def test_compare_string(self):
zoo = Table('zoo')
zoo1 = zoo[0]['name'] # aardvark
zoo2 = zoo[1]['name'] # antelope
self.assertTrue(zoo1 < zoo2)
self.assertTrue(zoo1 >= "aardvark")
def generateGraph(self):
self.Error.clear()
self.Warning.clear()
matrix = None
if self.graphMatrix is None:
if hasattr(self, "infoa"):
self.infoa.setText("No data loaded.")
if hasattr(self, "infob"):
self.infob.setText("")
if hasattr(self, "infoc"):
self.infoc.setText("")
self.pconnected = 0
self.nedges = 0
self.graph = None
return
nEdges = len(self.graphMatrix) * self.kNN
if nEdges > 200000:
self.graph = None
self.Error.number_of_edges(nEdges)
else:
items = None
matrix = self.graphMatrix
if matrix is not None and matrix.row_items is not None:
row_items = self.graphMatrix.row_items
if isinstance(row_items, Table):
if self.graphMatrix.axis == 1:
items = row_items
else:
items = [[v.name] for v in row_items.domain.attributes]
else:
items = [[str(x)] for x in self.graphMatrix.row_items]
if len(items) != self.graphMatrix.shape[0]:
self.Warning.invalid_number_of_items()
items = None
if items is None:
items = list(range(self.graphMatrix.shape[0]))
if not isinstance(items, Table):
items = Table(
Domain([], metas=[StringVariable('label')]),
items)
self.Warning.kNN_too_large.clear()
if self.kNN >= self.graphMatrix.shape[0]:
self.Warning.kNN_too_large(self.graphMatrix.shape[0] - 1)
nb_data = len(matrix)
row_index = []
col_index = []
distances_data = []
for i in range(nb_data):
distances = []
for j in range(nb_data):
distances.append((self.graphMatrix[i][j], j))
distances.sort()
for k in range(self.kNN):
row_index.append(i)
col_index.append(distances[k][1])
distances_data.append(distances[k][0])
row = np.array(row_index)
col = np.array(col_index)
weights = np.array(distances_data)
edges = sp.csr_matrix((weights, (row, col)))
graph = Network(items, edges)
self.graph = graph
if self.graph is None:
self.pconnected = 0
self.nedges = 0
else:
self.pconnected = self.graph.number_of_nodes()
self.nedges = self.graph.number_of_edges()
if hasattr(self, "infoa"):
self.infoa.setText("Data items on input: %d" % self.graphMatrix.shape[0])
if hasattr(self, "infob"):
self.infob.setText("Network nodes: %d (%3.1f%%)" % (self.pconnected,
self.pconnected / float(self.graphMatrix.shape[0]) * 100))
if hasattr(self, "infoc"):
self.infoc.setText("Network edges: %d (%.2f edges/node)" % (
self.nedges, self.nedges / float(self.pconnected)
if self.pconnected else 0))
self.Warning.large_number_of_nodes.clear()
if self.pconnected > 1000 or self.nedges > 2000:
self.Warning.large_number_of_nodes()
self.send_network()
def __call__(self, data, ret=Value):
if not 0 <= ret <= 2:
raise ValueError("invalid value of argument 'ret'")
if (ret > 0 and any(v.is_continuous for v in self.domain.class_vars)):
raise ValueError("cannot predict continuous distributions")
# Call the predictor
if isinstance(data, np.ndarray):
prediction = self.predict(np.atleast_2d(data))
elif isinstance(data, scipy.sparse.csr.csr_matrix):
prediction = self.predict(data)
elif isinstance(data, Instance):
if data.domain != self.domain:
data = Instance(self.domain, data)
data = Table(data.domain, [data])
prediction = self.predict_storage(data)
elif isinstance(data, Table):
if data.domain != self.domain:
data = data.from_table(self.domain, data)
prediction = self.predict_storage(data)
elif isinstance(data, (list, tuple)):
if not isinstance(data[0], (list, tuple)):
data = [data]
data = Table(self.original_domain, data)
data = Table(self.domain, data)
prediction = self.predict_storage(data)
else:
raise TypeError("Unrecognized argument (instance of '{}')".format(
type(data).__name__))
# Parse the result into value and probs
multitarget = len(self.domain.class_vars) > 1
if isinstance(prediction, tuple):
value, probs = prediction
elif prediction.ndim == 1 + multitarget:
value, probs = prediction, None
elif prediction.ndim == 2 + multitarget:
value, probs = None, prediction
else:
raise TypeError("model returned a %i-dimensional array",
prediction.ndim)
# Ensure that we have what we need to return
if ret != Model.Probs and value is None:
value = np.argmax(probs, axis=-1)
if ret != Model.Value and probs is None:
if multitarget:
max_card = max(len(c.values) for c in self.domain.class_vars)
probs = np.zeros(value.shape + (max_card, ), float)
for i, cvar in enumerate(self.domain.class_vars):
probs[:, i, :], _ = bn.bincount(np.atleast_2d(value[:, i]),
max_card - 1)
else:
probs, _ = bn.bincount(np.atleast_2d(value),
len(self.domain.class_var.values) - 1)
if ret == Model.ValueProbs:
return value, probs
else:
return probs
# Return what we need to
if ret == Model.Probs:
return probs
if isinstance(data, Instance) and not multitarget:
value = Value(self.domain.class_var, value[0])
if ret == Model.Value:
return value
else: # ret == Model.ValueProbs
return value, probs
def moved(self):
point = self.widget.rect().bottomRight()
global_point = self.widget.mapToGlobal(point)
self.move(global_point - QPoint(self.width(), 0))
class DropDownToolButton(QToolButton):
def __init__(self, parent, var, lc):
QToolButton.__init__(self, parent)
self.desc_text = ''
self.popup = CheckBoxPopup(var, lc, parent, self)
self.setMenu(QMenu()) # to show arrow
self.clicked.connect(self.open_popup)
def open_popup(self):
self.popup.moved()
self.popup.show()
def set_text(self):
metrics = QFontMetrics(self.font())
self.setText(
metrics.elidedText(self.desc_text, Qt.ElideRight,
self.width() - 15))
def resizeEvent(self, QResizeEvent):
self.set_text()
if __name__ == "__main__": # pragma: no cover
WidgetPreview(OWSelectRows).run(Table("zoo"))
def test_warnings(self):
domain = Domain([ContinuousVariable("x")])
self.assertWarns(OrangeDeprecationWarning, Table, domain)
self.assertWarns(OrangeDeprecationWarning, Table, domain, Table())
self.assertWarns(OrangeDeprecationWarning, Table, domain, [[12]])
self.assertWarns(OrangeDeprecationWarning, Table, np.zeros((5, 5)))
def setUpClass(cls):
cls.data = Table("iris")
cls.distances = Euclidean(cls.data)
cls.init = torgerson(cls.distances)
cls.args = (cls.distances, 300, 25, 0, cls.init)
def test_string_variables(self):
self.send_signal(self.widget.Inputs.data, Table("zoo"))
items["Iteration limt"] = self.max_iter if self.limit_iter else "unlimited"
return items
def _report_kernel_parameters(self, items):
gamma = self.gamma or self._default_gamma
if self.kernel_type == 0:
items["Kernel"] = "Linear"
elif self.kernel_type == 1:
items["Kernel"] = \
"Polynomial, ({g:.4} x⋅y + {c:.4})<sup>{d}</sup>".format(
g=gamma, c=self.coef0, d=self.degree)
elif self.kernel_type == 2:
items["Kernel"] = "RBF, exp(-{:.4}|x-y|²)".format(gamma)
else:
items["Kernel"] = "Sigmoid, tanh({g:.4} x⋅y + {c:.4})".format(
g=gamma, c=self.coef0)
if __name__ == "__main__":
import sys
from AnyQt.QtWidgets import QApplication
a = QApplication(sys.argv)
ow = OWSVM()
ow.resetSettings()
d = Table(sys.argv[1] if len(sys.argv) > 1 else 'iris')
ow.set_data(d)
ow.show()
a.exec_()
ow.saveSettings()
else:
self.invalidate()
def send_report(self):
# False positives (Setting is not recognized as int)
# pylint: disable=invalid-sequence-index
if self.optimize_k and self.selected_row() is not None:
k_clusters = self.k_from + self.selected_row()
else:
k_clusters = self.k
init_method = self.INIT_METHODS[self.smart_init][0]
init_method = init_method[0].lower() + init_method[1:]
self.report_items((
("Number of clusters", k_clusters),
("Optimization", "{}, {} re-runs limited to {} steps".format(
init_method, self.n_init, self.max_iterations))))
if self.data is not None:
self.report_data("Data", self.data)
if self.optimize_k:
self.report_table(
"Silhouette scores for different numbers of clusters",
self.table_view)
def onDeleteWidget(self):
self.cancel()
super().onDeleteWidget()
if __name__ == "__main__": # pragma: no cover
WidgetPreview(OWKMeans).run(Table("iris.tab"))
def test_empty(self):
autompg = Table('auto-mpg')
learn = MeanLearner()
clf = learn(autompg[:0])
y = clf(autompg[0])
self.assertTrue(y == 0)
def test_discrete(self):
iris = Table('iris')
learn = MeanLearner()
self.assertRaises(ValueError, learn, iris)
def setUp(self):
self.zoo = Table("zoo")
params['Random seed for shuffling'] = self.random_state
return list(params.items())
def update_model(self):
super().update_model()
coeffs = None
if self.model is not None:
if self.model.domain.class_var.is_discrete:
coeffs = create_coef_table(self.model)
else:
attrs = [ContinuousVariable("coef")]
domain = Domain(attrs, metas=[StringVariable("name")])
cfs = list(self.model.intercept) + list(
self.model.coefficients)
names = ["intercept"] + \
[attr.name for attr in self.model.domain.attributes]
coeffs = Table(domain, list(zip(cfs, names)))
coeffs.name = "coefficients"
self.Outputs.coefficients.send(coeffs)
@classmethod
def migrate_settings(cls, settings, version):
if version < 2:
settings["max_iter"] = settings.pop("n_iter", 5)
settings["tol_enabled"] = False
if __name__ == "__main__": # pragma: no cover
WidgetPreview(OWSGD).run(Table("iris"))
def setUpClass(cls):
cls.ionosphere = Table('ionosphere')
self.Outputs.preprocessor.send(prep)
def clear(self):
super().clear()
self.projector = self.projection = None
if __name__ == "__main__":
class OWProjectionWidgetWithName(OWDataProjectionWidget):
name = "projection"
def get_embedding(self):
if self.data is None:
return None
self.valid_data = np.any(np.isfinite(self.data.X), 1)
x_data = self.data.X
x_data[x_data == np.inf] = np.nan
x_data = np.nanmean(x_data[self.valid_data], 1)
y_data = np.ones(len(x_data))
return np.vstack((x_data, y_data)).T
app = QApplication([])
ow = OWProjectionWidgetWithName()
table = Table("iris")
ow.set_data(table)
ow.set_subset_data(table[::10])
ow.handleNewSignals()
ow.show()
app.exec_()
ow.saveSettings()
def send_data(self):
if self.optimize_k:
row = self.selected_row()
k = self.k_from + row if row is not None else None
else:
k = self.k
km = self.clusterings.get(k)
if self.data is None or km is None or isinstance(km, str):
self.Outputs.annotated_data.send(None)
self.Outputs.centroids.send(None)
return
domain = self.data.domain
cluster_var = DiscreteVariable(
get_unique_names(domain, "Cluster"),
values=["C%d" % (x + 1) for x in range(km.k)]
)
clust_ids = km(self.data)
clust_col = clust_ids.X.ravel()
silhouette_var = ContinuousVariable(
get_unique_names(domain, "Silhouette"))
if km.silhouette_samples is not None:
self.Warning.no_silhouettes.clear()
scores = np.arctan(km.silhouette_samples) / np.pi + 0.5
clust_scores = []
for i in range(km.k):
in_clust = clust_col == i
if in_clust.any():
clust_scores.append(np.mean(scores[in_clust]))
else:
clust_scores.append(0.)
clust_scores = np.atleast_2d(clust_scores).T
else:
self.Warning.no_silhouettes()
scores = np.nan
clust_scores = np.full((km.k, 1), np.nan)
new_domain = add_columns(domain, metas=[cluster_var, silhouette_var])
new_table = self.data.transform(new_domain)
new_table.get_column_view(cluster_var)[0][:] = clust_col
new_table.get_column_view(silhouette_var)[0][:] = scores
centroid_attributes = [
attr.compute_value.variable
if isinstance(attr.compute_value, ReplaceUnknowns)
and attr.compute_value.variable in domain.attributes
else attr
for attr in km.pre_domain.attributes]
centroid_domain = add_columns(
Domain(centroid_attributes, [], domain.metas),
metas=[cluster_var, silhouette_var])
centroids = Table(
centroid_domain, km.centroids, None,
np.hstack((np.full((km.k, len(domain.metas)), np.nan),
np.arange(km.k).reshape(km.k, 1),
clust_scores))
)
if self.data.name == Table.name:
centroids.name = "centroids"
else:
centroids.name = f"{self.data.name} centroids"
self.Outputs.annotated_data.send(new_table)
self.Outputs.centroids.send(centroids)
def setUp(self):
self.widget = self.create_widget(OWDistanceMatrix)
self.iris = Table("iris")[:5]
self.distances = Euclidean(self.iris)
def setUpClass(cls):
cls.data = Table(test_filename("datasets/test5.tab"))
def setUp(self):
self.widget = self.create_widget(owcolor.OWColor)
self.iris = Table("iris")
def setUpClass(cls):
cls.zoo = Table("zoo") # disc. features, disc. class
cls.housing = Table("housing") # cont. features, cont. class
cls.monk = Table("monks-1")
cls.adult = Table("adult_sample")
def setUp(self):
self.widget = self.create_widget(
OWLouvainClustering, stored_settings={'auto_commit': False})
self.iris = Table('iris')[::5]
def setUpClass(cls):
cls.ionosphere = Table('ionosphere')
cls.iris = Table('iris')
cls.zoo = Table('zoo')
def test_report(self):
widget = self.widget
data = Table("iris")[::5]
self.send_signal(widget.Inputs.data, data)
widget.send_report()
def setUp(self):
self.iris = Table('iris')
def test_invalid_call_with_kwargs(self):
self.assertRaises(TypeError, Table, Y=[])
self.assertRaises(TypeError, Table, "iris", 42)
self.assertRaises(TypeError, Table, Table(), 42)
def setUp(self):
self.widget = self.create_widget(OWConcatenate)
self.iris = Table("iris")
self.titanic = Table("titanic")
settings.migrate_str_to_variable(context, names="lat_attr",
none_placeholder="")
settings.migrate_str_to_variable(context, names="lon_attr",
none_placeholder="")
settings.migrate_str_to_variable(context, names="class_attr",
none_placeholder="(None)")
# those settings can have two none placeholder
attr_placeholders = [("color_attr", "(Same color)"),
("label_attr", "(No labels)"),
("shape_attr", "(Same shape)"),
("size_attr", "(Same size)")]
for attr, place in attr_placeholders:
if context.values[attr][0] == place:
context.values[attr] = ("", context.values[attr][1])
settings.migrate_str_to_variable(context, names=attr,
none_placeholder="")
if version < 3:
settings.rename_setting(context, "lat_attr", "attr_lat")
settings.rename_setting(context, "lon_attr", "attr_lon")
settings.rename_setting(context, "color_attr", "attr_color")
settings.rename_setting(context, "label_attr", "attr_label")
settings.rename_setting(context, "shape_attr", "attr_shape")
settings.rename_setting(context, "size_attr", "attr_size")
if __name__ == "__main__":
data = Table("India_census_district_population")
WidgetPreview(OWMap).run(data)
def setUp(self):
super().setUp()
self.widget = self.create_widget(OWOutliers)
self.iris = Table("iris")
self.heart_disease = Table("heart_disease")
def setUpClass(cls):
cls.iris = Table("iris")
def test_data_name(self):
table1 = Table('iris')
table2 = TabReader(table1.__file__).read()
self.assertEqual(table1.name, 'iris')
self.assertEqual(table2.name, 'iris')
