def test_select_by_label_multiindex():
"""
Test getting column(s) by label with MultiIndex
"""
ca = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("b", "x", ""): [4, 5, 6],
("a", "d", "e"): [3, 4, 5],
},
multiindex=True,
)
expect = ColumnAccessor(
{("b", "c"): [1, 2, 3], ("b", "e"): [2, 3, 4], ("d", "e"): [3, 4, 5]},
multiindex=True,
)
got = ca.select_by_label("a")
check_ca_equal(expect, got)
expect = ColumnAccessor({"c": [1, 2, 3], "e": [2, 3, 4]}, multiindex=False)
got = ca.select_by_label(("a", "b"))
check_ca_equal(expect, got)
expect = ColumnAccessor(
{("b", "c"): [1, 2, 3], ("b", "e"): [2, 3, 4], ("d", "e"): [3, 4, 5]},
multiindex=True,
)
got = ca.select_by_label("a")
check_ca_equal(expect, got)
expect = ColumnAccessor({"c": [1, 2, 3], "e": [2, 3, 4]}, multiindex=False)
got = ca.select_by_label(("a", "b"))
check_ca_equal(expect, got)
def test_select_by_label_simple():
"""
Test getting a column by label
"""
ca = ColumnAccessor({"a": [1, 2, 3], "b": [2, 3, 4]})
check_ca_equal(ca.select_by_label("a"), ColumnAccessor({"a": [1, 2, 3]}))
check_ca_equal(ca.select_by_label("b"), ColumnAccessor({"b": [2, 3, 4]}))
def test_all_columns(simple_data):
"""
Test that all values of the CA are
columns.
"""
ca = ColumnAccessor(simple_data)
for col in ca.values():
assert isinstance(col, cudf.core.column.ColumnBase)
def test_to_pandas_multiindex_names():
ca = ColumnAccessor(
{("a", "b"): [1, 2, 3], ("c", "d"): [3, 4, 5]},
multiindex=True,
level_names=("foo", "bar"),
)
assert_eq(
ca.to_pandas_index(),
pd.MultiIndex.from_tuples(
(("a", "b"), ("c", "d")), names=("foo", "bar")
),
)
def test_column_size_mismatch():
"""
Test that constructing a CA from columns of
differing sizes throws an error.
"""
with pytest.raises(ValueError):
_ = ColumnAccessor({"a": [1], "b": [1, 2]})
def test_iter(simple_data):
"""
Test that iterating over the CA
yields column names.
"""
ca = ColumnAccessor(simple_data)
for expect_key, got_key in zip(simple_data, ca):
assert expect_key == got_key
def test_select_by_index_empty():
ca = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("b", "x", ""): [4, 5, 6],
("a", "d", "e"): [3, 4, 5],
},
multiindex=True,
)
expect = ColumnAccessor({},
multiindex=True,
level_names=((None, None, None)))
got = ca.select_by_index(slice(None, 0))
check_ca_equal(expect, got)
got = ca.select_by_index([])
check_ca_equal(expect, got)
def test_select_by_index_simple():
"""
Test getting a column by label
"""
ca = ColumnAccessor({"a": [1, 2, 3], "b": [2, 3, 4]})
check_ca_equal(ca.select_by_index(0), ColumnAccessor({"a": [1, 2, 3]}))
check_ca_equal(ca.select_by_index(1), ColumnAccessor({"b": [2, 3, 4]}))
check_ca_equal(ca.select_by_index([0, 1]), ca)
check_ca_equal(ca.select_by_index(slice(0, None)), ca)
def test_replace_level_values_MultiColumn():
ca = ColumnAccessor(
{
("a", 1): [1, 2, 3],
("a", 2): [2, 3, 4],
("b", 1): [3, 4, 5]
},
multiindex=True,
)
expect = ColumnAccessor(
{
("f", 1): [1, 2, 3],
("f", 2): [2, 3, 4],
("b", 1): [3, 4, 5]
},
multiindex=True,
)
got = ca.rename_levels(mapper={"a": "f"}, level=0)
check_ca_equal(expect, got)
def test_replace_level_values_RangeIndex():
ca = ColumnAccessor(
{
("a"): [1, 2, 3],
("b"): [2, 3, 4],
("c"): [3, 4, 5]
},
multiindex=False,
)
expect = ColumnAccessor(
{
("f"): [1, 2, 3],
("b"): [2, 3, 4],
("c"): [3, 4, 5]
},
multiindex=False,
)
got = ca.rename_levels(mapper={"a": "f"}, level=0)
check_ca_equal(expect, got)
def test_select_by_index_multiindex():
"""
Test getting column(s) by label with MultiIndex
"""
ca = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("b", "x", ""): [4, 5, 6],
("a", "d", "e"): [3, 4, 5],
},
multiindex=True,
)
expect = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("b", "x", ""): [4, 5, 6],
},
multiindex=True,
)
got = ca.select_by_index(slice(0, 3))
check_ca_equal(expect, got)
expect = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("a", "d", "e"): [3, 4, 5],
},
multiindex=True,
)
got = ca.select_by_index([0, 1, 3])
check_ca_equal(expect, got)
def test_select_by_label_multiindex_slice():
ca = ColumnAccessor(
{
("a", "b", "c"): [1, 2, 3],
("a", "b", "e"): [2, 3, 4],
("a", "d", "e"): [3, 4, 5],
("b", "x", ""): [4, 5, 6],
},
multiindex=True,
) # pandas needs columns to be sorted to do slicing with multiindex
expect = ca
got = ca.select_by_label(slice(None, None))
check_ca_equal(expect, got)
expect = ColumnAccessor(
{
("a", "b", "e"): [2, 3, 4],
("a", "d", "e"): [3, 4, 5],
("b", "x", ""): [4, 5, 6],
},
multiindex=True,
)
got = ca.select_by_label(slice(("a", "b", "e"), ("b", "x", "")))
check_ca_equal(expect, got)
def test_to_pandas_simple(simple_data):
"""
Test that a ColumnAccessor converts to a correct pd.Index
"""
ca = ColumnAccessor(simple_data)
assert_eq(ca.to_pandas_index(), pd.DataFrame(simple_data).columns)
def test_by_label_list():
ca = ColumnAccessor({"a": [1, 2, 3], "b": [2, 3, 4], "c": [3, 4, 5]})
expect = ColumnAccessor({"b": [2, 3, 4], "c": [3, 4, 5]})
got = ca.select_by_label(["b", "c"])
check_ca_equal(expect, got)
def timeseries(
start="2000-01-01",
end="2000-01-31",
freq="1s",
dtypes=None,
nulls_frequency=0,
seed=None,
):
"""Create timeseries dataframe with random data
Parameters
----------
start : datetime (or datetime-like string)
Start of time series
end : datetime (or datetime-like string)
End of time series
dtypes : dict
Mapping of column names to types.
Valid types include {float, int, str, 'category'}.
If none is provided, this defaults to
``{"name": "category", "id": int, "x": float, "y": float}``
freq : string
String like '2s' or '1H' or '12W' for the time series frequency
nulls_frequency : float
Fill the series with the specified proportion of nulls. Default is 0.
seed : int (optional)
Randomstate seed
Examples
--------
>>> import cudf as gd
>>> gdf = gd.datasets.timeseries()
>>> gdf.head() # doctest: +SKIP
timestamp id name x y
2000-01-01 00:00:00 967 Jerry -0.031348 -0.040633
2000-01-01 00:00:01 1066 Michael -0.262136 0.307107
2000-01-01 00:00:02 988 Wendy -0.526331 0.128641
2000-01-01 00:00:03 1016 Yvonne 0.620456 0.767270
2000-01-01 00:00:04 998 Ursula 0.684902 -0.463278
"""
if dtypes is None:
dtypes = {"name": "category", "id": int, "x": float, "y": float}
index = pd.DatetimeIndex(
pd.date_range(start, end, freq=freq, name="timestamp"))
state = np.random.RandomState(seed)
columns = {k: make[dt](len(index), state) for k, dt in dtypes.items()}
df = pd.DataFrame(columns, index=index, columns=sorted(columns))
if df.index[-1] == end:
df = df.iloc[:-1]
gdf = cudf.from_pandas(df)
for col in gdf:
mask = state.choice(
[True, False],
size=len(index),
p=[1 - nulls_frequency, nulls_frequency],
)
mask_buf = bools_to_mask(cudf.core.column.as_column(mask))
masked_col = gdf[col]._column.set_mask(mask_buf)
gdf[col] = cudf.Series._from_data(ColumnAccessor({None: masked_col}),
index=gdf.index)
return gdf
def test_to_pandas_multiindex(mi_data):
ca = ColumnAccessor(mi_data, multiindex=True)
assert_eq(ca.to_pandas_index(), pd.DataFrame(mi_data).columns)
def test_select_by_label_simple_slice():
ca = ColumnAccessor({"a": [1, 2, 3], "b": [2, 3, 4], "c": [3, 4, 5]})
expect = ColumnAccessor({"b": [2, 3, 4], "c": [3, 4, 5]})
got = ca.select_by_label(slice("b", "c"))
check_ca_equal(expect, got)
def _data(self):
from cudf.core.column_accessor import ColumnAccessor
return ColumnAccessor({self.name: self._values})