def test_multiindex_construction():
levels = [['a', 'b'], ['c', 'd']]
codes = [[0, 1], [1, 0]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels=levels, codes=codes)
assert_eq(pmi, mi)
def test_multiindex_construction():
levels = [["a", "b"], ["c", "d"]]
codes = [[0, 1], [1, 0]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels=levels, codes=codes)
assert_eq(pmi, mi)
def test_multiindex_equals():
# mi made from groupby
# mi made manually to be identical
# are they equal?
gdf = cudf.DataFrame({
"x": [1, 5, 3, 4, 1],
"y": [1, 1, 2, 2, 5],
"z": [0, 1, 0, 1, 0]
})
mi1 = gdf.groupby(["x", "y"]).mean().index
mi2 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
assert_eq(mi1.equals(mi2), True)
# mi made from two groupbys, are they equal?
mi2 = gdf.groupby(["x", "y"]).max().index
assert_eq(mi1.equals(mi2), True)
# mi made manually twice are they equal?
mi1 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
mi2 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
assert_eq(mi1.equals(mi2), True)
# mi made from different groupbys are they not equal?
mi1 = gdf.groupby(["x", "y"]).mean().index
mi2 = gdf.groupby(["x", "z"]).mean().index
assert_eq(mi1.equals(mi2), False)
# mi made from different manuals are they not equal?
mi1 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
mi2 = cudf.MultiIndex(
levels=[[0, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
assert_eq(mi1.equals(mi2), False)
def test_multiindex_types():
codes = [[0, 1], [1, 0]]
levels = [[0, 1], [2, 3]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
levels = [[1.2, 2.1], [1.3, 3.1]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
levels = [["a", "b"], ["c", "d"]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
def test_multiindex_types():
codes = [[0, 1], [1, 0]]
levels = [[0, 1], [2, 3]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
levels = [[1.2, 2.1], [1.3, 3.1]]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
levels = [['a', 'b'], ['c', 'd']]
pmi = pd.MultiIndex(levels, codes)
mi = cudf.MultiIndex(levels, codes)
assert_eq(pmi, mi)
def test_multiindex_index_and_columns():
gdf = cudf.DataFrame()
gdf['x'] = np.random.randint(0, 5, 5)
gdf['y'] = np.random.randint(0, 5, 5)
pdf = gdf.to_pandas()
mi = cudf.MultiIndex(levels=[[0, 1, 2], [3, 4]], codes=[[0, 0, 1, 1, 2],
[0, 1, 0, 1, 1]], names=['x', 'y'])
gdf.index = mi
mc = cudf.MultiIndex(levels=[['val'], ['mean', 'min']],
codes=[[0, 0], [0, 1]])
gdf.columns = mc
pdf.index = mi
pdf.index.names = ['x', 'y']
pdf.columns = mc
assert_eq(pdf, gdf)
def test_difference():
midx = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
midx2 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3, 3], [0, 2, 1, 1, 0, 2]],
names=["x", "y"],
)
expected = midx2.to_pandas().difference(midx.to_pandas())
actual = midx2.difference(midx)
assert_eq(expected, actual)
def test_MI():
gdf = cudf.DataFrame(
{
"a": np.random.randint(0, 4, 10),
"b": np.random.randint(0, 4, 10),
"c": np.random.randint(0, 4, 10),
}
)
levels = [["a", "b", "c", "d"], ["w", "x", "y", "z"], ["m", "n"]]
codes = cudf.DataFrame(
{
"a": [0, 0, 0, 0, 1, 1, 2, 2, 3, 3],
"b": [0, 1, 2, 3, 0, 1, 2, 3, 0, 1],
"c": [0, 1, 0, 1, 0, 1, 0, 1, 0, 1],
}
)
pd.options.display.max_rows = 999
pd.options.display.max_columns = 0
gdf = gdf.set_index(cudf.MultiIndex(levels=levels, codes=codes))
pdf = gdf.to_pandas()
gdfT = gdf.T
pdfT = pdf.T
assert gdf.__repr__() == pdf.__repr__()
assert gdf.index.__repr__() == pdf.index.__repr__()
assert gdfT.__repr__() == pdfT.__repr__()
pd.reset_option("display.max_rows")
pd.reset_option("display.max_columns")
def test_multiindex_df_assignment():
pdf = pd.DataFrame({'x': [1, 2, 3]})
gdf = cudf.from_pandas(pdf)
pdf.index = pd.MultiIndex([['a', 'b'], ['c', 'd']], [[0, 1, 0], [1, 0, 1]])
gdf.index = cudf.MultiIndex(levels=[['a', 'b'], ['c', 'd']],
codes=[[0, 1, 0], [1, 0, 1]])
assert_eq(pdf, gdf)
def test_multiindex_series_assignment():
ps = pd.Series([1, 2, 3])
gs = cudf.from_pandas(ps)
ps.index = pd.MultiIndex([["a", "b"], ["c", "d"]], [[0, 1, 0], [1, 0, 1]])
gs.index = cudf.MultiIndex(levels=[["a", "b"], ["c", "d"]],
codes=[[0, 1, 0], [1, 0, 1]])
assert_eq(ps, gs)
def test_multiindex_copy():
# mi made from groupby
# make a copy with .copy
gdf = cudf.DataFrame({
"x": [1, 5, 3, 4, 1],
"y": [1, 1, 2, 2, 5],
"z": [0, 1, 0, 1, 0]
})
mi1 = gdf.groupby(["x", "y"]).mean().index
mi2 = mi1.copy(deep=False)
assert_eq(mi1, mi2)
mi2 = mi1.copy(deep=True)
assert_eq(mi1, mi2)
# mi made manually
# make a copy with .copy
# is it equal?
mi1 = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
mi2 = mi1.copy(deep=False)
assert_eq(mi1, mi2)
mi2 = mi1.copy(deep=True)
assert_eq(mi1, mi2)
def test_multiindex_df_assignment():
pdf = pd.DataFrame({"x": [1, 2, 3]})
gdf = cudf.from_pandas(pdf)
pdf.index = pd.MultiIndex([["a", "b"], ["c", "d"]], [[0, 1, 0], [1, 0, 1]])
gdf.index = cudf.MultiIndex(levels=[["a", "b"], ["c", "d"]],
codes=[[0, 1, 0], [1, 0, 1]])
assert_eq(pdf, gdf)
def test_array_func_missing_cudf_multi_index(func):
levels = [["a", "b"], ["c", "d"]]
codes = [[0, 1], [1, 0]]
cudf_multi_index = cudf.MultiIndex(levels, codes)
with pytest.raises(TypeError):
func(cudf_multi_index)
def test_multiindex_index_and_columns():
gdf = cudf.DataFrame()
gdf["x"] = np.random.randint(0, 5, 5)
gdf["y"] = np.random.randint(0, 5, 5)
pdf = gdf.to_pandas()
mi = cudf.MultiIndex(
levels=[[0, 1, 2], [3, 4]],
codes=[[0, 0, 1, 1, 2], [0, 1, 0, 1, 1]],
names=["x", "y"],
)
gdf.index = mi
mc = cudf.MultiIndex(levels=[["val"], ["mean", "min"]],
codes=[[0, 0], [0, 1]])
gdf.columns = mc
pdf.index = mi.to_pandas()
pdf.columns = mc.to_pandas()
assert_eq(pdf, gdf)
def test_multiindex_values_host():
midx = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
pmidx = midx.to_pandas()
assert_eq(midx.values_host, pmidx.values)
def keys(self):
nkeys = len(self._key_columns)
if nkeys > 1:
return cudf.MultiIndex(
source_data=cudf.DataFrame(
dict(zip(range(nkeys), self._key_columns))),
names=self.names,
)
else:
return cudf.core.index.as_index(self._key_columns[0],
name=self.names[0])
def test_multiindex_equality():
# mi made from groupby
# mi made manually to be identical
# are they equal?
gdf = cudf.DataFrame({
'x': [1, 5, 3, 4, 1],
'y': [1, 1, 2, 2, 5],
'z': [0, 1, 0, 1, 0]
})
mi1 = gdf.groupby(['x', 'y']).mean().index
mi2 = cudf.MultiIndex(levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=['x', 'y'])
assert_eq(mi1, mi2)
# mi made from two groupbys, are they equal?
mi2 = gdf.groupby(['x', 'y']).max().index
assert_eq(mi1, mi2)
# mi made manually twice are they equal?
mi1 = cudf.MultiIndex(levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=['x', 'y'])
mi1 = cudf.MultiIndex(levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=['x', 'y'])
assert_eq(mi1, mi2)
# mi made from different groupbys are they not equal?
mi1 = gdf.groupby(['x', 'y']).mean().index
mi1 = gdf.groupby(['x', 'z']).mean().index
assert_neq(mi1, mi2)
# mi made from different manuals are they not equal?
mi1 = cudf.MultiIndex(levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=['x', 'y'])
mi1 = cudf.MultiIndex(levels=[[0, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=['x', 'y'])
assert_neq(mi1, mi2)
def test_multiindex_values():
midx = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
result = midx.values
assert isinstance(result, cp.ndarray)
np.testing.assert_array_equal(
result.get(), np.array([[1, 1], [1, 5], [3, 2], [4, 2], [5, 1]]))
def test_multiindex_levels_codes_validation():
levels = [["a", "b"], ["c", "d"]]
# Codes not a sequence of sequences
with pytest.raises(TypeError):
pd.MultiIndex(levels, [0, 1])
with pytest.raises(TypeError):
cudf.MultiIndex(levels, [0, 1])
# Codes don't match levels
with pytest.raises(ValueError):
pd.MultiIndex(levels, [[0], [1], [1]])
with pytest.raises(ValueError):
cudf.MultiIndex(levels, [[0], [1], [1]])
# Largest code greater than number of levels
with pytest.raises(ValueError):
pd.MultiIndex(levels, [[0, 1], [0, 2]])
with pytest.raises(ValueError):
cudf.MultiIndex(levels, [[0, 1], [0, 2]])
# Unequal code lengths
with pytest.raises(ValueError):
pd.MultiIndex(levels, [[0, 1], [0]])
with pytest.raises(ValueError):
cudf.MultiIndex(levels, [[0, 1], [0]])
# Didn't pass levels and codes
with pytest.raises(TypeError):
pd.MultiIndex()
with pytest.raises(TypeError):
cudf.MultiIndex()
# Didn't pass non zero levels and codes
with pytest.raises(ValueError):
pd.MultiIndex([], [])
with pytest.raises(ValueError):
cudf.MultiIndex([], [])
def test_multiIndex_duplicate_names():
gi = cudf.MultiIndex(
levels=[["a", "b"], ["b", "a"]],
codes=[[0, 0], [0, 1]],
names=["a", "a"],
)
pi = pd.MultiIndex(
levels=[["a", "b"], ["b", "a"]],
codes=[[0, 0], [0, 1]],
names=["a", "a"],
)
assert_eq(gi, pi)
def test_multiindex_iter_error():
midx = cudf.MultiIndex(
levels=[[1, 3, 4, 5], [1, 2, 5]],
codes=[[0, 0, 1, 2, 3], [0, 2, 1, 1, 0]],
names=["x", "y"],
)
with pytest.raises(
TypeError,
match=re.escape(
f"{midx.__class__.__name__} object is not iterable. "
f"Consider using `.to_arrow()`, `.to_pandas()` or `.values_host` "
f"if you wish to iterate over the values."),
):
iter(midx)
def test_frequency_features():
actual = clx.features.frequency(df, "user", "computer")
expected = cudf.DataFrame({
"user": ["u1", "u2", "u3"],
"c1": [0.75, 0.00, 0.00],
"c2": [0.25, 0.50, 0.0],
"c3": [0.0, 0.5, 1.0],
})
expected = expected.set_index("user")
expected.columns = cudf.MultiIndex(
names=[None, "computer"],
codes=[[0, 0, 0], [0, 1, 2]],
levels=[["time"], ["c1", "c2", "c3"]],
)
assert expected.equals(actual)
def _concat(cls, objs):
source_data = [o._source_data for o in objs]
if len(source_data) > 1:
for index, obj in enumerate(source_data[1:]):
obj.columns = source_data[0].columns
source_data[index + 1] = obj
source_data = cudf.DataFrame._concat(source_data)
names = [None for x in source_data.columns]
objs = list(filter(lambda o: o.names is not None, objs))
for o in range(len(objs)):
for i, name in enumerate(objs[o].names):
names[i] = names[i] or name
return cudf.MultiIndex(names=names, source_data=source_data)
def test_dataframe_take_with_multiIndex(ntake):
np.random.seed(0)
df = DataFrame(index=cudf.MultiIndex(
levels=[["lama", "cow", "falcon"], ["speed", "weight", "length"]],
codes=[[0, 0, 0, 1, 1, 1, 2, 2, 2], [0, 1, 2, 0, 1, 2, 0, 1, 2]],
))
nelem = 9
df["ii"] = np.random.randint(0, 20, nelem)
df["ff"] = np.random.random(nelem)
take_indices = np.random.randint(0, len(df), ntake)
actual = df.take(take_indices)
expected = df.to_pandas().take(take_indices)
assert_eq(actual, expected)
def test_binary_features():
actual = clx.features.binary(df, "user", "computer")
expected = cudf.DataFrame({
"user": ["u1", "u2", "u3"],
"c1": [1, 0, 0],
"c2": [1, 1, 0],
"c3": [0, 1, 1]
})
expected = expected.set_index("user")
expected["c1"] = expected["c1"].astype("int32")
expected["c2"] = expected["c2"].astype("int32")
expected["c3"] = expected["c3"].astype("int32")
expected.columns = cudf.MultiIndex(
names=[None, "computer"],
codes=[[0, 0, 0], [0, 1, 2]],
levels=[["time"], ["c1", "c2", "c3"]],
)
assert expected.equals(actual)
def test_MI():
gdf = cudf.DataFrame({
"a": np.random.randint(0, 4, 10),
"b": np.random.randint(0, 4, 10),
"c": np.random.randint(0, 4, 10),
})
levels = [["a", "b", "c", "d"], ["w", "x", "y", "z"], ["m", "n"]]
codes = cudf.DataFrame({
"a": np.random.randint(0, 4, 10),
"b": np.random.randint(0, 4, 10),
"c": np.random.randint(0, 2, 10),
})
pd.options.display.max_rows = 999
gdf = gdf.set_index(cudf.MultiIndex(levels=levels, codes=codes))
pdf = gdf.to_pandas()
gdfT = gdf.T
pdfT = pdf.T
assert gdf.__repr__() == pdf.__repr__()
assert gdfT.__repr__() == pdfT.__repr__()
],
"Symbol": [
"AMZN",
"AMZN",
"AMZN",
"MSFT",
"MSFT",
"MSFT",
"NVDA",
"NVDA",
"NVDA",
],
},
cudf.MultiIndex(
levels=[[1001, 1002], [2001, 2002]],
codes=[[1, 1, 0, 0], [0, 1, 0, 1]],
names=["col1", "col2"],
),
],
)
@pytest.mark.parametrize("deep", [True, False])
def test_multiindex_copy_deep(data, deep):
"""Test memory idendity for deep copy
Case1: Constructed from GroupBy, StringColumns
Case2: Constrcuted from MultiIndex, NumericColumns
"""
same_ref = not deep
if isinstance(data, dict):
import operator
from functools import reduce
],
"Symbol": [
"AMZN",
"AMZN",
"AMZN",
"MSFT",
"MSFT",
"MSFT",
"NVDA",
"NVDA",
"NVDA",
],
},
cudf.MultiIndex(
levels=[[1001, 1002], [2001, 2002]],
codes=[[1, 1, 0, 0], [0, 1, 0, 1]],
names=["col1", "col2"],
),
],
)
@pytest.mark.parametrize("deep", [True, False])
def test_multiindex_copy_deep(data, deep):
"""Test memory identity for deep copy
Case1: Constructed from GroupBy, StringColumns
Case2: Constructed from MultiIndex, NumericColumns
"""
same_ref = not deep
if isinstance(data, dict):
import operator
from functools import reduce