CLN: deprivatize factorize_from_iterable

pandas/core/arrays/categorical.py

@@ -2678,7 +2678,7 @@ def _convert_to_list_like(list_like):
         return [list_like]
 
 
-def _factorize_from_iterable(values):
+def factorize_from_iterable(values):
     """
     Factorize an input `values` into `categories` and `codes`. Preserves
     categorical dtype in `categories`.
@@ -2716,9 +2716,9 @@ def _factorize_from_iterable(values):
     return codes, categories
 
 
-def _factorize_from_iterables(iterables):
+def factorize_from_iterables(iterables):
     """
-    A higher-level wrapper over `_factorize_from_iterable`.
+    A higher-level wrapper over `factorize_from_iterable`.
 
     *This is an internal function*
 
@@ -2733,9 +2733,9 @@ def _factorize_from_iterables(iterables):
 
     Notes
     -----
-    See `_factorize_from_iterable` for more info.
+    See `factorize_from_iterable` for more info.
     """
     if len(iterables) == 0:
         # For consistency, it should return a list of 2 lists.
         return [[], []]
-    return map(list, zip(*(_factorize_from_iterable(it) for it in iterables)))
+    return map(list, zip(*(factorize_from_iterable(it) for it in iterables)))

pandas/core/indexes/multi.py

@@ -31,7 +31,7 @@
 
 import pandas.core.algorithms as algos
 from pandas.core.arrays import Categorical
-from pandas.core.arrays.categorical import _factorize_from_iterables
+from pandas.core.arrays.categorical import factorize_from_iterables
 import pandas.core.common as com
 import pandas.core.indexes.base as ibase
 from pandas.core.indexes.base import (
@@ -440,7 +440,7 @@ def from_arrays(cls, arrays, sortorder=None, names=_no_default_names):
             if len(arrays[i]) != len(arrays[i - 1]):
                 raise ValueError("all arrays must be same length")
 
-        codes, levels = _factorize_from_iterables(arrays)
+        codes, levels = factorize_from_iterables(arrays)
         if names is _no_default_names:
             names = [getattr(arr, "name", None) for arr in arrays]
 
@@ -562,7 +562,7 @@ def from_product(cls, iterables, sortorder=None, names=_no_default_names):
         elif is_iterator(iterables):
             iterables = list(iterables)
 
-        codes, levels = _factorize_from_iterables(iterables)
+        codes, levels = factorize_from_iterables(iterables)
         if names is _no_default_names:
             names = [getattr(it, "name", None) for it in iterables]
 

pandas/core/reshape/concat.py

@@ -8,8 +8,8 @@
 
 from pandas import DataFrame, Index, MultiIndex, Series
 from pandas.core.arrays.categorical import (
-    _factorize_from_iterable,
-    _factorize_from_iterables,
+    factorize_from_iterable,
+    factorize_from_iterables,
 )
 import pandas.core.common as com
 from pandas.core.generic import NDFrame
@@ -604,7 +604,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None):
             names = [None] * len(zipped)
 
         if levels is None:
-            _, levels = _factorize_from_iterables(zipped)
+            _, levels = factorize_from_iterables(zipped)
         else:
             levels = [ensure_index(x) for x in levels]
     else:
@@ -645,7 +645,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None):
             levels.extend(concat_index.levels)
             codes_list.extend(concat_index.codes)
         else:
-            codes, categories = _factorize_from_iterable(concat_index)
+            codes, categories = factorize_from_iterable(concat_index)
             levels.append(categories)
             codes_list.append(codes)
 

pandas/core/reshape/reshape.py

@@ -22,7 +22,7 @@
 
 import pandas.core.algorithms as algos
 from pandas.core.arrays import SparseArray
-from pandas.core.arrays.categorical import _factorize_from_iterable
+from pandas.core.arrays.categorical import factorize_from_iterable
 from pandas.core.construction import extract_array
 from pandas.core.frame import DataFrame
 from pandas.core.index import Index, MultiIndex
@@ -504,7 +504,7 @@ def stack(frame, level=-1, dropna=True):
     def factorize(index):
         if index.is_unique:
             return index, np.arange(len(index))
-        codes, categories = _factorize_from_iterable(index)
+        codes, categories = factorize_from_iterable(index)
         return categories, codes
 
     N, K = frame.shape
@@ -725,7 +725,7 @@ def _convert_level_number(level_num, columns):
         new_names = list(this.index.names)
         new_codes = [lab.repeat(levsize) for lab in this.index.codes]
     else:
-        old_codes, old_levels = _factorize_from_iterable(this.index)
+        old_codes, old_levels = factorize_from_iterable(this.index)
         new_levels = [old_levels]
         new_codes = [old_codes.repeat(levsize)]
         new_names = [this.index.name]  # something better?
@@ -949,7 +949,7 @@ def _get_dummies_1d(
     from pandas.core.reshape.concat import concat
 
     # Series avoids inconsistent NaN handling
-    codes, levels = _factorize_from_iterable(Series(data))
+    codes, levels = factorize_from_iterable(Series(data))
 
     if dtype is None:
         dtype = np.uint8