De-privatize (#36107)

Author: jbrockmendel

pandas/_libs/indexing.pyx

@@ -1,4 +1,4 @@
-cdef class _NDFrameIndexerBase:
+cdef class NDFrameIndexerBase:
     """
     A base class for _NDFrameIndexer for fast instantiation and attribute access.
     """

pandas/_libs/tslibs/parsing.pyx

@@ -771,7 +771,7 @@ class _timelex:
 _DATEUTIL_LEXER_SPLIT = _timelex.split
 
 
-def _format_is_iso(f) -> bint:
+def format_is_iso(f: str) -> bint:
     """
     Does format match the iso8601 set that can be handled by the C parser?
     Generally of form YYYY-MM-DDTHH:MM:SS - date separator can be different
@@ -789,7 +789,7 @@ def _format_is_iso(f) -> bint:
     return False
 
 
-def _guess_datetime_format(
+def guess_datetime_format(
     dt_str,
     bint dayfirst=False,
     dt_str_parse=du_parse,

pandas/core/arrays/datetimes.py

@@ -602,9 +602,9 @@ def astype(self, dtype, copy=True):
     # Rendering Methods
 
     def _format_native_types(self, na_rep="NaT", date_format=None, **kwargs):
-        from pandas.io.formats.format import _get_format_datetime64_from_values
+        from pandas.io.formats.format import get_format_datetime64_from_values
 
-        fmt = _get_format_datetime64_from_values(self, date_format)
+        fmt = get_format_datetime64_from_values(self, date_format)
 
         return tslib.format_array_from_datetime(
             self.asi8.ravel(), tz=self.tz, format=fmt, na_rep=na_rep

pandas/core/arrays/timedeltas.py

@@ -379,14 +379,14 @@ def median(
     # Rendering Methods
 
     def _formatter(self, boxed=False):
-        from pandas.io.formats.format import _get_format_timedelta64
+        from pandas.io.formats.format import get_format_timedelta64
 
-        return _get_format_timedelta64(self, box=True)
+        return get_format_timedelta64(self, box=True)
 
     def _format_native_types(self, na_rep="NaT", date_format=None, **kwargs):
-        from pandas.io.formats.format import _get_format_timedelta64
+        from pandas.io.formats.format import get_format_timedelta64
 
-        formatter = _get_format_timedelta64(self._data, na_rep)
+        formatter = get_format_timedelta64(self._data, na_rep)
         return np.array([formatter(x) for x in self._data.ravel()]).reshape(self.shape)
 
     # ----------------------------------------------------------------

pandas/core/common.py

@@ -31,7 +31,7 @@
     ABCIndexClass,
     ABCSeries,
 )
-from pandas.core.dtypes.inference import _iterable_not_string
+from pandas.core.dtypes.inference import iterable_not_string
 from pandas.core.dtypes.missing import isna, isnull, notnull  # noqa
 
 
@@ -61,7 +61,7 @@ def flatten(l):
     flattened : generator
     """
     for el in l:
-        if _iterable_not_string(el):
+        if iterable_not_string(el):
             for s in flatten(el):
                 yield s
         else:

pandas/core/computation/common.py

@@ -5,7 +5,7 @@
 from pandas._config import get_option
 
 
-def _ensure_decoded(s):
+def ensure_decoded(s):
     """
     If we have bytes, decode them to unicode.
     """

pandas/core/computation/ops.py

@@ -15,7 +15,7 @@
 from pandas.core.dtypes.common import is_list_like, is_scalar
 
 import pandas.core.common as com
-from pandas.core.computation.common import _ensure_decoded, result_type_many
+from pandas.core.computation.common import ensure_decoded, result_type_many
 from pandas.core.computation.scope import _DEFAULT_GLOBALS
 
 from pandas.io.formats.printing import pprint_thing, pprint_thing_encoded
@@ -466,7 +466,7 @@ def stringify(value):
             v = rhs.value
             if isinstance(v, (int, float)):
                 v = stringify(v)
-            v = Timestamp(_ensure_decoded(v))
+            v = Timestamp(ensure_decoded(v))
             if v.tz is not None:
                 v = v.tz_convert("UTC")
             self.rhs.update(v)
@@ -475,7 +475,7 @@ def stringify(value):
             v = lhs.value
             if isinstance(v, (int, float)):
                 v = stringify(v)
-            v = Timestamp(_ensure_decoded(v))
+            v = Timestamp(ensure_decoded(v))
             if v.tz is not None:
                 v = v.tz_convert("UTC")
             self.lhs.update(v)

pandas/core/computation/pytables.py

@@ -14,7 +14,7 @@
 import pandas as pd
 import pandas.core.common as com
 from pandas.core.computation import expr, ops, scope as _scope
-from pandas.core.computation.common import _ensure_decoded
+from pandas.core.computation.common import ensure_decoded
 from pandas.core.computation.expr import BaseExprVisitor
 from pandas.core.computation.ops import UndefinedVariableError, is_term
 from pandas.core.construction import extract_array
@@ -189,12 +189,12 @@ def stringify(value):
                 encoder = pprint_thing
             return encoder(value)
 
-        kind = _ensure_decoded(self.kind)
-        meta = _ensure_decoded(self.meta)
+        kind = ensure_decoded(self.kind)
+        meta = ensure_decoded(self.meta)
         if kind == "datetime64" or kind == "datetime":
             if isinstance(v, (int, float)):
                 v = stringify(v)
-            v = _ensure_decoded(v)
+            v = ensure_decoded(v)
             v = Timestamp(v)
             if v.tz is not None:
                 v = v.tz_convert("UTC")

pandas/core/dtypes/common.py

@@ -635,8 +635,8 @@ def is_dtype_equal(source, target) -> bool:
     False
     """
     try:
-        source = _get_dtype(source)
-        target = _get_dtype(target)
+        source = get_dtype(source)
+        target = get_dtype(target)
         return source == target
     except (TypeError, AttributeError):
 
@@ -984,10 +984,10 @@ def is_datetime64_ns_dtype(arr_or_dtype) -> bool:
     if arr_or_dtype is None:
         return False
     try:
-        tipo = _get_dtype(arr_or_dtype)
+        tipo = get_dtype(arr_or_dtype)
     except TypeError:
         if is_datetime64tz_dtype(arr_or_dtype):
-            tipo = _get_dtype(arr_or_dtype.dtype)
+            tipo = get_dtype(arr_or_dtype.dtype)
         else:
             return False
     return tipo == DT64NS_DTYPE or getattr(tipo, "base", None) == DT64NS_DTYPE
@@ -1372,7 +1372,7 @@ def is_bool_dtype(arr_or_dtype) -> bool:
     if arr_or_dtype is None:
         return False
     try:
-        dtype = _get_dtype(arr_or_dtype)
+        dtype = get_dtype(arr_or_dtype)
     except TypeError:
         return False
 
@@ -1557,13 +1557,13 @@ def _is_dtype(arr_or_dtype, condition) -> bool:
     if arr_or_dtype is None:
         return False
     try:
-        dtype = _get_dtype(arr_or_dtype)
+        dtype = get_dtype(arr_or_dtype)
     except (TypeError, ValueError, UnicodeEncodeError):
         return False
     return condition(dtype)
 
 
-def _get_dtype(arr_or_dtype) -> DtypeObj:
+def get_dtype(arr_or_dtype) -> DtypeObj:
     """
     Get the dtype instance associated with an array
     or dtype object.
@@ -1694,7 +1694,7 @@ def infer_dtype_from_object(dtype):
         try:
             return infer_dtype_from_object(getattr(np, dtype))
         except (AttributeError, TypeError):
-            # Handles cases like _get_dtype(int) i.e.,
+            # Handles cases like get_dtype(int) i.e.,
             # Python objects that are valid dtypes
             # (unlike user-defined types, in general)
             #

pandas/core/dtypes/inference.py

@@ -68,7 +68,7 @@ def is_number(obj) -> bool:
     return isinstance(obj, (Number, np.number))
 
 
-def _iterable_not_string(obj) -> bool:
+def iterable_not_string(obj) -> bool:
     """
     Check if the object is an iterable but not a string.
 
@@ -83,11 +83,11 @@ def _iterable_not_string(obj) -> bool:
 
     Examples
     --------
-    >>> _iterable_not_string([1, 2, 3])
+    >>> iterable_not_string([1, 2, 3])
     True
-    >>> _iterable_not_string("foo")
+    >>> iterable_not_string("foo")
     False
-    >>> _iterable_not_string(1)
+    >>> iterable_not_string(1)
     False
     """
     return isinstance(obj, abc.Iterable) and not isinstance(obj, str)

pandas/core/dtypes/missing.py

@@ -338,7 +338,7 @@ def notna(obj):
 notnull = notna
 
 
-def _isna_compat(arr, fill_value=np.nan) -> bool:
+def isna_compat(arr, fill_value=np.nan) -> bool:
     """
     Parameters
     ----------
@@ -496,7 +496,7 @@ def array_equals(left: ArrayLike, right: ArrayLike) -> bool:
         return array_equivalent(left, right, dtype_equal=True)
 
 
-def _infer_fill_value(val):
+def infer_fill_value(val):
     """
     infer the fill value for the nan/NaT from the provided
     scalar/ndarray/list-like if we are a NaT, return the correct dtyped
@@ -516,11 +516,11 @@ def _infer_fill_value(val):
     return np.nan
 
 
-def _maybe_fill(arr, fill_value=np.nan):
+def maybe_fill(arr, fill_value=np.nan):
     """
     if we have a compatible fill_value and arr dtype, then fill
     """
-    if _isna_compat(arr, fill_value):
+    if isna_compat(arr, fill_value):
         arr.fill(fill_value)
     return arr
 

pandas/core/groupby/ops.py

@@ -37,7 +37,7 @@
     is_timedelta64_dtype,
     needs_i8_conversion,
 )
-from pandas.core.dtypes.missing import _maybe_fill, isna
+from pandas.core.dtypes.missing import isna, maybe_fill
 
 import pandas.core.algorithms as algorithms
 from pandas.core.base import SelectionMixin
@@ -524,13 +524,11 @@ def _cython_operation(
         codes, _, _ = self.group_info
 
         if kind == "aggregate":
-            result = _maybe_fill(
-                np.empty(out_shape, dtype=out_dtype), fill_value=np.nan
-            )
+            result = maybe_fill(np.empty(out_shape, dtype=out_dtype), fill_value=np.nan)
             counts = np.zeros(self.ngroups, dtype=np.int64)
             result = self._aggregate(result, counts, values, codes, func, min_count)
         elif kind == "transform":
-            result = _maybe_fill(
+            result = maybe_fill(
                 np.empty_like(values, dtype=out_dtype), fill_value=np.nan
             )
 

pandas/core/indexes/timedeltas.py

@@ -177,9 +177,9 @@ def _simple_new(cls, values: TimedeltaArray, name: Label = None):
 
     @property
     def _formatter_func(self):
-        from pandas.io.formats.format import _get_format_timedelta64
+        from pandas.io.formats.format import get_format_timedelta64
 
-        return _get_format_timedelta64(self, box=True)
+        return get_format_timedelta64(self, box=True)
 
     # -------------------------------------------------------------------
 

pandas/core/indexing.py

@@ -4,7 +4,7 @@
 
 from pandas._config.config import option_context
 
-from pandas._libs.indexing import _NDFrameIndexerBase
+from pandas._libs.indexing import NDFrameIndexerBase
 from pandas._libs.lib import item_from_zerodim
 from pandas.errors import AbstractMethodError, InvalidIndexError
 from pandas.util._decorators import doc
@@ -22,7 +22,7 @@
 )
 from pandas.core.dtypes.concat import concat_compat
 from pandas.core.dtypes.generic import ABCDataFrame, ABCMultiIndex, ABCSeries
-from pandas.core.dtypes.missing import _infer_fill_value, isna
+from pandas.core.dtypes.missing import infer_fill_value, isna
 
 import pandas.core.common as com
 from pandas.core.construction import array as pd_array
@@ -583,7 +583,7 @@ def iat(self) -> "_iAtIndexer":
         return _iAtIndexer("iat", self)
 
 
-class _LocationIndexer(_NDFrameIndexerBase):
+class _LocationIndexer(NDFrameIndexerBase):
     _valid_types: str
     axis = None
 
@@ -1604,7 +1604,7 @@ def _setitem_with_indexer(self, indexer, value):
                             return
 
                         # add a new item with the dtype setup
-                        self.obj[key] = _infer_fill_value(value)
+                        self.obj[key] = infer_fill_value(value)
 
                         new_indexer = convert_from_missing_indexer_tuple(
                             indexer, self.obj.axes
@@ -2017,7 +2017,7 @@ def _align_frame(self, indexer, df: ABCDataFrame):
         raise ValueError("Incompatible indexer with DataFrame")
 
 
-class _ScalarAccessIndexer(_NDFrameIndexerBase):
+class _ScalarAccessIndexer(NDFrameIndexerBase):
     """
     Access scalars quickly.
     """

pandas/core/internals/blocks.py

@@ -56,7 +56,7 @@
     ABCPandasArray,
     ABCSeries,
 )
-from pandas.core.dtypes.missing import _isna_compat, is_valid_nat_for_dtype, isna
+from pandas.core.dtypes.missing import is_valid_nat_for_dtype, isna, isna_compat
 
 import pandas.core.algorithms as algos
 from pandas.core.array_algos.transforms import shift
@@ -487,7 +487,7 @@ def _maybe_downcast(self, blocks: List["Block"], downcast=None) -> List["Block"]
         ):
             return blocks
 
-        return _extend_blocks([b.downcast(downcast) for b in blocks])
+        return extend_blocks([b.downcast(downcast) for b in blocks])
 
     def downcast(self, dtypes=None):
         """ try to downcast each item to the dict of dtypes if present """
@@ -2474,7 +2474,7 @@ def _maybe_downcast(self, blocks: List["Block"], downcast=None) -> List["Block"]
             return blocks
 
         # split and convert the blocks
-        return _extend_blocks([b.convert(datetime=True, numeric=False) for b in blocks])
+        return extend_blocks([b.convert(datetime=True, numeric=False) for b in blocks])
 
     def _can_hold_element(self, element: Any) -> bool:
         return True
@@ -2503,7 +2503,7 @@ def replace(self, to_replace, value, inplace=False, regex=False, convert=True):
                     result = b._replace_single(
                         to_rep, v, inplace=inplace, regex=regex, convert=convert
                     )
-                    result_blocks = _extend_blocks(result, result_blocks)
+                    result_blocks = extend_blocks(result, result_blocks)
                 blocks = result_blocks
             return result_blocks
 
@@ -2514,7 +2514,7 @@ def replace(self, to_replace, value, inplace=False, regex=False, convert=True):
                     result = b._replace_single(
                         to_rep, value, inplace=inplace, regex=regex, convert=convert
                     )
-                    result_blocks = _extend_blocks(result, result_blocks)
+                    result_blocks = extend_blocks(result, result_blocks)
                 blocks = result_blocks
             return result_blocks
 
@@ -2769,7 +2769,7 @@ def make_block(values, placement, klass=None, ndim=None, dtype=None):
 # -----------------------------------------------------------------
 
 
-def _extend_blocks(result, blocks=None):
+def extend_blocks(result, blocks=None):
     """ return a new extended blocks, given the result """
     if blocks is None:
         blocks = []
@@ -2860,7 +2860,7 @@ def _putmask_smart(v: np.ndarray, mask: np.ndarray, n) -> np.ndarray:
     else:
         # make sure that we have a nullable type
         # if we have nulls
-        if not _isna_compat(v, nn[0]):
+        if not isna_compat(v, nn[0]):
             pass
         elif not (is_float_dtype(nn.dtype) or is_integer_dtype(nn.dtype)):
             # only compare integers/floats