def _getitem_tuple_arg(self, arg):
from cudf.core.dataframe import Series, DataFrame
from cudf.core.column import column
from cudf.core.index import as_index
from cudf.utils.cudautils import arange
from cudf import MultiIndex
# Step 1: Gather columns
if isinstance(self._df.columns, MultiIndex):
columns_df = self._df.columns._get_column_major(self._df, arg[1])
if isinstance(columns_df, Series):
return columns_df
else:
columns = self._get_column_selection(arg[1])
columns_df = DataFrame(index=self._df.index)
for i, col in enumerate(columns):
columns_df.insert(i, col, self._df[col])
# Step 2: Gather rows
if isinstance(columns_df.index, MultiIndex):
return columns_df.index._get_row_major(columns_df, arg[0])
else:
if isinstance(self._df.columns, MultiIndex):
if isinstance(arg[0], slice):
start, stop, step = arg[0].indices(len(columns_df))
indices = arange(start, stop, step)
df = columns_df.take(indices)
else:
df = columns_df.take(arg[0])
else:
df = DataFrame()
for col in columns_df.columns:
# need Series() in case a scalar is returned
df[col] = Series(columns_df[col].loc[arg[0]])
df.columns = columns_df.columns
# Step 3: Gather index
if df.shape[0] == 1: # we have a single row
if isinstance(arg[0], slice):
start = arg[0].start
if start is None:
start = self._df.index[0]
df.index = as_index(start)
else:
row_selection = column.as_column(arg[0])
if pd.api.types.is_bool_dtype(row_selection.dtype):
df.index = self._df.index.take(row_selection)
else:
df.index = as_index(row_selection)
# Step 4: Downcast
if self._can_downcast_to_series(df, arg):
return self._downcast_to_series(df, arg)
return df
def _getitem_tuple_arg(self, arg):
from cudf import MultiIndex
from cudf.core.dataframe import DataFrame, Series
from cudf.core.index import as_index
# Iloc Step 1:
# Gather the columns specified by the second tuple arg
columns_df = self._get_column_selection(arg[1])
columns_df._index = self._df._index
# Iloc Step 2:
# Gather the rows specified by the first tuple arg
if isinstance(columns_df.index, MultiIndex):
if isinstance(arg[0], slice):
df = columns_df[arg[0]]
else:
df = columns_df.index._get_row_major(columns_df, arg[0])
if (len(df) == 1 and len(columns_df) >= 1) and not (isinstance(
arg[0], slice) or isinstance(arg[1], slice)):
# Pandas returns a numpy scalar in this case
return df[0]
if self._can_downcast_to_series(df, arg):
return self._downcast_to_series(df, arg)
return df
else:
df = DataFrame()
for i, col in enumerate(columns_df._columns):
# need Series() in case a scalar is returned
df[i] = Series(col[arg[0]])
df.index = as_index(columns_df.index[arg[0]])
df.columns = columns_df.columns
# Iloc Step 3:
# Reindex
if df.shape[0] == 1: # we have a single row without an index
df.index = as_index(self._df.index[arg[0]])
# Iloc Step 4:
# Downcast
if self._can_downcast_to_series(df, arg):
return self._downcast_to_series(df, arg)
if df.shape[0] == 0 and df.shape[1] == 0 and isinstance(arg[0], slice):
from cudf.core.index import RangeIndex
slice_len = len(self._df)
start, stop, step = arg[0].indices(slice_len)
df._index = RangeIndex(start, stop)
return df
def _getitem_tuple_arg(self, arg):
from cudf import MultiIndex
from cudf.core.dataframe import DataFrame, Series
from cudf.core.column import column_empty
from cudf.core.index import as_index
# Iloc Step 1:
# Gather the columns specified by the second tuple arg
columns = self._get_column_selection(arg[1])
if isinstance(self._df.columns, MultiIndex):
columns_df = self._df.columns._get_column_major(self._df, arg[1])
if (len(columns_df) == 0 and len(columns_df.columns) == 0
and not isinstance(arg[0], slice)):
result = Series(column_empty(0, dtype="float64"), name=arg[0])
result._index = columns_df.columns.copy(deep=False)
return result
else:
if isinstance(arg[0], slice):
columns_df = DataFrame()
for i, col in enumerate(columns):
columns_df.insert(i, col, self._df[col])
columns_df._index = self._df._index
else:
columns_df = self._df._columns_view(columns)
# Iloc Step 2:
# Gather the rows specified by the first tuple arg
if isinstance(columns_df.index, MultiIndex):
df = columns_df.index._get_row_major(columns_df, arg[0])
if (len(df) == 1 and len(columns_df) >= 1) and not (isinstance(
arg[0], slice) or isinstance(arg[1], slice)):
# Pandas returns a numpy scalar in this case
return df[0]
if self._can_downcast_to_series(df, arg):
return self._downcast_to_series(df, arg)
return df
else:
df = DataFrame()
for i, col in enumerate(columns_df._columns):
# need Series() in case a scalar is returned
df[i] = Series(col[arg[0]])
df.index = as_index(columns_df.index[arg[0]])
df.columns = columns_df.columns
# Iloc Step 3:
# Reindex
if df.shape[0] == 1: # we have a single row without an index
if isinstance(arg[0], slice):
start = arg[0].start
if start is None:
start = 0
df.index = as_index(self._df.index[start])
else:
df.index = as_index(self._df.index[arg[0]])
# Iloc Step 4:
# Downcast
if self._can_downcast_to_series(df, arg):
if isinstance(df.columns, MultiIndex):
if len(df) > 0 and not (isinstance(arg[0], slice)
or isinstance(arg[1], slice)):
return list(df._data.values())[0][0]
elif df.shape[1] > 1:
result = self._downcast_to_series(df, arg)
result.index = df.columns
return result
elif not isinstance(arg[0], slice):
if len(df._data) == 0:
return Series(
column_empty(0, dtype="float64"),
index=df.columns,
name=arg[0],
)
else:
result_series = df[df.columns[0]]
result_series.index = df.columns
result_series.name = arg[0]
return result_series
else:
return df[df.columns[0]]
return self._downcast_to_series(df, arg)
if df.shape[0] == 0 and df.shape[1] == 0:
from cudf.core.index import RangeIndex
slice_len = arg[0].stop or len(self._df)
start, stop, step = arg[0].indices(slice_len)
df._index = RangeIndex(start, stop)
return df
