BUG: don't assume series is length > 0

Author: hexgnu

doc/source/whatsnew/v0.23.0.txt

@@ -557,3 +557,4 @@ Other
 ^^^^^
 
 - Improved error message when attempting to use a Python keyword as an identifier in a ``numexpr`` backed query (:issue:`18221`)
+- Bug in `Series.memory_usage` which assumes series will always have more than one element (:issue:`19368`)

pandas/_libs/lib.pyx

@@ -67,7 +67,8 @@ def memory_usage_of_objects(ndarray[object, ndim=1] arr):
  cdef int64_t s = 0
 
  n = len(arr)
- for i from 0 <= i < n:
+ # Hrm why was this 0 <= i < n
+ for i from 0 < i < n:
  s += arr[i].__sizeof__()
  return s
 

pandas/tests/sparse/series/test_series.py

@@ -971,6 +971,17 @@ def test_combine_first(self):
  tm.assert_sp_series_equal(result, result2)
  tm.assert_sp_series_equal(result, expected)
 
+ @pytest.mark.parametrize('deep,fill_values', [([True, False],
+ [0, 1, np.nan, None])])
+ def test_memory_usage_deep(self, deep, fill_values):
+ for fv in fill_values:
+ sparse_series = SparseSeries(fill_values, fill_value=fv)
+ dense_series = Series(fill_values)
+ sparse_usage = sparse_series.memory_usage(deep=deep)
+ dense_usage = dense_series.memory_usage(deep=deep)
+
+ assert sparse_usage < dense_usage
+
 
 class TestSparseHandlingMultiIndexes(object):