def guess_categorical(data):
if safe_is_pandas_categorical(data):
return True
if isinstance(data, _CategoricalBox):
return True
data = np.asarray(data)
if safe_issubdtype(data.dtype, np.number):
return False
return True
def guess_categorical(data):
if safe_is_pandas_categorical(data):
return True
if isinstance(data, _CategoricalBox):
return True
data = np.asarray(data)
if safe_issubdtype(data.dtype, np.number):
return False
return True
def sniff(self, data):
if hasattr(data, "contrast"):
self._contrast = data.contrast
# returns a bool: are we confident that we found all the levels?
if isinstance(data, _CategoricalBox):
if data.levels is not None:
self._levels = tuple(data.levels)
return True
else:
# unbox and fall through
data = data.data
if safe_is_pandas_categorical(data):
# pandas.Categorical has its own NA detection, so don't try to
# second-guess it.
self._levels = tuple(pandas_Categorical_categories(data))
return True
# fastpath to avoid doing an item-by-item iteration over boolean
# arrays, as requested by #44
if hasattr(data, "dtype") and safe_issubdtype(data.dtype, np.bool_):
self._level_set = set([True, False])
return True
data = _categorical_shape_fix(data)
for value in data:
if self._NA_action.is_categorical_NA(value):
continue
if value is True or value is False:
self._level_set.update([True, False])
else:
try:
self._level_set.add(value)
except TypeError:
raise PatsyError("Error interpreting categorical data: "
"all items must be hashable",
self._origin)
# If everything we've seen is boolean, assume that everything else
# would be too. Otherwise we need to keep looking.
return self._level_set == set([True, False])
def sniff(self, data):
if hasattr(data, "contrast"):
self._contrast = data.contrast
# returns a bool: are we confident that we found all the levels?
if isinstance(data, _CategoricalBox):
if data.levels is not None:
self._levels = tuple(data.levels)
return True
else:
# unbox and fall through
data = data.data
if safe_is_pandas_categorical(data):
# pandas.Categorical has its own NA detection, so don't try to
# second-guess it.
self._levels = tuple(pandas_Categorical_categories(data))
return True
# fastpath to avoid doing an item-by-item iteration over boolean
# arrays, as requested by #44
if hasattr(data, "dtype") and safe_issubdtype(data.dtype, np.bool_):
self._level_set = set([True, False])
return True
data = _categorical_shape_fix(data)
for value in data:
if self._NA_action.is_categorical_NA(value):
continue
if value is True or value is False:
self._level_set.update([True, False])
else:
try:
self._level_set.add(value)
except TypeError:
raise PatsyError(
"Error interpreting categorical data: "
"all items must be hashable", self._origin)
# If everything we've seen is boolean, assume that everything else
# would be too. Otherwise we need to keep looking.
return self._level_set == set([True, False])
def categorical_to_int(data, levels, NA_action, origin=None):
assert isinstance(levels, tuple)
# In this function, missing values are always mapped to -1
if safe_is_pandas_categorical(data):
data_levels_tuple = tuple(pandas_Categorical_categories(data))
if not data_levels_tuple == levels:
raise PatsyError("mismatching levels: expected %r, got %r"
% (levels, data_levels_tuple), origin)
# pandas.Categorical also uses -1 to indicate NA, and we don't try to
# second-guess its NA detection, so we can just pass it back.
return pandas_Categorical_codes(data)
if isinstance(data, _CategoricalBox):
if data.levels is not None and tuple(data.levels) != levels:
raise PatsyError("mismatching levels: expected %r, got %r"
% (levels, tuple(data.levels)), origin)
data = data.data
data = _categorical_shape_fix(data)
try:
level_to_int = dict(zip(levels, range(len(levels))))
except TypeError:
raise PatsyError("Error interpreting categorical data: "
"all items must be hashable", origin)
# fastpath to avoid doing an item-by-item iteration over boolean arrays,
# as requested by #44
if hasattr(data, "dtype") and safe_issubdtype(data.dtype, np.bool_):
if level_to_int[False] == 0 and level_to_int[True] == 1:
return data.astype(np.int_)
out = np.empty(len(data), dtype=int)
for i, value in enumerate(data):
if NA_action.is_categorical_NA(value):
out[i] = -1
else:
try:
out[i] = level_to_int[value]
except KeyError:
SHOW_LEVELS = 4
level_strs = []
if len(levels) <= SHOW_LEVELS:
level_strs += [repr(level) for level in levels]
else:
level_strs += [repr(level)
for level in levels[:SHOW_LEVELS//2]]
level_strs.append("...")
level_strs += [repr(level)
for level in levels[-SHOW_LEVELS//2:]]
level_str = "[%s]" % (", ".join(level_strs))
raise PatsyError("Error converting data to categorical: "
"observation with value %r does not match "
"any of the expected levels (expected: %s)"
% (value, level_str), origin)
except TypeError:
raise PatsyError("Error converting data to categorical: "
"encountered unhashable value %r"
% (value,), origin)
if have_pandas and isinstance(data, pandas.Series):
out = pandas.Series(out, index=data.index)
return out
def categorical_to_int(data, levels, NA_action, origin=None):
assert isinstance(levels, tuple)
# In this function, missing values are always mapped to -1
if safe_is_pandas_categorical(data):
data_levels_tuple = tuple(pandas_Categorical_categories(data))
if not data_levels_tuple == levels:
raise PatsyError(
"mismatching levels: expected %r, got %r" %
(levels, data_levels_tuple), origin)
# pandas.Categorical also uses -1 to indicate NA, and we don't try to
# second-guess its NA detection, so we can just pass it back.
return pandas_Categorical_codes(data)
if isinstance(data, _CategoricalBox):
if data.levels is not None and tuple(data.levels) != levels:
raise PatsyError(
"mismatching levels: expected %r, got %r" %
(levels, tuple(data.levels)), origin)
data = data.data
data = _categorical_shape_fix(data)
try:
level_to_int = dict(zip(levels, range(len(levels))))
except TypeError:
raise PatsyError(
"Error interpreting categorical data: "
"all items must be hashable", origin)
# fastpath to avoid doing an item-by-item iteration over boolean arrays,
# as requested by #44
if hasattr(data, "dtype") and safe_issubdtype(data.dtype, np.bool_):
if level_to_int[False] == 0 and level_to_int[True] == 1:
return data.astype(np.int_)
out = np.empty(len(data), dtype=int)
for i, value in enumerate(data):
if NA_action.is_categorical_NA(value):
out[i] = -1
else:
try:
out[i] = level_to_int[value]
except KeyError:
SHOW_LEVELS = 4
level_strs = []
if len(levels) <= SHOW_LEVELS:
level_strs += [repr(level) for level in levels]
else:
level_strs += [
repr(level) for level in levels[:SHOW_LEVELS // 2]
]
level_strs.append("...")
level_strs += [
repr(level) for level in levels[-SHOW_LEVELS // 2:]
]
level_str = "[%s]" % (", ".join(level_strs))
raise PatsyError(
"Error converting data to categorical: "
"observation with value %r does not match "
"any of the expected levels (expected: %s)" %
(value, level_str), origin)
except TypeError:
raise PatsyError(
"Error converting data to categorical: "
"encountered unhashable value %r" % (value, ), origin)
if have_pandas and isinstance(data, pandas.Series):
out = pandas.Series(out, index=data.index)
return out