def test_typecast_on_join_indexes_matching_categorical():
join_data_l = Series(["a", "b", "c", "d", "e"], dtype="category")
join_data_r = Series(["a", "b", "c", "d", "e"], dtype="str")
other_data = [1, 2, 3, 4, 5]
gdf_l = DataFrame({"join_col": join_data_l, "B": other_data})
gdf_r = DataFrame({"join_col": join_data_r, "B": other_data})
gdf_l = gdf_l.set_index("join_col")
gdf_r = gdf_r.set_index("join_col")
exp_join_data = ["a", "b", "c", "d", "e"]
exp_other_data = [1, 2, 3, 4, 5]
expect = DataFrame(
{
"join_col": exp_join_data,
"B_x": exp_other_data,
"B_y": exp_other_data,
}
)
expect = expect.set_index("join_col")
got = gdf_l.join(gdf_r, how="inner", lsuffix="_x", rsuffix="_y")
assert_eq(expect, got)
def test_dataframe_join_cats():
lhs = DataFrame()
lhs["a"] = pd.Categorical(list("aababcabbc"), categories=list("abc"))
lhs["b"] = bb = np.arange(len(lhs))
lhs = lhs.set_index("a")
rhs = DataFrame()
rhs["a"] = pd.Categorical(list("abcac"), categories=list("abc"))
rhs["c"] = cc = np.arange(len(rhs))
rhs = rhs.set_index("a")
got = lhs.join(rhs)
expect = lhs.to_pandas().join(rhs.to_pandas())
# Note: pandas make a object Index after joining
pd.util.testing.assert_frame_equal(
got.sort_values(by="b")
.to_pandas()
.sort_index()
.reset_index(drop=True),
expect.reset_index(drop=True),
)
# Just do some rough checking here.
assert list(got.columns) == ["b", "c"]
assert len(got) > 0
assert set(got.index.to_pandas()) & set("abc")
assert set(got["b"]) & set(bb)
assert set(got["c"]) & set(cc)
def test_typecast_on_join_multiindices():
join_data_l_0 = Series([1, 2, 3, 4, 5], dtype="int8")
join_data_l_1 = Series([2, 3, 4.1, 5.9, 6], dtype="float32")
join_data_l_2 = Series([7, 8, 9, 0, 1], dtype="float32")
join_data_r_0 = Series([1, 2, 3, 4, 5], dtype="int32")
join_data_r_1 = Series([2, 3, 4, 5, 6], dtype="int32")
join_data_r_2 = Series([7, 8, 9, 0, 0], dtype="float64")
other_data = ["a", "b", "c", "d", "e"]
gdf_l = DataFrame(
{
"join_col_0": join_data_l_0,
"join_col_1": join_data_l_1,
"join_col_2": join_data_l_2,
"B": other_data,
}
)
gdf_r = DataFrame(
{
"join_col_0": join_data_r_0,
"join_col_1": join_data_r_1,
"join_col_2": join_data_r_2,
"B": other_data,
}
)
gdf_l = gdf_l.set_index(["join_col_0", "join_col_1", "join_col_2"])
gdf_r = gdf_r.set_index(["join_col_0", "join_col_1", "join_col_2"])
exp_join_data_0 = Series([1, 2], dtype="int32")
exp_join_data_1 = Series([2, 3], dtype="float64")
exp_join_data_2 = Series([7, 8], dtype="float64")
exp_other_data = Series(["a", "b"])
expect = DataFrame(
{
"join_col_0": exp_join_data_0,
"join_col_1": exp_join_data_1,
"join_col_2": exp_join_data_2,
"B_x": exp_other_data,
"B_y": exp_other_data,
}
)
expect = expect.set_index(["join_col_0", "join_col_1", "join_col_2"])
got = gdf_l.join(gdf_r, how="inner", lsuffix="_x", rsuffix="_y")
assert_eq(expect, got)
