make unique_label_indices use intp

Author: realead

pandas/_libs/hashtable.pyx

@@ -60,11 +60,9 @@ include "hashtable_func_helper.pxi"
 if np.dtype(np.intp) == np.dtype(np.int64):
     IntpHashTable = Int64HashTable
     unique_label_indices = _unique_label_indices_int64
-    unique_label_indices_intp = _unique_label_indices_int64
 elif np.dtype(np.intp) == np.dtype(np.int32):
     IntpHashTable = Int32HashTable
-    unique_label_indices = _unique_label_indices_int64
-    unique_label_indices_intp = _unique_label_indices_int32
+    unique_label_indices = _unique_label_indices_int32
 else:
     raise ValueError(np.dtype(np.intp))
 

pandas/core/sorting.py

@@ -257,8 +257,7 @@ def decons_obs_group_ids(comp_ids: np.ndarray, obs_ids, shape, labels, xnull: bo
         out = decons_group_index(obs_ids, shape)
         return out if xnull or not lift.any() else [x - y for x, y in zip(out, lift)]
 
-    # TODO: unique_label_indices only used here, should take ndarray[np.intp]
-    indexer = unique_label_indices(ensure_int64(comp_ids))
+    indexer = unique_label_indices(comp_ids)
     return [lab[indexer].astype(np.intp, subok=False, copy=True) for lab in labels]
 
 

pandas/tests/test_algos.py

@@ -1726,7 +1726,7 @@ def test_quantile():
 
 def test_unique_label_indices():
 
-    a = np.random.randint(1, 1 << 10, 1 << 15).astype("int64")
+    a = np.random.randint(1, 1 << 10, 1 << 15).astype(np.intp)
 
     left = ht.unique_label_indices(a)
     right = np.unique(a, return_index=True)[1]