def _try_incr_builders(formula_like, data_iter_maker, eval_env):
if isinstance(formula_like, DesignMatrixBuilder):
return (design_matrix_builders([[]], data_iter_maker)[0],
formula_like)
if (isinstance(formula_like, tuple)
and len(formula_like) == 2
and isinstance(formula_like[0], DesignMatrixBuilder)
and isinstance(formula_like[1], DesignMatrixBuilder)):
return formula_like
if hasattr(formula_like, "__patsy_get_model_desc__"):
formula_like = formula_like.__patsy_get_model_desc__(eval_env)
if not isinstance(formula_like, ModelDesc):
raise PatsyError("bad value from %r.__patsy_get_model_desc__"
% (formula_like,))
# fallthrough
if isinstance(formula_like, basestring):
eval_env = _get_env(eval_env)
formula_like = ModelDesc.from_formula(formula_like, eval_env)
# fallthrough
if isinstance(formula_like, ModelDesc):
return design_matrix_builders([formula_like.lhs_termlist,
formula_like.rhs_termlist],
data_iter_maker)
else:
return None
def _try_incr_builders(formula_like, data_iter_maker, eval_env,
NA_action):
if isinstance(formula_like, DesignInfo):
return (design_matrix_builders([[]], data_iter_maker, eval_env, NA_action)[0],
formula_like)
if (isinstance(formula_like, tuple)
and len(formula_like) == 2
and isinstance(formula_like[0], DesignInfo)
and isinstance(formula_like[1], DesignInfo)):
return formula_like
if hasattr(formula_like, "__patsy_get_model_desc__"):
formula_like = formula_like.__patsy_get_model_desc__(eval_env)
if not isinstance(formula_like, ModelDesc):
raise PatsyError("bad value from %r.__patsy_get_model_desc__"
% (formula_like,))
# fallthrough
if isinstance(formula_like, str):
formula_like = ModelDesc.from_formula(formula_like)
# fallthrough
if isinstance(formula_like, ModelDesc):
assert isinstance(eval_env, EvalEnvironment)
return design_matrix_builders([formula_like.lhs_termlist,
formula_like.rhs_termlist],
data_iter_maker,
eval_env,
NA_action)
else:
return None
def _try_incr_builders(formula_like, data_iter_maker, eval_env,
NA_action):
if isinstance(formula_like, DesignInfo):
return (design_matrix_builders([[]], data_iter_maker, eval_env, NA_action)[0],
formula_like)
if (isinstance(formula_like, tuple)
and len(formula_like) == 2
and isinstance(formula_like[0], DesignInfo)
and isinstance(formula_like[1], DesignInfo)):
return formula_like
if hasattr(formula_like, "__patsy_get_model_desc__"):
formula_like = formula_like.__patsy_get_model_desc__(eval_env)
if not isinstance(formula_like, ModelDesc):
raise PatsyError("bad value from %r.__patsy_get_model_desc__"
% (formula_like,))
# fallthrough
if not six.PY3 and isinstance(formula_like, unicode):
# Included for the convenience of people who are using py2 with
# __future__.unicode_literals.
try:
formula_like = formula_like.encode("ascii")
except UnicodeEncodeError:
raise PatsyError(
"On Python 2, formula strings must be either 'str' objects, "
"or else 'unicode' objects containing only ascii "
"characters. You passed a unicode string with non-ascii "
"characters. I'm afraid you'll have to either switch to "
"ascii-only, or else upgrade to Python 3.")
if isinstance(formula_like, str):
formula_like = ModelDesc.from_formula(formula_like)
# fallthrough
if isinstance(formula_like, ModelDesc):
assert isinstance(eval_env, EvalEnvironment)
return design_matrix_builders([formula_like.lhs_termlist,
formula_like.rhs_termlist],
data_iter_maker,
eval_env,
NA_action)
else:
return None
def _try_incr_builders(formula_like, data_iter_maker, eval_env, NA_action):
if isinstance(formula_like, DesignMatrixBuilder):
return (design_matrix_builders([[]], data_iter_maker,
NA_action)[0], formula_like)
if (isinstance(formula_like, tuple) and len(formula_like) == 2
and isinstance(formula_like[0], DesignMatrixBuilder)
and isinstance(formula_like[1], DesignMatrixBuilder)):
return formula_like
if hasattr(formula_like, "__patsy_get_model_desc__"):
formula_like = formula_like.__patsy_get_model_desc__(eval_env)
if not isinstance(formula_like, ModelDesc):
raise PatsyError("bad value from %r.__patsy_get_model_desc__" %
(formula_like, ))
# fallthrough
if isinstance(formula_like, basestring):
assert isinstance(eval_env, EvalEnvironment)
formula_like = ModelDesc.from_formula(formula_like, eval_env)
# fallthrough
if isinstance(formula_like, ModelDesc):
return design_matrix_builders(
[formula_like.lhs_termlist, formula_like.rhs_termlist],
data_iter_maker, NA_action)
else:
return None
def _try_incr_builders(formula_like, data_iter_maker, eval_env, NA_action):
if isinstance(formula_like, DesignInfo):
return (design_matrix_builders([[]], data_iter_maker, eval_env,
NA_action)[0], formula_like)
if (isinstance(formula_like, tuple) and len(formula_like) == 2
and isinstance(formula_like[0], DesignInfo)
and isinstance(formula_like[1], DesignInfo)):
return formula_like
if hasattr(formula_like, "__patsy_get_model_desc__"):
formula_like = formula_like.__patsy_get_model_desc__(eval_env)
if not isinstance(formula_like, ModelDesc):
raise PatsyError("bad value from %r.__patsy_get_model_desc__" %
(formula_like, ))
# fallthrough
if not six.PY3 and isinstance(formula_like, unicode):
# Included for the convenience of people who are using py2 with
# __future__.unicode_literals.
try:
formula_like = formula_like.encode("ascii")
except UnicodeEncodeError:
raise PatsyError(
"On Python 2, formula strings must be either 'str' objects, "
"or else 'unicode' objects containing only ascii "
"characters. You passed a unicode string with non-ascii "
"characters. I'm afraid you'll have to either switch to "
"ascii-only, or else upgrade to Python 3.")
if isinstance(formula_like, str):
formula_like = ModelDesc.from_formula(formula_like)
# fallthrough
if isinstance(formula_like, ModelDesc):
assert isinstance(eval_env, EvalEnvironment)
return design_matrix_builders(
[formula_like.lhs_termlist, formula_like.rhs_termlist],
data_iter_maker, eval_env, NA_action)
else:
return None
def test_formula_likes():
# Plain array-like, rhs only
t([[1, 2, 3], [4, 5, 6]], {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t((None, [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t(np.asarray([[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
t((None, np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
t(dm, {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"])
t((None, dm), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"])
# Plain array-likes, lhs and rhs
t(([1, 2], [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t(([[1], [2]], [[1, 2, 3], [4, 5, 6]]), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t((np.asarray([1, 2]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
t((np.asarray([[1], [2]]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"],
[[1], [2]], ["y0"])
x_dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
y_dm = DesignMatrix([1, 2], default_column_prefix="bar")
t((y_dm, x_dm), {}, 0,
False,
[[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"],
[[1], [2]], ["bar0"])
# number of rows must match
t_invalid(([1, 2, 3], [[1, 2, 3], [4, 5, 6]]), {}, 0)
# tuples must have the right size
t_invalid(([[1, 2, 3]],), {}, 0)
t_invalid(([[1, 2, 3]], [[1, 2, 3]], [[1, 2, 3]]), {}, 0)
# plain Series and DataFrames
if have_pandas:
# Names are extracted
t(pandas.DataFrame({"x": [1, 2, 3]}), {}, 0,
False,
[[1], [2], [3]], ["x"])
t(pandas.Series([1, 2, 3], name="asdf"), {}, 0,
False,
[[1], [2], [3]], ["asdf"])
t((pandas.DataFrame({"y": [4, 5, 6]}),
pandas.DataFrame({"x": [1, 2, 3]})), {}, 0,
False,
[[1], [2], [3]], ["x"],
[[4], [5], [6]], ["y"])
t((pandas.Series([4, 5, 6], name="y"),
pandas.Series([1, 2, 3], name="x")), {}, 0,
False,
[[1], [2], [3]], ["x"],
[[4], [5], [6]], ["y"])
# Or invented
t((pandas.DataFrame([[4, 5, 6]]),
pandas.DataFrame([[1, 2, 3]], columns=[7, 8, 9])), {}, 0,
False,
[[1, 2, 3]], ["x7", "x8", "x9"],
[[4, 5, 6]], ["y0", "y1", "y2"])
t(pandas.Series([1, 2, 3]), {}, 0,
False,
[[1], [2], [3]], ["x0"])
# indices must match
t_invalid((pandas.DataFrame([[1]], index=[1]),
pandas.DataFrame([[1]], index=[2])),
{}, 0)
# Foreign ModelDesc factories
class ForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return ModelDesc([Term([LookupFactor("Y")])],
[Term([LookupFactor("X")])])
foreign_model = ForeignModelSource()
t(foreign_model,
{"Y": [1, 2],
"X": [[1, 2], [3, 4]]},
0,
True,
[[1, 2], [3, 4]], ["X[0]", "X[1]"],
[[1], [2]], ["Y"])
class BadForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return data
t_invalid(BadForeignModelSource(), {}, 0)
# string formulas
t("y ~ x", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3], [1, 4]], ["Intercept", "x"],
[[1], [2]], ["y"])
t("~ x", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3], [1, 4]], ["Intercept", "x"])
t("x + y", {"y": [1, 2], "x": [3, 4]}, 0,
True,
[[1, 3, 1], [1, 4, 2]], ["Intercept", "x", "y"])
# ModelDesc
desc = ModelDesc([], [Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0,
True,
[[1.5], [2.5], [3.5]], ["x"])
desc = ModelDesc([], [Term([]), Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0,
True,
[[1, 1.5], [1, 2.5], [1, 3.5]], ["Intercept", "x"])
desc = ModelDesc([Term([LookupFactor("y")])],
[Term([]), Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5], "y": [10, 20, 30]}, 0,
True,
[[1, 1.5], [1, 2.5], [1, 3.5]], ["Intercept", "x"],
[[10], [20], [30]], ["y"])
# builders
termlists = ([],
[Term([LookupFactor("x")])],
[Term([]), Term([LookupFactor("x")])],
)
builders = design_matrix_builders(termlists,
lambda: iter([{"x": [1, 2, 3]}]))
# twople but with no LHS
t((builders[0], builders[2]), {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"])
# single DesignMatrixBuilder
t(builders[2], {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"])
# twople with LHS
t((builders[1], builders[2]), {"x": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"],
[[10], [20], [30]], ["x"])
# check depth arguments
x_in_env = [1, 2, 3]
t("~ x_in_env", {}, 0,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
t("~ x_in_env", {"x_in_env": [10, 20, 30]}, 0,
True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x_in_env"])
# Trying to pull x_in_env out of our *caller* shouldn't work.
t_invalid("~ x_in_env", {}, 1, exc=(NameError, PatsyError))
# But then again it should, if called from one down on the stack:
def check_nested_call():
x_in_env = "asdf"
t("~ x_in_env", {}, 1,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
check_nested_call()
# passing in an explicit EvalEnvironment also works:
e = EvalEnvironment.capture(1)
t_invalid("~ x_in_env", {}, e, exc=(NameError, PatsyError))
e = EvalEnvironment.capture(0)
def check_nested_call_2():
x_in_env = "asdf"
t("~ x_in_env", {}, e,
True,
[[1, 1], [1, 2], [1, 3]], ["Intercept", "x_in_env"])
check_nested_call_2()
def test_formula_likes():
# Plain array-like, rhs only
t([[1, 2, 3], [4, 5, 6]], {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["x0", "x1", "x2"])
t((None, [[1, 2, 3], [4, 5, 6]]), {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["x0", "x1", "x2"])
t(np.asarray([[1, 2, 3], [4, 5, 6]]), {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["x0", "x1", "x2"])
t((None, np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0, False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"])
dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
t(dm, {}, 0, False, [[1, 2, 3], [4, 5, 6]], ["foo0", "foo1", "foo2"])
t((None, dm), {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["foo0", "foo1", "foo2"])
# Plain array-likes, lhs and rhs
t(([1, 2], [[1, 2, 3], [4, 5, 6]]), {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["x0", "x1", "x2"], [[1], [2]], ["y0"])
t(([[1], [2]], [[1, 2, 3], [4, 5, 6]]), {}, 0, False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"], [[1], [2]], ["y0"])
t((np.asarray([1, 2]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0, False,
[[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"], [[1], [2]], ["y0"])
t((np.asarray([[1], [2]]), np.asarray([[1, 2, 3], [4, 5, 6]])), {}, 0,
False, [[1, 2, 3], [4, 5, 6]], ["x0", "x1", "x2"], [[1], [2]], ["y0"])
x_dm = DesignMatrix([[1, 2, 3], [4, 5, 6]], default_column_prefix="foo")
y_dm = DesignMatrix([1, 2], default_column_prefix="bar")
t((y_dm, x_dm), {}, 0, False, [[1, 2, 3], [4, 5, 6]],
["foo0", "foo1", "foo2"], [[1], [2]], ["bar0"])
# number of rows must match
t_invalid(([1, 2, 3], [[1, 2, 3], [4, 5, 6]]), {}, 0)
# tuples must have the right size
t_invalid(([[1, 2, 3]], ), {}, 0)
t_invalid(([[1, 2, 3]], [[1, 2, 3]], [[1, 2, 3]]), {}, 0)
# plain Series and DataFrames
if have_pandas:
# Names are extracted
t(pandas.DataFrame({"x": [1, 2, 3]}), {}, 0, False, [[1], [2], [3]],
["x"])
t(pandas.Series([1, 2, 3], name="asdf"), {}, 0, False, [[1], [2], [3]],
["asdf"])
t((pandas.DataFrame({"y": [4, 5, 6]
}), pandas.DataFrame({"x": [1, 2, 3]})), {}, 0,
False, [[1], [2], [3]], ["x"], [[4], [5], [6]], ["y"])
t((pandas.Series([4, 5, 6],
name="y"), pandas.Series([1, 2, 3], name="x")), {}, 0,
False, [[1], [2], [3]], ["x"], [[4], [5], [6]], ["y"])
# Or invented
t((pandas.DataFrame([[4, 5, 6]]),
pandas.DataFrame([[1, 2, 3]], columns=[7, 8, 9])), {}, 0, False,
[[1, 2, 3]], ["x7", "x8", "x9"], [[4, 5, 6]], ["y0", "y1", "y2"])
t(pandas.Series([1, 2, 3]), {}, 0, False, [[1], [2], [3]], ["x0"])
# indices must match
t_invalid((pandas.DataFrame(
[[1]], index=[1]), pandas.DataFrame([[1]], index=[2])), {}, 0)
# Foreign ModelDesc factories
class ForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return ModelDesc([Term([LookupFactor("Y")])],
[Term([LookupFactor("X")])])
foreign_model = ForeignModelSource()
t(foreign_model, {
"Y": [1, 2],
"X": [[1, 2], [3, 4]]
}, 0, True, [[1, 2], [3, 4]], ["X[0]", "X[1]"], [[1], [2]], ["Y"])
class BadForeignModelSource(object):
def __patsy_get_model_desc__(self, data):
return data
t_invalid(BadForeignModelSource(), {}, 0)
# string formulas
t("y ~ x", {
"y": [1, 2],
"x": [3, 4]
}, 0, True, [[1, 3], [1, 4]], ["Intercept", "x"], [[1], [2]], ["y"])
t("~ x", {
"y": [1, 2],
"x": [3, 4]
}, 0, True, [[1, 3], [1, 4]], ["Intercept", "x"])
t("x + y", {
"y": [1, 2],
"x": [3, 4]
}, 0, True, [[1, 3, 1], [1, 4, 2]], ["Intercept", "x", "y"])
# ModelDesc
desc = ModelDesc([], [Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0, True, [[1.5], [2.5], [3.5]], ["x"])
desc = ModelDesc([], [Term([]), Term([LookupFactor("x")])])
t(desc, {"x": [1.5, 2.5, 3.5]}, 0, True, [[1, 1.5], [1, 2.5], [1, 3.5]],
["Intercept", "x"])
desc = ModelDesc([Term([LookupFactor("y")])],
[Term([]), Term([LookupFactor("x")])])
t(desc, {
"x": [1.5, 2.5, 3.5],
"y": [10, 20, 30]
}, 0, True, [[1, 1.5], [1, 2.5], [1, 3.5]], ["Intercept", "x"],
[[10], [20], [30]], ["y"])
# builders
termlists = (
[],
[Term([LookupFactor("x")])],
[Term([]), Term([LookupFactor("x")])],
)
builders = design_matrix_builders(termlists, lambda: iter([{
"x": [1, 2, 3]
}]))
# twople but with no LHS
t((builders[0], builders[2]), {"x": [10, 20, 30]}, 0, True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"])
# single DesignMatrixBuilder
t(builders[2], {"x": [10, 20, 30]}, 0, True, [[1, 10], [1, 20], [1, 30]],
["Intercept", "x"])
# twople with LHS
t((builders[1], builders[2]), {"x": [10, 20, 30]}, 0, True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x"], [[10], [20], [30]],
["x"])
# check depth arguments
x_in_env = [1, 2, 3]
t("~ x_in_env", {}, 0, True, [[1, 1], [1, 2], [1, 3]],
["Intercept", "x_in_env"])
t("~ x_in_env", {"x_in_env": [10, 20, 30]}, 0, True,
[[1, 10], [1, 20], [1, 30]], ["Intercept", "x_in_env"])
# Trying to pull x_in_env out of our *caller* shouldn't work.
t_invalid("~ x_in_env", {}, 1, exc=(NameError, PatsyError))
# But then again it should, if called from one down on the stack:
def check_nested_call():
x_in_env = "asdf"
t("~ x_in_env", {}, 1, True, [[1, 1], [1, 2], [1, 3]],
["Intercept", "x_in_env"])
check_nested_call()
# passing in an explicit EvalEnvironment also works:
e = EvalEnvironment.capture(1)
t_invalid("~ x_in_env", {}, e, exc=(NameError, PatsyError))
e = EvalEnvironment.capture(0)
def check_nested_call_2():
x_in_env = "asdf"
t("~ x_in_env", {}, e, True, [[1, 1], [1, 2], [1, 3]],
["Intercept", "x_in_env"])
check_nested_call_2()
