Merge branch 'master' of https://github.com/pandas-dev/pandas into tst-needs2

Author: jbrockmendel

doc/source/whatsnew/v1.0.0.rst

@@ -837,6 +837,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrame.groupby` where ``any``, ``all``, ``nunique`` and transform functions would incorrectly handle duplicate column labels (:issue:`21668`)
 - Bug in :meth:`DataFrameGroupBy.agg` with timezone-aware datetime64 column incorrectly casting results to the original dtype (:issue:`29641`)
 - Bug in :meth:`DataFrame.groupby` when using axis=1 and having a single level columns index (:issue:`30208`)
+- Bug in :meth:`DataFrame.groupby` when using nunique on axis=1 (:issue:`30253`)
 
 Reshaping
 ^^^^^^^^^

pandas/core/groupby/generic.py

@@ -1813,9 +1813,20 @@ def groupby_series(obj, col=None):
             # Try to consolidate with normal wrapping functions
             from pandas.core.reshape.concat import concat
 
-            results = [groupby_series(content, label) for label, content in obj.items()]
+            axis_number = obj._get_axis_number(self.axis)
+            other_axis = int(not axis_number)
+            if axis_number == 0:
+                iter_func = obj.items
+            else:
+                iter_func = obj.iterrows
+
+            results = [groupby_series(content, label) for label, content in iter_func()]
             results = concat(results, axis=1)
-            results.columns.names = obj.columns.names
+
+            if axis_number == 1:
+                results = results.T
+
+            results._get_axis(other_axis).names = obj._get_axis(other_axis).names
 
         if not self.as_index:
             results.index = ibase.default_index(len(results))

pandas/tests/groupby/test_groupby.py

@@ -1994,3 +1994,20 @@ def test_dup_labels_output_shape(groupby_func, idx):
 
     assert result.shape == (1, 2)
     tm.assert_index_equal(result.columns, idx)
+
+
+def test_groupby_crash_on_nunique(axis):
+    # Fix following 30253
+    df = pd.DataFrame({("A", "B"): [1, 2], ("A", "C"): [1, 3], ("D", "B"): [0, 0]})
+
+    axis_number = df._get_axis_number(axis)
+    if not axis_number:
+        df = df.T
+
+    result = df.groupby(axis=axis_number, level=0).nunique()
+
+    expected = pd.DataFrame({"A": [1, 2], "D": [1, 1]})
+    if not axis_number:
+        expected = expected.T
+
+    tm.assert_frame_equal(result, expected)

setup.py

@@ -544,17 +544,10 @@ def srcpath(name=None, suffix=".pyx", subdir="src"):
 
 klib_include = ["pandas/_libs/src/klib"]
 
-np_datetime_headers = [
+tseries_depends = [
     "pandas/_libs/tslibs/src/datetime/np_datetime.h",
     "pandas/_libs/tslibs/src/datetime/np_datetime_strings.h",
 ]
-np_datetime_sources = [
-    "pandas/_libs/tslibs/src/datetime/np_datetime.c",
-    "pandas/_libs/tslibs/src/datetime/np_datetime_strings.c",
-]
-
-tseries_depends = np_datetime_headers
-
 
 ext_data = {
     "_libs.algos": {
@@ -573,7 +566,6 @@ def srcpath(name=None, suffix=".pyx", subdir="src"):
         "pyxfile": "_libs/index",
         "include": klib_include,
         "depends": _pxi_dep["index"],
-        "sources": np_datetime_sources,
     },
     "_libs.indexing": {"pyxfile": "_libs/indexing"},
     "_libs.internals": {"pyxfile": "_libs/internals"},
@@ -607,38 +599,34 @@ def srcpath(name=None, suffix=".pyx", subdir="src"):
     "_libs.properties": {"pyxfile": "_libs/properties"},
     "_libs.reshape": {"pyxfile": "_libs/reshape", "depends": []},
     "_libs.sparse": {"pyxfile": "_libs/sparse", "depends": _pxi_dep["sparse"]},
-    "_libs.tslib": {
-        "pyxfile": "_libs/tslib",
-        "depends": tseries_depends,
-        "sources": np_datetime_sources,
-    },
+    "_libs.tslib": {"pyxfile": "_libs/tslib", "depends": tseries_depends},
     "_libs.tslibs.c_timestamp": {
         "pyxfile": "_libs/tslibs/c_timestamp",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.ccalendar": {"pyxfile": "_libs/tslibs/ccalendar"},
     "_libs.tslibs.conversion": {
         "pyxfile": "_libs/tslibs/conversion",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
+        "sources": ["pandas/_libs/tslibs/src/datetime/np_datetime.c"],
     },
     "_libs.tslibs.fields": {
         "pyxfile": "_libs/tslibs/fields",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.frequencies": {"pyxfile": "_libs/tslibs/frequencies"},
     "_libs.tslibs.nattype": {"pyxfile": "_libs/tslibs/nattype"},
     "_libs.tslibs.np_datetime": {
         "pyxfile": "_libs/tslibs/np_datetime",
-        "depends": np_datetime_headers,
-        "sources": np_datetime_sources,
+        "depends": tseries_depends,
+        "sources": [
+            "pandas/_libs/tslibs/src/datetime/np_datetime.c",
+            "pandas/_libs/tslibs/src/datetime/np_datetime_strings.c",
+        ],
     },
     "_libs.tslibs.offsets": {
         "pyxfile": "_libs/tslibs/offsets",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.parsing": {
         "pyxfile": "_libs/tslibs/parsing",
@@ -649,33 +637,28 @@ def srcpath(name=None, suffix=".pyx", subdir="src"):
     "_libs.tslibs.period": {
         "pyxfile": "_libs/tslibs/period",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
+        "sources": ["pandas/_libs/tslibs/src/datetime/np_datetime.c"],
     },
     "_libs.tslibs.resolution": {
         "pyxfile": "_libs/tslibs/resolution",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.strptime": {
         "pyxfile": "_libs/tslibs/strptime",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.timedeltas": {
         "pyxfile": "_libs/tslibs/timedeltas",
-        "depends": np_datetime_headers,
-        "sources": np_datetime_sources,
+        "depends": tseries_depends,
     },
     "_libs.tslibs.timestamps": {
         "pyxfile": "_libs/tslibs/timestamps",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.tslibs.timezones": {"pyxfile": "_libs/tslibs/timezones"},
     "_libs.tslibs.tzconversion": {
         "pyxfile": "_libs/tslibs/tzconversion",
         "depends": tseries_depends,
-        "sources": np_datetime_sources,
     },
     "_libs.testing": {"pyxfile": "_libs/testing"},
     "_libs.window.aggregations": {
@@ -734,7 +717,10 @@ def srcpath(name=None, suffix=".pyx", subdir="src"):
             "pandas/_libs/src/ujson/lib/ultrajsonenc.c",
             "pandas/_libs/src/ujson/lib/ultrajsondec.c",
         ]
-        + np_datetime_sources
+        + [
+            "pandas/_libs/tslibs/src/datetime/np_datetime.c",
+            "pandas/_libs/tslibs/src/datetime/np_datetime_strings.c",
+        ]
     ),
     include_dirs=[
         "pandas/_libs/src/ujson/python",