def _get_row_major(self, df, row_tuple):
valid_indices = self._compute_validity_mask(df, row_tuple)
from cudf import Series
result = df.take(Series(valid_indices))
# Build new index - INDEX based MultiIndex
# ---------------
from cudf import DataFrame
out_index = DataFrame()
# Select the last n-k columns where n is the number of source
# levels and k is the length of the indexing tuple
for k in range(len(row_tuple), len(df.index.levels)):
out_index.add_column(df.index.names[k],
df.index.codes[df.index.codes.columns[k]])
# If there's only one column remaining in the output index, convert
# it into a StringIndex and name the final index values according
# to the proper codes.
if len(out_index.columns) == 1:
out_index = []
for val in result.index.codes[result.index.codes.columns[len(result.index.codes.columns)-1]]: # noqa: E501
out_index.append(result.index.levels[
len(result.index.codes.columns)-1][val])
# TODO: Warning! The final index column could be arbitrarily
# ordered integers, not Strings, so we need to check for that
# dtype and produce a GenericIndex instead of a StringIndex
out_index = StringIndex(out_index)
out_index.name = result.index.names[len(result.index.names)-1]
result.index = out_index
else:
# Otherwise pop the leftmost levels, names, and codes from the
# source index until it has the correct number of columns (n-k)
if(len(out_index.columns)) > 0:
result.reset_index(drop=True)
result.index = result.index._popn(len(row_tuple))
return result
def test_string_index(testlist):
index = StringIndex(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_string_index():
pdf = pd.DataFrame(np.random.rand(5, 5))
gdf = DataFrame.from_pandas(pdf)
stringIndex = ["a", "b", "c", "d", "e"]
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = np.array(["a", "b", "c", "d", "e"])
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = StringIndex(["a", "b", "c", "d", "e"], name="name")
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = StringColumn(["a", "b", "c", "d", "e"], name="name")
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
def test_string_index():
pdf = pd.DataFrame(np.random.rand(5, 5))
gdf = DataFrame.from_pandas(pdf)
stringIndex = ['a', 'b', 'c', 'd', 'e']
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = np.array(['a', 'b', 'c', 'd', 'e'])
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = StringIndex(['a', 'b', 'c', 'd', 'e'], name='name')
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
stringIndex = StringColumn(['a', 'b', 'c', 'd', 'e'], name='name')
pdf.index = stringIndex
gdf.index = stringIndex
assert_eq(pdf, gdf)
def _get_column_major(self, df, row_tuple):
valid_indices = self._compute_validity_mask(df, row_tuple)
from cudf import DataFrame
result = DataFrame()
for ix, col in enumerate(df.columns):
if ix in valid_indices:
result[ix] = list(df._cols.values())[ix]
# Build new index - COLUMN based MultiIndex
# ---------------
if len(row_tuple) < len(self.levels):
columns = self._popn(len(row_tuple))
result.columns = columns.take(valid_indices)
else:
result.columns = self.take(valid_indices)
if len(result.columns.levels) == 1:
columns = []
for code in result.columns.codes[result.columns.codes.columns[0]]:
columns.append(result.columns.levels[0][code])
name = result.columns.names[0]
result.columns = StringIndex(columns, name=name)
return result