REF: rename _data->_mgr

pandas/_libs/properties.pyx

@@ -56,10 +56,10 @@ cdef class AxisProperty:
             list axes
 
         if obj is None:
-            # Only instances have _data, not classes
+            # Only instances have _mgr, not classes
             return self
         else:
-            axes = obj._data.axes
+            axes = obj._mgr.axes
         return axes[self.axis]
 
     def __set__(self, obj, value):

pandas/_libs/reduction.pyx

@@ -127,7 +127,7 @@ cdef class Reducer:
                     name = labels[i]
 
                     object.__setattr__(
-                        cached_typ._data._block, 'values', chunk)
+                        cached_typ._mgr._block, 'values', chunk)
                     object.__setattr__(cached_typ, 'name', name)
                     res = self.f(cached_typ)
                 else:
@@ -180,8 +180,8 @@ cdef class _BaseGrouper:
             # to a 1-d ndarray like datetime / timedelta / period.
             object.__setattr__(cached_ityp, '_index_data', islider.buf)
             cached_ityp._engine.clear_mapping()
-            object.__setattr__(cached_typ._data._block, 'values', vslider.buf)
-            object.__setattr__(cached_typ._data._block, 'mgr_locs',
+            object.__setattr__(cached_typ._mgr._block, 'values', vslider.buf)
+            object.__setattr__(cached_typ._mgr._block, 'mgr_locs',
                                slice(len(vslider.buf)))
             object.__setattr__(cached_typ, '_index', cached_ityp)
             object.__setattr__(cached_typ, 'name', self.name)
@@ -551,7 +551,7 @@ cdef class BlockSlider:
         self.dummy = frame[:0]
         self.index = self.dummy.index
 
-        self.blocks = [b.values for b in self.dummy._data.blocks]
+        self.blocks = [b.values for b in self.dummy._mgr.blocks]
 
         for x in self.blocks:
             util.set_array_not_contiguous(x)

pandas/_libs/src/ujson/python/objToJSON.c

@@ -279,7 +279,7 @@ static PyObject *get_sub_attr(PyObject *obj, char *attr, char *subAttr) {
 }
 
 static int is_simple_frame(PyObject *obj) {
-    PyObject *check = get_sub_attr(obj, "_data", "is_mixed_type");
+    PyObject *check = get_sub_attr(obj, "_mgr", "is_mixed_type");
     int ret = (check == Py_False);
 
     if (!check) {
@@ -760,7 +760,7 @@ void PdBlock_iterBegin(JSOBJ _obj, JSONTypeContext *tc) {
         goto BLKRET;
     }
 
-    blocks = get_sub_attr(obj, "_data", "blocks");
+    blocks = get_sub_attr(obj, "_mgr", "blocks");
     if (!blocks) {
         GET_TC(tc)->iterNext = NpyArr_iterNextNone;
         goto BLKRET;

pandas/core/algorithms.py

@@ -1645,7 +1645,7 @@ def take_nd(
         if arr.flags.f_contiguous and axis == arr.ndim - 1:
             # minor tweak that can make an order-of-magnitude difference
             # for dataframes initialized directly from 2-d ndarrays
-            # (s.t. df.values is c-contiguous and df._data.blocks[0] is its
+            # (s.t. df.values is c-contiguous and df._mgr.blocks[0] is its
             # f-contiguous transpose)
             out = np.empty(out_shape, dtype=dtype, order="F")
         else:

pandas/core/apply.py

@@ -165,7 +165,7 @@ def get_result(self):
         # ufunc
         elif isinstance(self.f, np.ufunc):
             with np.errstate(all="ignore"):
-                results = self.obj._data.apply("apply", func=self.f)
+                results = self.obj._mgr.apply("apply", func=self.f)
             return self.obj._constructor(
                 data=results, index=self.index, columns=self.columns, copy=False
             )

pandas/core/frame.py

@@ -431,7 +431,7 @@ def __init__(
             dtype = self._validate_dtype(dtype)
 
         if isinstance(data, DataFrame):
-            data = data._data
+            data = data._mgr
 
         if isinstance(data, BlockManager):
             mgr = self._init_mgr(
@@ -590,10 +590,10 @@ def _is_homogeneous_type(self) -> bool:
         ...    "B": np.array([1, 2], dtype=np.int64)})._is_homogeneous_type
         False
         """
-        if self._data.any_extension_types:
-            return len({block.dtype for block in self._data.blocks}) == 1
+        if self._mgr.any_extension_types:
+            return len({block.dtype for block in self._mgr.blocks}) == 1
         else:
-            return not self._data.is_mixed_type
+            return not self._mgr.is_mixed_type
 
     # ----------------------------------------------------------------------
     # Rendering Methods
@@ -2537,7 +2537,7 @@ def _ixs(self, i: int, axis: int = 0):
         """
         # irow
         if axis == 0:
-            new_values = self._data.fast_xs(i)
+            new_values = self._mgr.fast_xs(i)
 
             # if we are a copy, mark as such
             copy = isinstance(new_values, np.ndarray) and new_values.base is None
@@ -2554,7 +2554,7 @@ def _ixs(self, i: int, axis: int = 0):
         else:
             label = self.columns[i]
 
-            values = self._data.iget(i)
+            values = self._mgr.iget(i)
             result = self._box_col_values(values, label)
 
             # this is a cached value, mark it so
@@ -2865,7 +2865,7 @@ def _ensure_valid_index(self, value):
                     "and a value that cannot be converted to a Series"
                 ) from err
 
-            self._data = self._data.reindex_axis(
+            self._mgr = self._mgr.reindex_axis(
                 value.index.copy(), axis=1, fill_value=np.nan
             )
 
@@ -3313,7 +3313,7 @@ def insert(self, loc, column, value, allow_duplicates=False) -> None:
         """
         self._ensure_valid_index(value)
         value = self._sanitize_column(column, value, broadcast=False)
-        self._data.insert(loc, column, value, allow_duplicates=allow_duplicates)
+        self._mgr.insert(loc, column, value, allow_duplicates=allow_duplicates)
 
     def assign(self, **kwargs) -> "DataFrame":
         r"""
@@ -3494,7 +3494,7 @@ def reindexer(value):
     @property
     def _series(self):
         return {
-            item: Series(self._data.iget(idx), index=self.index, name=item)
+            item: Series(self._mgr.iget(idx), index=self.index, name=item)
             for idx, item in enumerate(self.columns)
         }
 
@@ -4403,7 +4403,7 @@ def _maybe_casted_values(index, labels=None):
                     values_dtype = values.dtype
 
                     if issubclass(values_type, DatetimeLikeArray):
-                        values = values._data
+                        values = values._data  # TODO: can we de-kludge yet?
 
                     if mask.any():
                         values, _ = maybe_upcast_putmask(values, mask, np.nan)
@@ -4787,7 +4787,7 @@ def sort_values(
                 k, kind=kind, ascending=ascending, na_position=na_position
             )
 
-        new_data = self._data.take(
+        new_data = self._mgr.take(
             indexer, axis=self._get_block_manager_axis(axis), verify=False
         )
 
@@ -4922,7 +4922,7 @@ def sort_index(
             )
 
         baxis = self._get_block_manager_axis(axis)
-        new_data = self._data.take(indexer, axis=baxis, verify=False)
+        new_data = self._mgr.take(indexer, axis=baxis, verify=False)
 
         # reconstruct axis if needed
         new_data.axes[baxis] = new_data.axes[baxis]._sort_levels_monotonic()
@@ -6661,7 +6661,7 @@ def diff(self, periods: int = 1, axis: Axis = 0) -> "DataFrame":
         5  NaN  NaN   NaN
         """
         bm_axis = self._get_block_manager_axis(axis)
-        new_data = self._data.diff(n=periods, axis=bm_axis)
+        new_data = self._mgr.diff(n=periods, axis=bm_axis)
         return self._constructor(new_data)
 
     # ----------------------------------------------------------------------
@@ -7855,7 +7855,7 @@ def count(self, axis=0, level=None, numeric_only=False):
         if len(frame._get_axis(axis)) == 0:
             result = Series(0, index=frame._get_agg_axis(axis))
         else:
-            if frame._is_mixed_type or frame._data.any_extension_types:
+            if frame._is_mixed_type or frame._mgr.any_extension_types:
                 # the or any_extension_types is really only hit for single-
                 # column frames with an extension array
                 result = notna(frame).sum(axis=axis)
@@ -7979,7 +7979,7 @@ def blk_func(values):
 
             # After possibly _get_data and transposing, we are now in the
             #  simple case where we can use BlockManager._reduce
-            res = df._data.reduce(blk_func)
+            res = df._mgr.reduce(blk_func)
             assert isinstance(res, dict)
             if len(res):
                 assert len(res) == max(list(res.keys())) + 1, res.keys()
@@ -8421,7 +8421,7 @@ def quantile(self, q=0.5, axis=0, numeric_only=True, interpolation="linear"):
                 return self._constructor([], index=q, columns=cols)
             return self._constructor_sliced([], index=cols, name=q, dtype=np.float64)
 
-        result = data._data.quantile(
+        result = data._mgr.quantile(
             qs=q, axis=1, interpolation=interpolation, transposed=is_transposed
         )