def _eval_factor(factor_info, data, NA_action):
factor = factor_info.factor
result = factor.eval(factor_info.state, data)
# Returns either a 2d ndarray, or a DataFrame, plus is_NA mask
if factor_info.type == "numerical":
result = atleast_2d_column_default(result, preserve_pandas=True)
_max_allowed_dim(2, result, factor)
if result.shape[1] != factor_info.num_columns:
raise PatsyError("when evaluating factor %s, I got %s columns "
"instead of the %s I was expecting"
% (factor.name(),
factor_info.num_columns,
result.shape[1]),
factor)
if not safe_issubdtype(np.asarray(result).dtype, np.number):
raise PatsyError("when evaluating numeric factor %s, "
"I got non-numeric data of type '%s'"
% (factor.name(), result.dtype),
factor)
return result, NA_action.is_numerical_NA(result)
# returns either a 1d ndarray or a pandas.Series, plus is_NA mask
else:
assert factor_info.type == "categorical"
result = categorical_to_int(result, factor_info.categories, NA_action,
origin=factor_info.factor)
assert result.ndim == 1
return result, np.asarray(result == -1)
def eval(self, data, NA_action):
result = self.factor.eval(self._state, data)
result = categorical_to_int(result,
self._levels,
NA_action,
origin=self.factor)
assert result.ndim == 1
return result, np.asarray(result == -1)
def eval(self, data, NA_action):
result = self.factor.eval(self._state, data)
result = categorical_to_int(result, self._levels, NA_action,
origin=self.factor)
assert result.ndim == 1
return result, np.asarray(result == -1)
