PERF: GH15498 - asv tests and whatsnew

Author: jeet63

asv_bench/benchmarks/categoricals.py

@@ -63,3 +63,46 @@ def time_value_counts_dropna(self):
 
     def time_rendering(self):
         str(self.sel)
+
+
+class Categoricals3(object):
+    goal_time = 0.2
+
+    def setup(self):
+        n = 100
+
+        strng = pd.util.testing.makeCategoricalIndex(n)
+        self.s1 = pd.Series(strng)
+
+        dt = pd.util.testing.makeDateIndex(n)
+        self.s2 = pd.Series(dt).astype('category', categories=dt)
+        self.s2o = pd.Series(dt).astype('category', categories=dt, ordered=True)
+
+        fl = pd.util.testing.makeFloatIndex(n)
+        self.s3 = pd.Series(fl).astype('category', categories=fl)
+        self.s3o = pd.Series(fl).astype('category', categories=fl, ordered=True)
+
+        intg = pd.util.testing.makeIntIndex(n)
+        self.s4 = pd.Series(intg).astype('category', categories=intg)
+        self.s4o = pd.Series(intg).astype('category', categories=intg, ordered=True)
+
+    def time_rank_string_unordered(self):
+        self.s1.rank()
+
+    def time_rank_dt_unordered(self):
+        self.s2.rank()
+
+    def time_rank_dt_ordered(self):
+        self.s2o.rank()
+
+    def time_rank_float_unordered(self):
+        self.s3.rank()
+
+    def time_rank_float_ordered(self):
+        self.s3o.rank()
+
+    def time_rank_int_unordered(self):
+        self.s4.rank()
+
+    def time_rank_int_ordered(self):
+        self.s4o.rank()

doc/source/whatsnew/v0.20.0.txt

@@ -562,6 +562,7 @@ Performance Improvements
 - Improved performance of ``groupby().cummin()`` and ``groupby().cummax()`` (:issue:`15048`, :issue:`15109`)
 - Improved performance and reduced memory when indexing with a ``MultiIndex`` (:issue:`15245`)
 - When reading buffer object in ``read_sas()`` method without specified format, filepath string is inferred rather than buffer object. (:issue:`14947`)
+- Improved performance of `rank()` for categorical data (:issue:`15498`)
 
 
 

pandas/core/categorical.py

@@ -1426,6 +1426,8 @@ def _values_for_rank(self):
         elif self.categories.is_numeric():
             values = np.array(self)
         else:
+            #  reorder the categories (so rank can use the float codes)
+            #  instead of passing an object array to rank
             values = np.array(
                 self.rename_categories(Series(self.categories).rank())
             )

pandas/tests/series/test_analytics.py

@@ -1065,8 +1065,9 @@ def test_rank_categorical(self):
         exp_desc = pd.Series([6., 5., 4., 3., 2., 1.])
         ordered = pd.Series(
             ['first', 'second', 'third', 'fourth', 'fifth', 'sixth']
-        ).astype('category', ).cat.set_categories(
-            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
+        ).astype(
+            'category',
+            categories=['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
             ordered=True
         )
         assert_series_equal(ordered.rank(), exp)
@@ -1075,8 +1076,9 @@ def test_rank_categorical(self):
         # Unordered categoricals should be ranked as objects
         unordered = pd.Series(
             ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
-        ).astype('category').cat.set_categories(
-            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
+        ).astype(
+            'category',
+            categories=['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
             ordered=False
         )
         exp_unordered = pd.Series([2., 4., 6., 3., 1., 5.])
@@ -1085,8 +1087,9 @@ def test_rank_categorical(self):
 
         unordered1 = pd.Series(
             [1, 2, 3, 4, 5, 6],
-        ).astype('category').cat.set_categories(
-            [1, 2, 3, 4, 5, 6],
+        ).astype(
+            'category',
+            categories=[1, 2, 3, 4, 5, 6],
             ordered=False
         )
         exp_unordered1 = pd.Series([1., 2., 3., 4., 5., 6.])
@@ -1096,8 +1099,9 @@ def test_rank_categorical(self):
         # Test na_option for rank data
         na_ser = pd.Series(
             ['first', 'second', 'third', 'fourth', 'fifth', 'sixth', np.NaN]
-        ).astype('category', ).cat.set_categories(
-            [
+        ).astype(
+            'category',
+            categories=[
                 'first', 'second', 'third', 'fourth',
                 'fifth', 'sixth', 'seventh'
             ],
@@ -1133,8 +1137,9 @@ def test_rank_categorical(self):
         # Test with pct=True
         na_ser = pd.Series(
             ['first', 'second', 'third', 'fourth', np.NaN],
-        ).astype('category').cat.set_categories(
-            ['first', 'second', 'third', 'fourth'],
+        ).astype(
+            'category',
+            categories=['first', 'second', 'third', 'fourth'],
             ordered=True
         )
         exp_top = pd.Series([0.4, 0.6, 0.8, 1., 0.2])