judahrand commented on code in PR #34234:
URL: https://github.com/apache/arrow/pull/34234#discussion_r1510947458
##########
python/pyarrow/table.pxi:
##########
@@ -4859,6 +4859,91 @@ cdef class Table(_Tabular):
output_type=Table
)
+ def join_asof(self, right_table, on, by, tolerance, right_on=None,
right_by=None):
+ """
+ Perform an asof join between this table and another one.
+
+ Result of the join will be a new Table, where further
+ operations can be applied.
+
+ Parameters
+ ----------
+ right_table : Table
+ The table to join to the current one, acting as the right table
+ in the join operation.
+ on : str
+ The column from current table that should be used as the on key
+ of the join operation left side.
+
+ An inexact match is used on the “on” key.i.e., a row is considered
a
+ match iff left_on - tolerance <= right_on <= left_on.
+
+ The input dataset must be sorted by the “on” key. Must be a single
+ field of a common type.
+
+ Currently, the “on” key must be an integer, date, or timestamp
type.
+ by : str or list[str]
+ The columns from current table that should be used as the keys
+ of the join operation left side. The join operation is then done
+ only for the matches in these columns.
+ tolerance : int
+ The tolerance for inexact "on" key matching. A right row is
considered
+ a match with the left row ``right.on - left.on <= tolerance``. The
+ ``tolerance`` may be:
+
+ - negative, in which case a past-as-of-join occurs;
+ - or positive, in which case a future-as-of-join occurs;
+ - or zero, in which case an exact-as-of-join occurs.
+
+ The tolerance is interpreted in the same units as the "on" key.
+ right_on : str or list[str], default None
+ The columns from the right_table that should be used as the on key
+ on the join operation right side.
+ When ``None`` use the same key name as the left table.
+ right_by : str or list[str], default None
+ The columns from the right_table that should be used as keys
+ on the join operation right side.
+ When ``None`` use the same key names as the left table.
+
+ Returns
+ -------
+ Table
+
+ Example
+ --------
+ >>> import pandas as pd
+ >>> import pyarrow as pa
+ >>> df1 = pd.DataFrame({'id': [1, 2, 3],
+ ... 'year': [2020, 2022, 2019]})
+ >>> df2 = pd.DataFrame({'id': [3, 4],
+ ... 'year': [2020, 2021],
+ ... 'n_legs': [5, 100],
+ ... 'animal': ["Brittle stars", "Centipede"]})
+ >>> t1 = pa.Table.from_pandas(df1).sort_by('year')
+ >>> t2 = pa.Table.from_pandas(df2).sort_by('year')
+
+ >>> t1.join_asof(
+ ... t2, on='year', by='id', tolerance=1
Review Comment:
https://github.com/apache/arrow/pull/34234/commits/0553f1dcb1c556729839e36b59e7fc84de2c5faa
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
