)
if self.placement not in [self.Placement.Circular, self.Placement.LDA]:
msg = "Suggest Features works only for Circular and " \
"Linear Discriminant Analysis Projection"
elif self.graph.attr_color is None:
msg = "Color variable has to be selected"
elif self.graph.attr_color.is_continuous and self.placement == self.Placement.LDA:
msg = "Suggest Features does not work for Linear Discriminant Analysis Projection " \
"when continuous color variable is selected."
elif len(vars) < 3:
msg = "Not enough available continuous variables"
else:
is_enabled = True
msg = ""
self.btn_vizrank.setToolTip(msg)
self.btn_vizrank.setEnabled(is_enabled)
self.vizrank.stop_and_reset(is_enabled)
@Inputs.projection
def set_projection(self, projection):
self.Warning.not_enough_components.clear()
if projection and len(projection) < 2:
self.Warning.not_enough_components()
projection = None
if projection is not None:
self.placement = self.Placement.Projection
self.projection = projection
@Inputs.data
def set_data(self, data):
"""
Set the input dataset.
Args:
data (Orange.data.table): data instances
"""
def sql(data):
if isinstance(data, SqlTable):
if data.approx_len() < 4000:
data = Table(data)
else:
self.information("Data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(2000, partial=True)
data = Table(data_sample)
return data
def settings(data):
# get the default encoded state, replacing the position with Inf
state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
state = {key: (source_ind, np.inf) for key, (source_ind, _) in state.items()}
self.openContext(data.domain)
selected_keys = [key for key, (sind, _) in self.variable_state.items() if sind == 0]
if set(selected_keys).issubset(set(state.keys())):
pass
if self.__pending_selection_restore is not None:
self._selection = np.array(self.__pending_selection_restore, dtype=int)
self.__pending_selection_restore = None
# update the defaults state (the encoded state must contain
# all variables in the input domain)
state.update(self.variable_state)
# ... and restore it with saved positions taking precedence over
# the defaults
selected, other = VariablesSelection.decode_var_state(
state, [list(self.model_selected), list(self.model_other)])
return selected, other
self.closeContext()
self.clear()
self.Warning.no_cont_features.clear()
self.information()
data = sql(data)
if data is not None:
domain = data.domain
vars = [var for var in chain(domain.variables, domain.metas) if var.is_continuous]
if not len(vars):
self.Warning.no_cont_features()
data = None
self.data = data
self.init_attr_values()
if data is not None and len(data):
self._initialize(data)
self.model_selected[:], self.model_other[:] = settings(data)
self.vizrank.stop_and_reset()
self.vizrank.attrs = self.data.domain.attributes if self.data is not None else []
def _check_possible_opt(self):
def set_enabled(is_enabled):
for btn in self.radio_placement.buttons:
btn.setEnabled(is_enabled)
self.variables_selection.set_enabled(is_enabled)
p_Circular = self.Placement.Circular
p_LDA = self.Placement.LDA
p_Input = self.Placement.Projection
if self.data:
set_enabled(True)
domain = self.data.domain
if not domain.has_discrete_class or len(domain.class_var.values) < 2:
self.radio_placement.buttons[p_LDA].setEnabled(False)
if self.placement == p_LDA:
self.placement = p_Circular
if not self.projection:
self.radio_placement.buttons[p_Input].setEnabled(False)
if self.placement == p_Input:
self.placement = p_Circular
self._setup_plot()
else:
self.graph.new_data(None)
self.rslider.setEnabled(False)
set_enabled(False)
self.commit()
@Inputs.data_subset
def set_subset_data(self, subset):
"""
Set the supplementary input subset dataset.
Args:
subset (Orange.data.table): subset of data instances
"""
self.subset_data = subset
self._subset_mask = None
self.controls.graph.alpha_value.setEnabled(subset is None)
def handleNewSignals(self):
if self.data is not None and self.subset_data is not None:
# Update the plot's highlight items
dataids = self.data.ids.ravel()
subsetids = np.unique(self.subset_data.ids)
self._subset_mask = np.in1d(dataids, subsetids, assume_unique=True)
self._check_possible_opt()
self._change_placement()
self.commit()
def customEvent(self, event):
if event.type() == OWLinearProjection.ReplotRequest:
self.__replot_requested = False
self._setup_plot()
self.commit()
else:
super().customEvent(event)
def closeContext(self):
self.variable_state = VariablesSelection.encode_var_state(
[list(self.model_selected), list(self.model_other)]
)
super().closeContext()
def _initialize(self, data):
# Initialize the GUI controls from data's domain.
vars = [v for v in chain(data.domain.metas, data.domain.attributes) if v.is_continuous]
self.model_other[:] = vars[3:]
self.model_selected[:] = vars[:3]
def prepare_plot_data(self, variables):
def projection(variables):
if set(self.projection.domain.attributes).issuperset(variables):
axes = self.projection[:2, variables].X
elif set(f.name for f in
self.projection.domain.attributes).issuperset(f.name for f in variables):
axes = self.projection[:2, [f.name for f in variables]].X
else:
self.Error.proj_and_domain_match()
axes = None
return axes
def get_axes(variables):
self.Error.proj_and_domain_match.clear()
axes = None
if self.placement == self.Placement.Circular:
axes = LinProj.defaultaxes(len(variables))
elif self.placement == self.Placement.LDA:
axes = self._get_lda(self.data, variables)
elif self.placement == self.Placement.Projection and self.projection:
axes = projection(variables)
return axes
coords = [column_data(self.data, var, dtype=float) for var in variables]
coords = np.vstack(coords)
p, N = coords.shape
assert N == len(self.data), p == len(variables)
axes = get_axes(variables)
if axes is None:
return None, None, None
assert axes.shape == (2, p)
valid_mask = ~np.isnan(coords).any(axis=0)
coords = coords[:, valid_mask]
X, Y = np.dot(axes, coords)
if X.size and Y.size:
X = normalized(X)
Y = normalized(Y)
return valid_mask, np.stack((X, Y), axis=1), axes.T
def _setup_plot(self):
self._clear_plot()
if self.data is None:
return
self.__replot_requested = False
names = get_unique_names([v.name for v in chain(self.data.domain.variables,
self.data.domain.metas)],
["{}-x".format(self.Variable_name[self.placement]),
"{}-y".format(self.Variable_name[self.placement])])
self.variable_x = ContinuousVariable(names[0])
self.variable_y = ContinuousVariable(names[1])
if self.placement in [self.Placement.Circular, self.Placement.LDA]:
variables = list(self.model_selected)
elif self.placement == self.Placement.Projection:
variables = self.model_selected[:] + self.model_other[:]
elif self.placement == self.Placement.PCA:
variables = [var for var in self.data.domain.attributes if var.is_continuous]
if not variables:
self.graph.new_data(None)
return
if self.placement == self.Placement.PCA:
valid_mask, ec, axes = self._get_pca()
variables = self._pca.orig_domain.attributes
else:
valid_mask, ec, axes = self.prepare_plot_data(variables)
self.plotdata.variables = variables
self.plotdata.valid_mask = valid_mask
self.plotdata.embedding_coords = ec
self.plotdata.axes = axes
if any(e is None for e in (valid_mask, ec, axes)):
return
if not sum(valid_mask):
self.Error.no_valid_data()
self.graph.new_data(None, None)
return
self.Error.no_valid_data.clear()
self._anchor_circle(variables=variables)
self._plot()
def _plot(self):
domain = self.data.domain
new_metas = domain.metas + (self.variable_x, self.variable_y)
domain = Domain(attributes=domain.attributes, class_vars=domain.class_vars, metas=new_metas)
valid_mask = self.plotdata.valid_mask
array = np.zeros((len(self.data), 2), dtype=np.float)
array[valid_mask] = self.plotdata.embedding_coords
self.plotdata.data = data = self.data.transform(domain)
data[:, self.variable_x] = array[:, 0].reshape(-1, 1)
data[:, self.variable_y] = array[:, 1].reshape(-1, 1)
subset_data = data[self._subset_mask & valid_mask]\
if self._subset_mask is not None and len(self._subset_mask) else None
self.plotdata.data = data
self.graph.new_data(data[valid_mask], subset_data)
if self._selection is not None:
self.graph.selection = self._selection[valid_mask]
self.graph.update_data(self.variable_x, self.variable_y, False)
def _get_lda(self, data, variables):
domain = Domain(attributes=variables, class_vars=data.domain.class_vars)
data = data.transform(domain)
lda = LinearDiscriminantAnalysis(solver='eigen', n_components=2)
lda.fit(data.X, data.Y)
scalings = lda.scalings_[:, :2].T
if scalings.shape == (1, 1):
scalings = np.array([[1.], [0.]])
return scalings
def _get_pca(self):
data = self.data
MAX_COMPONENTS = 2
ncomponents = 2
DECOMPOSITIONS = [PCA] # TruncatedSVD
cls = DECOMPOSITIONS[0]
pca_projector = cls(n_components=MAX_COMPONENTS)
pca_projector.component = ncomponents
pca_projector.preprocessors = cls.preprocessors + [Normalize()]
pca = pca_projector(data)
variance_ratio = pca.explained_variance_ratio_
cumulative = np.cumsum(variance_ratio)
self._pca = pca
if not np.isfinite(cumulative[-1]):
self.Warning.trivial_components()
coords = pca(data).X
valid_mask = ~np.isnan(coords).any(axis=1)
# scale axes
max_radius = np.min([np.abs(np.min(coords, axis=0)), np.max(coords, axis=0)])
axes = pca.components_.T.copy()
axes *= max_radius / np.max(np.linalg.norm(axes, axis=1))
return valid_mask, coords, axes
def _update_graph(self, reset_view=False):
self.graph.zoomStack = []
if self.graph.data is None:
return
self.graph.update_data(self.variable_x, self.variable_y, reset_view)
def update_density(self):
self._update_graph(reset_view=False)
def selection_changed(self):
if self.graph.selection is not None:
self._selection = np.zeros(len(self.data), dtype=np.uint8)
self._selection[self.plotdata.valid_mask] = self.graph.selection
self.selection_indices = self._selection.tolist()
else:
self._selection = self.selection_indices = None
self.commit()
def prepare_data(self):
pass
def commit(self):
def prepare_components():
if self.placement in [self.Placement.Circular, self.Placement.LDA]:
attrs = [a for a in self.model_selected[:]]
axes = self.plotdata.axes
elif self.placement == self.Placement.PCA:
axes = self._pca.components_.T
attrs = [a for a in self._pca.orig_domain.attributes]
if self.placement != self.Placement.Projection:
domain = Domain([ContinuousVariable(a.name, compute_value=lambda _: None)
for a in attrs],
metas=[StringVariable(name='component')])
metas = np.array([["{}{}".format(self.Component_name[self.placement], i + 1)
for i in range(axes.shape[1])]],
dtype=object).T
components = Table(domain, axes.T, metas=metas)
components.name = 'components'
else:
components = self.projection
return components
selected = annotated = components = None
if self.data is not None and self.plotdata.data is not None:
components = prepare_components()
graph = self.graph
mask = self.plotdata.valid_mask.astype(int)
mask[mask == 1] = graph.selection if graph.selection is not None \
else [False * len(mask)]
selection = np.array([], dtype=np.uint8) if mask is None else np.flatnonzero(mask)
name = self.data.name
data = self.plotdata.data
if len(selection):
selected = data[selection]
selected.name = name + ": selected"
selected.attributes = self.data.attributes
if graph.selection is not None and np.max(graph.selection) > 1:
annotated = create_groups_table(data, mask)
else:
annotated = create_annotated_table(data, selection)
annotated.attributes = self.data.attributes
annotated.name = name + ": annotated"
self.Outputs.selected_data.send(selected)
self.Outputs.annotated_data.send(annotated)
self.Outputs.components.send(components)
def send_report(self):
if self.data is None:
return
def name(var):
return var and var.name
def projection_name():
name = ("Circular Placement",
"Linear Discriminant Analysis",
"Principal Component Analysis",
"Input projection")
return name[self.placement]
caption = report.render_items_vert((
("Projection", projection_name()),
("Color", name(self.graph.attr_color)),
("Label", name(self.graph.attr_label)),
("Shape", name(self.graph.attr_shape)),
("Size", name(self.graph.attr_size)),
("Jittering", self.graph.jitter_size != 0 and "{} %".format(self.graph.jitter_size))))
self.report_plot()
if caption:
self.report_caption(caption)
@classmethod
def migrate_settings(cls, settings_, version):
if version < 2:
settings_["point_width"] = settings_["point_size"]
if version < 3:
settings_graph = {}
settings_graph["jitter_size"] = settings_["jitter_value"]
settings_graph["point_width"] = settings_["point_width"]
settings_graph["alpha_value"] = settings_["alpha_value"]
settings_graph["class_density"] = settings_["class_density"]
settings_["graph"] = settings_graph
@classmethod
def migrate_context(cls, context, version):
if version < 2:
domain = context.ordered_domain
c_domain = [t for t in context.ordered_domain if t[1] == 2]
d_domain = [t for t in context.ordered_domain if t[1] == 1]
for d, old_val, new_val in ((domain, "color_index", "attr_color"),
(d_domain, "shape_index", "attr_shape"),
(c_domain, "size_index", "attr_size")):
index = context.values[old_val][0] - 1
context.values[new_val] = (d[index][0], d[index][1] + 100) \
if 0 <= index < len(d) else None
if version < 3:
context.values["graph"] = {
"attr_color": context.values["attr_color"],
"attr_shape": context.values["attr_shape"],
"attr_size": context.values["attr_size"]
}