pitrou commented on a change in pull request #11624:
URL: https://github.com/apache/arrow/pull/11624#discussion_r751458857
##########
File path: python/pyarrow/table.pxi
##########
@@ -2192,6 +2192,48 @@ cdef class Table(_PandasConvertible):
return table
+ def group_by(self, keys):
+ """Declare a grouping over the columns of the table.
+
+ resulting grouping can then be used to perform aggregations.
+
+ Parameters
+ ----------
+ keys : str or list[str]
+ Name of the columns that should be used as the grouping key.
+
+ Returns
+ -------
+ TableGroupBy
+ """
+ return TableGroupBy(self, keys)
+
+ def sort_by(self, sorting):
+ """
+ Sort the table by one or multiple columns.
+
+ Parameters
+ ----------
+ sorting : str or list[tuple(name, order)]
+ Name of the column to use to sort, or
+ a list of multiple sorting conditions where
+ each entry is a tuple with column name
+ and sorting order ("ascending" or "descending")
+
+ Returns
+ -------
+ Table
+ A new table sorted according to the sort key.
Review comment:
"sort key(s)" perhaps?
##########
File path: python/pyarrow/table.pxi
##########
@@ -2387,3 +2429,62 @@ def _from_pydict(cls, mapping, schema, metadata):
return cls.from_arrays(arrays, schema=schema, metadata=metadata)
else:
raise TypeError('Schema must be an instance of pyarrow.Schema')
+
+
+class TableGroupBy:
+ """
+ A grouping of columns in a table on which to perform aggregations.
+ """
+
+ def __init__(self, table, keys):
+ if isinstance(keys, str):
+ keys = [keys]
+
+ self._table = table
+ self.keys = keys
+
+ def aggregate(self, aggregations):
+ """
+ Perform an aggregation over the grouped columns of the table.
+
+ Parameters
+ ----------
+ aggregations : list[tuple(str, str)] or\
+ list[tuple(str, str, FunctionOptions)]
+ List of tuples made of aggregation functions names followed
+ by column names and optionally aggregation function options.
+
+ Returns
+ -------
+ Table
+ Results of the aggregation functions.
+ """
+ columns = [a[1] for a in aggregations]
+ aggrfuncs = [
+ (a[0], a[2]) if len(a) > 2 else (a[0], None)
+ for a in aggregations
+ ]
+
+ group_by_aggrs = []
+ for aggr in aggrfuncs:
+ if isinstance(aggr, str):
Review comment:
Can this happen? It seems this case is already dealt with when
constructing `aggrfuncs`.
--
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]
