def test_remove_categories(self):
cat = Categorical(["a", "b", "c", "a"], ordered=True)
old = cat.copy()
new = Categorical(["a", "b", np.nan, "a"], categories=["a", "b"],
ordered=True)
# first inplace == False
res = cat.remove_categories("c")
tm.assert_categorical_equal(cat, old)
tm.assert_categorical_equal(res, new)
res = cat.remove_categories(["c"])
tm.assert_categorical_equal(cat, old)
tm.assert_categorical_equal(res, new)
# inplace == True
res = cat.remove_categories("c", inplace=True)
tm.assert_categorical_equal(cat, new)
assert res is None
# removal is not in categories
def f():
cat.remove_categories(["c"])
pytest.raises(ValueError, f)
def test_set_ordered(self):
cat = Categorical(["a", "b", "c", "a"], ordered=True)
cat2 = cat.as_unordered()
assert not cat2.ordered
cat2 = cat.as_ordered()
assert cat2.ordered
cat2.as_unordered(inplace=True)
assert not cat2.ordered
cat2.as_ordered(inplace=True)
assert cat2.ordered
assert cat2.set_ordered(True).ordered
assert not cat2.set_ordered(False).ordered
cat2.set_ordered(True, inplace=True)
assert cat2.ordered
cat2.set_ordered(False, inplace=True)
assert not cat2.ordered
# removed in 0.19.0
msg = "can\'t set attribute"
with tm.assert_raises_regex(AttributeError, msg):
cat.ordered = True
with tm.assert_raises_regex(AttributeError, msg):
cat.ordered = False
def test_rename_categories(self):
cat = Categorical(["a", "b", "c", "a"])
# inplace=False: the old one must not be changed
res = cat.rename_categories([1, 2, 3])
tm.assert_numpy_array_equal(res.__array__(), np.array([1, 2, 3, 1],
dtype=np.int64))
tm.assert_index_equal(res.categories, Index([1, 2, 3]))
exp_cat = np.array(["a", "b", "c", "a"], dtype=np.object_)
tm.assert_numpy_array_equal(cat.__array__(), exp_cat)
exp_cat = Index(["a", "b", "c"])
tm.assert_index_equal(cat.categories, exp_cat)
# GH18862 (let rename_categories take callables)
result = cat.rename_categories(lambda x: x.upper())
expected = Categorical(["A", "B", "C", "A"])
tm.assert_categorical_equal(result, expected)
# and now inplace
res = cat.rename_categories([1, 2, 3], inplace=True)
assert res is None
tm.assert_numpy_array_equal(cat.__array__(), np.array([1, 2, 3, 1],
dtype=np.int64))
tm.assert_index_equal(cat.categories, Index([1, 2, 3]))
# Lengthen
with pytest.raises(ValueError):
cat.rename_categories([1, 2, 3, 4])
# Shorten
with pytest.raises(ValueError):
cat.rename_categories([1, 2])
def test_codes_immutable(self):
# Codes should be read only
c = Categorical(["a", "b", "c", "a", np.nan])
exp = np.array([0, 1, 2, 0, -1], dtype='int8')
tm.assert_numpy_array_equal(c.codes, exp)
# Assignments to codes should raise
def f():
c.codes = np.array([0, 1, 2, 0, 1], dtype='int8')
pytest.raises(ValueError, f)
# changes in the codes array should raise
# np 1.6.1 raises RuntimeError rather than ValueError
codes = c.codes
def f():
codes[4] = 1
pytest.raises(ValueError, f)
# But even after getting the codes, the original array should still be
# writeable!
c[4] = "a"
exp = np.array([0, 1, 2, 0, 0], dtype='int8')
tm.assert_numpy_array_equal(c.codes, exp)
c._codes[4] = 2
exp = np.array([0, 1, 2, 0, 2], dtype='int8')
tm.assert_numpy_array_equal(c.codes, exp)
def test_groupby_categorical_index(self):
s = np.random.RandomState(12345)
levels = ['foo', 'bar', 'baz', 'qux']
codes = s.randint(0, 4, size=20)
cats = Categorical.from_codes(codes, levels, ordered=True)
df = DataFrame(
np.repeat(
np.arange(20), 4).reshape(-1, 4), columns=list('abcd'))
df['cats'] = cats
# with a cat index
result = df.set_index('cats').groupby(level=0).sum()
expected = df[list('abcd')].groupby(cats.codes).sum()
expected.index = CategoricalIndex(
Categorical.from_codes(
[0, 1, 2, 3], levels, ordered=True), name='cats')
assert_frame_equal(result, expected)
# with a cat column, should produce a cat index
result = df.groupby('cats').sum()
expected = df[list('abcd')].groupby(cats.codes).sum()
expected.index = CategoricalIndex(
Categorical.from_codes(
[0, 1, 2, 3], levels, ordered=True), name='cats')
assert_frame_equal(result, expected)
def test_groupby_categorical_no_compress(self):
data = Series(np.random.randn(9))
codes = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2])
cats = Categorical.from_codes(codes, [0, 1, 2], ordered=True)
result = data.groupby(cats).mean()
exp = data.groupby(codes).mean()
exp.index = CategoricalIndex(exp.index, categories=cats.categories,
ordered=cats.ordered)
assert_series_equal(result, exp)
codes = np.array([0, 0, 0, 1, 1, 1, 3, 3, 3])
cats = Categorical.from_codes(codes, [0, 1, 2, 3], ordered=True)
result = data.groupby(cats).mean()
exp = data.groupby(codes).mean().reindex(cats.categories)
exp.index = CategoricalIndex(exp.index, categories=cats.categories,
ordered=cats.ordered)
assert_series_equal(result, exp)
cats = Categorical(["a", "a", "a", "b", "b", "b", "c", "c", "c"],
categories=["a", "b", "c", "d"], ordered=True)
data = DataFrame({"a": [1, 1, 1, 2, 2, 2, 3, 4, 5], "b": cats})
result = data.groupby("b").mean()
result = result["a"].values
exp = np.array([1, 2, 4, np.nan])
tm.assert_numpy_array_equal(result, exp)
def test_shift(fill_value):
ct = Categorical(['a', 'b', 'c', 'd'],
categories=['a', 'b', 'c', 'd'], ordered=False)
expected = Categorical([None, 'a', 'b', 'c'],
categories=['a', 'b', 'c', 'd'], ordered=False)
res = ct.shift(1, fill_value=fill_value)
assert_equal(res, expected)
def test_right(self):
data = np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1, 2.575])
result, bins = cut(data, 4, right=True, retbins=True)
intervals = IntervalIndex.from_breaks(bins.round(3))
expected = Categorical(intervals, ordered=True)
expected = expected.take([0, 0, 0, 2, 3, 0, 0])
tm.assert_categorical_equal(result, expected)
tm.assert_almost_equal(bins, np.array([0.1905, 2.575, 4.95,
7.325, 9.7]))
def test_from_codes_with_dtype_raises(self):
msg = 'Cannot specify'
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([0, 1], categories=['a', 'b'],
dtype=CategoricalDtype(['a', 'b']))
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([0, 1], ordered=True,
dtype=CategoricalDtype(['a', 'b']))
def _bins_to_cuts(x, bins, right=True, labels=None,
precision=3, include_lowest=False,
dtype=None, duplicates='raise'):
if duplicates not in ['raise', 'drop']:
raise ValueError("invalid value for 'duplicates' parameter, "
"valid options are: raise, drop")
if isinstance(bins, IntervalIndex):
# we have a fast-path here
ids = bins.get_indexer(x)
result = algos.take_nd(bins, ids)
result = Categorical(result, categories=bins, ordered=True)
return result, bins
unique_bins = algos.unique(bins)
if len(unique_bins) < len(bins) and len(bins) != 2:
if duplicates == 'raise':
raise ValueError("Bin edges must be unique: {bins!r}.\nYou "
"can drop duplicate edges by setting "
"the 'duplicates' kwarg".format(bins=bins))
else:
bins = unique_bins
side = 'left' if right else 'right'
ids = _ensure_int64(bins.searchsorted(x, side=side))
if include_lowest:
# Numpy 1.9 support: ensure this mask is a Numpy array
ids[np.asarray(x == bins[0])] = 1
na_mask = isna(x) | (ids == len(bins)) | (ids == 0)
has_nas = na_mask.any()
if labels is not False:
if labels is None:
labels = _format_labels(bins, precision, right=right,
include_lowest=include_lowest,
dtype=dtype)
else:
if len(labels) != len(bins) - 1:
raise ValueError('Bin labels must be one fewer than '
'the number of bin edges')
if not is_categorical_dtype(labels):
labels = Categorical(labels, categories=labels, ordered=True)
np.putmask(ids, na_mask, 0)
result = algos.take_nd(labels, ids - 1)
else:
result = ids - 1
if has_nas:
result = result.astype(np.float64)
np.putmask(result, na_mask, np.nan)
return result, bins
def test_from_codes_with_nan_code(self):
# GH21767
codes = [1, 2, np.nan]
dtype = CategoricalDtype(categories=['a', 'b', 'c'])
with pytest.raises(ValueError,
match="codes need to be array-like integers"):
Categorical.from_codes(codes, categories=dtype.categories)
with pytest.raises(ValueError,
match="codes need to be array-like integers"):
Categorical.from_codes(codes, dtype=dtype)
def test_argsort(self):
c = Categorical([5, 3, 1, 4, 2], ordered=True)
expected = np.array([2, 4, 1, 3, 0])
tm.assert_numpy_array_equal(c.argsort(ascending=True), expected,
check_dtype=False)
expected = expected[::-1]
tm.assert_numpy_array_equal(c.argsort(ascending=False), expected,
check_dtype=False)
def test_mask_with_boolean(index):
s = Series(range(3))
idx = Categorical([True, False, True])
if index:
idx = CategoricalIndex(idx)
assert com.is_bool_indexer(idx)
result = s[idx]
expected = s[idx.astype('object')]
tm.assert_series_equal(result, expected)
def test_rename_categories_dict(self):
# GH 17336
cat = Categorical(['a', 'b', 'c', 'd'])
res = cat.rename_categories({'a': 4, 'b': 3, 'c': 2, 'd': 1})
expected = Index([4, 3, 2, 1])
tm.assert_index_equal(res.categories, expected)
# Test for inplace
res = cat.rename_categories({'a': 4, 'b': 3, 'c': 2, 'd': 1},
inplace=True)
assert res is None
tm.assert_index_equal(cat.categories, expected)
# Test for dicts of smaller length
cat = Categorical(['a', 'b', 'c', 'd'])
res = cat.rename_categories({'a': 1, 'c': 3})
expected = Index([1, 'b', 3, 'd'])
tm.assert_index_equal(res.categories, expected)
# Test for dicts with bigger length
cat = Categorical(['a', 'b', 'c', 'd'])
res = cat.rename_categories({'a': 1, 'b': 2, 'c': 3,
'd': 4, 'e': 5, 'f': 6})
expected = Index([1, 2, 3, 4])
tm.assert_index_equal(res.categories, expected)
# Test for dicts with no items from old categories
cat = Categorical(['a', 'b', 'c', 'd'])
res = cat.rename_categories({'f': 1, 'g': 3})
expected = Index(['a', 'b', 'c', 'd'])
tm.assert_index_equal(res.categories, expected)
def test_fillna_iterable_category(self, named):
# https://github.com/pandas-dev/pandas/issues/21097
if named:
Point = collections.namedtuple("Point", "x y")
else:
Point = lambda *args: args # tuple
cat = Categorical([Point(0, 0), Point(0, 1), None])
result = cat.fillna(Point(0, 0))
expected = Categorical([Point(0, 0), Point(0, 1), Point(0, 0)])
tm.assert_categorical_equal(result, expected)
def test_rename_categories_series(self):
# https://github.com/pandas-dev/pandas/issues/17981
c = Categorical(['a', 'b'])
xpr = "Treating Series 'new_categories' as a list-like "
with tm.assert_produces_warning(FutureWarning) as rec:
result = c.rename_categories(Series([0, 1]))
assert len(rec) == 1
assert xpr in str(rec[0].message)
expected = Categorical([0, 1])
tm.assert_categorical_equal(result, expected)
def test_from_codes_with_float(self):
# GH21767
codes = [1.0, 2.0, 0] # integer, but in float dtype
categories = ['a', 'b', 'c']
with tm.assert_produces_warning(FutureWarning):
cat = Categorical.from_codes(codes, categories)
tm.assert_numpy_array_equal(cat.codes, np.array([1, 2, 0], dtype='i1'))
codes = [1.1, 2.0, 0] # non-integer
with pytest.raises(ValueError):
Categorical.from_codes(codes, categories)
def test_unique_ordered(self):
# keep categories order when ordered=True
cat = Categorical(['b', 'a', 'b'], categories=['a', 'b'], ordered=True)
res = cat.unique()
exp_cat = Categorical(['b', 'a'], categories=['a', 'b'], ordered=True)
tm.assert_categorical_equal(res, exp_cat)
cat = Categorical(['c', 'b', 'a', 'a'], categories=['a', 'b', 'c'],
ordered=True)
res = cat.unique()
exp_cat = Categorical(['c', 'b', 'a'], categories=['a', 'b', 'c'],
ordered=True)
tm.assert_categorical_equal(res, exp_cat)
cat = Categorical(['b', 'a', 'a'], categories=['a', 'b', 'c'],
ordered=True)
res = cat.unique()
exp_cat = Categorical(['b', 'a'], categories=['a', 'b'], ordered=True)
tm.assert_categorical_equal(res, exp_cat)
cat = Categorical(['b', 'b', np.nan, 'a'], categories=['a', 'b', 'c'],
ordered=True)
res = cat.unique()
exp_cat = Categorical(['b', np.nan, 'a'], categories=['a', 'b'],
ordered=True)
tm.assert_categorical_equal(res, exp_cat)
def test_unique(self):
# categories are reordered based on value when ordered=False
cat = Categorical(["a", "b"])
exp = Index(["a", "b"])
res = cat.unique()
tm.assert_index_equal(res.categories, exp)
tm.assert_categorical_equal(res, cat)
cat = Categorical(["a", "b", "a", "a"], categories=["a", "b", "c"])
res = cat.unique()
tm.assert_index_equal(res.categories, exp)
tm.assert_categorical_equal(res, Categorical(exp))
cat = Categorical(["c", "a", "b", "a", "a"],
categories=["a", "b", "c"])
exp = Index(["c", "a", "b"])
res = cat.unique()
tm.assert_index_equal(res.categories, exp)
exp_cat = Categorical(exp, categories=['c', 'a', 'b'])
tm.assert_categorical_equal(res, exp_cat)
# nan must be removed
cat = Categorical(["b", np.nan, "b", np.nan, "a"],
categories=["a", "b", "c"])
res = cat.unique()
exp = Index(["b", "a"])
tm.assert_index_equal(res.categories, exp)
exp_cat = Categorical(["b", np.nan, "a"], categories=["b", "a"])
tm.assert_categorical_equal(res, exp_cat)
def test_map(self):
c = Categorical(list('ABABC'), categories=list('CBA'), ordered=True)
result = c.map(lambda x: x.lower())
exp = Categorical(list('ababc'), categories=list('cba'), ordered=True)
tm.assert_categorical_equal(result, exp)
c = Categorical(list('ABABC'), categories=list('ABC'), ordered=False)
result = c.map(lambda x: x.lower())
exp = Categorical(list('ababc'), categories=list('abc'), ordered=False)
tm.assert_categorical_equal(result, exp)
result = c.map(lambda x: 1)
# GH 12766: Return an index not an array
tm.assert_index_equal(result, Index(np.array([1] * 5, dtype=np.int64)))
def test_categories_assigments(self):
s = Categorical(["a", "b", "c", "a"])
exp = np.array([1, 2, 3, 1], dtype=np.int64)
s.categories = [1, 2, 3]
tm.assert_numpy_array_equal(s.__array__(), exp)
tm.assert_index_equal(s.categories, Index([1, 2, 3]))
# lengthen
with pytest.raises(ValueError):
s.categories = [1, 2, 3, 4]
# shorten
with pytest.raises(ValueError):
s.categories = [1, 2]
def test_cut_pass_labels(self):
arr = [50, 5, 10, 15, 20, 30, 70]
bins = [0, 25, 50, 100]
labels = ['Small', 'Medium', 'Large']
result = cut(arr, bins, labels=labels)
exp = Categorical(['Medium'] + 4 * ['Small'] + ['Medium', 'Large'],
ordered=True)
tm.assert_categorical_equal(result, exp)
result = cut(arr, bins, labels=Categorical.from_codes([0, 1, 2],
labels))
exp = Categorical.from_codes([1] + 4 * [0] + [1, 2], labels)
tm.assert_categorical_equal(result, exp)
def test_validate_ordered(self):
# see gh-14058
exp_msg = "'ordered' must either be 'True' or 'False'"
exp_err = TypeError
# This should be a boolean.
ordered = np.array([0, 1, 2])
with tm.assert_raises_regex(exp_err, exp_msg):
Categorical([1, 2, 3], ordered=ordered)
with tm.assert_raises_regex(exp_err, exp_msg):
Categorical.from_codes([0, 0, 1], categories=['a', 'b', 'c'],
ordered=ordered)
def test_from_codes_with_categorical_categories(self):
# GH17884
expected = Categorical(['a', 'b'], categories=['a', 'b', 'c'])
result = Categorical.from_codes(
[0, 1], categories=Categorical(['a', 'b', 'c']))
tm.assert_categorical_equal(result, expected)
result = Categorical.from_codes(
[0, 1], categories=CategoricalIndex(['a', 'b', 'c']))
tm.assert_categorical_equal(result, expected)
# non-unique Categorical still raises
with pytest.raises(ValueError):
Categorical.from_codes([0, 1], Categorical(['a', 'b', 'a']))
def test_from_inferred_categories_coerces(self):
cats = ['1', '2', 'bad']
codes = np.array([0, 0, 1, 2], dtype='i8')
dtype = CategoricalDtype([1, 2])
result = Categorical._from_inferred_categories(cats, codes, dtype)
expected = Categorical([1, 1, 2, np.nan])
tm.assert_categorical_equal(result, expected)
def test_astype(self):
ci = self.create_index()
result = ci.astype('category')
tm.assert_index_equal(result, ci, exact=True)
result = ci.astype(object)
tm.assert_index_equal(result, Index(np.array(ci)))
# this IS equal, but not the same class
assert result.equals(ci)
assert isinstance(result, Index)
assert not isinstance(result, CategoricalIndex)
# interval
ii = IntervalIndex.from_arrays(left=[-0.001, 2.0],
right=[2, 4],
closed='right')
ci = CategoricalIndex(Categorical.from_codes(
[0, 1, -1], categories=ii, ordered=True))
result = ci.astype('interval')
expected = ii.take([0, 1, -1])
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(result.values)
tm.assert_index_equal(result, expected)
def f(a):
if isinstance(a, (CategoricalIndex, Categorical)):
categories = a.categories
a = Categorical.from_codes(np.arange(len(categories)),
categories=categories,
ordered=a.ordered)
return a
def test_reshaping_panel_categorical(self):
p = tm.makePanel()
p['str'] = 'foo'
df = p.to_frame()
df['category'] = df['str'].astype('category')
result = df['category'].unstack()
c = Categorical(['foo'] * len(p.major_axis))
expected = DataFrame({'A': c.copy(),
'B': c.copy(),
'C': c.copy(),
'D': c.copy()},
columns=Index(list('ABCD'), name='minor'),
index=p.major_axis.set_names('major'))
tm.assert_frame_equal(result, expected)
def test_cut_return_categorical(self):
s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
res = cut(s, 3)
exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
["(-0.008, 2.667]",
"(2.667, 5.333]", "(5.333, 8]"],
ordered=True))
tm.assert_series_equal(res, exp)
def test_qcut_return_categorical(self):
s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
res = qcut(s, [0, 0.333, 0.666, 1])
exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
["[0, 2.664]",
"(2.664, 5.328]", "(5.328, 8]"],
ordered=True))
tm.assert_series_equal(res, exp)
def test_isna(self):
exp = np.array([False, False, True])
cat = Categorical(["a", "b", np.nan])
res = cat.isna()
tm.assert_numpy_array_equal(res, exp)
def test_constructor_imaginary(self):
values = [1, 2, 3 + 1j]
c1 = Categorical(values)
tm.assert_index_equal(c1.categories, Index(values))
tm.assert_numpy_array_equal(np.array(c1), np.array(values))
def test_slicing_and_getting_ops(self):
# systematically test the slicing operations:
# for all slicing ops:
# - returning a dataframe
# - returning a column
# - returning a row
# - returning a single value
cats = Categorical(
["a", "c", "b", "c", "c", "c", "c"], categories=["a", "b", "c"]
)
idx = Index(["h", "i", "j", "k", "l", "m", "n"])
values = [1, 2, 3, 4, 5, 6, 7]
df = DataFrame({"cats": cats, "values": values}, index=idx)
# the expected values
cats2 = Categorical(["b", "c"], categories=["a", "b", "c"])
idx2 = Index(["j", "k"])
values2 = [3, 4]
# 2:4,: | "j":"k",:
exp_df = DataFrame({"cats": cats2, "values": values2}, index=idx2)
# :,"cats" | :,0
exp_col = Series(cats, index=idx, name="cats")
# "j",: | 2,:
exp_row = Series(["b", 3], index=["cats", "values"], dtype="object", name="j")
# "j","cats | 2,0
exp_val = "b"
# iloc
# frame
res_df = df.iloc[2:4, :]
tm.assert_frame_equal(res_df, exp_df)
assert is_categorical_dtype(res_df["cats"])
# row
res_row = df.iloc[2, :]
tm.assert_series_equal(res_row, exp_row)
assert isinstance(res_row["cats"], str)
# col
res_col = df.iloc[:, 0]
tm.assert_series_equal(res_col, exp_col)
assert is_categorical_dtype(res_col)
# single value
res_val = df.iloc[2, 0]
assert res_val == exp_val
# loc
# frame
res_df = df.loc["j":"k", :]
tm.assert_frame_equal(res_df, exp_df)
assert is_categorical_dtype(res_df["cats"])
# row
res_row = df.loc["j", :]
tm.assert_series_equal(res_row, exp_row)
assert isinstance(res_row["cats"], str)
# col
res_col = df.loc[:, "cats"]
tm.assert_series_equal(res_col, exp_col)
assert is_categorical_dtype(res_col)
# single value
res_val = df.loc["j", "cats"]
assert res_val == exp_val
# ix
# frame
# res_df = df.loc["j":"k",[0,1]] # doesn't work?
res_df = df.loc["j":"k", :]
tm.assert_frame_equal(res_df, exp_df)
assert is_categorical_dtype(res_df["cats"])
# row
res_row = df.loc["j", :]
tm.assert_series_equal(res_row, exp_row)
assert isinstance(res_row["cats"], str)
# col
res_col = df.loc[:, "cats"]
tm.assert_series_equal(res_col, exp_col)
assert is_categorical_dtype(res_col)
# single value
res_val = df.loc["j", df.columns[0]]
assert res_val == exp_val
# iat
res_val = df.iat[2, 0]
assert res_val == exp_val
# at
res_val = df.at["j", "cats"]
assert res_val == exp_val
# fancy indexing
exp_fancy = df.iloc[[2]]
res_fancy = df[df["cats"] == "b"]
tm.assert_frame_equal(res_fancy, exp_fancy)
res_fancy = df[df["values"] == 3]
tm.assert_frame_equal(res_fancy, exp_fancy)
# get_value
res_val = df.at["j", "cats"]
assert res_val == exp_val
# i : int, slice, or sequence of integers
res_row = df.iloc[2]
tm.assert_series_equal(res_row, exp_row)
assert isinstance(res_row["cats"], str)
res_df = df.iloc[slice(2, 4)]
tm.assert_frame_equal(res_df, exp_df)
assert is_categorical_dtype(res_df["cats"])
res_df = df.iloc[[2, 3]]
tm.assert_frame_equal(res_df, exp_df)
assert is_categorical_dtype(res_df["cats"])
res_col = df.iloc[:, 0]
tm.assert_series_equal(res_col, exp_col)
assert is_categorical_dtype(res_col)
res_df = df.iloc[:, slice(0, 2)]
tm.assert_frame_equal(res_df, df)
assert is_categorical_dtype(res_df["cats"])
res_df = df.iloc[:, [0, 1]]
tm.assert_frame_equal(res_df, df)
assert is_categorical_dtype(res_df["cats"])
def test_categories_match_up_to_permutation(self):
# test dtype comparisons between cats
c1 = Categorical(list("aabca"), categories=list("abc"), ordered=False)
c2 = Categorical(list("aabca"), categories=list("cab"), ordered=False)
c3 = Categorical(list("aabca"), categories=list("cab"), ordered=True)
assert c1._categories_match_up_to_permutation(c1)
assert c2._categories_match_up_to_permutation(c2)
assert c3._categories_match_up_to_permutation(c3)
assert c1._categories_match_up_to_permutation(c2)
assert not c1._categories_match_up_to_permutation(c3)
assert not c1._categories_match_up_to_permutation(Index(list("aabca")))
assert not c1._categories_match_up_to_permutation(c1.astype(object))
assert c1._categories_match_up_to_permutation(CategoricalIndex(c1))
assert c1._categories_match_up_to_permutation(
CategoricalIndex(c1, categories=list("cab"))
)
assert not c1._categories_match_up_to_permutation(
CategoricalIndex(c1, ordered=True)
)
# GH 16659
s1 = Series(c1)
s2 = Series(c2)
s3 = Series(c3)
assert c1._categories_match_up_to_permutation(s1)
assert c2._categories_match_up_to_permutation(s2)
assert c3._categories_match_up_to_permutation(s3)
assert c1._categories_match_up_to_permutation(s2)
assert not c1._categories_match_up_to_permutation(s3)
assert not c1._categories_match_up_to_permutation(s1.astype(object))
def test_is_dtype_equal_deprecated(self):
# GH#37545
c1 = Categorical(list("aabca"), categories=list("abc"), ordered=False)
with tm.assert_produces_warning(FutureWarning):
c1.is_dtype_equal(c1)
def test_reindexing(self):
# reindexing
# convert to a regular index
result = self.df2.reindex(["a", "b", "e"])
expected = DataFrame(
{"A": [0, 1, 5, 2, 3, np.nan], "B": Series(list("aaabbe"))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["a", "b"])
expected = DataFrame(
{"A": [0, 1, 5, 2, 3], "B": Series(list("aaabb"))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["e"])
expected = DataFrame({"A": [np.nan], "B": Series(["e"])}).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["d"])
expected = DataFrame({"A": [np.nan], "B": Series(["d"])}).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
# since we are actually reindexing with a Categorical
# then return a Categorical
cats = list("cabe")
result = self.df2.reindex(Categorical(["a", "d"], categories=cats))
expected = DataFrame(
{"A": [0, 1, 5, np.nan], "B": Series(list("aaad")).astype(CDT(cats))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(Categorical(["a"], categories=cats))
expected = DataFrame(
{"A": [0, 1, 5], "B": Series(list("aaa")).astype(CDT(cats))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["a", "b", "e"])
expected = DataFrame(
{"A": [0, 1, 5, 2, 3, np.nan], "B": Series(list("aaabbe"))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["a", "b"])
expected = DataFrame(
{"A": [0, 1, 5, 2, 3], "B": Series(list("aaabb"))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(["e"])
expected = DataFrame({"A": [np.nan], "B": Series(["e"])}).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
# give back the type of categorical that we received
result = self.df2.reindex(
Categorical(["a", "d"], categories=cats, ordered=True)
)
expected = DataFrame(
{
"A": [0, 1, 5, np.nan],
"B": Series(list("aaad")).astype(CDT(cats, ordered=True)),
}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
result = self.df2.reindex(Categorical(["a", "d"], categories=["a", "d"]))
expected = DataFrame(
{"A": [0, 1, 5, np.nan], "B": Series(list("aaad")).astype(CDT(["a", "d"]))}
).set_index("B")
assert_frame_equal(result, expected, check_index_type=True)
# passed duplicate indexers are not allowed
msg = "cannot reindex with a non-unique indexer"
with pytest.raises(ValueError, match=msg):
self.df2.reindex(["a", "a"])
# args NotImplemented ATM
msg = r"argument {} is not implemented for CategoricalIndex\.reindex"
with pytest.raises(NotImplementedError, match=msg.format("method")):
self.df2.reindex(["a"], method="ffill")
with pytest.raises(NotImplementedError, match=msg.format("level")):
self.df2.reindex(["a"], level=1)
with pytest.raises(NotImplementedError, match=msg.format("limit")):
self.df2.reindex(["a"], limit=2)
def test_iter_python_types(self):
# GH-19909
cat = Categorical([1, 2])
assert isinstance(list(cat)[0], int)
assert isinstance(cat.tolist()[0], int)
def test_set_dtype_nans(self):
c = Categorical(["a", "b", np.nan])
result = c._set_dtype(CategoricalDtype(["a", "c"]))
tm.assert_numpy_array_equal(result.codes,
np.array([0, -1, -1], dtype="int8"))
def test_set_dtype_same(self):
c = Categorical(["a", "b", "c"])
result = c._set_dtype(CategoricalDtype(["a", "b", "c"]))
tm.assert_categorical_equal(result, c)
def test_set_dtype_new_categories(self):
c = Categorical(["a", "b", "c"])
result = c._set_dtype(CategoricalDtype(list("abcd")))
tm.assert_numpy_array_equal(result.codes, c.codes)
tm.assert_index_equal(result.dtype.categories, Index(list("abcd")))
def test_set_dtype_many(self, values, categories, new_categories, ordered):
c = Categorical(values, categories)
expected = Categorical(values, new_categories, ordered)
result = c._set_dtype(expected.dtype)
tm.assert_categorical_equal(result, expected)
def test_set_dtype_no_overlap(self):
c = Categorical(["a", "b", "c"], ["d", "e"])
result = c._set_dtype(CategoricalDtype(["a", "b"]))
expected = Categorical([None, None, None], categories=["a", "b"])
tm.assert_categorical_equal(result, expected)
def test_iter_python_types_datetime(self):
cat = Categorical([Timestamp("2017-01-01"), Timestamp("2017-01-02")])
assert isinstance(list(cat)[0], Timestamp)
assert isinstance(cat.tolist()[0], Timestamp)
def test_construction_with_ordered(self, ordered):
# GH 9347, 9190
cat = Categorical([0, 1, 2], ordered=ordered)
assert cat.ordered == bool(ordered)
