def test_Origin():
o1 = Origin("012345", 2, 4)
o2 = Origin("012345", 4, 5)
assert o1.caretize() == "012345\n ^^"
assert o2.caretize() == "012345\n ^"
o3 = Origin.combine([o1, o2])
assert o3.code == "012345"
assert o3.start == 2
assert o3.end == 5
assert o3.caretize(indent=2) == " 012345\n ^^^"
assert o3 == Origin("012345", 2, 5)
class ObjWithOrigin(object):
def __init__(self, origin=None):
self.origin = origin
o4 = Origin.combine([ObjWithOrigin(o1), ObjWithOrigin(), None])
assert o4 == o1
o5 = Origin.combine([ObjWithOrigin(o1), o2])
assert o5 == o3
assert Origin.combine([ObjWithOrigin(), ObjWithOrigin()]) is None
from patsy.util import assert_no_pickling
assert_no_pickling(Origin("", 0, 0))
def test_LinearConstraint():
from numpy.testing.utils import assert_equal
lc = LinearConstraint(["foo", "bar"], [1, 1])
assert lc.variable_names == ["foo", "bar"]
assert_equal(lc.coefs, [[1, 1]])
assert_equal(lc.constants, [[0]])
lc = LinearConstraint(["foo", "bar"], [[1, 1], [2, 3]], [10, 20])
assert_equal(lc.coefs, [[1, 1], [2, 3]])
assert_equal(lc.constants, [[10], [20]])
assert lc.coefs.dtype == np.dtype(float)
assert lc.constants.dtype == np.dtype(float)
from nose.tools import assert_raises
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]])
assert_raises(ValueError, LinearConstraint, ["a"], [[[1]]])
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a"], [[0]])
assert_raises(ValueError, LinearConstraint, ["a"], [[1]], [[]])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [])
assert_raises(ValueError, LinearConstraint, ["a", "b"],
np.zeros((0, 2)))
assert_no_pickling(lc)
def test_LookupFactor():
l_a = LookupFactor("a")
assert l_a.name() == "a"
assert l_a == LookupFactor("a")
assert l_a != LookupFactor("b")
assert hash(l_a) == hash(LookupFactor("a"))
assert hash(l_a) != hash(LookupFactor("b"))
assert l_a.eval({}, {"a": 1}) == 1
assert l_a.eval({}, {"a": 2}) == 2
assert repr(l_a) == "LookupFactor('a')"
assert l_a.origin is None
l_with_origin = LookupFactor("b", origin="asdf")
assert l_with_origin.origin == "asdf"
l_c = LookupFactor("c",
force_categorical=True,
contrast="CONTRAST",
levels=(1, 2))
box = l_c.eval({}, {"c": [1, 1, 2]})
assert box.data == [1, 1, 2]
assert box.contrast == "CONTRAST"
assert box.levels == (1, 2)
import pytest
pytest.raises(ValueError, LookupFactor, "nc", contrast="CONTRAST")
pytest.raises(ValueError, LookupFactor, "nc", levels=(1, 2))
assert_no_pickling(LookupFactor("a"))
def test_LookupFactor():
l_a = LookupFactor("a")
assert l_a.name() == "a"
assert l_a == LookupFactor("a")
assert l_a != LookupFactor("b")
assert hash(l_a) == hash(LookupFactor("a"))
assert hash(l_a) != hash(LookupFactor("b"))
assert l_a.eval({}, {"a": 1}) == 1
assert l_a.eval({}, {"a": 2}) == 2
assert repr(l_a) == "LookupFactor('a')"
assert l_a.origin is None
l_with_origin = LookupFactor("b", origin="asdf")
assert l_with_origin.origin == "asdf"
l_c = LookupFactor("c", force_categorical=True,
contrast="CONTRAST", levels=(1, 2))
box = l_c.eval({}, {"c": [1, 1, 2]})
assert box.data == [1, 1, 2]
assert box.contrast == "CONTRAST"
assert box.levels == (1, 2)
from nose.tools import assert_raises
assert_raises(ValueError, LookupFactor, "nc", contrast="CONTRAST")
assert_raises(ValueError, LookupFactor, "nc", levels=(1, 2))
assert_no_pickling(LookupFactor("a"))
def test_LinearConstraint():
try:
from numpy.testing import assert_equal
except ImportError:
from numpy.testing.utils import assert_equal
lc = LinearConstraint(["foo", "bar"], [1, 1])
assert lc.variable_names == ["foo", "bar"]
assert_equal(lc.coefs, [[1, 1]])
assert_equal(lc.constants, [[0]])
lc = LinearConstraint(["foo", "bar"], [[1, 1], [2, 3]], [10, 20])
assert_equal(lc.coefs, [[1, 1], [2, 3]])
assert_equal(lc.constants, [[10], [20]])
assert lc.coefs.dtype == np.dtype(float)
assert lc.constants.dtype == np.dtype(float)
# statsmodels wants to be able to create degenerate constraints like this,
# see:
# https://github.com/pydata/patsy/issues/89
# We used to forbid it, but I guess it's harmless, so why not.
lc = LinearConstraint(["a"], [[0]])
assert_equal(lc.coefs, [[0]])
from pytest import raises
raises(ValueError, LinearConstraint, ["a"], [[1, 2]])
raises(ValueError, LinearConstraint, ["a"], [[[1]]])
raises(ValueError, LinearConstraint, ["a"], [[1, 2]], [3, 4])
raises(ValueError, LinearConstraint, ["a", "b"], [[1, 2]], [3, 4])
raises(ValueError, LinearConstraint, ["a"], [[1]], [[]])
raises(ValueError, LinearConstraint, ["a", "b"], [])
raises(ValueError, LinearConstraint, ["a", "b"], np.zeros((0, 2)))
assert_no_pickling(lc)
def test_NAAction_basic():
from nose.tools import assert_raises
assert_raises(ValueError, NAAction, on_NA="pord")
assert_raises(ValueError, NAAction, NA_types=("NaN", "asdf"))
assert_raises(ValueError, NAAction, NA_types="NaN")
assert_no_pickling(NAAction())
def test_LinearConstraint():
from numpy.testing.utils import assert_equal
lc = LinearConstraint(["foo", "bar"], [1, 1])
assert lc.variable_names == ["foo", "bar"]
assert_equal(lc.coefs, [[1, 1]])
assert_equal(lc.constants, [[0]])
lc = LinearConstraint(["foo", "bar"], [[1, 1], [2, 3]], [10, 20])
assert_equal(lc.coefs, [[1, 1], [2, 3]])
assert_equal(lc.constants, [[10], [20]])
assert lc.coefs.dtype == np.dtype(float)
assert lc.constants.dtype == np.dtype(float)
from nose.tools import assert_raises
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]])
assert_raises(ValueError, LinearConstraint, ["a"], [[[1]]])
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a"], [[0]])
assert_raises(ValueError, LinearConstraint, ["a"], [[1]], [[]])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [])
assert_raises(ValueError, LinearConstraint, ["a", "b"],
np.zeros((0, 2)))
assert_no_pickling(lc)
def test_NAAction_basic():
import pytest
pytest.raises(ValueError, NAAction, on_NA="pord")
pytest.raises(ValueError, NAAction, NA_types=("NaN", "asdf"))
pytest.raises(ValueError, NAAction, NA_types="NaN")
assert_no_pickling(NAAction())
def test_NAAction_basic():
from nose.tools import assert_raises
assert_raises(ValueError, NAAction, on_NA="pord")
assert_raises(ValueError, NAAction, NA_types=("NaN", "asdf"))
assert_raises(ValueError, NAAction, NA_types="NaN")
assert_no_pickling(NAAction())
def test_LinearConstraint():
from numpy.testing.utils import assert_equal
lc = LinearConstraint(["foo", "bar"], [1, 1])
assert lc.variable_names == ["foo", "bar"]
assert_equal(lc.coefs, [[1, 1]])
assert_equal(lc.constants, [[0]])
lc = LinearConstraint(["foo", "bar"], [[1, 1], [2, 3]], [10, 20])
assert_equal(lc.coefs, [[1, 1], [2, 3]])
assert_equal(lc.constants, [[10], [20]])
assert lc.coefs.dtype == np.dtype(float)
assert lc.constants.dtype == np.dtype(float)
# statsmodels wants to be able to create degenerate constraints like this,
# see:
# https://github.com/pydata/patsy/issues/89
# We used to forbid it, but I guess it's harmless, so why not.
lc = LinearConstraint(["a"], [[0]])
assert_equal(lc.coefs, [[0]])
from nose.tools import assert_raises
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]])
assert_raises(ValueError, LinearConstraint, ["a"], [[[1]]])
assert_raises(ValueError, LinearConstraint, ["a"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [[1, 2]], [3, 4])
assert_raises(ValueError, LinearConstraint, ["a"], [[1]], [[]])
assert_raises(ValueError, LinearConstraint, ["a", "b"], [])
assert_raises(ValueError, LinearConstraint, ["a", "b"],
np.zeros((0, 2)))
assert_no_pickling(lc)
def test_ContrastMatrix():
cm = ContrastMatrix([[1, 0], [0, 1]], ["a", "b"])
assert np.array_equal(cm.matrix, np.eye(2))
assert cm.column_suffixes == ["a", "b"]
# smoke test
repr(cm)
from nose.tools import assert_raises
assert_raises(PatsyError, ContrastMatrix, [[1], [0]], ["a", "b"])
assert_no_pickling(cm)
def test_EvalFactor_basics():
e = EvalFactor("a+b")
assert e.code == "a + b"
assert e.name() == "a + b"
e2 = EvalFactor("a +b", origin="asdf")
assert e == e2
assert hash(e) == hash(e2)
assert e.origin is None
assert e2.origin == "asdf"
assert_no_pickling(e)
def test_Term():
assert Term([1, 2, 1]).factors == (1, 2)
assert Term([1, 2]) == Term([2, 1])
assert hash(Term([1, 2])) == hash(Term([2, 1]))
f1 = _MockFactor("a")
f2 = _MockFactor("b")
assert Term([f1, f2]).name() == "a:b"
assert Term([f2, f1]).name() == "b:a"
assert Term([]).name() == "Intercept"
assert_no_pickling(Term([]))
def test_Term():
assert Term([1, 2, 1]).factors == (1, 2)
assert Term([1, 2]) == Term([2, 1])
assert hash(Term([1, 2])) == hash(Term([2, 1]))
f1 = _MockFactor("a")
f2 = _MockFactor("b")
assert Term([f1, f2]).name() == "a:b"
assert Term([f2, f1]).name() == "b:a"
assert Term([]).name() == "Intercept"
assert_no_pickling(Term([]))
def test_ContrastMatrix():
cm = ContrastMatrix([[1, 0], [0, 1]], ["a", "b"])
assert np.array_equal(cm.matrix, np.eye(2))
assert cm.column_suffixes == ["a", "b"]
# smoke test
repr(cm)
from nose.tools import assert_raises
assert_raises(PatsyError, ContrastMatrix, [[1], [0]], ["a", "b"])
assert_no_pickling(cm)
def test_EvalFactor_basics():
e = EvalFactor("a+b")
assert e.code == "a + b"
assert e.name() == "a + b"
e2 = EvalFactor("a +b", origin="asdf")
assert e == e2
assert hash(e) == hash(e2)
assert e.origin is None
assert e2.origin == "asdf"
assert_no_pickling(e)
def test_design_matrix():
from nose.tools import assert_raises
di = DesignInfo(["a1", "a2", "a3", "b"])
mm = DesignMatrix([[12, 14, 16, 18]], di)
assert mm.design_info.column_names == ["a1", "a2", "a3", "b"]
bad_di = DesignInfo(["a1"])
assert_raises(ValueError, DesignMatrix, [[12, 14, 16, 18]], bad_di)
mm2 = DesignMatrix([[12, 14, 16, 18]])
assert mm2.design_info.column_names == [
"column0", "column1", "column2", "column3"
]
mm3 = DesignMatrix([12, 14, 16, 18])
assert mm3.shape == (4, 1)
# DesignMatrix always has exactly 2 dimensions
assert_raises(ValueError, DesignMatrix, [[[1]]])
# DesignMatrix constructor passes through existing DesignMatrixes
mm4 = DesignMatrix(mm)
assert mm4 is mm
# But not if they are really slices:
mm5 = DesignMatrix(mm.diagonal())
assert mm5 is not mm
mm6 = DesignMatrix([[12, 14, 16, 18]], default_column_prefix="x")
assert mm6.design_info.column_names == ["x0", "x1", "x2", "x3"]
assert_no_pickling(mm6)
# Only real-valued matrices can be DesignMatrixs
assert_raises(ValueError, DesignMatrix, [1, 2, 3j])
assert_raises(ValueError, DesignMatrix, ["a", "b", "c"])
assert_raises(ValueError, DesignMatrix, [1, 2, object()])
# Just smoke tests
repr(mm)
repr(DesignMatrix(np.arange(100)))
repr(DesignMatrix(np.arange(100) * 2.0))
repr(mm[1:, :])
repr(DesignMatrix(np.arange(100).reshape((1, 100))))
repr(DesignMatrix([np.nan, np.inf]))
repr(DesignMatrix([np.nan, 0, 1e20, 20.5]))
# handling of zero-size matrices
repr(DesignMatrix(np.zeros((1, 0))))
repr(DesignMatrix(np.zeros((0, 1))))
repr(DesignMatrix(np.zeros((0, 0))))
def test_design_matrix():
from nose.tools import assert_raises
di = DesignInfo(["a1", "a2", "a3", "b"])
mm = DesignMatrix([[12, 14, 16, 18]], di)
assert mm.design_info.column_names == ["a1", "a2", "a3", "b"]
bad_di = DesignInfo(["a1"])
assert_raises(ValueError, DesignMatrix, [[12, 14, 16, 18]], bad_di)
mm2 = DesignMatrix([[12, 14, 16, 18]])
assert mm2.design_info.column_names == ["column0", "column1", "column2",
"column3"]
mm3 = DesignMatrix([12, 14, 16, 18])
assert mm3.shape == (4, 1)
# DesignMatrix always has exactly 2 dimensions
assert_raises(ValueError, DesignMatrix, [[[1]]])
# DesignMatrix constructor passes through existing DesignMatrixes
mm4 = DesignMatrix(mm)
assert mm4 is mm
# But not if they are really slices:
mm5 = DesignMatrix(mm.diagonal())
assert mm5 is not mm
mm6 = DesignMatrix([[12, 14, 16, 18]], default_column_prefix="x")
assert mm6.design_info.column_names == ["x0", "x1", "x2", "x3"]
assert_no_pickling(mm6)
# Only real-valued matrices can be DesignMatrixs
assert_raises(ValueError, DesignMatrix, [1, 2, 3j])
assert_raises(ValueError, DesignMatrix, ["a", "b", "c"])
assert_raises(ValueError, DesignMatrix, [1, 2, object()])
# Just smoke tests
repr(mm)
repr(DesignMatrix(np.arange(100)))
repr(DesignMatrix(np.arange(100) * 2.0))
repr(mm[1:, :])
repr(DesignMatrix(np.arange(100).reshape((1, 100))))
repr(DesignMatrix([np.nan, np.inf]))
repr(DesignMatrix([np.nan, 0, 1e20, 20.5]))
# handling of zero-size matrices
repr(DesignMatrix(np.zeros((1, 0))))
repr(DesignMatrix(np.zeros((0, 1))))
repr(DesignMatrix(np.zeros((0, 0))))
def test_ModelDesc():
f1 = _MockFactor("a")
f2 = _MockFactor("b")
m = ModelDesc([INTERCEPT, Term([f1])], [Term([f1]), Term([f1, f2])])
assert m.lhs_termlist == [INTERCEPT, Term([f1])]
assert m.rhs_termlist == [Term([f1]), Term([f1, f2])]
print(m.describe())
assert m.describe() == "1 + a ~ 0 + a + a:b"
assert_no_pickling(m)
assert ModelDesc([], []).describe() == "~ 0"
assert ModelDesc([INTERCEPT], []).describe() == "1 ~ 0"
assert ModelDesc([INTERCEPT], [INTERCEPT]).describe() == "1 ~ 1"
assert (ModelDesc([INTERCEPT],
[INTERCEPT, Term([f2])]).describe() == "1 ~ b")
def test_ModelDesc():
f1 = _MockFactor("a")
f2 = _MockFactor("b")
m = ModelDesc([INTERCEPT, Term([f1])], [Term([f1]), Term([f1, f2])])
assert m.lhs_termlist == [INTERCEPT, Term([f1])]
assert m.rhs_termlist == [Term([f1]), Term([f1, f2])]
print(m.describe())
assert m.describe() == "1 + a ~ 0 + a + a:b"
assert_no_pickling(m)
assert ModelDesc([], []).describe() == "~ 0"
assert ModelDesc([INTERCEPT], []).describe() == "1 ~ 0"
assert ModelDesc([INTERCEPT], [INTERCEPT]).describe() == "1 ~ 1"
assert (ModelDesc([INTERCEPT], [INTERCEPT, Term([f2])]).describe()
== "1 ~ b")
def test_VarLookupDict():
d1 = {"a": 1}
d2 = {"a": 2, "b": 3}
ds = VarLookupDict([d1, d2])
assert ds["a"] == 1
assert ds["b"] == 3
assert "a" in ds
assert "c" not in ds
from nose.tools import assert_raises
assert_raises(KeyError, ds.__getitem__, "c")
ds["a"] = 10
assert ds["a"] == 10
assert d1["a"] == 1
assert ds.get("c") is None
assert isinstance(repr(ds), six.string_types)
assert_no_pickling(ds)
def test_VarLookupDict():
d1 = {"a": 1}
d2 = {"a": 2, "b": 3}
ds = VarLookupDict([d1, d2])
assert ds["a"] == 1
assert ds["b"] == 3
assert "a" in ds
assert "c" not in ds
import pytest
pytest.raises(KeyError, ds.__getitem__, "c")
ds["a"] = 10
assert ds["a"] == 10
assert d1["a"] == 1
assert ds.get("c") is None
assert isinstance(repr(ds), six.string_types)
assert_no_pickling(ds)
def test_C():
c1 = C("asdf")
assert isinstance(c1, _CategoricalBox)
assert c1.data == "asdf"
assert c1.levels is None
assert c1.contrast is None
c2 = C("DATA", "CONTRAST", "LEVELS")
assert c2.data == "DATA"
assert c2.contrast == "CONTRAST"
assert c2.levels == "LEVELS"
c3 = C(c2, levels="NEW LEVELS")
assert c3.data == "DATA"
assert c3.contrast == "CONTRAST"
assert c3.levels == "NEW LEVELS"
c4 = C(c2, "NEW CONTRAST")
assert c4.data == "DATA"
assert c4.contrast == "NEW CONTRAST"
assert c4.levels == "LEVELS"
assert_no_pickling(c4)
def test_C():
c1 = C("asdf")
assert isinstance(c1, _CategoricalBox)
assert c1.data == "asdf"
assert c1.levels is None
assert c1.contrast is None
c2 = C("DATA", "CONTRAST", "LEVELS")
assert c2.data == "DATA"
assert c2.contrast == "CONTRAST"
assert c2.levels == "LEVELS"
c3 = C(c2, levels="NEW LEVELS")
assert c3.data == "DATA"
assert c3.contrast == "CONTRAST"
assert c3.levels == "NEW LEVELS"
c4 = C(c2, "NEW CONTRAST")
assert c4.data == "DATA"
assert c4.contrast == "NEW CONTRAST"
assert c4.levels == "LEVELS"
assert_no_pickling(c4)
def test_Origin():
o1 = Origin("012345", 2, 4)
o2 = Origin("012345", 4, 5)
assert o1.caretize() == "012345\n ^^"
assert o2.caretize() == "012345\n ^"
o3 = Origin.combine([o1, o2])
assert o3.code == "012345"
assert o3.start == 2
assert o3.end == 5
assert o3.caretize(indent=2) == " 012345\n ^^^"
assert o3 == Origin("012345", 2, 5)
class ObjWithOrigin(object):
def __init__(self, origin=None):
self.origin = origin
o4 = Origin.combine([ObjWithOrigin(o1), ObjWithOrigin(), None])
assert o4 == o1
o5 = Origin.combine([ObjWithOrigin(o1), o2])
assert o5 == o3
assert Origin.combine([ObjWithOrigin(), ObjWithOrigin()]) is None
from patsy.util import assert_no_pickling
assert_no_pickling(Origin("", 0, 0))
def test_EvalEnvironment_capture_namespace():
c0, c, b1, b2, a1, a2 = _a()
assert "test_EvalEnvironment_capture_namespace" in c0.namespace
assert "test_EvalEnvironment_capture_namespace" in c.namespace
assert "test_EvalEnvironment_capture_namespace" in b1.namespace
assert "test_EvalEnvironment_capture_namespace" in b2.namespace
assert "test_EvalEnvironment_capture_namespace" in a1.namespace
assert "test_EvalEnvironment_capture_namespace" in a2.namespace
assert c0.namespace["_c"] == 1
assert c.namespace["_c"] == 1
assert b1.namespace["_b"] == 1
assert b2.namespace["_b"] == 1
assert a1.namespace["_a"] == 1
assert a2.namespace["_a"] == 1
assert b1.namespace["_c"] is _c
assert b2.namespace["_c"] is _c
from nose.tools import assert_raises
assert_raises(ValueError, EvalEnvironment.capture, 10 ** 6)
assert EvalEnvironment.capture(b1) is b1
assert_raises(TypeError, EvalEnvironment.capture, 1.2)
assert_no_pickling(EvalEnvironment.capture())
def test_EvalEnvironment_capture_namespace():
c0, c, b1, b2, a1, a2 = _a()
assert "test_EvalEnvironment_capture_namespace" in c0.namespace
assert "test_EvalEnvironment_capture_namespace" in c.namespace
assert "test_EvalEnvironment_capture_namespace" in b1.namespace
assert "test_EvalEnvironment_capture_namespace" in b2.namespace
assert "test_EvalEnvironment_capture_namespace" in a1.namespace
assert "test_EvalEnvironment_capture_namespace" in a2.namespace
assert c0.namespace["_c"] == 1
assert c.namespace["_c"] == 1
assert b1.namespace["_b"] == 1
assert b2.namespace["_b"] == 1
assert a1.namespace["_a"] == 1
assert a2.namespace["_a"] == 1
assert b1.namespace["_c"] is _c
assert b2.namespace["_c"] is _c
import pytest
pytest.raises(ValueError, EvalEnvironment.capture, 10**6)
assert EvalEnvironment.capture(b1) is b1
pytest.raises(TypeError, EvalEnvironment.capture, 1.2)
assert_no_pickling(EvalEnvironment.capture())
def test_DesignInfo():
from nose.tools import assert_raises
class _MockFactor(object):
def __init__(self, name):
self._name = name
def name(self):
return self._name
f_x = _MockFactor("x")
f_y = _MockFactor("y")
t_x = Term([f_x])
t_y = Term([f_y])
factor_infos = {f_x:
FactorInfo(f_x, "numerical", {}, num_columns=3),
f_y:
FactorInfo(f_y, "numerical", {}, num_columns=1),
}
term_codings = OrderedDict([(t_x, [SubtermInfo([f_x], {}, 3)]),
(t_y, [SubtermInfo([f_y], {}, 1)])])
di = DesignInfo(["x1", "x2", "x3", "y"], factor_infos, term_codings)
assert di.column_names == ["x1", "x2", "x3", "y"]
assert di.term_names == ["x", "y"]
assert di.terms == [t_x, t_y]
assert di.column_name_indexes == {"x1": 0, "x2": 1, "x3": 2, "y": 3}
assert di.term_name_slices == {"x": slice(0, 3), "y": slice(3, 4)}
assert di.term_slices == {t_x: slice(0, 3), t_y: slice(3, 4)}
assert di.describe() == "x + y"
assert di.slice(1) == slice(1, 2)
assert di.slice("x1") == slice(0, 1)
assert di.slice("x2") == slice(1, 2)
assert di.slice("x3") == slice(2, 3)
assert di.slice("x") == slice(0, 3)
assert di.slice(t_x) == slice(0, 3)
assert di.slice("y") == slice(3, 4)
assert di.slice(t_y) == slice(3, 4)
assert di.slice(slice(2, 4)) == slice(2, 4)
assert_raises(PatsyError, di.slice, "asdf")
# smoke test
repr(di)
assert_no_pickling(di)
# One without term objects
di = DesignInfo(["a1", "a2", "a3", "b"])
assert di.column_names == ["a1", "a2", "a3", "b"]
assert di.term_names == ["a1", "a2", "a3", "b"]
assert di.terms is None
assert di.column_name_indexes == {"a1": 0, "a2": 1, "a3": 2, "b": 3}
assert di.term_name_slices == {"a1": slice(0, 1),
"a2": slice(1, 2),
"a3": slice(2, 3),
"b": slice(3, 4)}
assert di.term_slices is None
assert di.describe() == "a1 + a2 + a3 + b"
assert di.slice(1) == slice(1, 2)
assert di.slice("a1") == slice(0, 1)
assert di.slice("a2") == slice(1, 2)
assert di.slice("a3") == slice(2, 3)
assert di.slice("b") == slice(3, 4)
# Check intercept handling in describe()
assert DesignInfo(["Intercept", "a", "b"]).describe() == "1 + a + b"
# Failure modes
# must specify either both or neither of factor_infos and term_codings:
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos=factor_infos)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], term_codings=term_codings)
# factor_infos must be a dict
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], list(factor_infos), term_codings)
# wrong number of column names:
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y1", "y2"], factor_infos, term_codings)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3"], factor_infos, term_codings)
# name overlap problems
assert_raises(ValueError, DesignInfo,
["x1", "x2", "y", "y2"], factor_infos, term_codings)
# duplicate name
assert_raises(ValueError, DesignInfo,
["x1", "x1", "x1", "y"], factor_infos, term_codings)
# f_y is in factor_infos, but not mentioned in any term
term_codings_x_only = OrderedDict(term_codings)
del term_codings_x_only[t_y]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3"], factor_infos, term_codings_x_only)
# f_a is in a term, but not in factor_infos
f_a = _MockFactor("a")
t_a = Term([f_a])
term_codings_with_a = OrderedDict(term_codings)
term_codings_with_a[t_a] = [SubtermInfo([f_a], {}, 1)]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y", "a"],
factor_infos, term_codings_with_a)
# bad factor_infos
not_factor_infos = dict(factor_infos)
not_factor_infos[f_x] = "what is this I don't even"
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], not_factor_infos, term_codings)
mismatch_factor_infos = dict(factor_infos)
mismatch_factor_infos[f_x] = FactorInfo(f_a, "numerical", {}, num_columns=3)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], mismatch_factor_infos, term_codings)
# bad term_codings
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, dict(term_codings))
not_term_codings = OrderedDict(term_codings)
not_term_codings["this is a string"] = term_codings[t_x]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, not_term_codings)
non_list_term_codings = OrderedDict(term_codings)
non_list_term_codings[t_y] = tuple(term_codings[t_y])
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, non_list_term_codings)
non_subterm_term_codings = OrderedDict(term_codings)
non_subterm_term_codings[t_y][0] = "not a SubtermInfo"
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, non_subterm_term_codings)
bad_subterm = OrderedDict(term_codings)
# f_x is a factor in this model, but it is not a factor in t_y
term_codings[t_y][0] = SubtermInfo([f_x], {}, 1)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, bad_subterm)
# contrast matrix has wrong number of rows
factor_codings_a = {f_a:
FactorInfo(f_a, "categorical", {},
categories=["a1", "a2"])}
term_codings_a_bad_rows = OrderedDict([
(t_a,
[SubtermInfo([f_a],
{f_a: ContrastMatrix(np.ones((3, 2)),
["[1]", "[2]"])},
2)])])
assert_raises(ValueError, DesignInfo,
["a[1]", "a[2]"],
factor_codings_a,
term_codings_a_bad_rows)
# have a contrast matrix for a non-categorical factor
t_ax = Term([f_a, f_x])
factor_codings_ax = {f_a:
FactorInfo(f_a, "categorical", {},
categories=["a1", "a2"]),
f_x:
FactorInfo(f_x, "numerical", {},
num_columns=2)}
term_codings_ax_extra_cm = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{f_a: ContrastMatrix(np.ones((2, 2)), ["[1]", "[2]"]),
f_x: ContrastMatrix(np.ones((2, 2)), ["[1]", "[2]"])},
4)])])
assert_raises(ValueError, DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[1]:x[2]", "a[2]:x[2]"],
factor_codings_ax,
term_codings_ax_extra_cm)
# no contrast matrix for a categorical factor
term_codings_ax_missing_cm = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{},
4)])])
# This actually fails before it hits the relevant check with a KeyError,
# but that's okay... the previous test still exercises the check.
assert_raises((ValueError, KeyError), DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[1]:x[2]", "a[2]:x[2]"],
factor_codings_ax,
term_codings_ax_missing_cm)
# subterm num_columns doesn't match the value computed from the individual
# factors
term_codings_ax_wrong_subterm_columns = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{f_a: ContrastMatrix(np.ones((2, 3)),
["[1]", "[2]", "[3]"])},
# should be 2 * 3 = 6
5)])])
assert_raises(ValueError, DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[3]:x[1]",
"a[1]:x[2]", "a[2]:x[2]", "a[3]:x[2]"],
factor_codings_ax,
term_codings_ax_wrong_subterm_columns)
def test_DesignInfo():
from nose.tools import assert_raises
class _MockFactor(object):
def __init__(self, name):
self._name = name
def name(self):
return self._name
f_x = _MockFactor("x")
f_y = _MockFactor("y")
t_x = Term([f_x])
t_y = Term([f_y])
factor_infos = {f_x:
FactorInfo(f_x, "numerical", {}, num_columns=3),
f_y:
FactorInfo(f_y, "numerical", {}, num_columns=1),
}
term_codings = OrderedDict([(t_x, [SubtermInfo([f_x], {}, 3)]),
(t_y, [SubtermInfo([f_y], {}, 1)])])
di = DesignInfo(["x1", "x2", "x3", "y"], factor_infos, term_codings)
assert di.column_names == ["x1", "x2", "x3", "y"]
assert di.term_names == ["x", "y"]
assert di.terms == [t_x, t_y]
assert di.column_name_indexes == {"x1": 0, "x2": 1, "x3": 2, "y": 3}
assert di.term_name_slices == {"x": slice(0, 3), "y": slice(3, 4)}
assert di.term_slices == {t_x: slice(0, 3), t_y: slice(3, 4)}
assert di.describe() == "x + y"
assert di.slice(1) == slice(1, 2)
assert di.slice("x1") == slice(0, 1)
assert di.slice("x2") == slice(1, 2)
assert di.slice("x3") == slice(2, 3)
assert di.slice("x") == slice(0, 3)
assert di.slice(t_x) == slice(0, 3)
assert di.slice("y") == slice(3, 4)
assert di.slice(t_y) == slice(3, 4)
assert di.slice(slice(2, 4)) == slice(2, 4)
assert_raises(PatsyError, di.slice, "asdf")
# smoke test
repr(di)
assert_no_pickling(di)
# One without term objects
di = DesignInfo(["a1", "a2", "a3", "b"])
assert di.column_names == ["a1", "a2", "a3", "b"]
assert di.term_names == ["a1", "a2", "a3", "b"]
assert di.terms is None
assert di.column_name_indexes == {"a1": 0, "a2": 1, "a3": 2, "b": 3}
assert di.term_name_slices == {"a1": slice(0, 1),
"a2": slice(1, 2),
"a3": slice(2, 3),
"b": slice(3, 4)}
assert di.term_slices is None
assert di.describe() == "a1 + a2 + a3 + b"
assert di.slice(1) == slice(1, 2)
assert di.slice("a1") == slice(0, 1)
assert di.slice("a2") == slice(1, 2)
assert di.slice("a3") == slice(2, 3)
assert di.slice("b") == slice(3, 4)
# Check intercept handling in describe()
assert DesignInfo(["Intercept", "a", "b"]).describe() == "1 + a + b"
# Failure modes
# must specify either both or neither of factor_infos and term_codings:
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos=factor_infos)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], term_codings=term_codings)
# factor_infos must be a dict
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], list(factor_infos), term_codings)
# wrong number of column names:
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y1", "y2"], factor_infos, term_codings)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3"], factor_infos, term_codings)
# name overlap problems
assert_raises(ValueError, DesignInfo,
["x1", "x2", "y", "y2"], factor_infos, term_codings)
# duplicate name
assert_raises(ValueError, DesignInfo,
["x1", "x1", "x1", "y"], factor_infos, term_codings)
# f_y is in factor_infos, but not mentioned in any term
term_codings_x_only = OrderedDict(term_codings)
del term_codings_x_only[t_y]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3"], factor_infos, term_codings_x_only)
# f_a is in a term, but not in factor_infos
f_a = _MockFactor("a")
t_a = Term([f_a])
term_codings_with_a = OrderedDict(term_codings)
term_codings_with_a[t_a] = [SubtermInfo([f_a], {}, 1)]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y", "a"],
factor_infos, term_codings_with_a)
# bad factor_infos
not_factor_infos = dict(factor_infos)
not_factor_infos[f_x] = "what is this I don't even"
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], not_factor_infos, term_codings)
mismatch_factor_infos = dict(factor_infos)
mismatch_factor_infos[f_x] = FactorInfo(f_a, "numerical", {}, num_columns=3)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], mismatch_factor_infos, term_codings)
# bad term_codings
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, dict(term_codings))
not_term_codings = OrderedDict(term_codings)
not_term_codings["this is a string"] = term_codings[t_x]
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, not_term_codings)
non_list_term_codings = OrderedDict(term_codings)
non_list_term_codings[t_y] = tuple(term_codings[t_y])
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, non_list_term_codings)
non_subterm_term_codings = OrderedDict(term_codings)
non_subterm_term_codings[t_y][0] = "not a SubtermInfo"
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, non_subterm_term_codings)
bad_subterm = OrderedDict(term_codings)
# f_x is a factor in this model, but it is not a factor in t_y
term_codings[t_y][0] = SubtermInfo([f_x], {}, 1)
assert_raises(ValueError, DesignInfo,
["x1", "x2", "x3", "y"], factor_infos, bad_subterm)
# contrast matrix has wrong number of rows
factor_codings_a = {f_a:
FactorInfo(f_a, "categorical", {},
categories=["a1", "a2"])}
term_codings_a_bad_rows = OrderedDict([
(t_a,
[SubtermInfo([f_a],
{f_a: ContrastMatrix(np.ones((3, 2)),
["[1]", "[2]"])},
2)])])
assert_raises(ValueError, DesignInfo,
["a[1]", "a[2]"],
factor_codings_a,
term_codings_a_bad_rows)
# have a contrast matrix for a non-categorical factor
t_ax = Term([f_a, f_x])
factor_codings_ax = {f_a:
FactorInfo(f_a, "categorical", {},
categories=["a1", "a2"]),
f_x:
FactorInfo(f_x, "numerical", {},
num_columns=2)}
term_codings_ax_extra_cm = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{f_a: ContrastMatrix(np.ones((2, 2)), ["[1]", "[2]"]),
f_x: ContrastMatrix(np.ones((2, 2)), ["[1]", "[2]"])},
4)])])
assert_raises(ValueError, DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[1]:x[2]", "a[2]:x[2]"],
factor_codings_ax,
term_codings_ax_extra_cm)
# no contrast matrix for a categorical factor
term_codings_ax_missing_cm = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{},
4)])])
# This actually fails before it hits the relevant check with a KeyError,
# but that's okay... the previous test still exercises the check.
assert_raises((ValueError, KeyError), DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[1]:x[2]", "a[2]:x[2]"],
factor_codings_ax,
term_codings_ax_missing_cm)
# subterm num_columns doesn't match the value computed from the individual
# factors
term_codings_ax_wrong_subterm_columns = OrderedDict([
(t_ax,
[SubtermInfo([f_a, f_x],
{f_a: ContrastMatrix(np.ones((2, 3)),
["[1]", "[2]", "[3]"])},
# should be 2 * 3 = 6
5)])])
assert_raises(ValueError, DesignInfo,
["a[1]:x[1]", "a[2]:x[1]", "a[3]:x[1]",
"a[1]:x[2]", "a[2]:x[2]", "a[3]:x[2]"],
factor_codings_ax,
term_codings_ax_wrong_subterm_columns)
