De-privatize imported names (#36156)

Author: jbrockmendel

pandas/_libs/hashtable.pyx

@@ -56,7 +56,7 @@ from pandas._libs.missing cimport checknull
 
 
 cdef int64_t NPY_NAT = util.get_nat()
-_SIZE_HINT_LIMIT = (1 << 20) + 7
+SIZE_HINT_LIMIT = (1 << 20) + 7
 
 
 cdef Py_ssize_t _INIT_VEC_CAP = 128
@@ -176,7 +176,7 @@ def unique_label_indices(const int64_t[:] labels):
         ndarray[int64_t, ndim=1] arr
         Int64VectorData *ud = idx.data
 
-    kh_resize_int64(table, min(n, _SIZE_HINT_LIMIT))
+    kh_resize_int64(table, min(n, SIZE_HINT_LIMIT))
 
     with nogil:
         for i in range(n):

pandas/_libs/hashtable_class_helper.pxi.in

@@ -268,7 +268,7 @@ cdef class {{name}}HashTable(HashTable):
     def __cinit__(self, int64_t size_hint=1):
         self.table = kh_init_{{dtype}}()
         if size_hint is not None:
-            size_hint = min(size_hint, _SIZE_HINT_LIMIT)
+            size_hint = min(size_hint, SIZE_HINT_LIMIT)
             kh_resize_{{dtype}}(self.table, size_hint)
 
     def __len__(self) -> int:
@@ -603,7 +603,7 @@ cdef class StringHashTable(HashTable):
     def __init__(self, int64_t size_hint=1):
         self.table = kh_init_str()
         if size_hint is not None:
-            size_hint = min(size_hint, _SIZE_HINT_LIMIT)
+            size_hint = min(size_hint, SIZE_HINT_LIMIT)
             kh_resize_str(self.table, size_hint)
 
     def __dealloc__(self):
@@ -916,7 +916,7 @@ cdef class PyObjectHashTable(HashTable):
     def __init__(self, int64_t size_hint=1):
         self.table = kh_init_pymap()
         if size_hint is not None:
-            size_hint = min(size_hint, _SIZE_HINT_LIMIT)
+            size_hint = min(size_hint, SIZE_HINT_LIMIT)
             kh_resize_pymap(self.table, size_hint)
 
     def __dealloc__(self):

pandas/_libs/hashtable_func_helper.pxi.in

@@ -138,7 +138,7 @@ def duplicated_{{dtype}}(const {{c_type}}[:] values, object keep='first'):
         kh_{{ttype}}_t *table = kh_init_{{ttype}}()
         ndarray[uint8_t, ndim=1, cast=True] out = np.empty(n, dtype='bool')
 
-    kh_resize_{{ttype}}(table, min(n, _SIZE_HINT_LIMIT))
+    kh_resize_{{ttype}}(table, min(n, SIZE_HINT_LIMIT))
 
     if keep not in ('last', 'first', False):
         raise ValueError('keep must be either "first", "last" or False')

pandas/_libs/parsers.pyx

@@ -67,7 +67,7 @@ from pandas._libs.khash cimport (
     khiter_t,
 )
 
-from pandas.compat import _get_lzma_file, _import_lzma
+from pandas.compat import get_lzma_file, import_lzma
 from pandas.errors import DtypeWarning, EmptyDataError, ParserError, ParserWarning
 
 from pandas.core.dtypes.common import (
@@ -82,7 +82,7 @@ from pandas.core.dtypes.common import (
 )
 from pandas.core.dtypes.concat import union_categoricals
 
-lzma = _import_lzma()
+lzma = import_lzma()
 
 cdef:
     float64_t INF = <float64_t>np.inf
@@ -638,9 +638,9 @@ cdef class TextReader:
                                      f'zip file {zip_names}')
             elif self.compression == 'xz':
                 if isinstance(source, str):
-                    source = _get_lzma_file(lzma)(source, 'rb')
+                    source = get_lzma_file(lzma)(source, 'rb')
                 else:
-                    source = _get_lzma_file(lzma)(filename=source)
+                    source = get_lzma_file(lzma)(filename=source)
             else:
                 raise ValueError(f'Unrecognized compression type: '
                                  f'{self.compression}')

pandas/_testing.py

@@ -25,7 +25,7 @@
 from pandas._libs.lib import no_default
 import pandas._libs.testing as _testing
 from pandas._typing import Dtype, FilePathOrBuffer, FrameOrSeries
-from pandas.compat import _get_lzma_file, _import_lzma
+from pandas.compat import get_lzma_file, import_lzma
 
 from pandas.core.dtypes.common import (
     is_bool,
@@ -70,7 +70,7 @@
 from pandas.io.common import urlopen
 from pandas.io.formats.printing import pprint_thing
 
-lzma = _import_lzma()
+lzma = import_lzma()
 
 _N = 30
 _K = 4
@@ -243,7 +243,7 @@ def decompress_file(path, compression):
     elif compression == "bz2":
         f = bz2.BZ2File(path, "rb")
     elif compression == "xz":
-        f = _get_lzma_file(lzma)(path, "rb")
+        f = get_lzma_file(lzma)(path, "rb")
     elif compression == "zip":
         zip_file = zipfile.ZipFile(path)
         zip_names = zip_file.namelist()
@@ -288,7 +288,7 @@ def write_to_compressed(compression, path, data, dest="test"):
     elif compression == "bz2":
         compress_method = bz2.BZ2File
     elif compression == "xz":
-        compress_method = _get_lzma_file(lzma)
+        compress_method = get_lzma_file(lzma)
     else:
         raise ValueError(f"Unrecognized compression type: {compression}")
 

pandas/compat/__init__.py

@@ -77,7 +77,7 @@ def is_platform_mac() -> bool:
     return sys.platform == "darwin"
 
 
-def _import_lzma():
+def import_lzma():
     """
     Importing the `lzma` module.
 
@@ -97,7 +97,7 @@ def _import_lzma():
         warnings.warn(msg)
 
 
-def _get_lzma_file(lzma):
+def get_lzma_file(lzma):
     """
     Importing the `LZMAFile` class from the `lzma` module.
 

pandas/core/algorithms.py

@@ -462,7 +462,7 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
     return f(comps, values)
 
 
-def _factorize_array(
+def factorize_array(
     values, na_sentinel: int = -1, size_hint=None, na_value=None, mask=None
 ) -> Tuple[np.ndarray, np.ndarray]:
     """
@@ -671,7 +671,7 @@ def factorize(
         else:
             na_value = None
 
-        codes, uniques = _factorize_array(
+        codes, uniques = factorize_array(
             values, na_sentinel=na_sentinel, size_hint=size_hint, na_value=na_value
         )
 

pandas/core/arrays/base.py

@@ -31,7 +31,7 @@
 from pandas.core.dtypes.missing import isna
 
 from pandas.core import ops
-from pandas.core.algorithms import _factorize_array, unique
+from pandas.core.algorithms import factorize_array, unique
 from pandas.core.missing import backfill_1d, pad_1d
 from pandas.core.sorting import nargminmax, nargsort
 
@@ -845,7 +845,7 @@ def factorize(self, na_sentinel: int = -1) -> Tuple[np.ndarray, "ExtensionArray"
         #    Complete control over factorization.
         arr, na_value = self._values_for_factorize()
 
-        codes, uniques = _factorize_array(
+        codes, uniques = factorize_array(
             arr, na_sentinel=na_sentinel, na_value=na_value
         )
 

pandas/core/arrays/masked.py

@@ -17,7 +17,7 @@
 from pandas.core.dtypes.missing import isna, notna
 
 from pandas.core import nanops
-from pandas.core.algorithms import _factorize_array, take
+from pandas.core.algorithms import factorize_array, take
 from pandas.core.array_algos import masked_reductions
 from pandas.core.arrays import ExtensionArray, ExtensionOpsMixin
 from pandas.core.indexers import check_array_indexer
@@ -287,7 +287,7 @@ def factorize(self, na_sentinel: int = -1) -> Tuple[np.ndarray, ExtensionArray]:
         arr = self._data
         mask = self._mask
 
-        codes, uniques = _factorize_array(arr, na_sentinel=na_sentinel, mask=mask)
+        codes, uniques = factorize_array(arr, na_sentinel=na_sentinel, mask=mask)
 
         # the hashtables don't handle all different types of bits
         uniques = uniques.astype(self.dtype.numpy_dtype, copy=False)

pandas/core/computation/check.py

@@ -1,10 +1,10 @@
 from pandas.compat._optional import import_optional_dependency
 
 ne = import_optional_dependency("numexpr", raise_on_missing=False, on_version="warn")
-_NUMEXPR_INSTALLED = ne is not None
-if _NUMEXPR_INSTALLED:
-    _NUMEXPR_VERSION = ne.__version__
+NUMEXPR_INSTALLED = ne is not None
+if NUMEXPR_INSTALLED:
+    NUMEXPR_VERSION = ne.__version__
 else:
-    _NUMEXPR_VERSION = None
+    NUMEXPR_VERSION = None
 
-__all__ = ["_NUMEXPR_INSTALLED", "_NUMEXPR_VERSION"]
+__all__ = ["NUMEXPR_INSTALLED", "NUMEXPR_VERSION"]

pandas/core/computation/eval.py

@@ -38,10 +38,10 @@ def _check_engine(engine: Optional[str]) -> str:
     str
         Engine name.
     """
-    from pandas.core.computation.check import _NUMEXPR_INSTALLED
+    from pandas.core.computation.check import NUMEXPR_INSTALLED
 
     if engine is None:
-        engine = "numexpr" if _NUMEXPR_INSTALLED else "python"
+        engine = "numexpr" if NUMEXPR_INSTALLED else "python"
 
     if engine not in _engines:
         valid_engines = list(_engines.keys())
@@ -53,7 +53,7 @@ def _check_engine(engine: Optional[str]) -> str:
     # that won't necessarily be import-able)
     # Could potentially be done on engine instantiation
     if engine == "numexpr":
-        if not _NUMEXPR_INSTALLED:
+        if not NUMEXPR_INSTALLED:
             raise ImportError(
                 "'numexpr' is not installed or an unsupported version. Cannot use "
                 "engine='numexpr' for query/eval if 'numexpr' is not installed"

pandas/core/computation/expressions.py

@@ -15,15 +15,15 @@
 
 from pandas.core.dtypes.generic import ABCDataFrame
 
-from pandas.core.computation.check import _NUMEXPR_INSTALLED
+from pandas.core.computation.check import NUMEXPR_INSTALLED
 from pandas.core.ops import roperator
 
-if _NUMEXPR_INSTALLED:
+if NUMEXPR_INSTALLED:
     import numexpr as ne
 
 _TEST_MODE = None
 _TEST_RESULT: List[bool] = list()
-_USE_NUMEXPR = _NUMEXPR_INSTALLED
+_USE_NUMEXPR = NUMEXPR_INSTALLED
 _evaluate = None
 _where = None
 
@@ -40,7 +40,7 @@
 def set_use_numexpr(v=True):
     # set/unset to use numexpr
     global _USE_NUMEXPR
-    if _NUMEXPR_INSTALLED:
+    if NUMEXPR_INSTALLED:
         _USE_NUMEXPR = v
 
     # choose what we are going to do
@@ -53,7 +53,7 @@ def set_use_numexpr(v=True):
 def set_numexpr_threads(n=None):
     # if we are using numexpr, set the threads to n
     # otherwise reset
-    if _NUMEXPR_INSTALLED and _USE_NUMEXPR:
+    if NUMEXPR_INSTALLED and _USE_NUMEXPR:
         if n is None:
             n = ne.detect_number_of_cores()
         ne.set_num_threads(n)

pandas/core/computation/ops.py

@@ -600,11 +600,11 @@ def __repr__(self) -> str:
 
 class FuncNode:
     def __init__(self, name: str):
-        from pandas.core.computation.check import _NUMEXPR_INSTALLED, _NUMEXPR_VERSION
+        from pandas.core.computation.check import NUMEXPR_INSTALLED, NUMEXPR_VERSION
 
         if name not in _mathops or (
-            _NUMEXPR_INSTALLED
-            and _NUMEXPR_VERSION < LooseVersion("2.6.9")
+            NUMEXPR_INSTALLED
+            and NUMEXPR_VERSION < LooseVersion("2.6.9")
             and name in ("floor", "ceil")
         ):
             raise ValueError(f'"{name}" is not a supported function')

pandas/core/frame.py

@@ -5257,7 +5257,7 @@ def duplicated(
         4     True
         dtype: bool
         """
-        from pandas._libs.hashtable import _SIZE_HINT_LIMIT, duplicated_int64
+        from pandas._libs.hashtable import SIZE_HINT_LIMIT, duplicated_int64
 
         from pandas.core.sorting import get_group_index
 
@@ -5266,7 +5266,7 @@ def duplicated(
 
         def f(vals):
             labels, shape = algorithms.factorize(
-                vals, size_hint=min(len(self), _SIZE_HINT_LIMIT)
+                vals, size_hint=min(len(self), SIZE_HINT_LIMIT)
             )
             return labels.astype("i8", copy=False), len(shape)
 

pandas/core/indexes/multi.py

@@ -1342,9 +1342,9 @@ def format(
             )
 
         if adjoin:
-            from pandas.io.formats.format import _get_adjustment
+            from pandas.io.formats.format import get_adjustment
 
-            adj = _get_adjustment()
+            adj = get_adjustment()
             return adj.adjoin(space, *result_levels).split("\n")
         else:
             return result_levels

pandas/core/internals/__init__.py

@@ -10,8 +10,8 @@
     IntBlock,
     ObjectBlock,
     TimeDeltaBlock,
-    _safe_reshape,
     make_block,
+    safe_reshape,
 )
 from pandas.core.internals.concat import concatenate_block_managers
 from pandas.core.internals.managers import (
@@ -33,7 +33,7 @@
     "IntBlock",
     "ObjectBlock",
     "TimeDeltaBlock",
-    "_safe_reshape",
+    "safe_reshape",
     "make_block",
     "BlockManager",
     "SingleBlockManager",

pandas/core/internals/blocks.py

@@ -1678,7 +1678,7 @@ def putmask(
         if isinstance(new, (np.ndarray, ExtensionArray)) and len(new) == len(mask):
             new = new[mask]
 
-        mask = _safe_reshape(mask, new_values.shape)
+        mask = safe_reshape(mask, new_values.shape)
 
         new_values[mask] = new
         return [self.make_block(values=new_values)]
@@ -2820,7 +2820,7 @@ def _block_shape(values: ArrayLike, ndim: int = 1) -> ArrayLike:
     return values
 
 
-def _safe_reshape(arr, new_shape):
+def safe_reshape(arr, new_shape):
     """
     If possible, reshape `arr` to have shape `new_shape`,
     with a couple of exceptions (see gh-13012):

pandas/core/internals/managers.py

@@ -47,10 +47,10 @@
     DatetimeTZBlock,
     ExtensionBlock,
     ObjectValuesExtensionBlock,
-    _safe_reshape,
     extend_blocks,
     get_block_type,
     make_block,
+    safe_reshape,
 )
 from pandas.core.internals.ops import blockwise_all, operate_blockwise
 
@@ -1015,7 +1015,7 @@ def value_getitem(placement):
 
         else:
             if value.ndim == self.ndim - 1:
-                value = _safe_reshape(value, (1,) + value.shape)
+                value = safe_reshape(value, (1,) + value.shape)
 
                 def value_getitem(placement):
                     return value
@@ -1138,7 +1138,7 @@ def insert(self, loc: int, item: Label, value, allow_duplicates: bool = False):
 
         if value.ndim == self.ndim - 1 and not is_extension_array_dtype(value.dtype):
             # TODO(EA2D): special case not needed with 2D EAs
-            value = _safe_reshape(value, (1,) + value.shape)
+            value = safe_reshape(value, (1,) + value.shape)
 
         block = make_block(values=value, ndim=self.ndim, placement=slice(loc, loc + 1))
 

pandas/core/sorting.py

@@ -520,7 +520,7 @@ def compress_group_index(group_index, sort: bool = True):
     space can be huge, so this function compresses it, by computing offsets
     (comp_ids) into the list of unique labels (obs_group_ids).
     """
-    size_hint = min(len(group_index), hashtable._SIZE_HINT_LIMIT)
+    size_hint = min(len(group_index), hashtable.SIZE_HINT_LIMIT)
     table = hashtable.Int64HashTable(size_hint)
 
     group_index = ensure_int64(group_index)