def test_venn_diagram(self):
sources = ["SVM Learner", "Naive Bayes", "Random Forest"]
item_id_var = StringVariable("item_id")
source_var = StringVariable("source")
table = Table("zoo")
class_var = table.domain.class_var
cv = np.random.randint(len(class_var.values), size=(3, len(sources)))
tables = []
for i in range(len(sources)):
temp_table = Table.from_table(table.domain, table,
[0 + i, 1 + i, 2 + i])
temp_d = (
DiscreteVariable("%s(%s)" % (class_var.name, sources[0 + i]),
class_var.values),
source_var,
item_id_var,
)
temp_m = np.array(
[
[cv[0, i], sources[i], table.metas[0 + i, 0]],
[cv[1, i], sources[i], table.metas[1 + i, 0]],
[cv[2, i], sources[i], table.metas[2 + i, 0]],
],
dtype=object,
)
temp_table = self.add_metas(temp_table, temp_d, temp_m)
tables.append(temp_table)
data = table_concat(tables)
varying = varying_between(data, item_id_var)
if source_var in varying:
varying.remove(source_var)
data = reshape_wide(data, varying, [item_id_var], [source_var])
data = drop_columns(data, [item_id_var])
result = np.array(
[
[table.metas[0, 0], cv[0, 0], np.nan, np.nan],
[table.metas[1, 0], cv[1, 0], cv[0, 1], np.nan],
[table.metas[2, 0], cv[2, 0], cv[1, 1], cv[0, 2]],
[table.metas[3, 0], np.nan, cv[2, 1], cv[1, 2]],
[table.metas[4, 0], np.nan, np.nan, cv[2, 2]],
],
dtype=object,
)
for i in range(len(result)):
for j in range(len(result[0])):
val = result[i][j]
if isinstance(val, float) and np.isnan(val):
self.assertTrue(np.isnan(data.metas[i][j]))
else:
np.testing.assert_equal(data.metas[i][j], result[i][j])
def test_venn_diagram(self):
sources = ["SVM Learner", "Naive Bayes", "Random Forest"]
item_id_var = StringVariable("item_id")
source_var = StringVariable("source")
table = Table("zoo")
class_var = table.domain.class_var
cv = np.random.randint(len(class_var.values), size=(3, len(sources)))
tables = []
# pylint: disable=consider-using-enumerate
for i in range(len(sources)):
temp_table = Table.from_table(table.domain, table,
[0 + i, 1 + i, 2 + i])
temp_d = (DiscreteVariable("%s(%s)" % (class_var.name,
sources[0 + i]),
class_var.values),
source_var, item_id_var)
temp_m = np.array([[cv[0, i], sources[i], table.metas[0 + i, 0]],
[cv[1, i], sources[i], table.metas[1 + i, 0]],
[cv[2, i], sources[i], table.metas[2 + i, 0]]],
dtype=object)
temp_table = self.add_metas(temp_table, temp_d, temp_m)
tables.append(temp_table)
data = table_concat(tables)
varying = varying_between(data, item_id_var)
if source_var in varying:
varying.remove(source_var)
data = reshape_wide(data, varying, [item_id_var], [source_var])
data = drop_columns(data, [item_id_var])
result = np.array([[table.metas[0, 0], cv[0, 0], np.nan, np.nan],
[table.metas[1, 0], cv[1, 0], cv[0, 1], np.nan],
[table.metas[2, 0], cv[2, 0], cv[1, 1], cv[0, 2]],
[table.metas[3, 0], np.nan, cv[2, 1], cv[1, 2]],
[table.metas[4, 0], np.nan, np.nan, cv[2, 2]]],
dtype=object)
for i in range(len(result)):
for j in range(len(result[0])):
val = result[i][j]
if isinstance(val, float) and np.isnan(val):
self.assertTrue(np.isnan(data.metas[i][j]))
else:
np.testing.assert_equal(data.metas[i][j], result[i][j])
