def call_render(module_spec: ModuleSpec, render: Callable,
request: ttypes.RenderRequest) -> ttypes.RenderResult:
basedir = Path(request.basedir)
input_path = basedir / request.input_filename
table = load_trusted_arrow_file(input_path)
dataframe = cjwpandasmodule.convert.arrow_table_to_pandas_dataframe(table)
tab_outputs = {
k: _thrift_tab_output_to_pandas(v, basedir)
for k, v in request.tab_outputs.items()
}
params = _prepare_params(module_spec,
thrift_json_object_to_pydict(request.params),
basedir, tab_outputs)
spec = inspect.getfullargspec(render)
kwargs = {}
varkw = bool(spec.varkw) # if True, function accepts **kwargs
kwonlyargs = spec.kwonlyargs
if varkw or "fetch_result" in kwonlyargs:
if request.fetch_result is None:
fetch_result = None
else:
fetch_result_path = basedir / request.fetch_result.filename
errors = [
# Data comes in as FetchError and we return RenderError.
RenderError(thrift_i18n_message_to_arrow(e.message))
for e in request.fetch_result.errors
]
if (fetch_result_path.stat().st_size == 0
or cjwparquet.file_has_parquet_magic_number(
fetch_result_path)):
fetch_result = ptypes.ProcessResult(
dataframe=_parquet_to_pandas(fetch_result_path),
errors=errors,
# infer columns -- the fetch interface doesn't handle formats
# (TODO nix pandas_v0 fetching altogether by rewriting all modules)
)
else:
# TODO nix pandas Fetch modules. (Do any use files, even?)
fetch_result = types.FetchResult(path=fetch_result_path,
errors=errors)
kwargs["fetch_result"] = fetch_result
if varkw or "settings" in kwonlyargs:
kwargs["settings"] = settings
if varkw or "tab_name" in kwonlyargs:
kwargs["tab_name"] = request.tab_name
if varkw or "input_columns" in kwonlyargs:
kwargs["input_columns"] = arrow_schema_to_render_columns(table.schema)
input_columns = read_columns(table, full=False)
raw_result = render(dataframe, params, **kwargs)
# raise ValueError if invalid
pandas_result = ptypes.ProcessResult.coerce(
raw_result, try_fallback_columns=input_columns)
pandas_result.truncate_in_place_if_too_big()
arrow_result = pandas_result.to_arrow(basedir / request.output_filename)
return arrow_render_result_to_thrift(arrow_result)
def render_arrow(
table: types.ArrowTable,
params: Dict[str, Any],
tab_name: str,
fetch_result: Optional[types.FetchResult],
output_path: Path,
) -> types.RenderResult:
"""
Render using `cjwkernel.types` data types.
If outputting Arrow data, write to `output_path`.
Module authors are encouraged to replace this function, because Arrow
tables are simpler and more memory-efficient than Pandas tables. This is
the ideal signature for a "rename columns" module, for instance: Arrow
can pass data through without consuming excessive RAM.
This does not validate the render_pandas() return value.
"""
pandas_table = __arrow_to_pandas(table)
pandas_input_tabs = {
to.tab.slug: __arrow_tab_output_to_pandas(to)
for to in _find_tab_outputs(params)
}
if fetch_result is not None:
if fetch_result.path.stat(
).st_size == 0 or parquet.file_has_parquet_magic_number(
fetch_result.path):
fetched_table = __parquet_to_pandas(fetch_result.path)
pandas_fetch_result = ptypes.ProcessResult(
fetched_table,
[
ptypes.ProcessResultError.from_arrow(error)
for error in fetch_result.errors
],
)
else:
pandas_fetch_result = fetch_result
else:
pandas_fetch_result = None
pandas_result: ptypes.ProcessResult = render_pandas(
input_table=pandas_table,
input_table_shape=ptypes.TableShape.from_arrow(table.metadata),
params=_arrow_param_to_pandas_param(params),
tab_name=tab_name,
input_tabs=pandas_input_tabs,
fetch_result=pandas_fetch_result,
)
return pandas_result.to_arrow(output_path)
def render_arrow(
table: types.ArrowTable,
params: Dict[str, Any],
tab_name: str,
input_tabs: Dict[str, types.TabOutput],
fetch_result: Optional[types.FetchResult],
output_path: pathlib.Path,
) -> types.RenderResult:
"""
Render using `cjwkernel.types` data types.
If outputting Arrow data, write to `output_path`.
Module authors are encouraged to replace this function, because Arrow
tables are simpler and more memory-efficient than Pandas tables. This is
the ideal signature for a "rename columns" module, for instance: Arrow
can pass data through without consuming excessive RAM.
This does not validate the render_pandas() return value.
"""
pandas_table = __arrow_to_pandas(table.table)
pandas_input_tabs = {
k: __arrow_to_pandas(v)
for k, v in input_tabs.items()
}
if fetch_result is not None:
fetched_table = __parquet_to_pandas(fetch_result.path)
pandas_fetch_result = ptypes.ProcessResult(
fetched_table,
error=(""
if not fetch_result.errors else str(fetch_result.errors)),
)
else:
pandas_fetch_result = None
pandas_result: ptypes.ProcessResult = render_pandas(
input_table=pandas_table,
input_table_shape=ptypes.TableShape.from_arrow(table.metadata),
params=params,
tab_name=tab_name,
input_tabs=pandas_input_tabs,
fetch_result=pandas_fetch_result,
)
return pandas_result.to_arrow(output_path)
def __render_pandas(
*,
table: types.ArrowTable,
params: Dict[str, Any],
tab_name: str,
fetch_result: Optional[types.FetchResult],
output_path: Path,
) -> types.RenderResult:
"""
Call `render()` with the Pandas signature style.
Features:
* Convert input Arrow table to a Pandas dataframe
* Convert input params to Pandas format (producing extra arguments like
`input_tabs` as needed).
* Convert input `fetch_result` to Pandas dataframe, if it is a valid
Parquet file.
* Coerce output from a Pandas dataframe to an Arrow table
* Coerce output errors/json
"""
# Convert input arguments
pandas_table = __arrow_to_pandas(table)
pandas_params = __arrow_param_to_pandas_param(params)
spec = inspect.getfullargspec(render)
kwargs = {}
varkw = bool(spec.varkw) # if True, function accepts **kwargs
kwonlyargs = spec.kwonlyargs
if varkw or "fetch_result" in kwonlyargs:
if fetch_result is not None:
if (fetch_result.path.stat().st_size == 0
or cjwparquet.file_has_parquet_magic_number(
fetch_result.path)):
fetched_table = __parquet_to_pandas(fetch_result.path)
pandas_fetch_result = ptypes.ProcessResult(
fetched_table, fetch_result.errors)
else:
pandas_fetch_result = fetch_result
else:
pandas_fetch_result = None
kwargs["fetch_result"] = pandas_fetch_result
if varkw or "settings" in kwonlyargs:
kwargs["settings"] = settings
if varkw or "tab_name" in kwonlyargs:
kwargs["tab_name"] = tab_name
if varkw or "input_columns" in kwonlyargs:
kwargs["input_columns"] = {
c.name: ptypes.RenderColumn(c.name, c.type.name,
getattr(c.type, "format", None))
for c in table.metadata.columns
}
if varkw or "input_tabs" in kwonlyargs:
kwargs["input_tabs"] = {
to.tab.slug: __arrow_tab_output_to_pandas(to)
for to in __find_tab_outputs(params)
}
# call render()
raw_result = render(pandas_table, pandas_params, **kwargs)
# Coerce outputs
result = ptypes.ProcessResult.coerce(
raw_result, try_fallback_columns=table.metadata.columns
) # raise ValueError if invalid
result.truncate_in_place_if_too_big()
return result.to_arrow(output_path)