craftbeerpi4-pione/venv3/lib/python3.7/site-packages/pandas/tests/test_join.py

347 lines
9.1 KiB
Python
Raw Normal View History

2021-03-03 23:49:41 +01:00
import numpy as np
import pytest
from pandas._libs import join as _join
from pandas import Categorical, DataFrame, Index, merge
import pandas._testing as tm
class TestIndexer:
@pytest.mark.parametrize(
"dtype", ["int32", "int64", "float32", "float64", "object"]
)
def test_outer_join_indexer(self, dtype):
indexer = _join.outer_join_indexer
left = np.arange(3, dtype=dtype)
right = np.arange(2, 5, dtype=dtype)
empty = np.array([], dtype=dtype)
result, lindexer, rindexer = indexer(left, right)
assert isinstance(result, np.ndarray)
assert isinstance(lindexer, np.ndarray)
assert isinstance(rindexer, np.ndarray)
tm.assert_numpy_array_equal(result, np.arange(5, dtype=dtype))
exp = np.array([0, 1, 2, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, 0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)
result, lindexer, rindexer = indexer(empty, right)
tm.assert_numpy_array_equal(result, right)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)
result, lindexer, rindexer = indexer(left, empty)
tm.assert_numpy_array_equal(result, left)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)
def test_left_join_indexer_unique():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([2, 2, 3, 4, 4], dtype=np.int64)
result = _join.left_join_indexer_unique(b, a)
expected = np.array([1, 1, 2, 3, 3], dtype=np.int64)
tm.assert_numpy_array_equal(result, expected)
def test_left_outer_join_bug():
left = np.array(
[
0,
1,
0,
1,
1,
2,
3,
1,
0,
2,
1,
2,
0,
1,
1,
2,
3,
2,
3,
2,
1,
1,
3,
0,
3,
2,
3,
0,
0,
2,
3,
2,
0,
3,
1,
3,
0,
1,
3,
0,
0,
1,
0,
3,
1,
0,
1,
0,
1,
1,
0,
2,
2,
2,
2,
2,
0,
3,
1,
2,
0,
0,
3,
1,
3,
2,
2,
0,
1,
3,
0,
2,
3,
2,
3,
3,
2,
3,
3,
1,
3,
2,
0,
0,
3,
1,
1,
1,
0,
2,
3,
3,
1,
2,
0,
3,
1,
2,
0,
2,
],
dtype=np.int64,
)
right = np.array([3, 1], dtype=np.int64)
max_groups = 4
lidx, ridx = _join.left_outer_join(left, right, max_groups, sort=False)
exp_lidx = np.arange(len(left), dtype=np.int64)
exp_ridx = -np.ones(len(left), dtype=np.int64)
exp_ridx[left == 1] = 1
exp_ridx[left == 3] = 0
tm.assert_numpy_array_equal(lidx, exp_lidx)
tm.assert_numpy_array_equal(ridx, exp_ridx)
def test_inner_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)
index, ares, bres = _join.inner_join_indexer(a, b)
index_exp = np.array([3, 5], dtype=np.int64)
tm.assert_almost_equal(index, index_exp)
aexp = np.array([2, 4], dtype=np.int64)
bexp = np.array([1, 2], dtype=np.int64)
tm.assert_almost_equal(ares, aexp)
tm.assert_almost_equal(bres, bexp)
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)
index, ares, bres = _join.inner_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
def test_outer_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)
index, ares, bres = _join.outer_join_indexer(a, b)
index_exp = np.array([0, 1, 2, 3, 4, 5, 7, 9], dtype=np.int64)
tm.assert_almost_equal(index, index_exp)
aexp = np.array([-1, 0, 1, 2, 3, 4, -1, -1], dtype=np.int64)
bexp = np.array([0, -1, -1, 1, -1, 2, 3, 4], dtype=np.int64)
tm.assert_almost_equal(ares, aexp)
tm.assert_almost_equal(bres, bexp)
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)
index, ares, bres = _join.outer_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
def test_left_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)
index, ares, bres = _join.left_join_indexer(a, b)
tm.assert_almost_equal(index, a)
aexp = np.array([0, 1, 2, 3, 4], dtype=np.int64)
bexp = np.array([-1, -1, 1, -1, 2], dtype=np.int64)
tm.assert_almost_equal(ares, aexp)
tm.assert_almost_equal(bres, bexp)
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)
index, ares, bres = _join.left_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
def test_left_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])
res, lidx, ridx = _join.left_join_indexer(idx2.values, idx.values)
exp_res = np.array([1, 1, 2, 5, 7, 9], dtype=np.int64)
tm.assert_almost_equal(res, exp_res)
exp_lidx = np.array([0, 0, 1, 2, 3, 4], dtype=np.int64)
tm.assert_almost_equal(lidx, exp_lidx)
exp_ridx = np.array([0, 1, 2, 3, -1, -1], dtype=np.int64)
tm.assert_almost_equal(ridx, exp_ridx)
def test_outer_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])
res, lidx, ridx = _join.outer_join_indexer(idx2.values, idx.values)
exp_res = np.array([1, 1, 2, 5, 7, 9], dtype=np.int64)
tm.assert_almost_equal(res, exp_res)
exp_lidx = np.array([0, 0, 1, 2, 3, 4], dtype=np.int64)
tm.assert_almost_equal(lidx, exp_lidx)
exp_ridx = np.array([0, 1, 2, 3, -1, -1], dtype=np.int64)
tm.assert_almost_equal(ridx, exp_ridx)
def test_inner_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])
res, lidx, ridx = _join.inner_join_indexer(idx2.values, idx.values)
exp_res = np.array([1, 1, 2, 5], dtype=np.int64)
tm.assert_almost_equal(res, exp_res)
exp_lidx = np.array([0, 0, 1, 2], dtype=np.int64)
tm.assert_almost_equal(lidx, exp_lidx)
exp_ridx = np.array([0, 1, 2, 3], dtype=np.int64)
tm.assert_almost_equal(ridx, exp_ridx)
def test_merge_join_categorical_multiindex():
# From issue 16627
a = {
"Cat1": Categorical(["a", "b", "a", "c", "a", "b"], ["a", "b", "c"]),
"Int1": [0, 1, 0, 1, 0, 0],
}
a = DataFrame(a)
b = {
"Cat": Categorical(["a", "b", "c", "a", "b", "c"], ["a", "b", "c"]),
"Int": [0, 0, 0, 1, 1, 1],
"Factor": [1.1, 1.2, 1.3, 1.4, 1.5, 1.6],
}
b = DataFrame(b).set_index(["Cat", "Int"])["Factor"]
expected = merge(
a,
b.reset_index(),
left_on=["Cat1", "Int1"],
right_on=["Cat", "Int"],
how="left",
)
result = a.join(b, on=["Cat1", "Int1"])
expected = expected.drop(["Cat", "Int"], axis=1)
tm.assert_frame_equal(expected, result)
# Same test, but with ordered categorical
a = {
"Cat1": Categorical(
["a", "b", "a", "c", "a", "b"], ["b", "a", "c"], ordered=True
),
"Int1": [0, 1, 0, 1, 0, 0],
}
a = DataFrame(a)
b = {
"Cat": Categorical(
["a", "b", "c", "a", "b", "c"], ["b", "a", "c"], ordered=True
),
"Int": [0, 0, 0, 1, 1, 1],
"Factor": [1.1, 1.2, 1.3, 1.4, 1.5, 1.6],
}
b = DataFrame(b).set_index(["Cat", "Int"])["Factor"]
expected = merge(
a,
b.reset_index(),
left_on=["Cat1", "Int1"],
right_on=["Cat", "Int"],
how="left",
)
result = a.join(b, on=["Cat1", "Int1"])
expected = expected.drop(["Cat", "Int"], axis=1)
tm.assert_frame_equal(expected, result)