From 8bf2bc4a049642154ece3168621854d275710485 Mon Sep 17 00:00:00 2001
From: Karthik Mathur <22126205+mathurk1@users.noreply.github.com>
Date: Fri, 21 Aug 2020 17:34:51 -0500
Subject: [PATCH] TST: add test for agg on ordered categorical cols (#35630)

---
 .../tests/groupby/aggregate/test_aggregate.py | 79 +++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/pandas/tests/groupby/aggregate/test_aggregate.py b/pandas/tests/groupby/aggregate/test_aggregate.py
index ce9d4b892d775..8fe450fe6abfc 100644
--- a/pandas/tests/groupby/aggregate/test_aggregate.py
+++ b/pandas/tests/groupby/aggregate/test_aggregate.py
@@ -1063,6 +1063,85 @@ def test_groupby_get_by_index():
     pd.testing.assert_frame_equal(res, expected)
 
 
+@pytest.mark.parametrize(
+    "grp_col_dict, exp_data",
+    [
+        ({"nr": "min", "cat_ord": "min"}, {"nr": [1, 5], "cat_ord": ["a", "c"]}),
+        ({"cat_ord": "min"}, {"cat_ord": ["a", "c"]}),
+        ({"nr": "min"}, {"nr": [1, 5]}),
+    ],
+)
+def test_groupby_single_agg_cat_cols(grp_col_dict, exp_data):
+    # test single aggregations on ordered categorical cols GHGH27800
+
+    # create the result dataframe
+    input_df = pd.DataFrame(
+        {
+            "nr": [1, 2, 3, 4, 5, 6, 7, 8],
+            "cat_ord": list("aabbccdd"),
+            "cat": list("aaaabbbb"),
+        }
+    )
+
+    input_df = input_df.astype({"cat": "category", "cat_ord": "category"})
+    input_df["cat_ord"] = input_df["cat_ord"].cat.as_ordered()
+    result_df = input_df.groupby("cat").agg(grp_col_dict)
+
+    # create expected dataframe
+    cat_index = pd.CategoricalIndex(
+        ["a", "b"], categories=["a", "b"], ordered=False, name="cat", dtype="category"
+    )
+
+    expected_df = pd.DataFrame(data=exp_data, index=cat_index)
+
+    tm.assert_frame_equal(result_df, expected_df)
+
+
+@pytest.mark.parametrize(
+    "grp_col_dict, exp_data",
+    [
+        ({"nr": ["min", "max"], "cat_ord": "min"}, [(1, 4, "a"), (5, 8, "c")]),
+        ({"nr": "min", "cat_ord": ["min", "max"]}, [(1, "a", "b"), (5, "c", "d")]),
+        ({"cat_ord": ["min", "max"]}, [("a", "b"), ("c", "d")]),
+    ],
+)
+def test_groupby_combined_aggs_cat_cols(grp_col_dict, exp_data):
+    # test combined aggregations on ordered categorical cols GH27800
+
+    # create the result dataframe
+    input_df = pd.DataFrame(
+        {
+            "nr": [1, 2, 3, 4, 5, 6, 7, 8],
+            "cat_ord": list("aabbccdd"),
+            "cat": list("aaaabbbb"),
+        }
+    )
+
+    input_df = input_df.astype({"cat": "category", "cat_ord": "category"})
+    input_df["cat_ord"] = input_df["cat_ord"].cat.as_ordered()
+    result_df = input_df.groupby("cat").agg(grp_col_dict)
+
+    # create expected dataframe
+    cat_index = pd.CategoricalIndex(
+        ["a", "b"], categories=["a", "b"], ordered=False, name="cat", dtype="category"
+    )
+
+    # unpack the grp_col_dict to create the multi-index tuple
+    # this tuple will be used to create the expected dataframe index
+    multi_index_list = []
+    for k, v in grp_col_dict.items():
+        if isinstance(v, list):
+            for value in v:
+                multi_index_list.append([k, value])
+        else:
+            multi_index_list.append([k, v])
+    multi_index = pd.MultiIndex.from_tuples(tuple(multi_index_list))
+
+    expected_df = pd.DataFrame(data=exp_data, columns=multi_index, index=cat_index)
+
+    tm.assert_frame_equal(result_df, expected_df)
+
+
 def test_nonagg_agg():
     # GH 35490 - Single/Multiple agg of non-agg function give same results
     # TODO: agg should raise for functions that don't aggregate