def test_get_slice_bound_missing(label, side, kind):
mylist = [2, 4, 6, 8, 10]
index = GenericIndex(mylist)
index_pd = pd.Index(mylist)
assert index.get_slice_bound(
label, side, kind
) == index_pd.get_slice_bound(label, side, kind)
def test_get_slice_bound(testlist, side, kind):
index = GenericIndex(testlist)
index_pd = pd.Index(testlist)
for label in testlist:
assert index.get_slice_bound(
label, side, kind
) == index_pd.get_slice_bound(label, side, kind)
def test_index_comparision():
start, stop = 10, 34
rg = RangeIndex(start, stop)
gi = GenericIndex(np.arange(start, stop))
assert rg.equals(gi)
assert gi.equals(rg)
assert not rg[:-1].equals(gi)
assert rg[:-1].equals(gi[:-1])
def test_get_slice_bound_missing_str(label, side):
# Slicing for monotonic string indices not yet supported
# when missing values are specified (allowed in pandas)
mylist = ["b", "d", "f"]
index = GenericIndex(mylist)
index_pd = pd.Index(mylist)
assert index.get_slice_bound(
label, side, "getitem"
) == index_pd.get_slice_bound(label, side, "getitem")
def test_index_immutable():
start, stop = 10, 34
rg = RangeIndex(start, stop)
with pytest.raises(TypeError):
rg[1] = 5
gi = GenericIndex(np.arange(start, stop))
with pytest.raises(TypeError):
gi[1] = 5
def test_index_comparision():
start, stop = 10, 34
rg = RangeIndex(start, stop)
gi = GenericIndex(np.arange(start, stop))
assert rg == gi
assert gi == rg
assert rg[:-1] != gi
assert rg[:-1] == gi[:-1]
def test_generic_index(testlist):
index = GenericIndex(testlist)
index_pd = pd.Index(testlist)
assert index.is_unique == index_pd.is_unique
assert index.is_monotonic == index_pd.is_monotonic
assert index.is_monotonic_increasing == index_pd.is_monotonic_increasing
assert index.is_monotonic_decreasing == index_pd.is_monotonic_decreasing
def test_index_find_label_range():
idx = GenericIndex(np.asarray([4, 5, 6, 10]))
assert idx.find_label_range(4, 6) == (0, 3)
assert idx.find_label_range(5, 10) == (1, 4)
# Last value not found
with pytest.raises(ValueError) as raises:
idx.find_label_range(0, 6)
raises.match("value not found")
# Last value not found
with pytest.raises(ValueError) as raises:
idx.find_label_range(4, 11)
raises.match("value not found")
def apply_multiindex_or_single_index(self, result):
if len(result) == 0:
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(self._by) == 1 or len(final_result.columns) == 0:
dtype = 'float64' if len(self._by) == 1 else 'object'
name = self._by[0] if len(self._by) == 1 else None
from cudf.dataframe.index import GenericIndex
index = GenericIndex(Series([], dtype=dtype))
index.name = name
final_result.index = index
else:
mi = MultiIndex(source_data=result[self._by])
mi.names = self._by
final_result.index = mi
if len(final_result.columns) == 1 and hasattr(self, "_gotattr"):
final_series = Series([], name=final_result.columns[0])
final_series.index = final_result.index
return final_series
return final_result
if len(self._by) == 1:
from cudf.dataframe import index
idx = index.as_index(result[self._by[0]])
idx.name = self._by[0]
result = result.drop(idx.name)
if idx.name == self._LEVEL_0_INDEX_NAME:
idx.name = self._original_index_name
result = result.set_index(idx)
return result
else:
multi_index = MultiIndex(source_data=result[self._by])
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(final_result.columns) == 1 and hasattr(self, "_gotattr"):
final_series = Series(final_result[final_result.columns[0]])
final_series.name = final_result.columns[0]
final_series.index = multi_index
return final_series
return final_result.set_index(multi_index)
def test_name():
idx = GenericIndex(np.asarray([4, 5, 6, 10]), name='foo')
assert idx.name == 'foo'
def test_reductions(func):
x = np.asarray([4, 5, 6, 10])
idx = GenericIndex(np.asarray([4, 5, 6, 10]))
assert func(x) == func(idx)
def apply_multiindex_or_single_index(self, result):
if len(result) == 0:
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(self._by) == 1 or len(final_result.columns) == 0:
if len(self._by) == 1:
dtype = self._df[self._by[0]]
else:
dtype = 'object'
name = self._by[0] if len(self._by) == 1 else None
from cudf.dataframe.index import GenericIndex
index = GenericIndex(Series([], dtype=dtype))
index.name = name
final_result.index = index
else:
mi = MultiIndex(source_data=result[self._by])
mi.names = self._by
final_result.index = mi
return final_result
if len(self._by) == 1:
from cudf.dataframe import index
idx = index.as_index(result[self._by[0]])
name = self._by[0]
if isinstance(name, str):
name = self._by[0].split('+')
if name[0] == 'cudfvalcol':
idx.name = name[1]
else:
idx.name = name[0]
result = result.drop(self._by[0])
for col in result.columns:
if isinstance(col, str):
colnames = col.split('+')
if colnames[0] == 'cudfvalcol':
result[colnames[1]] = result[col]
result = result.drop(col)
if idx.name == _LEVEL_0_INDEX_NAME:
idx.name = self._original_index_name
result = result.set_index(idx)
return result
else:
for col in result.columns:
if isinstance(col, str):
colnames = col.split('+')
if colnames[0] == 'cudfvalcol':
result[colnames[1]] = result[col]
result = result.drop(col)
new_by = []
for by in self._by:
if isinstance(col, str):
splitby = by.split('+')
if splitby[0] == 'cudfvalcol':
new_by.append(splitby[1])
else:
new_by.append(splitby[0])
else:
new_by.append(by)
self._by = new_by
multi_index = MultiIndex(source_data=result[self._by])
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(final_result.columns) > 0:
return final_result.set_index(multi_index)
else:
return result.set_index(multi_index)
def apply_multiindex_or_single_index(self, result):
if len(result) == 0:
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(self._by) == 1 or len(final_result.columns) == 0:
dtype = 'float64' if len(self._by) == 1 else 'object'
name = self._by[0] if len(self._by) == 1 else None
from cudf.dataframe.index import GenericIndex
index = GenericIndex(Series([], dtype=dtype))
index.name = name
final_result.index = index
else:
levels = []
codes = []
names = []
for by in self._by:
levels.append([])
codes.append([])
names.append(by)
mi = MultiIndex(levels, codes)
mi.names = names
final_result.index = mi
if len(final_result.columns) == 1 and hasattr(self, "_gotattr"):
final_series = Series([], name=final_result.columns[0])
final_series.index = final_result.index
return final_series
return final_result
if len(self._by) == 1:
from cudf.dataframe import index
idx = index.as_index(result[self._by[0]])
idx.name = self._by[0]
result = result.drop(idx.name)
if idx.name == self._LEVEL_0_INDEX_NAME:
idx.name = self._original_index_name
result = result.set_index(idx)
return result
else:
levels = []
codes = DataFrame()
names = []
# Note: This is an O(N^2) solution using gpu masking
# to compute new codes for the MultiIndex. There may be
# a faster solution that could be executed on gpu at the same
# time the groupby is calculated.
for by in self._by:
level = result[by].unique()
replaced = result[by].replace(level, range(len(level)))
levels.append(level)
codes[by] = Series(replaced, dtype="int32")
names.append(by)
multi_index = MultiIndex(levels=levels, codes=codes, names=names)
final_result = DataFrame()
for col in result.columns:
if col not in self._by:
final_result[col] = result[col]
if len(final_result.columns) == 1 and hasattr(self, "_gotattr"):
final_series = Series(final_result[final_result.columns[0]])
final_series.name = final_result.columns[0]
final_series.index = multi_index
return final_series
return final_result.set_index(multi_index)