CLN/INT: Rename _possibly to _maybe (GH15764)

Also rename "private" functions in pandas.type.cast
closes pandas-dev#15764

Author: Dominik Stanczak <[email protected]>

Closes pandas-dev#15771 from StanczakDominik/rename-possibly and squashes the following commits:

486b932 [Dominik Stanczak] Cleanup missed linting errors
188c48b [Dominik Stanczak] CLN/INT: Rename _possibly to _maybe

Author: StanczakDominik

pandas/computation/expr.py

@@ -348,7 +348,7 @@ def _rewrite_membership_op(self, node, left, right):
         op = self.visit(op_instance)
         return op, op_instance, left, right
 
-    def _possibly_transform_eq_ne(self, node, left=None, right=None):
+    def _maybe_transform_eq_ne(self, node, left=None, right=None):
         if left is None:
             left = self.visit(node.left, side='left')
         if right is None:
@@ -357,7 +357,7 @@ def _possibly_transform_eq_ne(self, node, left=None, right=None):
                                                                 right)
         return op, op_class, left, right
 
-    def _possibly_downcast_constants(self, left, right):
+    def _maybe_downcast_constants(self, left, right):
         f32 = np.dtype(np.float32)
         if left.isscalar and not right.isscalar and right.return_type == f32:
             # right is a float32 array, left is a scalar
@@ -370,7 +370,7 @@ def _possibly_downcast_constants(self, left, right):
 
         return left, right
 
-    def _possibly_eval(self, binop, eval_in_python):
+    def _maybe_eval(self, binop, eval_in_python):
         # eval `in` and `not in` (for now) in "partial" python space
         # things that can be evaluated in "eval" space will be turned into
         # temporary variables. for example,
@@ -380,10 +380,10 @@ def _possibly_eval(self, binop, eval_in_python):
         return binop.evaluate(self.env, self.engine, self.parser,
                               self.term_type, eval_in_python)
 
-    def _possibly_evaluate_binop(self, op, op_class, lhs, rhs,
-                                 eval_in_python=('in', 'not in'),
-                                 maybe_eval_in_python=('==', '!=', '<', '>',
-                                                       '<=', '>=')):
+    def _maybe_evaluate_binop(self, op, op_class, lhs, rhs,
+                              eval_in_python=('in', 'not in'),
+                              maybe_eval_in_python=('==', '!=', '<', '>',
+                                                    '<=', '>=')):
         res = op(lhs, rhs)
 
         if res.has_invalid_return_type:
@@ -397,24 +397,24 @@ def _possibly_evaluate_binop(self, op, op_class, lhs, rhs,
                     getattr(rhs, 'is_datetime', False)):
                 # all date ops must be done in python bc numexpr doesn't work
                 # well with NaT
-                return self._possibly_eval(res, self.binary_ops)
+                return self._maybe_eval(res, self.binary_ops)
 
         if res.op in eval_in_python:
             # "in"/"not in" ops are always evaluated in python
-            return self._possibly_eval(res, eval_in_python)
+            return self._maybe_eval(res, eval_in_python)
         elif self.engine != 'pytables':
             if (getattr(lhs, 'return_type', None) == object or
                     getattr(rhs, 'return_type', None) == object):
                 # evaluate "==" and "!=" in python if either of our operands
                 # has an object return type
-                return self._possibly_eval(res, eval_in_python +
-                                           maybe_eval_in_python)
+                return self._maybe_eval(res, eval_in_python +
+                                        maybe_eval_in_python)
         return res
 
     def visit_BinOp(self, node, **kwargs):
-        op, op_class, left, right = self._possibly_transform_eq_ne(node)
-        left, right = self._possibly_downcast_constants(left, right)
-        return self._possibly_evaluate_binop(op, op_class, left, right)
+        op, op_class, left, right = self._maybe_transform_eq_ne(node)
+        left, right = self._maybe_downcast_constants(left, right)
+        return self._maybe_evaluate_binop(op, op_class, left, right)
 
     def visit_Div(self, node, **kwargs):
         truediv = self.env.scope['truediv']
@@ -662,9 +662,9 @@ def visitor(x, y):
             lhs = self._try_visit_binop(x)
             rhs = self._try_visit_binop(y)
 
-            op, op_class, lhs, rhs = self._possibly_transform_eq_ne(node, lhs,
-                                                                    rhs)
-            return self._possibly_evaluate_binop(op, node.op, lhs, rhs)
+            op, op_class, lhs, rhs = self._maybe_transform_eq_ne(
+                node, lhs, rhs)
+            return self._maybe_evaluate_binop(op, node.op, lhs, rhs)
 
         operands = node.values
         return reduce(visitor, operands)

pandas/core/algorithms.py

@@ -7,7 +7,7 @@
 import numpy as np
 
 from pandas import compat, _np_version_under1p8
-from pandas.types.cast import _maybe_promote
+from pandas.types.cast import maybe_promote
 from pandas.types.generic import ABCSeries, ABCIndex
 from pandas.types.common import (is_unsigned_integer_dtype,
                                  is_signed_integer_dtype,
@@ -1297,7 +1297,7 @@ def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan, mask_info=None,
         else:
             # check for promotion based on types only (do this first because
             # it's faster than computing a mask)
-            dtype, fill_value = _maybe_promote(arr.dtype, fill_value)
+            dtype, fill_value = maybe_promote(arr.dtype, fill_value)
             if dtype != arr.dtype and (out is None or out.dtype != dtype):
                 # check if promotion is actually required based on indexer
                 if mask_info is not None:
@@ -1380,7 +1380,7 @@ def take_2d_multi(arr, indexer, out=None, fill_value=np.nan, mask_info=None,
         else:
             # check for promotion based on types only (do this first because
             # it's faster than computing a mask)
-            dtype, fill_value = _maybe_promote(arr.dtype, fill_value)
+            dtype, fill_value = maybe_promote(arr.dtype, fill_value)
             if dtype != arr.dtype and (out is None or out.dtype != dtype):
                 # check if promotion is actually required based on indexer
                 if mask_info is not None:

pandas/core/categorical.py

@@ -10,8 +10,8 @@
 
 from pandas.types.generic import ABCSeries, ABCIndexClass, ABCCategoricalIndex
 from pandas.types.missing import isnull, notnull
-from pandas.types.cast import (_possibly_infer_to_datetimelike,
-                               _coerce_indexer_dtype)
+from pandas.types.cast import (maybe_infer_to_datetimelike,
+                               coerce_indexer_dtype)
 from pandas.types.dtypes import CategoricalDtype
 from pandas.types.common import (_ensure_int64,
                                  _ensure_object,
@@ -237,7 +237,7 @@ def __init__(self, values, categories=None, ordered=False, fastpath=False):
 
         if fastpath:
             # fast path
-            self._codes = _coerce_indexer_dtype(values, categories)
+            self._codes = coerce_indexer_dtype(values, categories)
             self._categories = self._validate_categories(
                 categories, fastpath=isinstance(categories, ABCIndexClass))
             self._ordered = ordered
@@ -266,8 +266,7 @@ def __init__(self, values, categories=None, ordered=False, fastpath=False):
             # correctly no need here this is an issue because _sanitize_array
             # also coerces np.nan to a string under certain versions of numpy
             # as well
-            values = _possibly_infer_to_datetimelike(values,
-                                                     convert_dates=True)
+            values = maybe_infer_to_datetimelike(values, convert_dates=True)
             if not isinstance(values, np.ndarray):
                 values = _convert_to_list_like(values)
                 from pandas.core.series import _sanitize_array
@@ -324,7 +323,7 @@ def __init__(self, values, categories=None, ordered=False, fastpath=False):
 
         self.set_ordered(ordered or False, inplace=True)
         self._categories = categories
-        self._codes = _coerce_indexer_dtype(codes, categories)
+        self._codes = coerce_indexer_dtype(codes, categories)
 
     @property
     def _constructor(self):
@@ -877,7 +876,7 @@ def add_categories(self, new_categories, inplace=False):
         new_categories = list(self._categories) + list(new_categories)
         cat = self if inplace else self.copy()
         cat._categories = self._validate_categories(new_categories)
-        cat._codes = _coerce_indexer_dtype(cat._codes, new_categories)
+        cat._codes = coerce_indexer_dtype(cat._codes, new_categories)
         if not inplace:
             return cat
 
@@ -961,7 +960,7 @@ def remove_unused_categories(self, inplace=False):
             idx, inv = idx[1:], inv - 1
 
         cat._categories = cat.categories.take(idx)
-        cat._codes = _coerce_indexer_dtype(inv, self._categories)
+        cat._codes = coerce_indexer_dtype(inv, self._categories)
 
         if not inplace:
             return cat
@@ -1065,8 +1064,8 @@ def __setstate__(self, state):
             state['_categories'] = self._validate_categories(state.pop(
                 '_levels'))
         if '_codes' not in state and 'labels' in state:
-            state['_codes'] = _coerce_indexer_dtype(state.pop('labels'),
-                                                    state['_categories'])
+            state['_codes'] = coerce_indexer_dtype(
+                state.pop('labels'), state['_categories'])
 
         # 0.16.0 ordered change
         if '_ordered' not in state:
@@ -2062,7 +2061,7 @@ def _get_codes_for_values(values, categories):
     (_, _), cats = _get_data_algo(categories, _hashtables)
     t = hash_klass(len(cats))
     t.map_locations(cats)
-    return _coerce_indexer_dtype(t.lookup(vals), cats)
+    return coerce_indexer_dtype(t.lookup(vals), cats)
 
 
 def _convert_to_list_like(list_like):

pandas/core/frame.py

@@ -23,15 +23,15 @@
 import numpy as np
 import numpy.ma as ma
 
-from pandas.types.cast import (_maybe_upcast, _infer_dtype_from_scalar,
-                               _possibly_cast_to_datetime,
-                               _possibly_infer_to_datetimelike,
-                               _possibly_convert_platform,
-                               _possibly_downcast_to_dtype,
-                               _invalidate_string_dtypes,
-                               _coerce_to_dtypes,
-                               _maybe_upcast_putmask,
-                               _find_common_type)
+from pandas.types.cast import (maybe_upcast, infer_dtype_from_scalar,
+                               maybe_cast_to_datetime,
+                               maybe_infer_to_datetimelike,
+                               maybe_convert_platform,
+                               maybe_downcast_to_dtype,
+                               invalidate_string_dtypes,
+                               coerce_to_dtypes,
+                               maybe_upcast_putmask,
+                               find_common_type)
 from pandas.types.common import (is_categorical_dtype,
                                  is_object_dtype,
                                  is_extension_type,
@@ -275,7 +275,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
             else:
                 mask = ma.getmaskarray(data)
                 if mask.any():
-                    data, fill_value = _maybe_upcast(data, copy=True)
+                    data, fill_value = maybe_upcast(data, copy=True)
                     data[mask] = fill_value
                 else:
                     data = data.copy()
@@ -335,7 +335,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
                 if isinstance(data, compat.string_types) and dtype is None:
                     dtype = np.object_
                 if dtype is None:
-                    dtype, data = _infer_dtype_from_scalar(data)
+                    dtype, data = infer_dtype_from_scalar(data)
 
                 values = np.empty((len(index), len(columns)), dtype=dtype)
                 values.fill(data)
@@ -469,7 +469,7 @@ def _get_axes(N, K, index=index, columns=columns):
         # on the entire block; this is to convert if we have datetimelike's
         # embedded in an object type
         if dtype is None and is_object_dtype(values):
-            values = _possibly_infer_to_datetimelike(values)
+            values = maybe_infer_to_datetimelike(values)
 
         return create_block_manager_from_blocks([values], [columns, index])
 
@@ -2359,7 +2359,7 @@ def select_dtypes(self, include=None, exclude=None):
         include, exclude = map(
             lambda x: frozenset(map(_get_dtype_from_object, x)), selection)
         for dtypes in (include, exclude):
-            _invalidate_string_dtypes(dtypes)
+            invalidate_string_dtypes(dtypes)
 
         # can't both include AND exclude!
         if not include.isdisjoint(exclude):
@@ -2659,7 +2659,7 @@ def reindexer(value):
             value = _sanitize_index(value, self.index, copy=False)
             if not isinstance(value, (np.ndarray, Index)):
                 if isinstance(value, list) and len(value) > 0:
-                    value = _possibly_convert_platform(value)
+                    value = maybe_convert_platform(value)
                 else:
                     value = com._asarray_tuplesafe(value)
             elif value.ndim == 2:
@@ -2671,13 +2671,13 @@ def reindexer(value):
 
             # possibly infer to datetimelike
             if is_object_dtype(value.dtype):
-                value = _possibly_infer_to_datetimelike(value)
+                value = maybe_infer_to_datetimelike(value)
 
         else:
             # upcast the scalar
-            dtype, value = _infer_dtype_from_scalar(value)
+            dtype, value = infer_dtype_from_scalar(value)
             value = np.repeat(value, len(self.index)).astype(dtype)
-            value = _possibly_cast_to_datetime(value, dtype)
+            value = maybe_cast_to_datetime(value, dtype)
 
         # return internal types directly
         if is_extension_type(value):
@@ -3000,8 +3000,8 @@ def _maybe_casted_values(index, labels=None):
                 else:
                     values = values.take(labels)
                     if mask.any():
-                        values, changed = _maybe_upcast_putmask(values, mask,
-                                                                np.nan)
+                        values, changed = maybe_upcast_putmask(
+                            values, mask, np.nan)
             return values
 
         new_index = _default_index(len(new_obj))
@@ -3722,7 +3722,7 @@ def combine(self, other, func, fill_value=None, overwrite=True):
             # if we have different dtypes, possibily promote
             new_dtype = this_dtype
             if not is_dtype_equal(this_dtype, other_dtype):
-                new_dtype = _find_common_type([this_dtype, other_dtype])
+                new_dtype = find_common_type([this_dtype, other_dtype])
                 if not is_dtype_equal(this_dtype, new_dtype):
                     series = series.astype(new_dtype)
                 if not is_dtype_equal(other_dtype, new_dtype):
@@ -3743,13 +3743,13 @@ def combine(self, other, func, fill_value=None, overwrite=True):
             # try to downcast back to the original dtype
             if needs_i8_conversion_i:
                 # ToDo: This conversion should be handled in
-                # _possibly_cast_to_datetime but the change affects lot...
+                # _maybe_cast_to_datetime but the change affects lot...
                 if is_datetime64tz_dtype(new_dtype):
                     arr = DatetimeIndex._simple_new(arr, tz=new_dtype.tz)
                 else:
-                    arr = _possibly_cast_to_datetime(arr, new_dtype)
+                    arr = maybe_cast_to_datetime(arr, new_dtype)
             else:
-                arr = _possibly_downcast_to_dtype(arr, this_dtype)
+                arr = maybe_downcast_to_dtype(arr, this_dtype)
 
             result[col] = arr
 
@@ -5003,7 +5003,7 @@ def f(x):
 
                 # try to coerce to the original dtypes item by item if we can
                 if axis == 0:
-                    result = _coerce_to_dtypes(result, self.dtypes)
+                    result = coerce_to_dtypes(result, self.dtypes)
 
         return Series(result, index=labels)
 
@@ -5505,7 +5505,7 @@ def _prep_ndarray(values, copy=True):
             return np.empty((0, 0), dtype=object)
 
         def convert(v):
-            return _possibly_convert_platform(v)
+            return maybe_convert_platform(v)
 
         # we could have a 1-dim or 2-dim list here
         # this is equiv of np.asarray, but does object conversion
@@ -5601,7 +5601,7 @@ def _masked_rec_array_to_mgr(data, index, columns, dtype, copy):
     for fv, arr, col in zip(fill_value, arrays, arr_columns):
         mask = ma.getmaskarray(data[col])
         if mask.any():
-            arr, fv = _maybe_upcast(arr, fill_value=fv, copy=True)
+            arr, fv = maybe_upcast(arr, fill_value=fv, copy=True)
             arr[mask] = fv
         new_arrays.append(arr)
 
@@ -5699,7 +5699,7 @@ def _convert_object_array(content, columns, coerce_float=False, dtype=None):
     def convert(arr):
         if dtype != object and dtype != np.object:
             arr = lib.maybe_convert_objects(arr, try_float=coerce_float)
-            arr = _possibly_cast_to_datetime(arr, dtype)
+            arr = maybe_cast_to_datetime(arr, dtype)
         return arr
 
     arrays = [convert(arr) for arr in content]

pandas/core/generic.py

@@ -23,7 +23,7 @@
                                  is_list_like,
                                  is_dict_like,
                                  is_re_compilable)
-from pandas.types.cast import _maybe_promote, _maybe_upcast_putmask
+from pandas.types.cast import maybe_promote, maybe_upcast_putmask
 from pandas.types.missing import isnull, notnull
 from pandas.types.generic import ABCSeries, ABCPanel
 
@@ -4956,10 +4956,10 @@ def _where(self, cond, other=np.nan, inplace=False, axis=None, level=None,
                         # or not try_quick
                         if not try_quick:
 
-                            dtype, fill_value = _maybe_promote(other.dtype)
+                            dtype, fill_value = maybe_promote(other.dtype)
                             new_other = np.empty(len(icond), dtype=dtype)
                             new_other.fill(fill_value)
-                            _maybe_upcast_putmask(new_other, icond, other)
+                            maybe_upcast_putmask(new_other, icond, other)
                             other = new_other
 
                     else:

pandas/core/groupby.py

@@ -32,7 +32,7 @@
                                  _ensure_object,
                                  _ensure_categorical,
                                  _ensure_float)
-from pandas.types.cast import _possibly_downcast_to_dtype
+from pandas.types.cast import maybe_downcast_to_dtype
 from pandas.types.missing import isnull, notnull, _maybe_fill
 
 from pandas.core.common import (_values_from_object, AbstractMethodError,
@@ -783,7 +783,7 @@ def _try_cast(self, result, obj, numeric_only=False):
 
         if not is_scalar(result):
             if numeric_only and is_numeric_dtype(dtype) or not numeric_only:
-                result = _possibly_downcast_to_dtype(result, dtype)
+                result = maybe_downcast_to_dtype(result, dtype)
 
         return result
 
@@ -2914,7 +2914,7 @@ def transform(self, func, *args, **kwargs):
         # the cython take a different path (and casting)
         dtype = self._selected_obj.dtype
         if is_numeric_dtype(dtype):
-            result = _possibly_downcast_to_dtype(result, dtype)
+            result = maybe_downcast_to_dtype(result, dtype)
 
         result.name = self._selected_obj.name
         result.index = self._selected_obj.index