renamed, repositioned bytes_to_size_label

doc/source/articles/serialize.py

@@ -19,6 +19,7 @@
 
 import static_frame as sf
 from static_frame.core.display_color import HexColor
+from static_frame.core.util import bytes_to_data_label
 
 
 class FileIOTest:
@@ -394,15 +395,6 @@ def plot_performance(frame: sf.Frame):
 
 
 #-------------------------------------------------------------------------------
-def convert_size(size_bytes):
-    import math
-    if size_bytes == 0:
-        return '0B'
-    size_name = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
-    i = int(math.floor(math.log(size_bytes, 1024)))
-    p = math.pow(1024, i)
-    s = round(size_bytes / p, 2)
-    return '%s %s' % (s, size_name[i])
 
 
 def plot_size(frame: sf.Frame):
@@ -450,8 +442,8 @@ def plot_size(frame: sf.Frame):
         size_max = results.max()
         ax.set_yticks([0, size_max * 0.5, size_max])
         ax.set_yticklabels(['',
-                convert_size(size_max * 0.5),
-                convert_size(size_max),
+                bytes_to_data_label(size_max * 0.5),
+                bytes_to_data_label(size_max),
                 ], fontsize=6)
         ax.tick_params(
                 axis='x',
@@ -514,21 +506,21 @@ def get_sizes():
         size_parquet = os.path.getsize(fp)
         os.unlink(fp)
         record.append(size_parquet)
-        record.append(convert_size(size_parquet))
+        record.append(bytes_to_data_label(size_parquet))
 
         _, fp = tempfile.mkstemp(suffix='.parquet')
         df.to_parquet(fp, compression=None)
         size_parquet_noc = os.path.getsize(fp)
         os.unlink(fp)
         record.append(size_parquet_noc)
-        record.append(convert_size(size_parquet_noc))
+        record.append(bytes_to_data_label(size_parquet_noc))
 
         _, fp = tempfile.mkstemp(suffix='.npz')
         f.to_npz(fp, include_columns=True)
         size_npz = os.path.getsize(fp)
         os.unlink(fp)
         record.append(size_npz)
-        record.append(convert_size(size_npz))
+        record.append(bytes_to_data_label(size_npz))
 
         _, fp = tempfile.mkstemp(suffix='.pickle')
         file = open(fp, 'wb')
@@ -537,7 +529,7 @@ def get_sizes():
         size_pickle = os.path.getsize(fp)
         os.unlink(fp)
         record.append(size_pickle)
-        record.append(convert_size(size_pickle))
+        record.append(bytes_to_data_label(size_pickle))
 
         record.append(round(size_npz / size_parquet, 3))
         record.append(round(size_npz / size_parquet_noc, 3))

static_frame/core/display.py

@@ -21,7 +21,7 @@
 from static_frame.core.util import DTYPE_STR_KINDS
 from static_frame.core.util import FLOAT_TYPES
 from static_frame.core.util import CallableToIterType
-from static_frame.core.util import _gen_skip_middle
+from static_frame.core.util import gen_skip_middle
 
 if tp.TYPE_CHECKING:
     from static_frame.core.index_base import IndexBase  # pylint: disable=unused-import #pragma: no cover
@@ -459,7 +459,7 @@ def from_values(cls,
             count_max = config.display_rows
             if len(values) > config.display_rows:
                 data_half_count = Display.truncate_half_count(count_max)
-                value_gen = partial(_gen_skip_middle,
+                value_gen = partial(gen_skip_middle,
                         forward_iter=values.__iter__,
                         forward_count=data_half_count,
                         reverse_iter=partial(reversed, values),
@@ -532,7 +532,7 @@ def from_params(cls,
             # columns as they will look after application of truncation and insertion of ellipsis
             data_half_count = cls.truncate_half_count(config.display_columns)
 
-            column_gen = partial(_gen_skip_middle,
+            column_gen = partial(gen_skip_middle,
                     forward_iter=column_forward_iter,
                     forward_count=data_half_count,
                     reverse_iter=column_reverse_iter,
@@ -847,7 +847,7 @@ def extend_iterable(self,
 
         if len(iterable) > count_max:
             data_half_count = self.truncate_half_count(count_max)
-            value_gen: tp.Callable[[], tp.Iterator[tp.Any]] = partial(_gen_skip_middle,
+            value_gen: tp.Callable[[], tp.Iterator[tp.Any]] = partial(gen_skip_middle,
                     forward_iter=iterable.__iter__,
                     forward_count=data_half_count,
                     reverse_iter=partial(reversed, iterable),

static_frame/core/memory_measure.py

@@ -9,6 +9,7 @@
 import numpy as np
 
 from static_frame.core.util import DTYPE_OBJECT_KIND
+from static_frame.core.util import bytes_to_data_label
 
 if tp.TYPE_CHECKING:
     from static_frame.core.frame import Frame  # pylint: disable=W0611 #pragma: no cover
@@ -35,29 +36,32 @@ class MeasureFormat(Enum):
             materialized=True,
             data_only=True,
             )
-    SHARED = MFConfig(
+    # NOTE MFConfig(local_only=True, materialized=False, data_only=True) is invalid
+
+    REFERENCED = MFConfig(
             local_only=False,
             materialized=False,
             data_only=False,
             )
-    SHARED_MATERIALIZED = MFConfig(
+    REFERENCED_MATERIALIZED = MFConfig(
             local_only=False,
             materialized=True,
             data_only=False,
             )
-    SHARED_MATERIALIZED_DATA = MFConfig(
+    REFERENCED_MATERIALIZED_DATA = MFConfig(
             local_only=False,
             materialized=True,
             data_only=True,
             )
+    # NOTE MFConfig(local_only=False, materialized=False, data_only=True) is invalid
 
 FORMAT_TO_DISPLAY = {
-        MeasureFormat.LOCAL: 'local',
-        MeasureFormat.LOCAL_MATERIALIZED: 'local_material',
-        MeasureFormat.LOCAL_MATERIALIZED_DATA: 'local_material_data',
-        MeasureFormat.SHARED: 'shared',
-        MeasureFormat.SHARED_MATERIALIZED: 'shared_material',
-        MeasureFormat.SHARED_MATERIALIZED_DATA: 'shared_material_data',
+        MeasureFormat.LOCAL: 'L',
+        MeasureFormat.LOCAL_MATERIALIZED: 'LM',
+        MeasureFormat.LOCAL_MATERIALIZED_DATA: 'LMD',
+        MeasureFormat.REFERENCED: 'R',
+        MeasureFormat.REFERENCED_MATERIALIZED: 'RM',
+        MeasureFormat.REFERENCED_MATERIALIZED_DATA: 'RMD',
         }
 
 class MaterializedArray:
@@ -127,7 +131,7 @@ def _iter_slots(obj: tp.Any) -> tp.Iterator[tp.Any]:
     def nested_sizable_elements(cls,
             obj: tp.Any,
             *,
-            format: MeasureFormat = MeasureFormat.SHARED,
+            format: MeasureFormat = MeasureFormat.REFERENCED,
             seen: tp.Set[int],
             ) -> tp.Iterator[tp.Any]:
         '''
@@ -165,20 +169,10 @@ def nested_sizable_elements(cls,
         yield obj
 
 
-def bytes_to_data_label(size_bytes: int) -> str:
-    if size_bytes == 0:
-        return '0B'
-    size_name = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
-    i = int(math.floor(math.log(size_bytes, 1024)))
-    p = math.pow(1024, i)
-    s = round(size_bytes / p, 2)
-    return f'{s} {size_name[i]}'
-
-
 def getsizeof_total(
         obj: tp.Any,
         *,
-        format: MeasureFormat = MeasureFormat.SHARED,
+        format: MeasureFormat = MeasureFormat.REFERENCED,
         seen: tp.Union[None, tp.Set[tp.Any]] = None,
         ) -> int:
     '''

static_frame/core/util.py

@@ -609,6 +609,16 @@ class PairRight(Pair):
 
 #-------------------------------------------------------------------------------
 
+def bytes_to_data_label(size_bytes: int) -> str:
+    if size_bytes == 0:
+        return '0B'
+    size_name = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
+    i = int(math.floor(math.log(size_bytes, 1024)))
+    p = math.pow(1024, i)
+    s = round(size_bytes / p, 2)
+    return f'{s} {size_name[i]}'
+
+
 
 # def mloc(array: np.ndarray) -> int:
 #     '''Return the memory location of an array.
@@ -693,7 +703,7 @@ class PairRight(Pair):
 #             yield v
 #         last = v
 
-def _gen_skip_middle(
+def gen_skip_middle(
         forward_iter: CallableToIterType,
         forward_count: int,
         reverse_iter: CallableToIterType,

static_frame/test/unit/test_util.py

@@ -18,7 +18,6 @@
 from static_frame.core.util import UFUNC_MAP
 from static_frame.core.util import WarningsSilent
 from static_frame.core.util import _array_to_duplicated_sortable
-from static_frame.core.util import _gen_skip_middle
 from static_frame.core.util import _isin_1d
 from static_frame.core.util import _isin_2d
 from static_frame.core.util import _ufunc_logical_skipna
@@ -42,6 +41,7 @@
 from static_frame.core.util import datetime64_not_aligned
 from static_frame.core.util import dtype_from_element
 from static_frame.core.util import dtype_to_fill_value
+from static_frame.core.util import gen_skip_middle
 from static_frame.core.util import get_tuple_constructor
 from static_frame.core.util import intersect1d
 from static_frame.core.util import intersect2d
@@ -89,7 +89,7 @@ def test_gen_skip_middle_a(self) -> None:
         forward = lambda: [3, 2, 5]
         reverse = lambda: [3, 2, 5]
 
-        post = _gen_skip_middle(
+        post = gen_skip_middle(
                 forward_iter=forward,
                 forward_count=3,
                 reverse_iter=reverse,
@@ -98,7 +98,7 @@ def test_gen_skip_middle_a(self) -> None:
 
         self.assertEqual(list(post), [3, 2, 5, -1, 5, 2, 3])
 
-        post = _gen_skip_middle(
+        post = gen_skip_middle(
                 forward_iter=forward,
                 forward_count=2,
                 reverse_iter=reverse,