def draw_distributions(self):
"""Draw distributions with discrete attributes"""
if not (self.show_distributions and self.have_data and self.data_has_discrete_class):
return
class_count = len(self.data_domain.class_var.values)
class_ = self.data_domain.class_var
# we create a hash table of possible class values (happens only if we have a discrete class)
if self.domain_contingencies is None:
self.domain_contingencies = dict(
zip(
[attr for attr in self.data_domain if isinstance(attr, DiscreteVariable)],
get_contingencies(self.raw_data, skipContinuous=True),
)
)
self.domain_contingencies[class_] = get_contingency(self.raw_data, class_, class_)
max_count = max([contingency.max() for contingency in self.domain_contingencies.values()] or [1])
sorted_class_values = get_variable_values_sorted(self.data_domain.class_var)
for axis_idx, attr_idx in enumerate(self.attribute_indices):
attr = self.data_domain[attr_idx]
if isinstance(attr, DiscreteVariable):
continue
contingency = self.domain_contingencies[attr]
attr_len = len(attr.values)
# we create a hash table of variable values and their indices
sorted_variable_values = get_variable_values_sorted(attr)
# create bar curve
for j in range(attr_len):
attribute_value = sorted_variable_values[j]
value_count = contingency[:, attribute_value]
for i in range(class_count):
class_value = sorted_class_values[i]
color = QColor(self.discrete_palette[i])
color.setAlpha(self.alpha_value)
width = float(value_count[class_value] * 0.5) / float(max_count)
y_off = float(1.0 + 2.0 * j) / float(2 * attr_len)
height = 0.7 / float(class_count * attr_len)
y_low_bottom = y_off + float(class_count * height) / 2.0 - i * height
curve = PolygonCurve(
QPen(color),
QBrush(color),
xData=[axis_idx, axis_idx + width, axis_idx + width, axis_idx],
yData=[y_low_bottom, y_low_bottom, y_low_bottom - height, y_low_bottom - height],
tooltip=attr.name,
)
curve.attach(self)
def draw_distributions(self):
"""Draw distributions with discrete attributes"""
if not (self.show_distributions and self.have_data and self.data_has_discrete_class):
return
class_count = len(self.data_domain.class_var.values)
class_ = self.data_domain.class_var
# we create a hash table of possible class values (happens only if we have a discrete class)
if self.domain_contingencies is None:
self.domain_contingencies = dict(
zip([attr for attr in self.data_domain if isinstance(attr, DiscreteVariable)],
get_contingencies(self.raw_data, skipContinuous=True)))
self.domain_contingencies[class_] = get_contingency(self.raw_data, class_, class_)
max_count = max([contingency.max() for contingency in self.domain_contingencies.values()] or [1])
sorted_class_values = get_variable_values_sorted(self.data_domain.class_var)
for axis_idx, attr_idx in enumerate(self.attribute_indices):
attr = self.data_domain[attr_idx]
if isinstance(attr, DiscreteVariable):
continue
contingency = self.domain_contingencies[attr]
attr_len = len(attr.values)
# we create a hash table of variable values and their indices
sorted_variable_values = get_variable_values_sorted(attr)
# create bar curve
for j in range(attr_len):
attribute_value = sorted_variable_values[j]
value_count = contingency[:, attribute_value]
for i in range(class_count):
class_value = sorted_class_values[i]
color = QColor(self.discrete_palette[i])
color.setAlpha(self.alpha_value)
width = float(value_count[class_value] * 0.5) / float(max_count)
y_off = float(1.0 + 2.0 * j) / float(2 * attr_len)
height = 0.7 / float(class_count * attr_len)
y_low_bottom = y_off + float(class_count * height) / 2.0 - i * height
curve = PolygonCurve(QPen(color),
QBrush(color),
xData=[axis_idx, axis_idx + width,
axis_idx + width, axis_idx],
yData=[y_low_bottom, y_low_bottom, y_low_bottom - height,
y_low_bottom - height],
tooltip=attr.name)
curve.attach(self)
def draw_axes(self):
self.remove_all_axes()
for i in range(len(self.attributes)):
axis_id = UserAxis + i
a = self.add_axis(axis_id,
line=QLineF(i, 0, i, 1),
arrows=AxisStart | AxisEnd,
zoomable=True)
a.always_horizontal_text = True
a.max_text_width = 100
a.title_margin = -10
a.text_margin = 0
a.setZValue(5)
self.set_axis_title(axis_id,
self.data_domain[self.attributes[i]].name)
self.set_show_axis_title(axis_id, self.show_attr_values)
if self.show_attr_values:
attr = self.data_domain[self.attributes[i]]
if attr.is_continuous:
self.set_axis_scale(axis_id,
self.attr_values[attr.name][0],
self.attr_values[attr.name][1])
elif attr.is_discrete:
attribute_values = get_variable_values_sorted(
self.data_domain[self.attributes[i]])
attr_len = len(attribute_values)
values = [
float(1.0 + 2.0 * j) / float(2 * attr_len)
for j in range(len(attribute_values))
]
a.set_bounds((0, 1))
self.set_axis_labels(axis_id,
labels=attribute_values,
values=values)
def get_max_label_width(attr):
values = get_variable_values_sorted(data.domain[attr])
maxw = 0
for val in values:
t = CanvasText(self.canvas, val, 0, 0, bold=0, show=False)
maxw = max(int(t.boundingRect().width()), maxw)
return maxw
def get_max_label_width(attr):
values = get_variable_values_sorted(data.domain[attr])
maxw = 0
for val in values:
t = CanvasText(self.canvas, val, 0, 0, bold=0, show=False)
maxw = max(int(t.boundingRect().width()), maxw)
return maxw
def update_properties(self):
## Mostly copied from OWScatterPlotGraph
if not self.plot():
return
if not self.rect:
x, y = self.axes()
self.rect = self.plot().data_rect_for_axes(x, y)
s = self.graph_transform().mapRect(self.rect).size().toSize()
if not s.isValid():
return
rx = s.width()
ry = s.height()
rx -= rx % self.granularity
ry -= ry % self.granularity
p = self.graph_transform().map(QPointF(
0, 0)) - self.graph_transform().map(self.rect.topLeft())
p = p.toPoint()
ox = p.x()
oy = -p.y()
if isinstance(self.classifier.classVar, ContinuousVariable):
imagebmp = orangeom.potentialsBitmap(self.classifier, rx, ry, ox,
oy, self.granularity,
self.scale)
palette = [
qRgb(255. * i / 255., 255. * i / 255., 255 - (255. * i / 255.))
for i in range(255)
] + [qRgb(255, 255, 255)]
else:
imagebmp, nShades = orangeom.potentialsBitmap(
self.classifier, rx, ry, ox, oy, self.granularity, self.scale,
self.spacing)
palette = []
sortedClasses = get_variable_values_sorted(
self.classifier.domain.classVar)
for cls in self.classifier.classVar.values:
color = self.plot().discPalette.getRGB(
sortedClasses.index(cls))
towhite = [255 - c for c in color]
for s in range(nShades):
si = 1 - float(s) / nShades
palette.append(
qRgb(*tuple(
[color[i] + towhite[i] * si for i in (0, 1, 2)])))
palette.extend(
[qRgb(255, 255, 255) for i in range(256 - len(palette))])
self.potentialsImage = QImage(imagebmp, rx, ry, QImage.Format_Indexed8)
self.potentialsImage.setColorTable(
ColorPaletteDlg.signedPalette(palette
) if qVersion() < "4.5" else palette)
self.potentialsImage.setNumColors(256)
self.pixmap_item.setPixmap(QPixmap.fromImage(self.potentialsImage))
self.pixmap_item.setPos(self.graph_transform().map(
self.rect.bottomLeft()))
def update_data(self, attr_x, attr_y):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y])
x_data, y_data = self.get_xy_data_positions(attr_x, attr_y,
self.valid_data)
x_data = x_data[self.valid_data]
y_data = y_data[self.valid_data]
self.n_points = len(x_data)
for axis, name, index in (("bottom", attr_x, index_x), ("left", attr_y,
index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if isinstance(var, DiscreteVariable):
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
self.scatterplot_item = ScatterPlotItem(x=x_data,
y=y_data,
data=np.arange(self.n_points),
symbol=shape_data,
size=size_data,
pen=color_data,
brush=brush_data)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def update_data(self, attr_x, attr_y):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y])
x_data, y_data = self.get_xy_data_positions(
attr_x, attr_y, self.valid_data)
x_data = x_data[self.valid_data]
y_data = y_data[self.valid_data]
self.n_points = len(x_data)
for axis, name, index in (("bottom", attr_x, index_x),
("left", attr_y, index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if isinstance(var, DiscreteVariable):
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
self.scatterplot_item = ScatterPlotItem(
x=x_data, y=y_data, data=np.arange(self.n_points),
symbol=shape_data, size=size_data, pen=color_data, brush=brush_data
)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def draw_legend(self):
if self.data_has_class:
if isinstance(self.data_domain.class_var, DiscreteVariable):
self.legend().clear()
values = get_variable_values_sorted(self.data_domain.class_var)
for i, value in enumerate(values):
self.legend().add_item(self.data_domain.class_var.name, value,
OWPoint(OWPoint.Rect, self.discrete_palette[i], self.point_width))
else:
values = self.attr_values[self.data_domain.class_var.name]
decimals = self.data_domain.class_var.number_of_decimals
self.legend().add_color_gradient(self.data_domain.class_var.name,
["%%.%df" % decimals % v for v in values])
else:
self.legend().clear()
self.old_legend_keys = []
def draw_legend(self):
if self.data_has_class:
if isinstance(self.data_domain.class_var, DiscreteVariable):
self.legend().clear()
values = get_variable_values_sorted(self.data_domain.class_var)
for i, value in enumerate(values):
self.legend().add_item(self.data_domain.class_var.name, value,
OWPoint(OWPoint.Rect, self.discrete_palette[i], self.point_width))
else:
values = self.attr_values[self.data_domain.class_var.name]
decimals = self.data_domain.class_var.number_of_decimals
self.legend().add_color_gradient(self.data_domain.class_var.name,
["%%.%df" % decimals % v for v in values])
else:
self.legend().clear()
self.old_legend_keys = []
def update_properties(self):
## Mostly copied from OWScatterPlotGraph
if not self.plot():
return
if not self.rect:
x, y = self.axes()
self.rect = self.plot().data_rect_for_axes(x, y)
s = self.graph_transform().mapRect(self.rect).size().toSize()
if not s.isValid():
return
rx = s.width()
ry = s.height()
rx -= rx % self.granularity
ry -= ry % self.granularity
p = self.graph_transform().map(QPointF(0, 0)) - self.graph_transform().map(self.rect.topLeft())
p = p.toPoint()
ox = p.x()
oy = -p.y()
if isinstance(self.classifier.classVar, ContinuousVariable):
imagebmp = orangeom.potentialsBitmap(self.classifier, rx, ry, ox, oy, self.granularity, self.scale)
palette = [qRgb(255.0 * i / 255.0, 255.0 * i / 255.0, 255 - (255.0 * i / 255.0)) for i in range(255)] + [
qRgb(255, 255, 255)
]
else:
imagebmp, nShades = orangeom.potentialsBitmap(
self.classifier, rx, ry, ox, oy, self.granularity, self.scale, self.spacing
)
palette = []
sortedClasses = get_variable_values_sorted(self.classifier.domain.classVar)
for cls in self.classifier.classVar.values:
color = self.plot().discPalette.getRGB(sortedClasses.index(cls))
towhite = [255 - c for c in color]
for s in range(nShades):
si = 1 - float(s) / nShades
palette.append(qRgb(*tuple([color[i] + towhite[i] * si for i in (0, 1, 2)])))
palette.extend([qRgb(255, 255, 255) for i in range(256 - len(palette))])
self.potentialsImage = QImage(imagebmp, rx, ry, QImage.Format_Indexed8)
self.potentialsImage.setColorTable(ColorPaletteDlg.signedPalette(palette) if qVersion() < "4.5" else palette)
self.potentialsImage.setNumColors(256)
self.pixmap_item.setPixmap(QPixmap.fromImage(self.potentialsImage))
self.pixmap_item.setPos(self.graph_transform().map(self.rect.bottomLeft()))
def draw_legend(self):
if self.data_has_class:
if self.data_domain.has_discrete_class:
self.legend().clear()
values = get_variable_values_sorted(self.data_domain.class_var)
for i, value in enumerate(values):
self.legend().add_item(
self.data_domain.class_var.name, value,
OWPoint(OWPoint.Rect, QColor(*self.colors[i]), 10))
else:
values = self.attr_values[self.data_domain.class_var.name]
decimals = self.data_domain.class_var.number_of_decimals
self.legend().add_color_gradient(self.data_domain.class_var.name,
["%%.%df" % decimals % v for v in values])
else:
self.legend().clear()
self.old_legend_keys = []
def draw_legend(self):
if self.data_has_class:
if self.data_domain.has_discrete_class:
self.legend().clear()
values = get_variable_values_sorted(self.data_domain.class_var)
for i, value in enumerate(values):
self.legend().add_item(
self.data_domain.class_var.name, value,
OWPoint(OWPoint.Rect, QColor(*self.colors[i]), 10))
else:
values = self.attr_values[self.data_domain.class_var.name]
decimals = self.data_domain.class_var.number_of_decimals
self.legend().add_color_gradient(
self.data_domain.class_var.name,
["%%.%df" % decimals % v for v in values])
else:
self.legend().clear()
self.old_legend_keys = []
def draw_legend(x0_x1, y0_y1):
x0, x1 = x0_x1
y0, y1 = y0_y1
if self.interior_coloring == self.PEARSON:
names = [
"<-8", "-8:-4", "-4:-2", "-2:2", "2:4", "4:8", ">8",
"Residuals:"
]
colors = self.RED_COLORS[::-1] + self.BLUE_COLORS[1:]
else:
names = get_variable_values_sorted(class_var) + \
[class_var.name + ":"]
colors = [QColor(*col) for col in class_var.colors]
names = [
CanvasText(self.canvas, name, alignment=Qt.AlignVCenter)
for name in names
]
totalwidth = sum(text.boundingRect().width() for text in names)
# compute the x position of the center of the legend
y = y1 + self.ATTR_NAME_OFFSET + self.ATTR_VAL_OFFSET + 35
distance = 30
startx = (x0 + x1) / 2 - (totalwidth + (len(names)) * distance) / 2
names[-1].setPos(startx + 15, y)
names[-1].show()
xoffset = names[-1].boundingRect().width() + distance
size = 8
for i in range(len(names) - 1):
if self.interior_coloring == self.PEARSON:
edgecolor = Qt.black
else:
edgecolor = colors[i]
CanvasRectangle(self.canvas, startx + xoffset, y - size / 2,
size, size, edgecolor, colors[i])
names[i].setPos(startx + xoffset + 10, y)
xoffset += distance + names[i].boundingRect().width()
def draw_axes(self):
self.remove_all_axes()
for i in range(len(self.attributes)):
axis_id = UserAxis + i
a = self.add_axis(axis_id, line=QLineF(i, 0, i, 1), arrows=AxisStart | AxisEnd, zoomable=True)
a.always_horizontal_text = True
a.max_text_width = 100
a.title_margin = -10
a.text_margin = 0
a.setZValue(5)
self.set_axis_title(axis_id, self.data_domain[self.attributes[i]].name)
self.set_show_axis_title(axis_id, self.show_attr_values)
if self.show_attr_values:
attr = self.data_domain[self.attributes[i]]
if isinstance(attr, ContinuousVariable):
self.set_axis_scale(axis_id, self.attr_values[attr.name][0], self.attr_values[attr.name][1])
elif isinstance(attr, DiscreteVariable):
attribute_values = get_variable_values_sorted(self.data_domain[self.attributes[i]])
attr_len = len(attribute_values)
values = [float(1.0 + 2.0 * j) / float(2 * attr_len) for j in range(len(attribute_values))]
a.set_bounds((0, 1))
self.set_axis_labels(axis_id, labels=attribute_values, values=values)
def draw_legend(x0_x1, y0_y1):
x0, x1 = x0_x1
y0, y1 = y0_y1
if self.interior_coloring == self.PEARSON:
names = ["<-8", "-8:-4", "-4:-2", "-2:2", "2:4", "4:8", ">8",
"Residuals:"]
colors = self.RED_COLORS[::-1] + self.BLUE_COLORS[1:]
else:
names = get_variable_values_sorted(class_var) + \
[class_var.name + ":"]
colors = [QColor(*col) for col in class_var.colors]
names = [CanvasText(self.canvas, name, alignment=Qt.AlignVCenter)
for name in names]
totalwidth = sum(text.boundingRect().width() for text in names)
# compute the x position of the center of the legend
y = y1 + self.ATTR_NAME_OFFSET + self.ATTR_VAL_OFFSET + 35
distance = 30
startx = (x0 + x1) / 2 - (totalwidth + (len(names)) * distance) / 2
names[-1].setPos(startx + 15, y)
names[-1].show()
xoffset = names[-1].boundingRect().width() + distance
size = 8
for i in range(len(names) - 1):
if self.interior_coloring == self.PEARSON:
edgecolor = Qt.black
else:
edgecolor = colors[i]
CanvasRectangle(self.canvas, startx + xoffset, y - size / 2,
size, size, edgecolor, colors[i])
names[i].setPos(startx + xoffset + 10, y)
xoffset += distance + names[i].boundingRect().width()
def add_rect(x0,
x1,
y0,
y1,
condition="",
used_attrs=[],
used_vals=[],
attr_vals=""):
area_index = len(self.areas)
if x0 == x1:
x1 += 1
if y0 == y1:
y1 += 1
# rectangles of width and height 1 are not shown - increase
if x1 - x0 + y1 - y0 == 2:
y1 += 1
if class_var and class_var.is_discrete:
colors = [QColor(*col) for col in class_var.colors]
else:
colors = None
def select_area(_, ev):
self.select_area(area_index, ev)
def rect(x, y, w, h, z, pen_color=None, brush_color=None, **args):
if pen_color is None:
return CanvasRectangle(self.canvas,
x,
y,
w,
h,
z=z,
onclick=select_area,
**args)
if brush_color is None:
brush_color = pen_color
return CanvasRectangle(self.canvas,
x,
y,
w,
h,
pen_color,
brush_color,
z=z,
onclick=select_area,
**args)
def line(x1, y1, x2, y2):
r = QGraphicsLineItem(x1, y1, x2, y2, None)
self.canvas.addItem(r)
r.setPen(QPen(Qt.white, 2))
r.setZValue(30)
outer_rect = rect(x0, y0, x1 - x0, y1 - y0, 30)
self.areas.append((used_attrs, used_vals, outer_rect))
if not conditionaldict[attr_vals]:
return
if self.interior_coloring == self.PEARSON:
s = sum(apriori_dists[0])
expected = s * reduce(
mul, (apriori_dists[i][used_vals[i]] / float(s)
for i in range(len(used_vals))))
actual = conditionaldict[attr_vals]
pearson = (actual - expected) / sqrt(expected)
if pearson == 0:
ind = 0
else:
ind = max(0, min(int(log(abs(pearson), 2)), 3))
color = [self.RED_COLORS, self.BLUE_COLORS][pearson > 0][ind]
rect(x0, y0, x1 - x0, y1 - y0, -20, color)
outer_rect.setToolTip(
condition + "<hr/>" + "Expected instances: %.1f<br>"
"Actual instances: %d<br>"
"Standardized (Pearson) residual: %.1f" %
(expected, conditionaldict[attr_vals], pearson))
else:
cls_values = get_variable_values_sorted(class_var)
prior = get_distribution(data, class_var.name)
total = 0
for i, value in enumerate(cls_values):
val = conditionaldict[attr_vals + "-" + value]
if val == 0:
continue
if i == len(cls_values) - 1:
v = y1 - y0 - total
else:
v = ((y1 - y0) * val) / conditionaldict[attr_vals]
rect(x0, y0 + total, x1 - x0, v, -20, colors[i])
total += v
if self.use_boxes and \
abs(x1 - x0) > bar_width and \
abs(y1 - y0) > bar_width:
total = 0
line(x0 + bar_width, y0, x0 + bar_width, y1)
n = sum(prior)
for i, (val, color) in enumerate(zip(prior, colors)):
if i == len(prior) - 1:
h = y1 - y0 - total
else:
h = (y1 - y0) * val / n
rect(x0, y0 + total, bar_width, h, 20, color)
total += h
if conditionalsubsetdict:
if conditionalsubsetdict[attr_vals]:
counts = [
conditionalsubsetdict[attr_vals + "-" + val]
for val in cls_values
]
if sum(counts) == 1:
rect(x0 - 2,
y0 - 2,
x1 - x0 + 5,
y1 - y0 + 5,
-550,
colors[counts.index(1)],
Qt.white,
penWidth=2,
penStyle=Qt.DashLine)
if self.subset_data is not None:
line(x1 - bar_width, y0, x1 - bar_width, y1)
total = 0
n = conditionalsubsetdict[attr_vals]
if n:
for i, (cls, color) in \
enumerate(zip(cls_values, colors)):
val = conditionalsubsetdict[attr_vals +
"-" + cls]
if val == 0:
continue
if i == len(prior) - 1:
v = y1 - y0 - total
else:
v = ((y1 - y0) * val) / n
rect(x1 - bar_width, y0 + total, bar_width,
v, 15, color)
total += v
actual = [
conditionaldict[attr_vals + "-" + cls_values[i]]
for i in range(len(prior))
]
n_actual = sum(actual)
if n_actual > 0:
apriori = [prior[key] for key in cls_values]
n_apriori = sum(apriori)
text = "<br/>".join(
"<b>%s</b>: %d / %.1f%% (Expected %.1f / %.1f%%)" %
(cls, act, 100.0 * act / n_actual,
apr / n_apriori * n_actual, 100.0 * apr / n_apriori)
for cls, act, apr in zip(cls_values, actual, apriori))
else:
text = ""
outer_rect.setToolTip("{}<hr>Instances: {}<br><br>{}".format(
condition, n_actual, text[:-4]))
def draw_text(side, attr, x0_x1, y0_y1, total_attrs, used_attrs,
used_vals, attr_vals):
x0, x1 = x0_x1
y0, y1 = y0_y1
if side in drawn_sides:
return
# the text on the right will be drawn when we are processing
# visualization of the last value of the first attribute
if side == 3:
attr1values = \
get_variable_values_sorted(data.domain[used_attrs[0]])
if used_vals[0] != attr1values[-1]:
return
if not conditionaldict[attr_vals]:
if side not in draw_positions:
draw_positions[side] = (x0, x1, y0, y1)
return
else:
if side in draw_positions:
# restore the positions of attribute values and name
(x0, x1, y0, y1) = draw_positions[side]
drawn_sides.add(side)
values = get_variable_values_sorted(data.domain[attr])
if side % 2:
values = values[::-1]
spaces = spacing * (total_attrs - side) * (len(values) - 1)
width = x1 - x0 - spaces * (side % 2 == 0)
height = y1 - y0 - spaces * (side % 2 == 1)
# calculate position of first attribute
currpos = 0
if attr_vals == "":
counts = [conditionaldict.get(val, 1) for val in values]
else:
counts = [
conditionaldict.get(attr_vals + "-" + val, 1)
for val in values
]
total = sum(counts)
if total == 0:
counts = [1] * len(values)
total = sum(counts)
aligns = [
Qt.AlignTop | Qt.AlignHCenter, Qt.AlignRight | Qt.AlignVCenter,
Qt.AlignBottom | Qt.AlignHCenter,
Qt.AlignLeft | Qt.AlignVCenter
]
align = aligns[side]
for i in range(len(values)):
val = values[i]
perc = counts[i] / float(total)
if distributiondict[val] != 0:
if side == 0:
CanvasText(self.canvas, str(val),
x0 + currpos + width * 0.5 * perc,
y1 + self.ATTR_VAL_OFFSET, align)
elif side == 1:
CanvasText(self.canvas, str(val),
x0 - self.ATTR_VAL_OFFSET,
y0 + currpos + height * 0.5 * perc, align)
elif side == 2:
CanvasText(self.canvas, str(val),
x0 + currpos + width * perc * 0.5,
y0 - self.ATTR_VAL_OFFSET, align)
else:
CanvasText(self.canvas, str(val),
x1 + self.ATTR_VAL_OFFSET,
y0 + currpos + height * 0.5 * perc, align)
if side % 2 == 0:
currpos += perc * width + spacing * (total_attrs - side)
else:
currpos += perc * height + spacing * (total_attrs - side)
if side == 0:
CanvasText(self.canvas,
attr,
x0 + (x1 - x0) / 2,
y1 + self.ATTR_VAL_OFFSET + self.ATTR_NAME_OFFSET,
align,
bold=1)
elif side == 1:
CanvasText(self.canvas,
attr,
x0 - max_ylabel_w1 - self.ATTR_VAL_OFFSET,
y0 + (y1 - y0) / 2,
align,
bold=1,
vertical=True)
elif side == 2:
CanvasText(self.canvas,
attr,
x0 + (x1 - x0) / 2,
y0 - self.ATTR_VAL_OFFSET - self.ATTR_NAME_OFFSET,
align,
bold=1)
else:
CanvasText(self.canvas,
attr,
x1 + max_ylabel_w2 + self.ATTR_VAL_OFFSET,
y0 + (y1 - y0) / 2,
align,
bold=1,
vertical=True)
def draw_data(attr_list,
x0_x1,
y0_y1,
side,
condition,
total_attrs,
used_attrs=[],
used_vals=[],
attr_vals=""):
x0, x1 = x0_x1
y0, y1 = y0_y1
if conditionaldict[attr_vals] == 0:
add_rect(x0,
x1,
y0,
y1,
"",
used_attrs,
used_vals,
attr_vals=attr_vals)
# store coordinates for later drawing of labels
draw_text(side, attr_list[0], (x0, x1), (y0, y1), total_attrs,
used_attrs, used_vals, attr_vals)
return
attr = attr_list[0]
# how much smaller rectangles do we draw
edge = len(attr_list) * spacing
values = get_variable_values_sorted(data.domain[attr])
if side % 2:
values = values[::-1] # reverse names if necessary
if side % 2 == 0: # we are drawing on the x axis
# remove the space needed for separating different attr. values
whole = max(0, (x1 - x0) - edge * (len(values) - 1))
if whole == 0:
edge = (x1 - x0) / float(len(values) - 1)
else: # we are drawing on the y axis
whole = max(0, (y1 - y0) - edge * (len(values) - 1))
if whole == 0:
edge = (y1 - y0) / float(len(values) - 1)
if attr_vals == "":
counts = [conditionaldict[val] for val in values]
else:
counts = [
conditionaldict[attr_vals + "-" + val] for val in values
]
total = sum(counts)
# if we are visualizing the third attribute and the first attribute
# has the last value, we have to reverse the order in which the
# boxes will be drawn otherwise, if the last cell, nearest to the
# labels of the fourth attribute, is empty, we wouldn't be able to
# position the labels
valrange = list(range(len(values)))
if len(attr_list + used_attrs) == 4 and len(used_attrs) == 2:
attr1values = get_variable_values_sorted(
data.domain[used_attrs[0]])
if used_vals[0] == attr1values[-1]:
valrange = valrange[::-1]
for i in valrange:
start = i * edge + whole * float(sum(counts[:i]) / total)
end = i * edge + whole * float(sum(counts[:i + 1]) / total)
val = values[i]
htmlval = getHtmlCompatibleString(val)
if attr_vals != "":
newattrvals = attr_vals + "-" + val
else:
newattrvals = val
tooltip = condition + 4 * " " + attr + \
": <b>" + htmlval + "</b><br>"
attrs = used_attrs + [attr]
vals = used_vals + [val]
common_args = attrs, vals, newattrvals
if side % 2 == 0: # if we are moving horizontally
if len(attr_list) == 1:
add_rect(x0 + start, x0 + end, y0, y1, tooltip,
*common_args)
else:
draw_data(attr_list[1:], (x0 + start, x0 + end),
(y0, y1), side + 1, tooltip, total_attrs,
*common_args)
else:
if len(attr_list) == 1:
add_rect(x0, x1, y0 + start, y0 + end, tooltip,
*common_args)
else:
draw_data(attr_list[1:], (x0, x1),
(y0 + start, y0 + end), side + 1, tooltip,
total_attrs, *common_args)
draw_text(side, attr_list[0], (x0, x1), (y0, y1), total_attrs,
used_attrs, used_vals, attr_vals)
def update_data(self, attr_x, attr_y, reset_view=True):
self.master.warning(self.ID_MISSING_COORDS)
self.master.information(self.ID_MISSING_COORDS)
self._clear_plot_widget()
self.shown_x = attr_x
self.shown_y = attr_y
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
else:
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y],
also_class_if_exists=False)
if not np.any(self.valid_data):
self.valid_data = None
if self.valid_data is None:
self.selection = None
self.n_points = 0
self.master.warning(
self.ID_MISSING_COORDS,
"Plot cannot be displayed because '{}' or '{}' is missing for "
"all data points".format(self.shown_x, self.shown_y))
return
x_data, y_data = self.get_xy_data_positions(
attr_x, attr_y, self.valid_data)
self.n_points = len(x_data)
if reset_view:
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(
QRectF(min_x, min_y, max_x - min_x, max_y - min_y),
padding=0.025)
self.view_box.init_history()
self.view_box.tag_history()
[min_x, max_x], [min_y, max_y] = self.view_box.viewRange()
for axis, name, index in (("bottom", attr_x, index_x),
("left", attr_y, index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
if self.should_draw_density():
rgb_data = [pen.color().getRgb()[:3] for pen in color_data]
self.density_img = classdensity.class_density_image(
min_x, max_x, min_y, max_y, self.resolution,
x_data, y_data, rgb_data)
self.plot_widget.addItem(self.density_img)
data_indices = np.flatnonzero(self.valid_data)
if len(data_indices) != self.original_data.shape[1]:
self.master.information(
self.ID_MISSING_COORDS,
"Points with missing '{}' or '{}' are not displayed".
format(self.shown_x, self.shown_y))
self.scatterplot_item = ScatterPlotItem(
x=x_data, y=y_data, data=data_indices,
symbol=shape_data, size=size_data, pen=color_data, brush=brush_data
)
self.scatterplot_item_sel = ScatterPlotItem(
x=x_data, y=y_data, data=data_indices,
symbol=shape_data, size=size_data + SELECTION_WIDTH,
pen=color_data_sel, brush=brush_data_sel
)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def update_data(self, attr_x, attr_y):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
if self.scatterplot_item_sel:
self.plot_widget.removeItem(self.scatterplot_item_sel)
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y])
x_data, y_data = self.get_xy_data_positions(
attr_x, attr_y, self.valid_data)
x_data = x_data[self.valid_data]
y_data = y_data[self.valid_data]
self.n_points = len(x_data)
for axis, name, index in (("bottom", attr_x, index_x),
("left", attr_y, index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
self.scatterplot_item = ScatterPlotItem(
x=x_data, y=y_data, data=np.arange(self.n_points),
symbol=shape_data, size=size_data, pen=color_data, brush=brush_data
)
self.scatterplot_item_sel = ScatterPlotItem(
x=x_data, y=y_data, data=np.arange(self.n_points),
symbol=shape_data, size=size_data + SELECTION_WIDTH,
pen=color_data_sel, brush=brush_data_sel
)
self.plot_widget.addItem(self.scatterplot_item)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.view_box.init_history()
self.plot_widget.replot()
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(
QRectF(min_x, min_y, max_x - min_x, max_y - min_y),
padding=0.025)
self.view_box.tag_history()
def update_data(self, attr_x, attr_y, reset_view=True):
self.master.warning(self.ID_MISSING_COORDS)
self.master.information(self.ID_MISSING_COORDS)
self._clear_plot_widget()
self.shown_x = attr_x
self.shown_y = attr_y
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
else:
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y],
also_class_if_exists=False)
if not np.any(self.valid_data):
self.valid_data = None
if self.valid_data is None:
self.selection = None
self.n_points = 0
self.master.warning(
self.ID_MISSING_COORDS,
"Plot cannot be displayed because '{}' or '{}' is missing for "
"all data points".format(self.shown_x, self.shown_y))
return
x_data, y_data = self.get_xy_data_positions(attr_x, attr_y,
self.valid_data)
self.n_points = len(x_data)
if reset_view:
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(QRectF(min_x, min_y, max_x - min_x,
max_y - min_y),
padding=0.025)
self.view_box.init_history()
self.view_box.tag_history()
[min_x, max_x], [min_y, max_y] = self.view_box.viewRange()
for axis, name, index in (("bottom", attr_x, index_x), ("left", attr_y,
index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
if self.should_draw_density():
rgb_data = [pen.color().getRgb()[:3] for pen in color_data]
self.density_img = classdensity.class_density_image(
min_x, max_x, min_y, max_y, self.resolution, x_data, y_data,
rgb_data)
self.plot_widget.addItem(self.density_img)
data_indices = np.flatnonzero(self.valid_data)
if len(data_indices) != self.original_data.shape[1]:
self.master.information(
self.ID_MISSING_COORDS,
"Points with missing '{}' or '{}' are not displayed".format(
self.shown_x, self.shown_y))
self.scatterplot_item = ScatterPlotItem(x=x_data,
y=y_data,
data=data_indices,
symbol=shape_data,
size=size_data,
pen=color_data,
brush=brush_data)
self.scatterplot_item_sel = ScatterPlotItem(x=x_data,
y=y_data,
data=data_indices,
symbol=shape_data,
size=size_data +
SELECTION_WIDTH,
pen=color_data_sel,
brush=brush_data_sel)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def add_rect(x0, x1, y0, y1, condition="",
used_attrs=[], used_vals=[], attr_vals=""):
area_index = len(self.areas)
if x0 == x1:
x1 += 1
if y0 == y1:
y1 += 1
# rectangles of width and height 1 are not shown - increase
if x1 - x0 + y1 - y0 == 2:
y1 += 1
if class_var and class_var.is_discrete:
colors = [QColor(*col) for col in class_var.colors]
else:
colors = None
def select_area(_, ev):
self.select_area(area_index, ev)
def rect(x, y, w, h, z, pen_color=None, brush_color=None, **args):
if pen_color is None:
return CanvasRectangle(
self.canvas, x, y, w, h, z=z, onclick=select_area,
**args)
if brush_color is None:
brush_color = pen_color
return CanvasRectangle(
self.canvas, x, y, w, h, pen_color, brush_color, z=z,
onclick=select_area, **args)
def line(x1, y1, x2, y2):
r = QGraphicsLineItem(x1, y1, x2, y2, None)
self.canvas.addItem(r)
r.setPen(QPen(Qt.white, 2))
r.setZValue(30)
outer_rect = rect(x0, y0, x1 - x0, y1 - y0, 30)
self.areas.append((used_attrs, used_vals, outer_rect))
if not conditionaldict[attr_vals]:
return
if self.interior_coloring == self.PEARSON:
s = sum(apriori_dists[0])
expected = s * reduce(
mul,
(apriori_dists[i][used_vals[i]] / float(s)
for i in range(len(used_vals))))
actual = conditionaldict[attr_vals]
pearson = (actual - expected) / sqrt(expected)
if pearson == 0:
ind = 0
else:
ind = max(0, min(int(log(abs(pearson), 2)), 3))
color = [self.RED_COLORS, self.BLUE_COLORS][pearson > 0][ind]
rect(x0, y0, x1 - x0, y1 - y0, -20, color)
outer_rect.setToolTip(
condition + "<hr/>" +
"Expected instances: %.1f<br>"
"Actual instances: %d<br>"
"Standardized (Pearson) residual: %.1f" %
(expected, conditionaldict[attr_vals], pearson))
else:
cls_values = get_variable_values_sorted(class_var)
prior = get_distribution(data, class_var.name)
total = 0
for i, value in enumerate(cls_values):
val = conditionaldict[attr_vals + "-" + value]
if val == 0:
continue
if i == len(cls_values) - 1:
v = y1 - y0 - total
else:
v = ((y1 - y0) * val) / conditionaldict[attr_vals]
rect(x0, y0 + total, x1 - x0, v, -20, colors[i])
total += v
if self.use_boxes and \
abs(x1 - x0) > bar_width and \
abs(y1 - y0) > bar_width:
total = 0
line(x0 + bar_width, y0, x0 + bar_width, y1)
n = sum(prior)
for i, (val, color) in enumerate(zip(prior, colors)):
if i == len(prior) - 1:
h = y1 - y0 - total
else:
h = (y1 - y0) * val / n
rect(x0, y0 + total, bar_width, h, 20, color)
total += h
if conditionalsubsetdict:
if conditionalsubsetdict[attr_vals]:
counts = [conditionalsubsetdict[attr_vals + "-" + val]
for val in cls_values]
if sum(counts) == 1:
rect(x0 - 2, y0 - 2, x1 - x0 + 5, y1 - y0 + 5, -550,
colors[counts.index(1)], Qt.white,
penWidth=2, penStyle=Qt.DashLine)
if self.subset_data is not None:
line(x1 - bar_width, y0, x1 - bar_width, y1)
total = 0
n = conditionalsubsetdict[attr_vals]
if n:
for i, (cls, color) in \
enumerate(zip(cls_values, colors)):
val = conditionalsubsetdict[
attr_vals + "-" + cls]
if val == 0:
continue
if i == len(prior) - 1:
v = y1 - y0 - total
else:
v = ((y1 - y0) * val) / n
rect(x1 - bar_width, y0 + total,
bar_width, v, 15, color)
total += v
actual = [conditionaldict[attr_vals + "-" + cls_values[i]]
for i in range(len(prior))]
n_actual = sum(actual)
if n_actual > 0:
apriori = [prior[key] for key in cls_values]
n_apriori = sum(apriori)
text = "<br/>".join(
"<b>%s</b>: %d / %.1f%% (Expected %.1f / %.1f%%)" %
(cls, act, 100.0 * act / n_actual,
apr / n_apriori * n_actual, 100.0 * apr / n_apriori
)
for cls, act, apr in zip(cls_values, actual, apriori
))
else:
text = ""
outer_rect.setToolTip(
"{}<hr>Instances: {}<br><br>{}".format(
condition, n_actual, text[:-4]))
def draw_text(side, attr, x0_x1, y0_y1,
total_attrs, used_attrs, used_vals, attr_vals):
x0, x1 = x0_x1
y0, y1 = y0_y1
if side in drawn_sides:
return
# the text on the right will be drawn when we are processing
# visualization of the last value of the first attribute
if side == 3:
attr1values = \
get_variable_values_sorted(data.domain[used_attrs[0]])
if used_vals[0] != attr1values[-1]:
return
if not conditionaldict[attr_vals]:
if side not in draw_positions:
draw_positions[side] = (x0, x1, y0, y1)
return
else:
if side in draw_positions:
# restore the positions of attribute values and name
(x0, x1, y0, y1) = draw_positions[side]
drawn_sides.add(side)
values = get_variable_values_sorted(data.domain[attr])
if side % 2:
values = values[::-1]
spaces = spacing * (total_attrs - side) * (len(values) - 1)
width = x1 - x0 - spaces * (side % 2 == 0)
height = y1 - y0 - spaces * (side % 2 == 1)
# calculate position of first attribute
currpos = 0
if attr_vals == "":
counts = [conditionaldict.get(val, 1) for val in values]
else:
counts = [conditionaldict.get(attr_vals + "-" + val, 1)
for val in values]
total = sum(counts)
if total == 0:
counts = [1] * len(values)
total = sum(counts)
aligns = [Qt.AlignTop | Qt.AlignHCenter,
Qt.AlignRight | Qt.AlignVCenter,
Qt.AlignBottom | Qt.AlignHCenter,
Qt.AlignLeft | Qt.AlignVCenter]
align = aligns[side]
for i in range(len(values)):
val = values[i]
perc = counts[i] / float(total)
if distributiondict[val] != 0:
if side == 0:
CanvasText(self.canvas, str(val),
x0 + currpos + width * 0.5 * perc,
y1 + self.ATTR_VAL_OFFSET, align)
elif side == 1:
CanvasText(self.canvas, str(val),
x0 - self.ATTR_VAL_OFFSET,
y0 + currpos + height * 0.5 * perc, align)
elif side == 2:
CanvasText(self.canvas, str(val),
x0 + currpos + width * perc * 0.5,
y0 - self.ATTR_VAL_OFFSET, align)
else:
CanvasText(self.canvas, str(val),
x1 + self.ATTR_VAL_OFFSET,
y0 + currpos + height * 0.5 * perc, align)
if side % 2 == 0:
currpos += perc * width + spacing * (total_attrs - side)
else:
currpos += perc * height + spacing * (total_attrs - side)
if side == 0:
CanvasText(
self.canvas, attr,
x0 + (x1 - x0) / 2,
y1 + self.ATTR_VAL_OFFSET +
self.ATTR_NAME_OFFSET,
align, bold=1)
elif side == 1:
CanvasText(
self.canvas, attr,
x0 - max_ylabel_w1 - self.ATTR_VAL_OFFSET,
y0 + (y1 - y0) / 2,
align, bold=1, vertical=True)
elif side == 2:
CanvasText(
self.canvas, attr,
x0 + (x1 - x0) / 2,
y0 - self.ATTR_VAL_OFFSET -
self.ATTR_NAME_OFFSET,
align, bold=1)
else:
CanvasText(
self.canvas, attr,
x1 + max_ylabel_w2 + self.ATTR_VAL_OFFSET,
y0 + (y1 - y0) / 2,
align, bold=1, vertical=True)
def update_data(self, attr_x, attr_y, reset_view=True):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.density_img:
self.plot_widget.removeItem(self.density_img)
self.density_img = None
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
self.scatterplot_item = None
if self.scatterplot_item_sel:
self.plot_widget.removeItem(self.scatterplot_item_sel)
self.scatterplot_item_sel = None
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.selection = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y],
also_class_if_exists=False)
x_data, y_data = self.get_xy_data_positions(attr_x, attr_y,
self.valid_data)
self.n_points = len(x_data)
if reset_view:
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(QRectF(min_x, min_y, max_x - min_x,
max_y - min_y),
padding=0.025)
self.view_box.init_history()
self.view_box.tag_history()
[min_x, max_x], [min_y, max_y] = self.view_box.viewRange()
for axis, name, index in (("bottom", attr_x, index_x), ("left", attr_y,
index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
if self.should_draw_density():
rgb_data = [pen.color().getRgb()[:3] for pen in color_data]
self.density_img = classdensity.class_density_image(
min_x, max_x, min_y, max_y, self.resolution, x_data, y_data,
rgb_data)
self.plot_widget.addItem(self.density_img)
data_indices = np.flatnonzero(self.valid_data)
self.scatterplot_item = ScatterPlotItem(x=x_data,
y=y_data,
data=data_indices,
symbol=shape_data,
size=size_data,
pen=color_data,
brush=brush_data)
self.scatterplot_item_sel = ScatterPlotItem(x=x_data,
y=y_data,
data=data_indices,
symbol=shape_data,
size=size_data +
SELECTION_WIDTH,
pen=color_data_sel,
brush=brush_data_sel)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def draw_statistics(self):
"""Draw lines that represent standard deviation or quartiles"""
return # TODO: Implement using BasicStats
if self.show_statistics and self.have_data:
data = []
for attr_idx in self.attribute_indices:
if not self.data_domain[attr_idx].is_continuous:
data.append([()])
continue # only for continuous attributes
if not self.data_has_class or self.data_has_continuous_class: # no class
if self.show_statistics == MEANS:
m = self.domain_data_stat[attr_idx].mean
dev = self.domain_data_stat[attr_idx].var
data.append([(m - dev, m, m + dev)])
elif self.show_statistics == MEDIAN:
data.append([(0, 0, 0)])
continue
sorted_array = np.sort(attr_values)
if len(sorted_array) > 0:
data.append([
(sorted_array[int(len(sorted_array) / 4.0)],
sorted_array[int(len(sorted_array) / 2.0)],
sorted_array[int(len(sorted_array) * 0.75)])
])
else:
data.append([(0, 0, 0)])
else:
curr = []
class_values = get_variable_values_sorted(
self.data_domain.class_var)
for c in range(len(class_values)):
attr_values = self.data[
attr_idx, self.data[self.data_class_index] == c]
attr_values = attr_values[~np.isnan(attr_values)]
if len(attr_values) == 0:
curr.append((0, 0, 0))
continue
if self.show_statistics == MEANS:
m = attr_values.mean()
dev = attr_values.std()
curr.append((m - dev, m, m + dev))
elif self.show_statistics == MEDIAN:
sorted_array = np.sort(attr_values)
curr.append(
(sorted_array[int(len(attr_values) / 4.0)],
sorted_array[int(len(attr_values) / 2.0)],
sorted_array[int(len(attr_values) * 0.75)]))
data.append(curr)
# draw vertical lines
for i in range(len(data)):
for c in range(len(data[i])):
if data[i][c] == ():
continue
x = i - 0.03 * (len(data[i]) - 1) / 2.0 + c * 0.03
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve(
"",
col,
col,
3,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=[x, x, x],
yData=[data[i][c][0], data[i][c][1], data[i][c][2]],
lineWidth=4)
self.add_curve("",
col,
col,
1,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=[x - 0.03, x + 0.03],
yData=[data[i][c][0], data[i][c][0]],
lineWidth=4)
self.add_curve("",
col,
col,
1,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=[x - 0.03, x + 0.03],
yData=[data[i][c][1], data[i][c][1]],
lineWidth=4)
self.add_curve("",
col,
col,
1,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=[x - 0.03, x + 0.03],
yData=[data[i][c][2], data[i][c][2]],
lineWidth=4)
# draw lines with mean/median values
if not self.data_has_class or self.data_has_continuous_class:
class_count = 1
else:
class_count = len(self.data_domain.class_var.values)
for c in range(class_count):
diff = -0.03 * (class_count - 1) / 2.0 + c * 0.03
ys = []
xs = []
for i in range(len(data)):
if data[i] != [()]:
ys.append(data[i][c][1])
xs.append(i + diff)
else:
if len(xs) > 1:
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve("",
col,
col,
1,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=xs,
yData=ys,
lineWidth=4)
xs = []
ys = []
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve("",
col,
col,
1,
OWCurve.Lines,
OWPoint.NoSymbol,
xData=xs,
yData=ys,
lineWidth=4)
def update_data(self, attr_x, attr_y, reset_view=True):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.density_img:
self.plot_widget.removeItem(self.density_img)
self.density_img = None
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
self.scatterplot_item = None
if self.scatterplot_item_sel:
self.plot_widget.removeItem(self.scatterplot_item_sel)
self.scatterplot_item_sel = None
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.selection = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y],
also_class_if_exists=False)
x_data, y_data = self.get_xy_data_positions(
attr_x, attr_y, self.valid_data)
self.n_points = len(x_data)
if reset_view:
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(
QRectF(min_x, min_y, max_x - min_x, max_y - min_y),
padding=0.025)
self.view_box.init_history()
self.view_box.tag_history()
[min_x, max_x], [min_y, max_y] = self.view_box.viewRange()
for axis, name, index in (("bottom", attr_x, index_x),
("left", attr_y, index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
if self.should_draw_density():
rgb_data = [pen.color().getRgb()[:3] for pen in color_data]
self.density_img = classdensity.class_density_image(min_x, max_x, min_y, max_y, self.resolution,
x_data, y_data, rgb_data)
self.plot_widget.addItem(self.density_img)
data_indices = np.flatnonzero(self.valid_data)
self.scatterplot_item = ScatterPlotItem(
x=x_data, y=y_data, data=data_indices,
symbol=shape_data, size=size_data, pen=color_data, brush=brush_data
)
self.scatterplot_item_sel = ScatterPlotItem(
x=x_data, y=y_data, data=data_indices,
symbol=shape_data, size=size_data + SELECTION_WIDTH,
pen=color_data_sel, brush=brush_data_sel
)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.plot_widget.addItem(self.scatterplot_item)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.plot_widget.replot()
def draw_data(attr_list, x0_x1, y0_y1, side, condition,
total_attrs, used_attrs=[], used_vals=[],
attr_vals=""):
x0, x1 = x0_x1
y0, y1 = y0_y1
if conditionaldict[attr_vals] == 0:
add_rect(x0, x1, y0, y1, "",
used_attrs, used_vals, attr_vals=attr_vals)
# store coordinates for later drawing of labels
draw_text(side, attr_list[0], (x0, x1), (y0, y1), total_attrs,
used_attrs, used_vals, attr_vals)
return
attr = attr_list[0]
# how much smaller rectangles do we draw
edge = len(attr_list) * spacing
values = get_variable_values_sorted(data.domain[attr])
if side % 2:
values = values[::-1] # reverse names if necessary
if side % 2 == 0: # we are drawing on the x axis
# remove the space needed for separating different attr. values
whole = max(0, (x1 - x0) - edge * (
len(values) - 1))
if whole == 0:
edge = (x1 - x0) / float(len(values) - 1)
else: # we are drawing on the y axis
whole = max(0, (y1 - y0) - edge * (len(values) - 1))
if whole == 0:
edge = (y1 - y0) / float(len(values) - 1)
if attr_vals == "":
counts = [conditionaldict[val] for val in values]
else:
counts = [conditionaldict[attr_vals + "-" + val]
for val in values]
total = sum(counts)
# if we are visualizing the third attribute and the first attribute
# has the last value, we have to reverse the order in which the
# boxes will be drawn otherwise, if the last cell, nearest to the
# labels of the fourth attribute, is empty, we wouldn't be able to
# position the labels
valrange = list(range(len(values)))
if len(attr_list + used_attrs) == 4 and len(used_attrs) == 2:
attr1values = get_variable_values_sorted(
data.domain[used_attrs[0]])
if used_vals[0] == attr1values[-1]:
valrange = valrange[::-1]
for i in valrange:
start = i * edge + whole * float(sum(counts[:i]) / total)
end = i * edge + whole * float(sum(counts[:i + 1]) / total)
val = values[i]
htmlval = to_html(val)
if attr_vals != "":
newattrvals = attr_vals + "-" + val
else:
newattrvals = val
tooltip = condition + 4 * " " + attr + \
": <b>" + htmlval + "</b><br>"
attrs = used_attrs + [attr]
vals = used_vals + [val]
common_args = attrs, vals, newattrvals
if side % 2 == 0: # if we are moving horizontally
if len(attr_list) == 1:
add_rect(x0 + start, x0 + end, y0, y1,
tooltip, *common_args)
else:
draw_data(attr_list[1:], (x0 + start, x0 + end),
(y0, y1), side + 1,
tooltip, total_attrs, *common_args)
else:
if len(attr_list) == 1:
add_rect(x0, x1, y0 + start, y0 + end,
tooltip, *common_args)
else:
draw_data(attr_list[1:], (x0, x1),
(y0 + start, y0 + end), side + 1,
tooltip, total_attrs, *common_args)
draw_text(side, attr_list[0], (x0, x1), (y0, y1),
total_attrs, used_attrs, used_vals, attr_vals)
def draw_statistics(self):
"""Draw lines that represent standard deviation or quartiles"""
return # TODO: Implement using BasicStats
if self.show_statistics and self.have_data:
data = []
for attr_idx in self.attribute_indices:
if not isinstance(self.data_domain[attr_idx], ContinuousVariable):
data.append([()])
continue # only for continuous attributes
if not self.data_has_class or self.data_has_continuous_class: # no class
if self.show_statistics == MEANS:
m = self.domain_data_stat[attr_idx].mean
dev = self.domain_data_stat[attr_idx].var
data.append([(m - dev, m, m + dev)])
elif self.show_statistics == MEDIAN:
data.append([(0, 0, 0)]); continue
sorted_array = np.sort(attr_values)
if len(sorted_array) > 0:
data.append([(sorted_array[int(len(sorted_array) / 4.0)],
sorted_array[int(len(sorted_array) / 2.0)],
sorted_array[int(len(sorted_array) * 0.75)])])
else:
data.append([(0, 0, 0)])
else:
curr = []
class_values = get_variable_values_sorted(self.data_domain.class_var)
for c in range(len(class_values)):
attr_values = self.data[attr_idx, self.data[self.data_class_index] == c]
attr_values = attr_values[~np.isnan(attr_values)]
if len(attr_values) == 0:
curr.append((0, 0, 0))
continue
if self.show_statistics == MEANS:
m = attr_values.mean()
dev = attr_values.std()
curr.append((m - dev, m, m + dev))
elif self.show_statistics == MEDIAN:
sorted_array = np.sort(attr_values)
curr.append((sorted_array[int(len(attr_values) / 4.0)],
sorted_array[int(len(attr_values) / 2.0)],
sorted_array[int(len(attr_values) * 0.75)]))
data.append(curr)
# draw vertical lines
for i in range(len(data)):
for c in range(len(data[i])):
if data[i][c] == ():
continue
x = i - 0.03 * (len(data[i]) - 1) / 2.0 + c * 0.03
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve("", col, col, 3, OWCurve.Lines, OWPoint.NoSymbol, xData=[x, x, x],
yData=[data[i][c][0], data[i][c][1], data[i][c][2]], lineWidth=4)
self.add_curve("", col, col, 1, OWCurve.Lines, OWPoint.NoSymbol, xData=[x - 0.03, x + 0.03],
yData=[data[i][c][0], data[i][c][0]], lineWidth=4)
self.add_curve("", col, col, 1, OWCurve.Lines, OWPoint.NoSymbol, xData=[x - 0.03, x + 0.03],
yData=[data[i][c][1], data[i][c][1]], lineWidth=4)
self.add_curve("", col, col, 1, OWCurve.Lines, OWPoint.NoSymbol, xData=[x - 0.03, x + 0.03],
yData=[data[i][c][2], data[i][c][2]], lineWidth=4)
# draw lines with mean/median values
if not self.data_has_class or self.data_has_continuous_class:
class_count = 1
else:
class_count = len(self.data_domain.class_var.values)
for c in range(class_count):
diff = - 0.03 * (class_count - 1) / 2.0 + c * 0.03
ys = []
xs = []
for i in range(len(data)):
if data[i] != [()]:
ys.append(data[i][c][1])
xs.append(i + diff)
else:
if len(xs) > 1:
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve("", col, col, 1, OWCurve.Lines,
OWPoint.NoSymbol, xData=xs, yData=ys, lineWidth=4)
xs = []
ys = []
col = QColor(self.discrete_palette[c])
col.setAlpha(self.alpha_value_2)
self.add_curve("", col, col, 1, OWCurve.Lines,
OWPoint.NoSymbol, xData=xs, yData=ys, lineWidth=4)
def update_data(self, attr_x, attr_y):
self.shown_x = attr_x
self.shown_y = attr_y
self.remove_legend()
if self.scatterplot_item:
self.plot_widget.removeItem(self.scatterplot_item)
if self.scatterplot_item_sel:
self.plot_widget.removeItem(self.scatterplot_item_sel)
for label in self.labels:
self.plot_widget.removeItem(label)
self.labels = []
self.set_axis_title("bottom", "")
self.set_axis_title("left", "")
if self.scaled_data is None or not len(self.scaled_data):
self.valid_data = None
self.n_points = 0
return
index_x = self.attribute_name_index[attr_x]
index_y = self.attribute_name_index[attr_y]
self.valid_data = self.get_valid_list([index_x, index_y])
x_data, y_data = self.get_xy_data_positions(attr_x, attr_y,
self.valid_data)
x_data = x_data[self.valid_data]
y_data = y_data[self.valid_data]
self.n_points = len(x_data)
for axis, name, index in (("bottom", attr_x, index_x), ("left", attr_y,
index_y)):
self.set_axis_title(axis, name)
var = self.data_domain[index]
if var.is_discrete:
self.set_labels(axis, get_variable_values_sorted(var))
else:
self.set_labels(axis, None)
color_data, brush_data = self.compute_colors()
color_data_sel, brush_data_sel = self.compute_colors_sel()
size_data = self.compute_sizes()
shape_data = self.compute_symbols()
self.scatterplot_item = ScatterPlotItem(x=x_data,
y=y_data,
data=np.arange(self.n_points),
symbol=shape_data,
size=size_data,
pen=color_data,
brush=brush_data)
self.scatterplot_item_sel = ScatterPlotItem(
x=x_data,
y=y_data,
data=np.arange(self.n_points),
symbol=shape_data,
size=size_data + SELECTION_WIDTH,
pen=color_data_sel,
brush=brush_data_sel)
self.plot_widget.addItem(self.scatterplot_item)
self.plot_widget.addItem(self.scatterplot_item_sel)
self.scatterplot_item.selected_points = []
self.scatterplot_item.sigClicked.connect(self.select_by_click)
self.update_labels()
self.make_legend()
self.view_box.init_history()
self.plot_widget.replot()
min_x, max_x = np.nanmin(x_data), np.nanmax(x_data)
min_y, max_y = np.nanmin(y_data), np.nanmax(y_data)
self.view_box.setRange(QRectF(min_x, min_y, max_x - min_x,
max_y - min_y),
padding=0.025)
self.view_box.tag_history()
