def make_aggregate_nullmask(df, columns=None, op="and"):
out_mask = None
for k in columns or df.columns:
if not df[k].has_null_mask:
continue
nullmask = df[k].nullmask
if out_mask is None:
out_mask = columnops.as_column(nullmask.copy(),
dtype=utils.mask_dtype)
continue
cpp_binops.apply_op(columnops.as_column(nullmask), out_mask, out_mask,
op)
return out_mask
def numeric_column_binop(lhs, rhs, op, out_dtype, reflect=False):
if reflect:
lhs, rhs = rhs, lhs
nvtx_range_push("CUDF_BINARY_OP", "orange")
# Allocate output
masked = False
name = None
if np.isscalar(lhs):
masked = rhs.has_null_mask
row_count = len(rhs)
name = rhs.name
elif np.isscalar(rhs):
masked = lhs.has_null_mask
row_count = len(lhs)
name = lhs.name
else:
masked = lhs.has_null_mask or rhs.has_null_mask
row_count = len(lhs)
is_op_comparison = op in ["lt", "gt", "le", "ge", "eq", "ne"]
out = columnops.column_empty(row_count, dtype=out_dtype, masked=masked)
# Call and fix null_count
null_count = cpp_binops.apply_op(lhs, rhs, out, op)
if is_op_comparison:
out.fillna(op == "ne", inplace=True)
else:
out = out.replace(null_count=null_count)
result = out.view(NumericalColumn, dtype=out_dtype, name=name)
nvtx_range_pop()
return result
def binop(lhs, rhs, op, out_dtype):
nvtx_range_push("CUDF_BINARY_OP", "orange")
masked = lhs.has_null_mask or rhs.has_null_mask
out = columnops.column_empty_like(lhs, dtype=out_dtype, masked=masked)
null_count = cpp_binops.apply_op(lhs, rhs, out, op)
out = out.replace(null_count=null_count)
nvtx_range_pop()
return out
def string_column_binop(lhs, rhs, op):
nvtx_range_push("CUDF_BINARY_OP", "orange")
# Allocate output
masked = lhs.has_null_mask or rhs.has_null_mask
out = columnops.column_empty_like(lhs, dtype='bool', masked=masked)
# Call and fix null_count
null_count = cpp_binops.apply_op(lhs=lhs, rhs=rhs, out=out, op=op)
result = out.replace(null_count=null_count)
nvtx_range_pop()
return result
def numeric_column_binop(lhs, rhs, op, out_dtype):
nvtx_range_push("CUDF_BINARY_OP", "orange")
# Allocate output
masked = lhs.has_null_mask or rhs.has_null_mask
out = columnops.column_empty_like(lhs, dtype=out_dtype, masked=masked)
# Call and fix null_count
null_count = cpp_binops.apply_op(lhs, rhs, out, op)
out = out.replace(null_count=null_count)
result = out.view(NumericalColumn, dtype=out_dtype)
nvtx_range_pop()
return result
def numeric_column_binop(lhs, rhs, op, out_dtype):
nvtx_range_push("CUDF_BINARY_OP", "orange")
# Allocate output
masked = lhs.has_null_mask or rhs.has_null_mask
out = columnops.column_empty_like(lhs, dtype=out_dtype, masked=masked)
# Call and fix null_count
if lhs.dtype != rhs.dtype or op not in _binary_impl:
# Use JIT implementation
null_count = cpp_binops.apply_op(lhs=lhs, rhs=rhs, out=out, op=op)
else:
# Use compiled implementation
null_count = _gdf.apply_binaryop(_binary_impl[op], lhs, rhs, out)
out = out.replace(null_count=null_count)
result = out.view(NumericalColumn, dtype=out_dtype)
nvtx_range_pop()
return result
def numeric_column_binop(lhs, rhs, op, out_dtype, reflect=False):
if reflect:
lhs, rhs = rhs, lhs
nvtx_range_push("CUDF_BINARY_OP", "orange")
# Allocate output
masked = False
if np.isscalar(lhs):
masked = rhs.has_null_mask
row_count = len(rhs)
elif np.isscalar(rhs):
masked = lhs.has_null_mask
row_count = len(lhs)
else:
masked = lhs.has_null_mask or rhs.has_null_mask
row_count = len(lhs)
out = columnops.column_empty(row_count, dtype=out_dtype, masked=masked)
# Call and fix null_count
null_count = cpp_binops.apply_op(lhs, rhs, out, op)
out = out.replace(null_count=null_count)
result = out.view(NumericalColumn, dtype=out_dtype)
nvtx_range_pop()
return result