From 01960d9fbfa1b5f0e360901f4a662740749ade8d Mon Sep 17 00:00:00 2001 From: phofl Date: Wed, 30 Sep 2020 20:39:32 +0200 Subject: [PATCH 1/4] Add example for categories dataframe functions --- doc/source/user_guide/categorical.rst | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst index 926c2d9be74c2..eae49025e13c1 100644 --- a/doc/source/user_guide/categorical.rst +++ b/doc/source/user_guide/categorical.rst @@ -618,6 +618,14 @@ even if some categories are not present in the data: s = pd.Series(pd.Categorical(["a", "b", "c", "c"], categories=["c", "a", "b", "d"])) s.value_counts() +``DataFrame`` methods like :meth:`DataFrame.sum` also show "unused" categories. + +.. ipython:: python + + columns = pd.Categorical(['One','One', 'Two'], categories=['One', 'Two', 'Three'], ordered=True) + df = pd.DataFrame(data=[[1, 2, 3], [4, 5, 6]], columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns])) + df.sum(axis=1, level=1) + Groupby will also show "unused" categories: .. ipython:: python From cb922d5a3647062f37d09142f35d46e2f9107a37 Mon Sep 17 00:00:00 2001 From: phofl Date: Wed, 30 Sep 2020 21:24:18 +0200 Subject: [PATCH 2/4] Format example --- doc/source/user_guide/categorical.rst | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst index eae49025e13c1..d911864cb848a 100644 --- a/doc/source/user_guide/categorical.rst +++ b/doc/source/user_guide/categorical.rst @@ -622,8 +622,13 @@ even if some categories are not present in the data: .. ipython:: python - columns = pd.Categorical(['One','One', 'Two'], categories=['One', 'Two', 'Three'], ordered=True) - df = pd.DataFrame(data=[[1, 2, 3], [4, 5, 6]], columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns])) + columns = pd.Categorical( + ["One", "One", "Two"], categories=["One", "Two", "Three"], ordered=True + ) + df = pd.DataFrame( + data=[[1, 2, 3], [4, 5, 6]], + columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns]), + ) df.sum(axis=1, level=1) Groupby will also show "unused" categories: From 6af0f05807311670c15f86b44759752be7a795a3 Mon Sep 17 00:00:00 2001 From: patrick <61934744+phofl@users.noreply.github.com> Date: Wed, 30 Sep 2020 21:40:23 +0200 Subject: [PATCH 3/4] Update doc/source/user_guide/categorical.rst Co-authored-by: Daniel Saxton <2658661+dsaxton@users.noreply.github.com> --- doc/source/user_guide/categorical.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst index d911864cb848a..bab89ad5e6ff3 100644 --- a/doc/source/user_guide/categorical.rst +++ b/doc/source/user_guide/categorical.rst @@ -624,7 +624,7 @@ even if some categories are not present in the data: columns = pd.Categorical( ["One", "One", "Two"], categories=["One", "Two", "Three"], ordered=True - ) + ) df = pd.DataFrame( data=[[1, 2, 3], [4, 5, 6]], columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns]), From 262e2845f517023de99a45ceb13adf0b31cf47a7 Mon Sep 17 00:00:00 2001 From: phofl Date: Wed, 30 Sep 2020 23:10:55 +0200 Subject: [PATCH 4/4] Fix black issues --- doc/source/user_guide/categorical.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst index bab89ad5e6ff3..6a8e1767ef7e8 100644 --- a/doc/source/user_guide/categorical.rst +++ b/doc/source/user_guide/categorical.rst @@ -623,7 +623,7 @@ even if some categories are not present in the data: .. ipython:: python columns = pd.Categorical( - ["One", "One", "Two"], categories=["One", "Two", "Three"], ordered=True + ["One", "One", "Two"], categories=["One", "Two", "Three"], ordered=True ) df = pd.DataFrame( data=[[1, 2, 3], [4, 5, 6]],