I am done

This commit is contained in:
2024-10-30 22:14:35 +01:00
parent 720dc28c09
commit 40e2a747cf
36901 changed files with 5011519 additions and 0 deletions

View File

@ -0,0 +1,80 @@
import numpy as np
import pytest
import pandas as pd
from pandas import (
Index,
MultiIndex,
Series,
)
import pandas._testing as tm
class TestIndexConstructor:
# Tests for the Index constructor, specifically for cases that do
# not return a subclass
@pytest.mark.parametrize("value", [1, np.int64(1)])
def test_constructor_corner(self, value):
# corner case
msg = (
r"Index\(\.\.\.\) must be called with a collection of some "
f"kind, {value} was passed"
)
with pytest.raises(TypeError, match=msg):
Index(value)
@pytest.mark.parametrize("index_vals", [[("A", 1), "B"], ["B", ("A", 1)]])
def test_construction_list_mixed_tuples(self, index_vals):
# see gh-10697: if we are constructing from a mixed list of tuples,
# make sure that we are independent of the sorting order.
index = Index(index_vals)
assert isinstance(index, Index)
assert not isinstance(index, MultiIndex)
def test_constructor_cast(self):
msg = "could not convert string to float"
with pytest.raises(ValueError, match=msg):
Index(["a", "b", "c"], dtype=float)
@pytest.mark.parametrize("tuple_list", [[()], [(), ()]])
def test_construct_empty_tuples(self, tuple_list):
# GH #45608
result = Index(tuple_list)
expected = MultiIndex.from_tuples(tuple_list)
tm.assert_index_equal(result, expected)
def test_index_string_inference(self):
# GH#54430
pytest.importorskip("pyarrow")
dtype = "string[pyarrow_numpy]"
expected = Index(["a", "b"], dtype=dtype)
with pd.option_context("future.infer_string", True):
ser = Index(["a", "b"])
tm.assert_index_equal(ser, expected)
expected = Index(["a", 1], dtype="object")
with pd.option_context("future.infer_string", True):
ser = Index(["a", 1])
tm.assert_index_equal(ser, expected)
def test_inference_on_pandas_objects(self):
# GH#56012
idx = Index([pd.Timestamp("2019-12-31")], dtype=object)
with tm.assert_produces_warning(FutureWarning, match="Dtype inference"):
result = Index(idx)
assert result.dtype != np.object_
ser = Series([pd.Timestamp("2019-12-31")], dtype=object)
with tm.assert_produces_warning(FutureWarning, match="Dtype inference"):
result = Index(ser)
assert result.dtype != np.object_
def test_constructor_not_read_only(self):
# GH#57130
ser = Series([1, 2], dtype=object)
with pd.option_context("mode.copy_on_write", True):
idx = Index(ser)
assert idx._values.flags.writeable

View File

@ -0,0 +1,163 @@
import numpy as np
import pytest
from pandas._config import using_pyarrow_string_dtype
import pandas._config.config as cf
from pandas import Index
import pandas._testing as tm
class TestIndexRendering:
def test_repr_is_valid_construction_code(self):
# for the case of Index, where the repr is traditional rather than
# stylized
idx = Index(["a", "b"])
res = eval(repr(idx))
tm.assert_index_equal(res, idx)
@pytest.mark.xfail(using_pyarrow_string_dtype(), reason="repr different")
@pytest.mark.parametrize(
"index,expected",
[
# ASCII
# short
(
Index(["a", "bb", "ccc"]),
"""Index(['a', 'bb', 'ccc'], dtype='object')""",
),
# multiple lines
(
Index(["a", "bb", "ccc"] * 10),
"Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', "
"'bb', 'ccc', 'a', 'bb', 'ccc',\n"
" 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', "
"'bb', 'ccc', 'a', 'bb', 'ccc',\n"
" 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],\n"
" dtype='object')",
),
# truncated
(
Index(["a", "bb", "ccc"] * 100),
"Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',\n"
" ...\n"
" 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],\n"
" dtype='object', length=300)",
),
# Non-ASCII
# short
(
Index(["", "いい", "ううう"]),
"""Index(['', 'いい', 'ううう'], dtype='object')""",
),
# multiple lines
(
Index(["", "いい", "ううう"] * 10),
(
"Index(['', 'いい', 'ううう', '', 'いい', 'ううう', "
"'', 'いい', 'ううう', '', 'いい', 'ううう',\n"
" '', 'いい', 'ううう', '', 'いい', 'ううう', "
"'', 'いい', 'ううう', '', 'いい', 'ううう',\n"
" '', 'いい', 'ううう', '', 'いい', "
"'ううう'],\n"
" dtype='object')"
),
),
# truncated
(
Index(["", "いい", "ううう"] * 100),
(
"Index(['', 'いい', 'ううう', '', 'いい', 'ううう', "
"'', 'いい', 'ううう', '',\n"
" ...\n"
" 'ううう', '', 'いい', 'ううう', '', 'いい', "
"'ううう', '', 'いい', 'ううう'],\n"
" dtype='object', length=300)"
),
),
],
)
def test_string_index_repr(self, index, expected):
result = repr(index)
assert result == expected
@pytest.mark.xfail(using_pyarrow_string_dtype(), reason="repr different")
@pytest.mark.parametrize(
"index,expected",
[
# short
(
Index(["", "いい", "ううう"]),
("Index(['', 'いい', 'ううう'], dtype='object')"),
),
# multiple lines
(
Index(["", "いい", "ううう"] * 10),
(
"Index(['', 'いい', 'ううう', '', 'いい', "
"'ううう', '', 'いい', 'ううう',\n"
" '', 'いい', 'ううう', '', 'いい', "
"'ううう', '', 'いい', 'ううう',\n"
" '', 'いい', 'ううう', '', 'いい', "
"'ううう', '', 'いい', 'ううう',\n"
" '', 'いい', 'ううう'],\n"
" dtype='object')"
""
),
),
# truncated
(
Index(["", "いい", "ううう"] * 100),
(
"Index(['', 'いい', 'ううう', '', 'いい', "
"'ううう', '', 'いい', 'ううう',\n"
" '',\n"
" ...\n"
" 'ううう', '', 'いい', 'ううう', '', "
"'いい', 'ううう', '', 'いい',\n"
" 'ううう'],\n"
" dtype='object', length=300)"
),
),
],
)
def test_string_index_repr_with_unicode_option(self, index, expected):
# Enable Unicode option -----------------------------------------
with cf.option_context("display.unicode.east_asian_width", True):
result = repr(index)
assert result == expected
def test_repr_summary(self):
with cf.option_context("display.max_seq_items", 10):
result = repr(Index(np.arange(1000)))
assert len(result) < 200
assert "..." in result
def test_summary_bug(self):
# GH#3869
ind = Index(["{other}%s", "~:{range}:0"], name="A")
result = ind._summary()
# shouldn't be formatted accidentally.
assert "~:{range}:0" in result
assert "{other}%s" in result
def test_index_repr_bool_nan(self):
# GH32146
arr = Index([True, False, np.nan], dtype=object)
msg = "Index.format is deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
exp1 = arr.format()
out1 = ["True", "False", "NaN"]
assert out1 == exp1
exp2 = repr(arr)
out2 = "Index([True, False, nan], dtype='object')"
assert out2 == exp2
def test_format_different_scalar_lengths(self):
# GH#35439
idx = Index(["aaaaaaaaa", "b"])
expected = ["aaaaaaaaa", "b"]
msg = r"Index\.format is deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
assert idx.format() == expected

View File

@ -0,0 +1,104 @@
import numpy as np
import pytest
from pandas._libs import index as libindex
import pandas as pd
from pandas import (
Index,
NaT,
)
import pandas._testing as tm
class TestGetSliceBounds:
@pytest.mark.parametrize("side, expected", [("left", 4), ("right", 5)])
def test_get_slice_bounds_within(self, side, expected):
index = Index(list("abcdef"))
result = index.get_slice_bound("e", side=side)
assert result == expected
@pytest.mark.parametrize("side", ["left", "right"])
@pytest.mark.parametrize(
"data, bound, expected", [(list("abcdef"), "x", 6), (list("bcdefg"), "a", 0)]
)
def test_get_slice_bounds_outside(self, side, expected, data, bound):
index = Index(data)
result = index.get_slice_bound(bound, side=side)
assert result == expected
def test_get_slice_bounds_invalid_side(self):
with pytest.raises(ValueError, match="Invalid value for side kwarg"):
Index([]).get_slice_bound("a", side="middle")
class TestGetIndexerNonUnique:
def test_get_indexer_non_unique_dtype_mismatch(self):
# GH#25459
indexes, missing = Index(["A", "B"]).get_indexer_non_unique(Index([0]))
tm.assert_numpy_array_equal(np.array([-1], dtype=np.intp), indexes)
tm.assert_numpy_array_equal(np.array([0], dtype=np.intp), missing)
@pytest.mark.parametrize(
"idx_values,idx_non_unique",
[
([np.nan, 100, 200, 100], [np.nan, 100]),
([np.nan, 100.0, 200.0, 100.0], [np.nan, 100.0]),
],
)
def test_get_indexer_non_unique_int_index(self, idx_values, idx_non_unique):
indexes, missing = Index(idx_values).get_indexer_non_unique(Index([np.nan]))
tm.assert_numpy_array_equal(np.array([0], dtype=np.intp), indexes)
tm.assert_numpy_array_equal(np.array([], dtype=np.intp), missing)
indexes, missing = Index(idx_values).get_indexer_non_unique(
Index(idx_non_unique)
)
tm.assert_numpy_array_equal(np.array([0, 1, 3], dtype=np.intp), indexes)
tm.assert_numpy_array_equal(np.array([], dtype=np.intp), missing)
class TestGetLoc:
@pytest.mark.slow # to_flat_index takes a while
def test_get_loc_tuple_monotonic_above_size_cutoff(self, monkeypatch):
# Go through the libindex path for which using
# _bin_search vs ndarray.searchsorted makes a difference
with monkeypatch.context():
monkeypatch.setattr(libindex, "_SIZE_CUTOFF", 100)
lev = list("ABCD")
dti = pd.date_range("2016-01-01", periods=10)
mi = pd.MultiIndex.from_product([lev, range(5), dti])
oidx = mi.to_flat_index()
loc = len(oidx) // 2
tup = oidx[loc]
res = oidx.get_loc(tup)
assert res == loc
def test_get_loc_nan_object_dtype_nonmonotonic_nonunique(self):
# case that goes through _maybe_get_bool_indexer
idx = Index(["foo", np.nan, None, "foo", 1.0, None], dtype=object)
# we dont raise KeyError on nan
res = idx.get_loc(np.nan)
assert res == 1
# we only match on None, not on np.nan
res = idx.get_loc(None)
expected = np.array([False, False, True, False, False, True])
tm.assert_numpy_array_equal(res, expected)
# we don't match at all on mismatched NA
with pytest.raises(KeyError, match="NaT"):
idx.get_loc(NaT)
def test_getitem_boolean_ea_indexer():
# GH#45806
ser = pd.Series([True, False, pd.NA], dtype="boolean")
result = ser.index[ser]
expected = Index([0])
tm.assert_index_equal(result, expected)

View File

@ -0,0 +1,11 @@
from pandas import Index
import pandas._testing as tm
def test_pickle_preserves_object_dtype():
# GH#43188, GH#43155 don't infer numeric dtype
index = Index([1, 2, 3], dtype=object)
result = tm.round_trip_pickle(index)
assert result.dtype == object
tm.assert_index_equal(index, result)

View File

@ -0,0 +1,95 @@
"""
Tests for ndarray-like method on the base Index class
"""
import numpy as np
import pytest
from pandas import Index
import pandas._testing as tm
class TestReshape:
def test_repeat(self):
repeats = 2
index = Index([1, 2, 3])
expected = Index([1, 1, 2, 2, 3, 3])
result = index.repeat(repeats)
tm.assert_index_equal(result, expected)
def test_insert(self):
# GH 7256
# validate neg/pos inserts
result = Index(["b", "c", "d"])
# test 0th element
tm.assert_index_equal(Index(["a", "b", "c", "d"]), result.insert(0, "a"))
# test Nth element that follows Python list behavior
tm.assert_index_equal(Index(["b", "c", "e", "d"]), result.insert(-1, "e"))
# test loc +/- neq (0, -1)
tm.assert_index_equal(result.insert(1, "z"), result.insert(-2, "z"))
# test empty
null_index = Index([])
tm.assert_index_equal(Index(["a"], dtype=object), null_index.insert(0, "a"))
def test_insert_missing(self, nulls_fixture, using_infer_string):
# GH#22295
# test there is no mangling of NA values
expected = Index(["a", nulls_fixture, "b", "c"], dtype=object)
result = Index(list("abc"), dtype=object).insert(
1, Index([nulls_fixture], dtype=object)
)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"val", [(1, 2), np.datetime64("2019-12-31"), np.timedelta64(1, "D")]
)
@pytest.mark.parametrize("loc", [-1, 2])
def test_insert_datetime_into_object(self, loc, val):
# GH#44509
idx = Index(["1", "2", "3"])
result = idx.insert(loc, val)
expected = Index(["1", "2", val, "3"])
tm.assert_index_equal(result, expected)
assert type(expected[2]) is type(val)
def test_insert_none_into_string_numpy(self):
# GH#55365
pytest.importorskip("pyarrow")
index = Index(["a", "b", "c"], dtype="string[pyarrow_numpy]")
result = index.insert(-1, None)
expected = Index(["a", "b", None, "c"], dtype="string[pyarrow_numpy]")
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"pos,expected",
[
(0, Index(["b", "c", "d"], name="index")),
(-1, Index(["a", "b", "c"], name="index")),
],
)
def test_delete(self, pos, expected):
index = Index(["a", "b", "c", "d"], name="index")
result = index.delete(pos)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
def test_delete_raises(self):
index = Index(["a", "b", "c", "d"], name="index")
msg = "index 5 is out of bounds for axis 0 with size 4"
with pytest.raises(IndexError, match=msg):
index.delete(5)
def test_append_multiple(self):
index = Index(["a", "b", "c", "d", "e", "f"])
foos = [index[:2], index[2:4], index[4:]]
result = foos[0].append(foos[1:])
tm.assert_index_equal(result, index)
# empty
result = index.append([])
tm.assert_index_equal(result, index)

View File

@ -0,0 +1,266 @@
from datetime import datetime
import numpy as np
import pytest
import pandas as pd
from pandas import (
Index,
Series,
)
import pandas._testing as tm
from pandas.core.algorithms import safe_sort
def equal_contents(arr1, arr2) -> bool:
"""
Checks if the set of unique elements of arr1 and arr2 are equivalent.
"""
return frozenset(arr1) == frozenset(arr2)
class TestIndexSetOps:
@pytest.mark.parametrize(
"method", ["union", "intersection", "difference", "symmetric_difference"]
)
def test_setops_sort_validation(self, method):
idx1 = Index(["a", "b"])
idx2 = Index(["b", "c"])
with pytest.raises(ValueError, match="The 'sort' keyword only takes"):
getattr(idx1, method)(idx2, sort=2)
# sort=True is supported as of GH#??
getattr(idx1, method)(idx2, sort=True)
def test_setops_preserve_object_dtype(self):
idx = Index([1, 2, 3], dtype=object)
result = idx.intersection(idx[1:])
expected = idx[1:]
tm.assert_index_equal(result, expected)
# if other is not monotonic increasing, intersection goes through
# a different route
result = idx.intersection(idx[1:][::-1])
tm.assert_index_equal(result, expected)
result = idx._union(idx[1:], sort=None)
expected = idx
tm.assert_numpy_array_equal(result, expected.values)
result = idx.union(idx[1:], sort=None)
tm.assert_index_equal(result, expected)
# if other is not monotonic increasing, _union goes through
# a different route
result = idx._union(idx[1:][::-1], sort=None)
tm.assert_numpy_array_equal(result, expected.values)
result = idx.union(idx[1:][::-1], sort=None)
tm.assert_index_equal(result, expected)
def test_union_base(self):
index = Index([0, "a", 1, "b", 2, "c"])
first = index[3:]
second = index[:5]
result = first.union(second)
expected = Index([0, 1, 2, "a", "b", "c"])
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("klass", [np.array, Series, list])
def test_union_different_type_base(self, klass):
# GH 10149
index = Index([0, "a", 1, "b", 2, "c"])
first = index[3:]
second = index[:5]
result = first.union(klass(second.values))
assert equal_contents(result, index)
def test_union_sort_other_incomparable(self):
# https://github.com/pandas-dev/pandas/issues/24959
idx = Index([1, pd.Timestamp("2000")])
# default (sort=None)
with tm.assert_produces_warning(RuntimeWarning):
result = idx.union(idx[:1])
tm.assert_index_equal(result, idx)
# sort=None
with tm.assert_produces_warning(RuntimeWarning):
result = idx.union(idx[:1], sort=None)
tm.assert_index_equal(result, idx)
# sort=False
result = idx.union(idx[:1], sort=False)
tm.assert_index_equal(result, idx)
def test_union_sort_other_incomparable_true(self):
idx = Index([1, pd.Timestamp("2000")])
with pytest.raises(TypeError, match=".*"):
idx.union(idx[:1], sort=True)
def test_intersection_equal_sort_true(self):
idx = Index(["c", "a", "b"])
sorted_ = Index(["a", "b", "c"])
tm.assert_index_equal(idx.intersection(idx, sort=True), sorted_)
def test_intersection_base(self, sort):
# (same results for py2 and py3 but sortedness not tested elsewhere)
index = Index([0, "a", 1, "b", 2, "c"])
first = index[:5]
second = index[:3]
expected = Index([0, 1, "a"]) if sort is None else Index([0, "a", 1])
result = first.intersection(second, sort=sort)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("klass", [np.array, Series, list])
def test_intersection_different_type_base(self, klass, sort):
# GH 10149
index = Index([0, "a", 1, "b", 2, "c"])
first = index[:5]
second = index[:3]
result = first.intersection(klass(second.values), sort=sort)
assert equal_contents(result, second)
def test_intersection_nosort(self):
result = Index(["c", "b", "a"]).intersection(["b", "a"])
expected = Index(["b", "a"])
tm.assert_index_equal(result, expected)
def test_intersection_equal_sort(self):
idx = Index(["c", "a", "b"])
tm.assert_index_equal(idx.intersection(idx, sort=False), idx)
tm.assert_index_equal(idx.intersection(idx, sort=None), idx)
def test_intersection_str_dates(self, sort):
dt_dates = [datetime(2012, 2, 9), datetime(2012, 2, 22)]
i1 = Index(dt_dates, dtype=object)
i2 = Index(["aa"], dtype=object)
result = i2.intersection(i1, sort=sort)
assert len(result) == 0
@pytest.mark.parametrize(
"index2,expected_arr",
[(Index(["B", "D"]), ["B"]), (Index(["B", "D", "A"]), ["A", "B"])],
)
def test_intersection_non_monotonic_non_unique(self, index2, expected_arr, sort):
# non-monotonic non-unique
index1 = Index(["A", "B", "A", "C"])
expected = Index(expected_arr)
result = index1.intersection(index2, sort=sort)
if sort is None:
expected = expected.sort_values()
tm.assert_index_equal(result, expected)
def test_difference_base(self, sort):
# (same results for py2 and py3 but sortedness not tested elsewhere)
index = Index([0, "a", 1, "b", 2, "c"])
first = index[:4]
second = index[3:]
result = first.difference(second, sort)
expected = Index([0, "a", 1])
if sort is None:
expected = Index(safe_sort(expected))
tm.assert_index_equal(result, expected)
def test_symmetric_difference(self):
# (same results for py2 and py3 but sortedness not tested elsewhere)
index = Index([0, "a", 1, "b", 2, "c"])
first = index[:4]
second = index[3:]
result = first.symmetric_difference(second)
expected = Index([0, 1, 2, "a", "c"])
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"method,expected,sort",
[
(
"intersection",
np.array(
[(1, "A"), (2, "A"), (1, "B"), (2, "B")],
dtype=[("num", int), ("let", "S1")],
),
False,
),
(
"intersection",
np.array(
[(1, "A"), (1, "B"), (2, "A"), (2, "B")],
dtype=[("num", int), ("let", "S1")],
),
None,
),
(
"union",
np.array(
[(1, "A"), (1, "B"), (1, "C"), (2, "A"), (2, "B"), (2, "C")],
dtype=[("num", int), ("let", "S1")],
),
None,
),
],
)
def test_tuple_union_bug(self, method, expected, sort):
index1 = Index(
np.array(
[(1, "A"), (2, "A"), (1, "B"), (2, "B")],
dtype=[("num", int), ("let", "S1")],
)
)
index2 = Index(
np.array(
[(1, "A"), (2, "A"), (1, "B"), (2, "B"), (1, "C"), (2, "C")],
dtype=[("num", int), ("let", "S1")],
)
)
result = getattr(index1, method)(index2, sort=sort)
assert result.ndim == 1
expected = Index(expected)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("first_list", [["b", "a"], []])
@pytest.mark.parametrize("second_list", [["a", "b"], []])
@pytest.mark.parametrize(
"first_name, second_name, expected_name",
[("A", "B", None), (None, "B", None), ("A", None, None)],
)
def test_union_name_preservation(
self, first_list, second_list, first_name, second_name, expected_name, sort
):
first = Index(first_list, name=first_name)
second = Index(second_list, name=second_name)
union = first.union(second, sort=sort)
vals = set(first_list).union(second_list)
if sort is None and len(first_list) > 0 and len(second_list) > 0:
expected = Index(sorted(vals), name=expected_name)
tm.assert_index_equal(union, expected)
else:
expected = Index(vals, name=expected_name)
tm.assert_index_equal(union.sort_values(), expected.sort_values())
@pytest.mark.parametrize(
"diff_type, expected",
[["difference", [1, "B"]], ["symmetric_difference", [1, 2, "B", "C"]]],
)
def test_difference_object_type(self, diff_type, expected):
# GH 13432
idx1 = Index([0, 1, "A", "B"])
idx2 = Index([0, 2, "A", "C"])
result = getattr(idx1, diff_type)(idx2)
expected = Index(expected)
tm.assert_index_equal(result, expected)

View File

@ -0,0 +1,13 @@
import numpy as np
from pandas import Index
import pandas._testing as tm
class TestWhere:
def test_where_intlike_str_doesnt_cast_ints(self):
idx = Index(range(3))
mask = np.array([True, False, True])
res = idx.where(mask, "2")
expected = Index([0, "2", 2])
tm.assert_index_equal(res, expected)