def transform(self, x, center=True, rescale=True, ddof=0):
# XX: this forces all inputs to double-precision real, even if the
# input is single- or extended-precision or complex. But I got all
# tangled up in knots trying to do that without breaking something
# else (e.g. by requiring an extra copy).
x = asarray_or_pandas(x, copy=True, dtype=float)
x_2d = atleast_2d_column_default(x, preserve_pandas=True)
if center:
x_2d -= self.current_mean
if rescale:
x_2d /= np.sqrt(self.current_M2 / (self.current_n - ddof))
return pandas_friendly_reshape(x_2d, x.shape)
def __init__(self, int_array, levels, contrast=None):
self.int_array = asarray_or_pandas(int_array, dtype=int)
if self.int_array.ndim != 1:
if self.int_array.ndim == 2 and self.int_array.shape[1] == 1:
new_shape = (self.int_array.shape[0],)
self.int_array = pandas_friendly_reshape(self.int_array,
new_shape)
else:
raise PatsyError("Categorical data must be 1 dimensional "
"or column vector")
self.levels = tuple(levels)
self.contrast = contrast
def transform(self, x, center=True, rescale=True, ddof=0):
# XX: this forces all inputs to double-precision real, even if the
# input is single- or extended-precision or complex. But I got all
# tangled up in knots trying to do that without breaking something
# else (e.g. by requiring an extra copy).
x = asarray_or_pandas(x, copy=True, dtype=float)
x_2d = atleast_2d_column_default(x, preserve_pandas=True)
if center:
x_2d -= self.current_mean
if rescale:
x_2d /= np.sqrt(self.current_M2 / (self.current_n - ddof))
return pandas_friendly_reshape(x_2d, x.shape)
def transform(self, x):
x = asarray_or_pandas(x)
# This doesn't copy data unless our input is a DataFrame that has
# heterogenous types. And in that case we're going to be munging the
# types anyway, so copying isn't a big deal.
x_arr = np.asarray(x)
if np.issubdtype(x_arr.dtype, np.integer):
dt = float
else:
dt = x_arr.dtype
mean_val = np.asarray(self._sum / self._count, dtype=dt)
centered = atleast_2d_column_default(x, preserve_pandas=True) - mean_val
return pandas_friendly_reshape(centered, x.shape)
def transform(self, x):
x = asarray_or_pandas(x)
# This doesn't copy data unless our input is a DataFrame that has
# heterogeneous types. And in that case we're going to be munging the
# types anyway, so copying isn't a big deal.
x_arr = np.asarray(x)
if safe_issubdtype(x_arr.dtype, np.integer):
dt = float
else:
dt = x_arr.dtype
mean_val = np.asarray(self._sum / self._count, dtype=dt)
centered = atleast_2d_column_default(x, preserve_pandas=True) - mean_val
return pandas_friendly_reshape(centered, x.shape)