bkietz commented on a change in pull request #7546:
URL: https://github.com/apache/arrow/pull/7546#discussion_r445811655
##########
File path: python/pyarrow/_dataset.pyx
##########
@@ -845,6 +845,28 @@ cdef class RowGroupInfo:
def num_rows(self):
return self.info.num_rows()
+ @property
+ def statistics(self):
+ if not self.info.HasStatistics():
+ return None
+
+ cdef:
+ CStructScalar* c_statistics
+ CStructScalar* c_minmax
+
+ statistics = dict()
+ c_statistics = self.info.statistics().get()
+ for i in range(c_statistics.value.size()):
+ name = frombytes(c_statistics.type.get().field(i).get().name())
+ c_minmax = <CStructScalar*> c_statistics.value[i].get()
+
+ statistics[name] = {
+ 'min': pyarrow_wrap_scalar(c_minmax.value[0]).as_py(),
+ 'max': pyarrow_wrap_scalar(c_minmax.value[1]).as_py(),
+ }
+
+ return statistics
+
Review comment:
If that's desired it can wait for a follow up
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
