API/ENH: IntervalIndex

closes pandas-dev#7640 closes pandas-dev#8625
jreback · Feb 8, 2017 · 455b3fd · 455b3fd
1 parent 704cdbf
commit 455b3fd
Show file tree

Hide file tree

Showing 19 changed files with 3,395 additions and 153 deletions.
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
@@ -405,7 +405,6 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
             cat, bins = cut(values, bins, retbins=True)
         except TypeError:
             raise TypeError("bins argument only works with numeric data.")
-        values = cat.codes
 
     if is_extension_type(values) and not is_datetimetz(values):
         # handle Categorical and sparse,

diff --git a/pandas/core/api.py b/pandas/core/api.py
@@ -12,6 +12,7 @@
 from pandas.core.index import (Index, CategoricalIndex, Int64Index,
                                UInt64Index, RangeIndex, Float64Index,
                                MultiIndex)
+from pandas.core.interval import Interval, IntervalIndex
 
 from pandas.core.series import Series, TimeSeries
 from pandas.core.frame import DataFrame

diff --git a/pandas/core/groupby.py b/pandas/core/groupby.py
@@ -42,8 +42,7 @@
 from pandas.core.categorical import Categorical
 from pandas.core.frame import DataFrame
 from pandas.core.generic import NDFrame
-from pandas.core.index import (Index, MultiIndex, CategoricalIndex,
-                               _ensure_index)
+from pandas.core.interval import IntervalIndex
 from pandas.core.internals import BlockManager, make_block
 from pandas.core.series import Series
 from pandas.core.panel import Panel
@@ -3065,12 +3064,20 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
         if bins is None:
             lab, lev = algos.factorize(val, sort=True)
         else:
-            cat, bins = cut(val, bins, retbins=True)
+            raise NotImplementedError('this is broken')
+            lab, bins = cut(val, bins, retbins=True)
             # bins[:-1] for backward compat;
             # o.w. cat.categories could be better
-            lab, lev, dropna = cat.codes, bins[:-1], False
-
-        sorter = np.lexsort((lab, ids))
+            # cat = Categorical(cat)
+            # lab, lev, dropna = cat.codes, bins[:-1], False
+
+        if (lab.dtype == object
+                and lib.is_interval_array_fixed_closed(lab[notnull(lab)])):
+            lab_index = Index(lab)
+            assert isinstance(lab, IntervalIndex)
+            sorter = np.lexsort((lab_index.left, lab_index.right, ids))
+        else:
+            sorter = np.lexsort((lab, ids))
         ids, lab = ids[sorter], lab[sorter]
 
         # group boundaries are where group ids change
@@ -3111,12 +3118,13 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
                 acc = rep(d)
             out /= acc
 
-        if sort and bins is None:
+        if sort:  # and bins is None:
             cat = ids[inc][mask] if dropna else ids[inc]
             sorter = np.lexsort((out if ascending else -out, cat))
             out, labels[-1] = out[sorter], labels[-1][sorter]
 
-        if bins is None:
+        # if bins is None:
+        if True:
             mi = MultiIndex(levels=levels, labels=labels, names=names,
                             verify_integrity=False)