amol- commented on code in PR #13409:
URL: https://github.com/apache/arrow/pull/13409#discussion_r914032940
##########
python/pyarrow/_dataset.pyx:
##########
@@ -432,6 +443,46 @@ cdef class Dataset(_Weakrefable):
use_threads=use_threads,
coalesce_keys=coalesce_keys,
output_type=InMemoryDataset)
+cdef class FilteredDataset(Dataset):
+ """
+ A Dataset with an applied filter.
+
+ Parameters
+ ----------
+ dataset : Dataset
+ The dataset to which the filter should be applied.
+ expression : Expression
+ The filter that should be applied to the dataset.
+ """
+
+ def __init__(self, dataset, expression):
+ self.init(<shared_ptr[CDataset]>(<Dataset>dataset).wrapped)
+ self._filter = expression
+
+ cdef void init(self, const shared_ptr[CDataset]& sp):
+ Dataset.init(self, sp)
+ self._filter = None
+
+ def filter(self, expression):
Review Comment:
Added docstrings. To avoid having them going out of sync I added a reference
to the original method documentation.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
