ENH: work on rank function, finish testing, ascending param, #875

pandas/core/algorithms.py

@@ -119,16 +119,18 @@ def value_counts(values, sort=True, ascending=False):
 
     return result
 
-def rank(values, axis=0, method='average', na_option='keep'):
+def rank(values, axis=0, method='average', na_option='keep',
+         ascending=True):
     """
 
     """
     if values.ndim == 1:
         f, values = _get_data_algo(values, _rank1d_functions)
-        ranks = f(values, ties_method=method)
+        ranks = f(values, ties_method=method, ascending=ascending)
     elif values.ndim == 2:
         f, values = _get_data_algo(values, _rank2d_functions)
-        ranks = f(values, axis=axis, ties_method=method)
+        ranks = f(values, axis=axis, ties_method=method,
+                  ascending=ascending)
     return ranks
 
 

pandas/core/frame.py

@@ -3731,7 +3731,7 @@ def clip_lower(self, threshold):
         return self.apply(lambda x: x.clip_lower(threshold))
 
     def rank(self, axis=0, numeric_only=None, method='average',
-             na_option='keep'):
+             na_option='keep', ascending=True):
         """
         Compute numerical data ranks (1 through n) along axis. Equal values are
         assigned a rank that is the average of the ranks of those values
@@ -3749,6 +3749,8 @@ def rank(self, axis=0, numeric_only=None, method='average',
             first: ranks assigned in order they appear in the array
         na_option : {'keep'}
             keep: leave NA values where they are
+        ascending : boolean, default True
+            False for ranks by high (1) to low (N)
 
         Returns
         -------
@@ -3758,7 +3760,8 @@ def rank(self, axis=0, numeric_only=None, method='average',
 
         if numeric_only is None:
             try:
-                ranks = rank(self.values, axis=axis, method=method)
+                ranks = rank(self.values, axis=axis, method=method,
+                             ascending=ascending)
                 return DataFrame(ranks, index=self.index, columns=self.columns)
             except TypeError:
                 numeric_only = True
@@ -3767,7 +3770,8 @@ def rank(self, axis=0, numeric_only=None, method='average',
             data = self._get_numeric_data()
         else:
             data = self
-        ranks = rank(data.values, axis=axis, method=method)
+        ranks = rank(data.values, axis=axis, method=method,
+                     ascending=ascending)
         return DataFrame(ranks, index=data.index, columns=data.columns)
 
     #----------------------------------------------------------------------

pandas/core/series.py

@@ -1576,7 +1576,7 @@ def argsort(self, axis=0, kind='quicksort', order=None):
             return Series(np.argsort(values, kind=kind), index=self.index,
                           name=self.name)
 
-    def rank(self, method='average', na_option='keep'):
+    def rank(self, method='average', na_option='keep', ascending=True):
         """
         Compute data ranks (1 through n). Equal values are assigned a rank that
         is the average of the ranks of those values
@@ -1590,13 +1590,16 @@ def rank(self, method='average', na_option='keep'):
             first: ranks assigned in order they appear in the array
         na_option : {'keep'}
             keep: leave NA values where they are
+        ascending : boolean, default True
+            False for ranks by high (1) to low (N)
 
         Returns
         -------
         ranks : Series
         """
         from pandas.core.algorithms import rank
-        ranks = rank(self.values, method=method, na_option=na_option)
+        ranks = rank(self.values, method=method, na_option=na_option,
+                     ascending=ascending)
         return Series(ranks, index=self.index, name=self.name)
 
     def order(self, na_last=True, ascending=True, kind='mergesort'):

pandas/src/sandbox.pyx

@@ -269,3 +269,18 @@ cdef extern from "math.h":
     double fabs(double)
 
 cdef float64_t FP_ERR = 1e-13
+
+cimport util
+
+cdef:
+    int TIEBREAK_AVERAGE = 0
+    int TIEBREAK_MIN = 1
+    int TIEBREAK_MAX = 2
+    int TIEBREAK_FIRST = 3
+
+tiebreakers = {
+    'average' : TIEBREAK_AVERAGE,
+    'min' : TIEBREAK_MIN,
+    'max' : TIEBREAK_MAX,
+    'first' : TIEBREAK_FIRST
+}