TST: Clean up tests of DataFrame.sort_{index,values} (pandas-dev#13496)

IamJeffG · jorisvandenbossche · commit 65849d3c9fee · 2016-07-11T20:21:06.000+02:00
* TST: Clean up tests of DataFrame.sort_{index,values}

* Factor out Series sorting tests to own file.

* Delegate deprecated sort() and order() to their own tests.

Before this commit, the `Series.sort_values()` tests relied on deprecated
`Series.sort()` and `Series.order()` as the source of truth. However
they both merely called `Series.sort_values()` under the hood.

This commit consolidates the core test logic against `.sort_values()`
directly, while `.sort()` and `.order()` merely check for equivalence
with `.sort_values()`.

Also removes some no-op assertions that had rotted from the old days of
`sort()`/`order()`.

* Remove 'by' docstring from Series.sort_values

* Document defaults for optional sorting args

* Move more sort_values, sort_index tests to be together.

* Add test for Series.sort_index(sort_remaining=True)

* Improve `sort_values` tests when multiple `by`s

Duplicates values in the test DataFrame are necessary
to fully test this feature.

* PEP8 cleanup

* Annotate tests with GH issue

* Fix indentation - docstring string replacement
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -68,8 +68,12 @@
 # ---------------------------------------------------------------------
 # Docstring templates
 
-_shared_doc_kwargs = dict(axes='index, columns', klass='DataFrame',
-                          axes_single_arg="{0, 1, 'index', 'columns'}")
+_shared_doc_kwargs = dict(
+    axes='index, columns', klass='DataFrame',
+    axes_single_arg="{0, 1, 'index', 'columns'}",
+    optional_by="""
+        by : str or list of str
+            Name or list of names which refer to the axis items.""")
 
 _numeric_only_doc = """numeric_only : boolean, default None
     Include only float, int, boolean data. If None, will attempt to use
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -37,10 +37,13 @@
 # goal is to be able to define the docs close to function, while still being
 # able to share
 _shared_docs = dict()
-_shared_doc_kwargs = dict(axes='keywords for axes', klass='NDFrame',
-                          axes_single_arg='int or labels for object',
-                          args_transpose='axes to permute (int or label for'
-                          ' object)')
+_shared_doc_kwargs = dict(
+    axes='keywords for axes', klass='NDFrame',
+    axes_single_arg='int or labels for object',
+    args_transpose='axes to permute (int or label for object)',
+    optional_by="""
+        by : str or list of str
+            Name or list of names which refer to the axis items.""")
 
 
 def is_dictlike(x):
@@ -1961,21 +1964,20 @@ def add_suffix(self, suffix):
         .. versionadded:: 0.17.0
 
         Parameters
-        ----------
-        by : string name or list of names which refer to the axis items
-        axis : %(axes)s to direct sorting
-        ascending : bool or list of bool
+        ----------%(optional_by)s
+        axis : %(axes)s to direct sorting, default 0
+        ascending : bool or list of bool, default True
              Sort ascending vs. descending. Specify list for multiple sort
              orders.  If this is a list of bools, must match the length of
              the by.
-        inplace : bool
+        inplace : bool, default False
              if True, perform operation in-place
-        kind : {`quicksort`, `mergesort`, `heapsort`}
+        kind : {'quicksort', 'mergesort', 'heapsort'}, default 'quicksort'
              Choice of sorting algorithm. See also ndarray.np.sort for more
              information.  `mergesort` is the only stable algorithm. For
              DataFrames, this option is only applied when sorting on a single
              column or label.
-        na_position : {'first', 'last'}
+        na_position : {'first', 'last'}, default 'last'
              `first` puts NaNs at the beginning, `last` puts NaNs at the end
 
         Returns
@@ -1997,16 +1999,16 @@ def sort_values(self, by, axis=0, ascending=True, inplace=False,
             if not None, sort on values in specified index level(s)
         ascending : boolean, default True
             Sort ascending vs. descending
-        inplace : bool
+        inplace : bool, default False
             if True, perform operation in-place
-        kind : {`quicksort`, `mergesort`, `heapsort`}
+        kind : {'quicksort', 'mergesort', 'heapsort'}, default 'quicksort'
              Choice of sorting algorithm. See also ndarray.np.sort for more
              information.  `mergesort` is the only stable algorithm. For
              DataFrames, this option is only applied when sorting on a single
              column or label.
-        na_position : {'first', 'last'}
+        na_position : {'first', 'last'}, default 'last'
              `first` puts NaNs at the beginning, `last` puts NaNs at the end
-        sort_remaining : bool
+        sort_remaining : bool, default True
             if true and sorting by level and index is multilevel, sort by other
             levels too (in order) after sorting by specified level
 
diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -62,7 +62,8 @@
     axes='index', klass='Series', axes_single_arg="{0, 'index'}",
     inplace="""inplace : boolean, default False
         If True, performs operation inplace and returns None.""",
-    duplicated='Series')
+    duplicated='Series',
+    optional_by='')
 
 
 def _coerce_method(converter):
diff --git a/pandas/tests/frame/test_sorting.py b/pandas/tests/frame/test_sorting.py
@@ -21,75 +21,68 @@ class TestDataFrameSorting(tm.TestCase, TestData):
 
     _multiprocess_can_split_ = True
 
-    def test_sort_values(self):
-        # API for 9816
+    def test_sort_index(self):
+        # GH13496
 
-        # sort_index
         frame = DataFrame(np.arange(16).reshape(4, 4), index=[1, 2, 3, 4],
                           columns=['A', 'B', 'C', 'D'])
 
-        # 9816 deprecated
-        with tm.assert_produces_warning(FutureWarning):
-            frame.sort(columns='A')
-        with tm.assert_produces_warning(FutureWarning):
-            frame.sort()
-
+        # axis=0 : sort rows by index labels
         unordered = frame.ix[[3, 2, 4, 1]]
-        expected = unordered.sort_index()
-
         result = unordered.sort_index(axis=0)
+        expected = frame
         assert_frame_equal(result, expected)
 
-        unordered = frame.ix[:, [2, 1, 3, 0]]
-        expected = unordered.sort_index(axis=1)
+        result = unordered.sort_index(ascending=False)
+        expected = frame[::-1]
+        assert_frame_equal(result, expected)
 
+        # axis=1 : sort columns by column names
+        unordered = frame.ix[:, [2, 1, 3, 0]]
         result = unordered.sort_index(axis=1)
-        assert_frame_equal(result, expected)
+        assert_frame_equal(result, frame)
+
+        result = unordered.sort_index(axis=1, ascending=False)
+        expected = frame.ix[:, ::-1]
         assert_frame_equal(result, expected)
 
-        # sortlevel
-        mi = MultiIndex.from_tuples([[1, 1, 3], [1, 1, 1]], names=list('ABC'))
+    def test_sort_index_multiindex(self):
+        # GH13496
+
+        # sort rows by specified level of multi-index
+        mi = MultiIndex.from_tuples([[2, 1, 3], [1, 1, 1]], names=list('ABC'))
         df = DataFrame([[1, 2], [3, 4]], mi)
 
         result = df.sort_index(level='A', sort_remaining=False)
         expected = df.sortlevel('A', sort_remaining=False)
         assert_frame_equal(result, expected)
 
+        # sort columns by specified level of multi-index
         df = df.T
         result = df.sort_index(level='A', axis=1, sort_remaining=False)
         expected = df.sortlevel('A', axis=1, sort_remaining=False)
         assert_frame_equal(result, expected)
 
-        # MI sort, but no by
+        # MI sort, but no level: sort_level has no effect
         mi = MultiIndex.from_tuples([[1, 1, 3], [1, 1, 1]], names=list('ABC'))
         df = DataFrame([[1, 2], [3, 4]], mi)
         result = df.sort_index(sort_remaining=False)
         expected = df.sort_index()
         assert_frame_equal(result, expected)
 
-    def test_sort_index(self):
+    def test_sort(self):
         frame = DataFrame(np.arange(16).reshape(4, 4), index=[1, 2, 3, 4],
                           columns=['A', 'B', 'C', 'D'])
 
-        # axis=0
-        unordered = frame.ix[[3, 2, 4, 1]]
-        sorted_df = unordered.sort_index(axis=0)
-        expected = frame
-        assert_frame_equal(sorted_df, expected)
-
-        sorted_df = unordered.sort_index(ascending=False)
-        expected = frame[::-1]
-        assert_frame_equal(sorted_df, expected)
-
-        # axis=1
-        unordered = frame.ix[:, ['D', 'B', 'C', 'A']]
-        sorted_df = unordered.sort_index(axis=1)
-        expected = frame
-        assert_frame_equal(sorted_df, expected)
+        # 9816 deprecated
+        with tm.assert_produces_warning(FutureWarning):
+            frame.sort(columns='A')
+        with tm.assert_produces_warning(FutureWarning):
+            frame.sort()
 
-        sorted_df = unordered.sort_index(axis=1, ascending=False)
-        expected = frame.ix[:, ::-1]
-        assert_frame_equal(sorted_df, expected)
+    def test_sort_values(self):
+        frame = DataFrame([[1, 1, 2], [3, 1, 0], [4, 5, 6]],
+                          index=[1, 2, 3], columns=list('ABC'))
 
         # by column
         sorted_df = frame.sort_values(by='A')
@@ -109,16 +102,17 @@ def test_sort_index(self):
         sorted_df = frame.sort_values(by=['A'], ascending=[False])
         assert_frame_equal(sorted_df, expected)
 
-        # check for now
-        sorted_df = frame.sort_values(by='A')
-        assert_frame_equal(sorted_df, expected[::-1])
-        expected = frame.sort_values(by='A')
+        # multiple bys
+        sorted_df = frame.sort_values(by=['B', 'C'])
+        expected = frame.loc[[2, 1, 3]]
         assert_frame_equal(sorted_df, expected)
 
-        expected = frame.sort_values(by=['A', 'B'], ascending=False)
-        sorted_df = frame.sort_values(by=['A', 'B'])
+        sorted_df = frame.sort_values(by=['B', 'C'], ascending=False)
         assert_frame_equal(sorted_df, expected[::-1])
 
+        sorted_df = frame.sort_values(by=['B', 'A'], ascending=[True, False])
+        assert_frame_equal(sorted_df, expected)
+
         self.assertRaises(ValueError, lambda: frame.sort_values(
             by=['A', 'B'], axis=2, inplace=True))
 
@@ -130,6 +124,25 @@ def test_sort_index(self):
         with assertRaisesRegexp(ValueError, msg):
             frame.sort_values(by=['A', 'B'], axis=0, ascending=[True] * 5)
 
+    def test_sort_values_inplace(self):
+        frame = DataFrame(np.random.randn(4, 4), index=[1, 2, 3, 4],
+                          columns=['A', 'B', 'C', 'D'])
+
+        sorted_df = frame.copy()
+        sorted_df.sort_values(by='A', inplace=True)
+        expected = frame.sort_values(by='A')
+        assert_frame_equal(sorted_df, expected)
+
+        sorted_df = frame.copy()
+        sorted_df.sort_values(by='A', ascending=False, inplace=True)
+        expected = frame.sort_values(by='A', ascending=False)
+        assert_frame_equal(sorted_df, expected)
+
+        sorted_df = frame.copy()
+        sorted_df.sort_values(by=['A', 'B'], ascending=False, inplace=True)
+        expected = frame.sort_values(by=['A', 'B'], ascending=False)
+        assert_frame_equal(sorted_df, expected)
+
     def test_sort_index_categorical_index(self):
 
         df = (DataFrame({'A': np.arange(6, dtype='int64'),
@@ -361,25 +374,6 @@ def test_sort_index_different_sortorder(self):
         result = idf['C'].sort_index(ascending=[1, 0])
         assert_series_equal(result, expected['C'])
 
-    def test_sort_inplace(self):
-        frame = DataFrame(np.random.randn(4, 4), index=[1, 2, 3, 4],
-                          columns=['A', 'B', 'C', 'D'])
-
-        sorted_df = frame.copy()
-        sorted_df.sort_values(by='A', inplace=True)
-        expected = frame.sort_values(by='A')
-        assert_frame_equal(sorted_df, expected)
-
-        sorted_df = frame.copy()
-        sorted_df.sort_values(by='A', ascending=False, inplace=True)
-        expected = frame.sort_values(by='A', ascending=False)
-        assert_frame_equal(sorted_df, expected)
-
-        sorted_df = frame.copy()
-        sorted_df.sort_values(by=['A', 'B'], ascending=False, inplace=True)
-        expected = frame.sort_values(by=['A', 'B'], ascending=False)
-        assert_frame_equal(sorted_df, expected)
-
     def test_sort_index_duplicates(self):
 
         # with 9816, these are all translated to .sort_values
diff --git a/pandas/tests/series/test_analytics.py b/pandas/tests/series/test_analytics.py
diff --git a/pandas/tests/series/test_sorting.py b/pandas/tests/series/test_sorting.py
