feat: add nunique method to Series/DataFrameGroupby (#256)

Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly: - [ ] Make sure to open an issue as a [bug/issue](https://togithub.com/googleapis/python-bigquery-dataframes/issues/new/choose) before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea - [ ] Ensure the tests and linter pass - [ ] Code coverage does not decrease (if any source code was changed) - [ ] Appropriate docs were updated (if necessary) Fixes #<issue_number_goes_here> 🦕

Author: TrevorBergeron

bigframes/core/groupby/__init__.py

@@ -179,6 +179,9 @@ def any(self) -> df.DataFrame:
  def count(self) -> df.DataFrame:
  return self._aggregate_all(agg_ops.count_op)
 
+ def nunique(self) -> df.DataFrame:
+ return self._aggregate_all(agg_ops.nunique_op)
+
  def cumsum(self, *args, numeric_only: bool = False, **kwargs) -> df.DataFrame:
  if not numeric_only:
  self._raise_on_non_numeric("cumsum")
@@ -442,6 +445,9 @@ def max(self, *args) -> series.Series:
  def count(self) -> series.Series:
  return self._aggregate(agg_ops.count_op)
 
+ def nunique(self) -> series.Series:
+ return self._aggregate(agg_ops.nunique_op)
+
  def sum(self, *args) -> series.Series:
  return self._aggregate(agg_ops.sum_op)
 

tests/system/small/test_groupby.py

@@ -69,11 +69,13 @@ def test_dataframe_groupby_median(scalars_df_index, scalars_pandas_df_index):
  ("operator"),
  [
  (lambda x: x.count()),
+ (lambda x: x.nunique()),
  (lambda x: x.any()),
  (lambda x: x.all()),
  ],
  ids=[
  "count",
+ "nunique",
  "any",
  "all",
  ],

third_party/bigframes_vendored/pandas/core/groupby/__init__.py

@@ -363,6 +363,15 @@ def agg(self, func):
  """
  raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
+ def nunique(self):
+ """
+ Return number of unique elements in the group.
+
+ Returns:
+ Series: Number of unique values within each group.
+ """
+ raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
 
 class DataFrameGroupBy(GroupBy):
  def agg(self, func, **kwargs):
@@ -391,3 +400,12 @@ def agg(self, func, **kwargs):
  DataFrame
  """
  raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
+ def nunique(self):
+ """
+ Return DataFrame with counts of unique elements in each position.
+
+ Returns:
+ DataFrame
+ """
+ raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)