memory optimization

Author: jreback

pandas/tools/hashing.py

@@ -9,18 +9,30 @@
 from pandas.lib import is_bool_array
 from pandas.types.generic import ABCIndexClass, ABCSeries, ABCDataFrame
 from pandas.types.common import (is_categorical_dtype, is_numeric_dtype,
-                                 is_datetime64_dtype, is_timedelta64_dtype)
+                                 is_datetime64_dtype, is_timedelta64_dtype,
+                                 is_list_like)
 
 # 16 byte long hashing key
 _default_hash_key = '0123456789123456'
 
 
 def _combine_hash_arrays(arrays, num_items):
-    "Should be the same as CPython's tupleobject.c"
-    first = next(arrays)
+    """
+    Parameters
+    ----------
+    arrays : generator
+    num_items : int
+
+    Should be the same as CPython's tupleobject.c
+    """
+    try:
+        first = next(arrays)
+    except StopIteration:
+        return np.array([], dtype=np.uint64)
+
     arrays = itertools.chain([first], arrays)
 
-    mult = np.zeros_like(first) + np.uint64(1000003)
+    mult = np.uint64(1000003)
     out = np.zeros_like(first) + np.uint64(0x345678)
     for i, a in enumerate(arrays):
         inverse_i = num_items - i
@@ -135,11 +147,11 @@ def _hash_lists(vals, encoding='utf8', hash_key=None):
 
 def hash_tuples(vals, encoding='utf8', hash_key=None):
     """
-    Hash an MultiIndex / array_of_tuples efficiently
+    Hash an MultiIndex / list-of-tuples efficiently
 
     Parameters
     ----------
-    vals : MultiIndex, ndarray of tuples, or single tuple
+    vals : MultiIndex, list-of-tuples, or single tuple
     encoding : string, default 'utf8'
     hash_key : string key to encode, default to _default_hash_key
 
@@ -152,6 +164,8 @@ def hash_tuples(vals, encoding='utf8', hash_key=None):
     if isinstance(vals, tuple):
         vals = [vals]
         is_tuple = True
+    elif not is_list_like(vals):
+        raise TypeError("must be convertible to a list-of-tuples")
 
     if not isinstance(vals, MultiIndex):
         vals = MultiIndex.from_tuples(vals)

pandas/tools/tests/test_hashing.py

@@ -53,7 +53,8 @@ def check_not_equal_with_index(self, obj):
         if not isinstance(obj, Index):
             a = hash_pandas_object(obj, index=True)
             b = hash_pandas_object(obj, index=False)
-            self.assertFalse((a == b).all())
+            if len(obj):
+                self.assertFalse((a == b).all())
 
     def test_hash_tuples(self):
         tups = [(1, 'one'), (1, 'two'), (2, 'one')]
@@ -64,6 +65,11 @@ def test_hash_tuples(self):
         result = hash_tuples(tups[0])
         self.assertEqual(result, expected[0])
 
+    def test_hash_tuples_err(self):
+
+        for val in [5, 'foo', pd.Timestamp('20130101')]:
+            self.assertRaises(TypeError, hash_tuples, val)
+
     def test_multiindex_unique(self):
         mi = MultiIndex.from_tuples([(118, 472), (236, 118),
                                      (51, 204), (102, 51)])
@@ -81,9 +87,11 @@ def test_hash_pandas_object(self):
                     Series(['a', np.nan, 'c']),
                     Series(['a', None, 'c']),
                     Series([True, False, True]),
+                    Series(),
                     Index([1, 2, 3]),
                     Index([True, False, True]),
                     DataFrame({'x': ['a', 'b', 'c'], 'y': [1, 2, 3]}),
+                    DataFrame(),
                     tm.makeMissingDataframe(),
                     tm.makeMixedDataFrame(),
                     tm.makeTimeDataFrame(),