Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Incorporate supported_formats property into NVT ops #1799

Merged
merged 4 commits into from
May 23, 2023
Merged

Incorporate supported_formats property into NVT ops #1799

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d52557f
Incorporate `supported_formats` property into NVT ops
karlhigley Apr 12, 2023
16bbd97
Merge branch 'main' into refactor/supported-formats
karlhigley May 11, 2023
7cecdd1
Merge branch 'main' into refactor/supported-formats
karlhigley May 22, 2023
5d6964f
Merge branch 'main' into refactor/supported-formats
karlhigley May 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions cpp/nvtabular/inference/categorify.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,6 +325,11 @@ namespace nvtabular
{
py::object supports = py::module_::import("nvtabular").attr("graph").attr("base_operator").attr("Supports");
return supports.attr("CPU_DICT_ARRAY");
})
.def_property_readonly("supported_formats", [](py::object self)
{
py::object supported = py::module_::import("nvtabular").attr("graph").attr("base_operator").attr("DataFormats");
return supported.attr("NUMPY_DICT_ARRAY");
});
}
} // namespace inference
Expand Down
5 changes: 5 additions & 0 deletions cpp/nvtabular/inference/fill.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,11 @@ namespace nvtabular
py::object supports = py::module_::import("nvtabular").attr("graph").attr("base_operator").attr("Supports");
return supports.attr("CPU_DICT_ARRAY");
})
.def_property_readonly("supported_formats", [](py::object self)
{
py::object supported = py::module_::import("nvtabular").attr("graph").attr("base_operator").attr("DataFormats");
return supported.attr("NUMPY_DICT_ARRAY");
})
.def("transform", &FillTransform::transform);
}
} // namespace inference
Expand Down
20 changes: 19 additions & 1 deletion nvtabular/ops/normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
flatten_list_column_values,
is_list_dtype,
)
from merlin.dag import Supports
from merlin.dag import DataFormats, Supports
from merlin.schema import Tags
from nvtabular.ops.moments import _custom_moments
from nvtabular.ops.operator import ColumnSelector, Operator
Expand Down Expand Up @@ -98,6 +98,15 @@ def supports(self):
| Supports.GPU_DATAFRAME
)

@property
def supported_formats(self):
return (
DataFormats.PANDAS_DATAFRAME
| DataFormats.CUDF_DATAFRAME
| DataFormats.NUMPY_DICT_ARRAY
| DataFormats.CUPY_DICT_ARRAY
)

def clear(self):
self.means = {}
self.stds = {}
Expand Down Expand Up @@ -181,6 +190,15 @@ def supports(self):
| Supports.GPU_DATAFRAME
)

@property
def supported_formats(self):
return (
DataFormats.PANDAS_DATAFRAME
| DataFormats.CUDF_DATAFRAME
| DataFormats.NUMPY_DICT_ARRAY
| DataFormats.CUPY_DICT_ARRAY
)

@property
def output_tags(self):
return [Tags.CONTINUOUS]
Expand Down
6 changes: 5 additions & 1 deletion nvtabular/ops/operator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@

import nvtabular as nvt
from merlin.core.dispatch import DataFrameType
from merlin.dag import BaseOperator, ColumnSelector
from merlin.dag import BaseOperator, ColumnSelector, DataFormats


class Operator(BaseOperator):
Expand Down Expand Up @@ -53,3 +53,7 @@ def inference_initialize(

def create_node(self, selector):
return nvt.workflow.node.WorkflowNode(selector)

@property
def supported_formats(self) -> DataFormats:
return DataFormats.PANDAS_DATAFRAME | DataFormats.CUDF_DATAFRAME