def test_C_and_pandas_categorical():
if not have_pandas_categorical:
return
objs = [pandas_Categorical_from_codes([1, 0, 1], ["b", "a"])]
if have_pandas_categorical_dtype:
objs.append(pandas.Series(objs[0]))
for obj in objs:
d = {"obj": obj}
assert np.allclose(dmatrix("obj", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj)", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj, levels=['b', 'a'])", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj, levels=['a', 'b'])", d),
[[1, 0],
[1, 1],
[1, 0]])
def test_C_and_pandas_categorical():
if not have_pandas_categorical:
return
objs = [pandas_Categorical_from_codes([1, 0, 1], ["b", "a"])]
if have_pandas_categorical_dtype:
objs.append(pandas.Series(objs[0]))
for obj in objs:
d = {"obj": obj}
assert np.allclose(dmatrix("obj", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj)", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj, levels=['b', 'a'])", d),
[[1, 1],
[1, 0],
[1, 1]])
assert np.allclose(dmatrix("C(obj, levels=['a', 'b'])", d),
[[1, 0],
[1, 1],
[1, 0]])
def Series_from_codes(codes, categories):
c = pandas_Categorical_from_codes(codes, categories)
return pandas.Series(c)
def test_CategoricalSniffer():
from patsy.missing import NAAction
def t(NA_types, datas, exp_finish_fast, exp_levels, exp_contrast=None):
sniffer = CategoricalSniffer(NAAction(NA_types=NA_types))
for data in datas:
done = sniffer.sniff(data)
if done:
assert exp_finish_fast
break
else:
assert not exp_finish_fast
assert sniffer.levels_contrast() == (exp_levels, exp_contrast)
if have_pandas_categorical:
# We make sure to test with both boxed and unboxed pandas objects,
# because we used to have a bug where boxed pandas objects would be
# treated as categorical, but their levels would be lost...
preps = [lambda x: x,
C]
if have_pandas_categorical_dtype:
preps += [pandas.Series,
lambda x: C(pandas.Series(x))]
for prep in preps:
t([], [prep(pandas.Categorical.from_array([1, 2, None]))],
True, (1, 2))
# check order preservation
t([], [prep(pandas_Categorical_from_codes([1, 0], ["a", "b"]))],
True, ("a", "b"))
t([], [prep(pandas_Categorical_from_codes([1, 0], ["b", "a"]))],
True, ("b", "a"))
# check that if someone sticks a .contrast field onto our object
obj = prep(pandas.Categorical.from_array(["a", "b"]))
obj.contrast = "CONTRAST"
t([], [obj], True, ("a", "b"), "CONTRAST")
t([], [C([1, 2]), C([3, 2])], False, (1, 2, 3))
# check order preservation
t([], [C([1, 2], levels=[1, 2, 3]), C([4, 2])], True, (1, 2, 3))
t([], [C([1, 2], levels=[3, 2, 1]), C([4, 2])], True, (3, 2, 1))
# do some actual sniffing with NAs in
t(["None", "NaN"], [C([1, np.nan]), C([10, None])],
False, (1, 10))
# But 'None' can be a type if we don't make it represent NA:
sniffer = CategoricalSniffer(NAAction(NA_types=["NaN"]))
sniffer.sniff(C([1, np.nan, None]))
# The level order here is different on py2 and py3 :-( Because there's no
# consistent way to sort mixed-type values on both py2 and py3. Honestly
# people probably shouldn't use this, but I don't know how to give a
# sensible error.
levels, _ = sniffer.levels_contrast()
assert set(levels) == set([None, 1])
# bool special cases
t(["None", "NaN"], [C([True, np.nan, None])],
True, (False, True))
t([], [C([10, 20]), C([False]), C([30, 40])],
False, (False, True, 10, 20, 30, 40))
# exercise the fast-path
t([], [np.asarray([True, False]), ["foo"]],
True, (False, True))
# check tuples too
t(["None", "NaN"], [C([("b", 2), None, ("a", 1), np.nan, ("c", None)])],
False, (("a", 1), ("b", 2), ("c", None)))
# contrasts
t([], [C([10, 20], contrast="FOO")], False, (10, 20), "FOO")
# no box
t([], [[10, 30], [20]], False, (10, 20, 30))
t([], [["b", "a"], ["a"]], False, ("a", "b"))
# 0d
t([], ["b"], False, ("b",))
from nose.tools import assert_raises
# unhashable level error:
sniffer = CategoricalSniffer(NAAction())
assert_raises(PatsyError, sniffer.sniff, [{}])
# >1d is illegal
assert_raises(PatsyError, sniffer.sniff, np.asarray([["b"]]))
def Series_from_codes(codes, categories):
c = pandas_Categorical_from_codes(codes, categories)
return pandas.Series(c)
def test_CategoricalSniffer():
from patsy.missing import NAAction
def t(NA_types, datas, exp_finish_fast, exp_levels, exp_contrast=None):
sniffer = CategoricalSniffer(NAAction(NA_types=NA_types))
for data in datas:
done = sniffer.sniff(data)
if done:
assert exp_finish_fast
break
else:
assert not exp_finish_fast
assert sniffer.levels_contrast() == (exp_levels, exp_contrast)
if have_pandas_categorical:
# We make sure to test with both boxed and unboxed pandas objects,
# because we used to have a bug where boxed pandas objects would be
# treated as categorical, but their levels would be lost...
preps = [lambda x: x, C]
if have_pandas_categorical_dtype:
preps += [pandas.Series, lambda x: C(pandas.Series(x))]
for prep in preps:
t([], [prep(pandas.Categorical([1, 2, None]))], True, (1, 2))
# check order preservation
t([], [prep(pandas_Categorical_from_codes([1, 0], ["a", "b"]))],
True, ("a", "b"))
t([], [prep(pandas_Categorical_from_codes([1, 0], ["b", "a"]))],
True, ("b", "a"))
# check that if someone sticks a .contrast field onto our object
obj = prep(pandas.Categorical(["a", "b"]))
obj.contrast = "CONTRAST"
t([], [obj], True, ("a", "b"), "CONTRAST")
t([], [C([1, 2]), C([3, 2])], False, (1, 2, 3))
# check order preservation
t([], [C([1, 2], levels=[1, 2, 3]), C([4, 2])], True, (1, 2, 3))
t([], [C([1, 2], levels=[3, 2, 1]), C([4, 2])], True, (3, 2, 1))
# do some actual sniffing with NAs in
t(["None", "NaN"], [C([1, np.nan]), C([10, None])], False, (1, 10))
# But 'None' can be a type if we don't make it represent NA:
sniffer = CategoricalSniffer(NAAction(NA_types=["NaN"]))
sniffer.sniff(C([1, np.nan, None]))
# The level order here is different on py2 and py3 :-( Because there's no
# consistent way to sort mixed-type values on both py2 and py3. Honestly
# people probably shouldn't use this, but I don't know how to give a
# sensible error.
levels, _ = sniffer.levels_contrast()
assert set(levels) == set([None, 1])
# bool special cases
t(["None", "NaN"], [C([True, np.nan, None])], True, (False, True))
t([], [C([10, 20]), C([False]), C([30, 40])], False,
(False, True, 10, 20, 30, 40))
# exercise the fast-path
t([], [np.asarray([True, False]), ["foo"]], True, (False, True))
# check tuples too
t(["None", "NaN"], [C([("b", 2), None, ("a", 1), np.nan, ("c", None)])],
False, (("a", 1), ("b", 2), ("c", None)))
# contrasts
t([], [C([10, 20], contrast="FOO")], False, (10, 20), "FOO")
# no box
t([], [[10, 30], [20]], False, (10, 20, 30))
t([], [["b", "a"], ["a"]], False, ("a", "b"))
# 0d
t([], ["b"], False, ("b", ))
from nose.tools import assert_raises
# unhashable level error:
sniffer = CategoricalSniffer(NAAction())
assert_raises(PatsyError, sniffer.sniff, [{}])
# >1d is illegal
assert_raises(PatsyError, sniffer.sniff, np.asarray([["b"]]))