PERF: categorical rank GH#15498

AnkurDedania · Mar 1, 2017 · 33249b3 · 33249b3
1 parent d0a281f
commit 33249b3
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 5 deletions.
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
@@ -974,9 +974,6 @@ def _get_data_algo(values, func_map):
 
     f = None
 
-    if is_categorical_dtype(values):
-        values = values._values_for_rank()
-
     if is_float_dtype(values):
         f = func_map['float64']
         values = _ensure_float64(values)
@@ -992,6 +989,11 @@ def _get_data_algo(values, func_map):
     elif is_unsigned_integer_dtype(values):
         f = func_map['uint64']
         values = _ensure_uint64(values)
+
+    elif is_categorical_dtype(values):
+        f = func_map['float64']
+        values = values._values_for_rank()
+
     else:
         values = _ensure_object(values)
 

diff --git a/pandas/core/categorical.py b/pandas/core/categorical.py
@@ -1416,14 +1416,17 @@ def _values_for_rank(self):
         numpy array
 
         """
+        from pandas import Series
         if self.ordered:
             values = self.codes
             mask = values == -1
+            values = values.astype('float64')
             if mask.any():
-                values = values.astype('float64')
                 values[mask] = np.nan
         else:
-            values = np.array(self)
+            values = np.array(
+                self.rename_categories(Series(self.categories).rank())
+            )
         return values
 
     def order(self, inplace=False, ascending=True, na_position='last'):