def numpy_to_dummies(endog):
from sm2.tools import tools
if endog.dtype.kind in ['S', 'O']:
endog_dummies, ynames = tools.categorical(endog, drop=True,
dictnames=True)
elif endog.ndim == 2:
endog_dummies = endog
ynames = range(endog.shape[1])
else:
endog_dummies, ynames = tools.categorical(endog, drop=True,
dictnames=True)
return endog_dummies, ynames
def test_categorical_recarray_2names():
# GH#302
arr = np.rec.fromrecords([[10, 12], [11, 13]], names=['group', 'whatever'])
actual = tools.categorical(arr, col=['group'])
expected = np.rec.array([(10, 12, 1.0, 0.0), (11, 13, 0.0, 1.0)],
dtype=[('group', int), ('whatever', int),
('group_10', float), ('group_11', float)])
assert_array_equal(actual, expected)
def test_categorical_recarray_1names():
# GH#302
arr = np.rec.fromrecords([[10], [11]], names='group')
actual = tools.categorical(arr)
expected = np.rec.array([(10, 1.0, 0.0), (11, 0.0, 1.0)],
dtype=[('group', int), ('group_10', float),
('group_11', float)])
assert_array_equal(actual, expected)
def test_const_indicator():
np.random.seed(12345)
X = np.random.randint(0, 3, size=30)
X = categorical(X, drop=True)
y = np.dot(X, [1., 2., 3.]) + np.random.normal(size=30)
modc = OLS(y, add_constant(X[:, 1:], prepend=True)).fit()
mod = OLS(y, X, hasconst=True).fit()
assert_almost_equal(modc.rsquared, mod.rsquared, 12)
def test_structarray1d_drop(self):
instr = self.structdes['str_instr'].view(dtype=[('var1', 'a10')])
dum = tools.categorical(instr, drop=True)
test_dum = np.column_stack(([dum[_] for _ in dum.dtype.names]))
assert_array_equal(test_dum, self.dummy)
assert_equal(len(dum.dtype.names), 5)
def test_structarray2d_drop(self):
des = tools.categorical(self.structdes, col='str_instr', drop=True)
test_des = np.column_stack(([des[_] for _ in des.dtype.names[-5:]]))
assert_array_equal(test_des, self.dummy)
assert_equal(len(des.dtype.names), 8)
def test_structarray2dint(self):
des = tools.categorical(self.structdes, col=3)
test_des = np.column_stack(([des[_] for _ in des.dtype.names[-5:]]))
assert_array_equal(test_des, self.dummy)
assert_equal(len(des.dtype.names), 9)
def test_recarray1d(self):
instr = self.structdes['str_instr'].view(np.recarray)
dum = tools.categorical(instr)
test_dum = np.column_stack(([dum[_] for _ in dum.dtype.names[-5:]]))
assert_array_equal(test_dum, self.dummy)
assert_equal(len(dum.dtype.names), 6)
def test_recarray2d(self):
des = tools.categorical(self.recdes, col='str_instr')
# better way to do this?
test_des = np.column_stack(([des[_] for _ in des.dtype.names[-5:]]))
assert_array_equal(test_des, self.dummy)
assert_equal(len(des.dtype.names), 9)
def test_array1d_drop(self):
des = tools.categorical(self.string_var, drop=True)
assert_array_equal(des, self.dummy)
assert_equal(des.shape[1], 5)
def test_structarray1d(self):
instr = self.structdes['instrument'].view(dtype=[('var1', 'f4')])
dum = tools.categorical(instr)
test_dum = np.column_stack(([dum[_] for _ in dum.dtype.names[-5:]]))
assert_array_equal(test_dum, self.dummy)
assert_equal(len(dum.dtype.names), 6)
def test_recarray1d_drop(self):
instr = self.structdes['instrument'].view(np.recarray)
dum = tools.categorical(instr, drop=True)
test_dum = np.column_stack(([dum[_] for _ in dum.dtype.names]))
assert_array_equal(test_dum, self.dummy)
assert_equal(len(dum.dtype.names), 5)
def test_array2d_drop(self):
des = np.column_stack((self.des, self.instr, self.des))
des = tools.categorical(des, col=2, drop=True)
assert_array_equal(des[:, -5:], self.dummy)
assert_equal(des.shape[1], 9)
def test_array1d(self):
des = tools.categorical(self.instr)
assert_array_equal(des[:, -5:], self.dummy)
assert_equal(des.shape[1], 6)
