STY: De-privatize imported names (#36235)

Author: jbrockmendel

pandas/_libs/interval.pyx

@@ -46,7 +46,7 @@ from pandas._libs.tslibs.util cimport (
     is_timedelta64_object,
 )
 
-_VALID_CLOSED = frozenset(['left', 'right', 'both', 'neither'])
+VALID_CLOSED = frozenset(['left', 'right', 'both', 'neither'])
 
 
 cdef class IntervalMixin:
@@ -318,7 +318,7 @@ cdef class Interval(IntervalMixin):
         self._validate_endpoint(left)
         self._validate_endpoint(right)
 
-        if closed not in _VALID_CLOSED:
+        if closed not in VALID_CLOSED:
             raise ValueError(f"invalid option for 'closed': {closed}")
         if not left <= right:
             raise ValueError("left side of interval must be <= right side")

pandas/core/arrays/_arrow_utils.py

@@ -4,7 +4,7 @@
 import numpy as np
 import pyarrow
 
-from pandas.core.arrays.interval import _VALID_CLOSED
+from pandas.core.arrays.interval import VALID_CLOSED
 
 _pyarrow_version_ge_015 = LooseVersion(pyarrow.__version__) >= LooseVersion("0.15")
 
@@ -83,7 +83,7 @@ class ArrowIntervalType(pyarrow.ExtensionType):
         def __init__(self, subtype, closed):
             # attributes need to be set first before calling
             # super init (as that calls serialize)
-            assert closed in _VALID_CLOSED
+            assert closed in VALID_CLOSED
             self._closed = closed
             if not isinstance(subtype, pyarrow.DataType):
                 subtype = pyarrow.type_for_alias(str(subtype))

pandas/core/arrays/interval.py

@@ -5,7 +5,12 @@
 
 from pandas._config import get_option
 
-from pandas._libs.interval import Interval, IntervalMixin, intervals_to_interval_bounds
+from pandas._libs.interval import (
+    VALID_CLOSED,
+    Interval,
+    IntervalMixin,
+    intervals_to_interval_bounds,
+)
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender
 
@@ -42,7 +47,6 @@
 from pandas.core.indexers import check_array_indexer
 from pandas.core.indexes.base import ensure_index
 
-_VALID_CLOSED = {"left", "right", "both", "neither"}
 _interval_shared_docs = {}
 
 _shared_docs_kwargs = dict(
@@ -475,7 +479,7 @@ def _validate(self):
         * left and right have the same missing values
         * left is always below right
         """
-        if self.closed not in _VALID_CLOSED:
+        if self.closed not in VALID_CLOSED:
             msg = f"invalid option for 'closed': {self.closed}"
             raise ValueError(msg)
         if len(self.left) != len(self.right):
@@ -1012,7 +1016,7 @@ def closed(self):
         )
     )
     def set_closed(self, closed):
-        if closed not in _VALID_CLOSED:
+        if closed not in VALID_CLOSED:
             msg = f"invalid option for 'closed': {closed}"
             raise ValueError(msg)
 

pandas/core/arrays/sparse/__init__.py

@@ -5,6 +5,6 @@
     BlockIndex,
     IntIndex,
     SparseArray,
-    _make_index,
+    make_sparse_index,
 )
 from pandas.core.arrays.sparse.dtype import SparseDtype

pandas/core/arrays/sparse/array.py

@@ -1556,15 +1556,15 @@ def make_sparse(arr: np.ndarray, kind="block", fill_value=None, dtype=None, copy
     else:
         indices = mask.nonzero()[0].astype(np.int32)
 
-    index = _make_index(length, indices, kind)
+    index = make_sparse_index(length, indices, kind)
     sparsified_values = arr[mask]
     if dtype is not None:
         sparsified_values = astype_nansafe(sparsified_values, dtype=dtype)
     # TODO: copy
     return sparsified_values, index, fill_value
 
 
-def _make_index(length, indices, kind):
+def make_sparse_index(length, indices, kind):
 
     if kind == "block" or isinstance(kind, BlockIndex):
         locs, lens = splib.get_blocks(indices)

pandas/core/computation/engines.py

@@ -130,7 +130,7 @@ def _evaluate(self) -> None:
         pass
 
 
-_engines: Dict[str, Type[AbstractEngine]] = {
+ENGINES: Dict[str, Type[AbstractEngine]] = {
     "numexpr": NumExprEngine,
     "python": PythonEngine,
 }

pandas/core/computation/eval.py

@@ -9,8 +9,8 @@
 from pandas._libs.lib import no_default
 from pandas.util._validators import validate_bool_kwarg
 
-from pandas.core.computation.engines import _engines
-from pandas.core.computation.expr import Expr, _parsers
+from pandas.core.computation.engines import ENGINES
+from pandas.core.computation.expr import PARSERS, Expr
 from pandas.core.computation.parsing import tokenize_string
 from pandas.core.computation.scope import ensure_scope
 
@@ -43,8 +43,8 @@ def _check_engine(engine: Optional[str]) -> str:
     if engine is None:
         engine = "numexpr" if NUMEXPR_INSTALLED else "python"
 
-    if engine not in _engines:
-        valid_engines = list(_engines.keys())
+    if engine not in ENGINES:
+        valid_engines = list(ENGINES.keys())
         raise KeyError(
             f"Invalid engine '{engine}' passed, valid engines are {valid_engines}"
         )
@@ -75,9 +75,9 @@ def _check_parser(parser: str):
     KeyError
       * If an invalid parser is passed
     """
-    if parser not in _parsers:
+    if parser not in PARSERS:
         raise KeyError(
-            f"Invalid parser '{parser}' passed, valid parsers are {_parsers.keys()}"
+            f"Invalid parser '{parser}' passed, valid parsers are {PARSERS.keys()}"
         )
 
 
@@ -341,7 +341,7 @@ def eval(
         parsed_expr = Expr(expr, engine=engine, parser=parser, env=env)
 
         # construct the engine and evaluate the parsed expression
-        eng = _engines[engine]
+        eng = ENGINES[engine]
         eng_inst = eng(parsed_expr)
         ret = eng_inst.evaluate()
 

pandas/core/computation/expr.py

@@ -782,7 +782,7 @@ def __init__(
         self.env = env or Scope(level=level + 1)
         self.engine = engine
         self.parser = parser
-        self._visitor = _parsers[parser](self.env, self.engine, self.parser)
+        self._visitor = PARSERS[parser](self.env, self.engine, self.parser)
         self.terms = self.parse()
 
     @property
@@ -814,4 +814,4 @@ def names(self):
         return frozenset(term.name for term in com.flatten(self.terms))
 
 
-_parsers = {"python": PythonExprVisitor, "pandas": PandasExprVisitor}
+PARSERS = {"python": PythonExprVisitor, "pandas": PandasExprVisitor}

pandas/core/config_init.py

@@ -314,9 +314,9 @@ def use_numba_cb(key):
 
 
 def table_schema_cb(key):
-    from pandas.io.formats.printing import _enable_data_resource_formatter
+    from pandas.io.formats.printing import enable_data_resource_formatter
 
-    _enable_data_resource_formatter(cf.get_option(key))
+    enable_data_resource_formatter(cf.get_option(key))
 
 
 def is_terminal() -> bool:

pandas/core/groupby/generic.py

@@ -70,9 +70,9 @@
     GroupBy,
     _agg_template,
     _apply_docs,
-    _group_selection_context,
     _transform_template,
     get_groupby,
+    group_selection_context,
 )
 from pandas.core.groupby.numba_ import generate_numba_func, split_for_numba
 from pandas.core.indexes.api import Index, MultiIndex, all_indexes_same
@@ -230,7 +230,7 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
                 raise NotImplementedError(
                     "Numba engine can only be used with a single function."
                 )
-            with _group_selection_context(self):
+            with group_selection_context(self):
                 data = self._selected_obj
             result, index = self._aggregate_with_numba(
                 data.to_frame(), func, *args, engine_kwargs=engine_kwargs, **kwargs
@@ -685,7 +685,7 @@ def value_counts(
         self, normalize=False, sort=True, ascending=False, bins=None, dropna=True
     ):
 
-        from pandas.core.reshape.merge import _get_join_indexers
+        from pandas.core.reshape.merge import get_join_indexers
         from pandas.core.reshape.tile import cut
 
         if bins is not None and not np.iterable(bins):
@@ -787,7 +787,7 @@ def value_counts(
 
         right = [diff.cumsum() - 1, codes[-1]]
 
-        _, idx = _get_join_indexers(left, right, sort=False, how="left")
+        _, idx = get_join_indexers(left, right, sort=False, how="left")
         out = np.where(idx != -1, out[idx], 0)
 
         if sort:
@@ -942,7 +942,7 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
                 raise NotImplementedError(
                     "Numba engine can only be used with a single function."
                 )
-            with _group_selection_context(self):
+            with group_selection_context(self):
                 data = self._selected_obj
             result, index = self._aggregate_with_numba(
                 data, func, *args, engine_kwargs=engine_kwargs, **kwargs

pandas/core/groupby/groupby.py

@@ -459,9 +459,9 @@ def f(self):
 
 
 @contextmanager
-def _group_selection_context(groupby: "_GroupBy"):
+def group_selection_context(groupby: "_GroupBy"):
     """
-    Set / reset the _group_selection_context.
+    Set / reset the group_selection_context.
     """
     groupby._set_group_selection()
     try:
@@ -737,7 +737,7 @@ def pipe(self, func, *args, **kwargs):
     def _make_wrapper(self, name: str) -> Callable:
         assert name in self._apply_allowlist
 
-        with _group_selection_context(self):
+        with group_selection_context(self):
             # need to setup the selection
             # as are not passed directly but in the grouper
             f = getattr(self._obj_with_exclusions, name)
@@ -868,7 +868,7 @@ def f(g):
                 # fails on *some* columns, e.g. a numeric operation
                 # on a string grouper column
 
-                with _group_selection_context(self):
+                with group_selection_context(self):
                     return self._python_apply_general(f, self._selected_obj)
 
         return result
@@ -994,7 +994,7 @@ def _agg_general(
         alias: str,
         npfunc: Callable,
     ):
-        with _group_selection_context(self):
+        with group_selection_context(self):
             # try a cython aggregation if we can
             try:
                 return self._cython_agg_general(
@@ -1499,7 +1499,7 @@ def var(self, ddof: int = 1):
             )
         else:
             func = lambda x: x.var(ddof=ddof)
-            with _group_selection_context(self):
+            with group_selection_context(self):
                 return self._python_agg_general(func)
 
     @Substitution(name="groupby")
@@ -1658,7 +1658,7 @@ def ohlc(self) -> DataFrame:
 
     @doc(DataFrame.describe)
     def describe(self, **kwargs):
-        with _group_selection_context(self):
+        with group_selection_context(self):
             result = self.apply(lambda x: x.describe(**kwargs))
             if self.axis == 1:
                 return result.T
@@ -1963,7 +1963,7 @@ def nth(self, n: Union[int, List[int]], dropna: Optional[str] = None) -> DataFra
                 nth_values = list(set(n))
 
             nth_array = np.array(nth_values, dtype=np.intp)
-            with _group_selection_context(self):
+            with group_selection_context(self):
 
                 mask_left = np.in1d(self._cumcount_array(), nth_array)
                 mask_right = np.in1d(
@@ -2226,7 +2226,7 @@ def ngroup(self, ascending: bool = True):
         5    0
         dtype: int64
         """
-        with _group_selection_context(self):
+        with group_selection_context(self):
             index = self._selected_obj.index
             result = self._obj_1d_constructor(self.grouper.group_info[0], index)
             if not ascending:
@@ -2287,7 +2287,7 @@ def cumcount(self, ascending: bool = True):
         5    0
         dtype: int64
         """
-        with _group_selection_context(self):
+        with group_selection_context(self):
             index = self._selected_obj.index
             cumcounts = self._cumcount_array(ascending=ascending)
             return self._obj_1d_constructor(cumcounts, index)

pandas/core/indexes/base.py

@@ -3660,15 +3660,15 @@ def _join_multi(self, other, how, return_indexers=True):
         return result
 
     def _join_non_unique(self, other, how="left", return_indexers=False):
-        from pandas.core.reshape.merge import _get_join_indexers
+        from pandas.core.reshape.merge import get_join_indexers
 
         # We only get here if dtypes match
         assert self.dtype == other.dtype
 
         lvalues = self._get_engine_target()
         rvalues = other._get_engine_target()
 
-        left_idx, right_idx = _get_join_indexers(
+        left_idx, right_idx = get_join_indexers(
             [lvalues], [rvalues], how=how, sort=True
         )
 

pandas/core/indexes/interval.py

@@ -59,7 +59,6 @@
 if TYPE_CHECKING:
     from pandas import CategoricalIndex  # noqa:F401
 
-_VALID_CLOSED = {"left", "right", "both", "neither"}
 _index_doc_kwargs = dict(ibase._index_doc_kwargs)
 
 _index_doc_kwargs.update(

pandas/core/reshape/merge.py

@@ -859,7 +859,7 @@ def _maybe_add_join_keys(self, result, left_indexer, right_indexer):
 
     def _get_join_indexers(self):
         """ return the join indexers """
-        return _get_join_indexers(
+        return get_join_indexers(
             self.left_join_keys, self.right_join_keys, sort=self.sort, how=self.how
         )
 
@@ -1298,7 +1298,7 @@ def _validate(self, validate: str):
             raise ValueError("Not a valid argument for validate")
 
 
-def _get_join_indexers(
+def get_join_indexers(
     left_keys, right_keys, sort: bool = False, how: str = "inner", **kwargs
 ):
     """

pandas/io/formats/printing.py

@@ -243,7 +243,7 @@ def pprint_thing_encoded(
     return value.encode(encoding, errors)
 
 
-def _enable_data_resource_formatter(enable: bool) -> None:
+def enable_data_resource_formatter(enable: bool) -> None:
     if "IPython" not in sys.modules:
         # definitely not in IPython
         return