def grid_bin(data, xvar, yvar, xbins, ybins, zvar=None):
x_disc = Discretizer.create_discretized_var(xvar, xbins[1:-1])
y_disc = Discretizer.create_discretized_var(yvar, ybins[1:-1])
x_min, x_max = xbins[0], xbins[-1]
y_min, y_max = ybins[0], ybins[-1]
querydomain = [x_disc, y_disc]
if zvar is not None:
querydomain = querydomain + [zvar]
querydomain = Orange.data.Domain(querydomain)
def interval_filter(var, low, high):
return Orange.data.filter.Values([
Orange.data.filter.FilterContinuous(
var,
max=high,
min=low,
oper=Orange.data.filter.FilterContinuous.Between)
])
def value_filter(var, val):
return Orange.data.filter.Values(
[Orange.data.filter.FilterDiscrete(var, [val])])
def filters_join(filters):
return Orange.data.filter.Values(
reduce(list.__iadd__, (f.conditions for f in filters), []))
inf_bounds = np.isinf([x_min, x_max, y_min, y_max])
if not all(inf_bounds):
# No need to filter the data
range_filters = [
interval_filter(xvar, x_min, x_max),
interval_filter(yvar, y_min, y_max)
]
range_filter = filters_join(range_filters)
subset = range_filter(data)
else:
subset = data
if zvar and zvar.is_discrete:
filters = [value_filter(zvar, val) for val in zvar.values]
contingencies = [
contingency.get_contingency(filter_(
subset.from_table(querydomain, subset)),
col_variable=y_disc,
row_variable=x_disc)
for filter_ in filters
]
contingencies = np.dstack(contingencies)
else:
contingencies = contingency.get_contingency(subset.from_table(
querydomain, subset),
col_variable=y_disc,
row_variable=x_disc)
contingencies = np.asarray(contingencies)
return Tree(xbins, ybins, contingencies, None)
def grid_bin(data, xvar, yvar, xbins, ybins, zvar=None):
x_disc = Discretizer.create_discretized_var(xvar, xbins[1:-1])
y_disc = Discretizer.create_discretized_var(yvar, ybins[1:-1])
x_min, x_max = xbins[0], xbins[-1]
y_min, y_max = ybins[0], ybins[-1]
querydomain = [x_disc, y_disc]
if zvar is not None:
querydomain = querydomain + [zvar]
querydomain = Orange.data.Domain(querydomain)
def interval_filter(var, low, high):
return Orange.data.filter.Values(
[Orange.data.filter.FilterContinuous(
var, max=high, min=low,
oper=Orange.data.filter.FilterContinuous.Between)]
)
def value_filter(var, val):
return Orange.data.filter.Values(
[Orange.data.filter.FilterDiscrete(var, [val])]
)
def filters_join(filters):
return Orange.data.filter.Values(
reduce(list.__iadd__, (f.conditions for f in filters), [])
)
inf_bounds = np.isinf([x_min, x_max, y_min, y_max])
if not all(inf_bounds):
# No need to filter the data
range_filters = [interval_filter(xvar, x_min, x_max),
interval_filter(yvar, y_min, y_max)]
range_filter = filters_join(range_filters)
subset = range_filter(data)
else:
subset = data
if zvar.is_discrete:
filters = [value_filter(zvar, val) for val in zvar.values]
contingencies = [
contingency.get_contingency(
filter_(subset.from_table(querydomain, subset)),
col_variable=y_disc, row_variable=x_disc
)
for filter_ in filters
]
contingencies = np.dstack(contingencies)
else:
contingencies = contingency.get_contingency(
subset.from_table(querydomain, subset),
col_variable=y_disc, row_variable=x_disc
)
contingencies = np.asarray(contingencies)
return Tree(xbins, ybins, contingencies, None)
def test_equality(self):
v1 = ContinuousVariable("x")
v2 = ContinuousVariable("x", number_of_decimals=42)
v3 = ContinuousVariable("y")
assert v1 == v2
t1 = Discretizer(v1, [0, 2, 1])
t1a = Discretizer(v2, [0, 2, 1])
t2 = Discretizer(v3, [0, 2, 1])
self.assertEqual(t1, t1)
self.assertEqual(t1, t1a)
self.assertNotEqual(t1, t2)
self.assertEqual(hash(t1), hash(t1a))
self.assertNotEqual(hash(t1), hash(t2))
t1 = Discretizer(v1, [0, 2, 1])
t1a = Discretizer(v2, [1, 2, 0])
self.assertNotEqual(t1, t1a)
self.assertNotEqual(hash(t1), hash(t1a))