Review (jreback & jschendel)

pandas-dev · jreback · Oct 18, 2018 · Oct 9, 2018 · Oct 9, 2018 · Oct 9, 2018
commit 15e3265524fa8a45331844d1dff9a2b6e989943b
diff --git a/doc/source/whatsnew/v0.24.0.txt b/doc/source/whatsnew/v0.24.0.txt
@@ -629,7 +629,6 @@ Other API Changes
 - :class:`Index` subtraction will attempt to operate element-wise instead of raising ``TypeError`` (:issue:`19369`)
 - :class:`pandas.io.formats.style.Styler` supports a ``number-format`` property when using :meth:`~pandas.io.formats.style.Styler.to_excel` (:issue:`22015`)
 - :meth:`DataFrame.corr` and :meth:`Series.corr` now raise a ``ValueError`` along with a helpful error message instead of a ``KeyError`` when supplied with an invalid method (:issue:`22298`)
-- :meth:`dtypes.common.is_list_like` has gained a ``strict``-kwarg, which is ``False`` by default. If set to ``True``, sets are not considered list-like. (:issue:`22397`)
 - :meth:`shift` will now always return a copy, instead of the previous behaviour of returning self when shifting by 0 (:issue:`22397`)
 
 .. _whatsnew_0240.deprecations:

diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
@@ -396,11 +396,11 @@ def isin(comps, values):
     boolean array same length as comps
     """
 
-    if not is_list_like(comps, strict=False):
+    if not is_list_like(comps):
         raise TypeError("only list-like objects are allowed to be passed"
                         " to isin(), you passed a [{comps_type}]"
                         .format(comps_type=type(comps).__name__))
-    if not is_list_like(values, strict=False):
+    if not is_list_like(values):
         raise TypeError("only list-like objects are allowed to be passed"
                         " to isin(), you passed a [{values_type}]"
                         .format(values_type=type(values).__name__))
@@ -1178,7 +1178,7 @@ class SelectNFrame(SelectN):
 
     def __init__(self, obj, n, keep, columns):
         super(SelectNFrame, self).__init__(obj, n, keep)
-        if not is_list_like(columns, strict=False):
+        if not is_list_like(columns):
             columns = [columns]
         columns = list(columns)
         self.columns = columns

diff --git a/pandas/core/apply.py b/pandas/core/apply.py
@@ -110,7 +110,7 @@ def get_result(self):
         """ compute the results """
 
         # dispatch to agg
-        if is_list_like(self.f, strict=False) or is_dict_like(self.f):
+        if is_list_like(self.f) or is_dict_like(self.f):
             return self.obj.aggregate(self.f, axis=self.axis,
                                       *self.args, **self.kwds)
 

diff --git a/pandas/core/arrays/base.py b/pandas/core/arrays/base.py
@@ -769,8 +769,7 @@ def _create_method(cls, op, coerce_to_dtype=True):
 
         def _binop(self, other):
             def convert_values(param):
-                if (isinstance(param, ExtensionArray)
-                        or is_list_like(param, strict=False)):
+                if isinstance(param, ExtensionArray) or is_list_like(param):
                     ovalues = param
                 else:  # Assume its an object
                     ovalues = [param] * len(self)

diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -1017,7 +1017,7 @@ def add_categories(self, new_categories, inplace=False):
         set_categories
         """
         inplace = validate_bool_kwarg(inplace, 'inplace')
-        if not is_list_like(new_categories, strict=False):
+        if not is_list_like(new_categories):
             new_categories = [new_categories]
         already_included = set(new_categories) & set(self.dtype.categories)
         if len(already_included) != 0:
@@ -1065,7 +1065,7 @@ def remove_categories(self, removals, inplace=False):
         set_categories
         """
         inplace = validate_bool_kwarg(inplace, 'inplace')
-        if not is_list_like(removals, strict=False):
+        if not is_list_like(removals):
             removals = [removals]
 
         removal_set = set(list(removals))
@@ -1981,7 +1981,7 @@ def __setitem__(self, key, value):
                 raise ValueError("Cannot set a Categorical with another, "
                                  "without identical categories")
 
-        rvalue = value if is_list_like(value, strict=False) else [value]
+        rvalue = value if is_list_like(value) else [value]
 
         from pandas import Index
         to_add = Index(rvalue).difference(self.categories)
@@ -2350,7 +2350,7 @@ def isin(self, values):
         array([ True, False,  True, False,  True, False])
         """
         from pandas.core.series import _sanitize_array
-        if not is_list_like(values, strict=False):
+        if not is_list_like(values):
             raise TypeError("only list-like objects are allowed to be passed"
                             " to isin(), you passed a [{values_type}]"
                             .format(values_type=type(values).__name__))
@@ -2523,7 +2523,7 @@ def _factorize_from_iterable(values):
     """
     from pandas.core.indexes.category import CategoricalIndex
 
-    if not is_list_like(values, strict=False):
+    if not is_list_like(values):
         raise TypeError("Input must be list-like")
 
     if is_categorical(values):

diff --git a/pandas/core/arrays/datetimelike.py b/pandas/core/arrays/datetimelike.py
@@ -751,7 +751,7 @@ def _evaluate_compare(self, other, op):
 
         if not isinstance(other, type(self)):
             # coerce to a similar object
-            if not is_list_like(other, strict=False):
+            if not is_list_like(other):
                 # scalar
                 other = [other]
             elif lib.is_scalar(lib.item_from_zerodim(other)):

diff --git a/pandas/core/arrays/integer.py b/pandas/core/arrays/integer.py
@@ -505,7 +505,7 @@ def cmp_method(self, other):
             mask = None
             if isinstance(other, IntegerArray):
                 other, mask = other._data, other._mask
-            elif is_list_like(other, strict=False):
+            elif is_list_like(other):
                 other = np.asarray(other)
                 if other.ndim > 0 and len(self) != len(other):
                     raise ValueError('Lengths must match to compare')
@@ -568,7 +568,7 @@ def integer_arithmetic_method(self, other):
             elif getattr(other, 'ndim', 0) > 1:
                 raise NotImplementedError(
                     "can only perform ops with 1-d structures")
-            elif is_list_like(other, strict=False):
+            elif is_list_like(other):
                 other = np.asarray(other)
                 if not other.ndim:
                     other = other.item()

diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py
@@ -76,7 +76,7 @@ def wrapper(self, other):
             if isna(other):
                 result.fill(nat_result)
 
-        elif not is_list_like(other, strict=False):
+        elif not is_list_like(other):
             raise TypeError(msg.format(cls=type(self).__name__,
                                        typ=type(other).__name__))
         else:

diff --git a/pandas/core/base.py b/pandas/core/base.py
@@ -543,8 +543,7 @@ def is_any_frame():
                                 name=getattr(self, 'name', None))
 
             return result, True
-        elif (is_list_like(arg, strict=False)
-              and arg not in compat.string_types):
+        elif is_list_like(arg) and arg not in compat.string_types:
             # we require a list, but not an 'str'
             return self._aggregate_multiple_funcs(arg,
                                                   _level=_level,

diff --git a/pandas/core/computation/ops.py b/pandas/core/computation/ops.py
@@ -234,7 +234,7 @@ def _in(x, y):
     try:
         return x.isin(y)
     except AttributeError:
-        if is_list_like(x, strict=False):
+        if is_list_like(x):
             try:
                 return y.isin(x)
             except AttributeError:
@@ -249,7 +249,7 @@ def _not_in(x, y):
     try:
         return ~x.isin(y)
     except AttributeError:
-        if is_list_like(x, strict=False):
+        if is_list_like(x):
             try:
                 return ~y.isin(x)
             except AttributeError:

diff --git a/pandas/core/computation/pytables.py b/pandas/core/computation/pytables.py
@@ -127,7 +127,7 @@ def pr(left, right):
 
     def conform(self, rhs):
         """ inplace conform rhs """
-        if not is_list_like(rhs, strict=False):
+        if not is_list_like(rhs):
             rhs = [rhs]
         if isinstance(rhs, np.ndarray):
             rhs = rhs.ravel()
@@ -472,8 +472,7 @@ def _validate_where(w):
     TypeError : An invalid data type was passed in for w (e.g. dict).
     """
 
-    if not (isinstance(w, (Expr, string_types))
-            or is_list_like(w, strict=False)):
+    if not (isinstance(w, (Expr, string_types)) or is_list_like(w)):
         raise TypeError("where must be passed as a string, Expr, "
                         "or list-like of Exprs")
 

diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
@@ -472,7 +472,7 @@ def infer_dtype_from_array(arr, pandas_dtype=False):
     if isinstance(arr, np.ndarray):
         return arr.dtype, arr
 
-    if not is_list_like(arr, strict=False):
+    if not is_list_like(arr):
         arr = [arr]
 
     if pandas_dtype and is_extension_type(arr):
@@ -518,7 +518,7 @@ def maybe_infer_dtype_type(element):
     tipo = None
     if hasattr(element, 'dtype'):
         tipo = element.dtype
-    elif is_list_like(element, strict=False):
+    elif is_list_like(element):
         element = np.asarray(element)
         tipo = element.dtype
     return tipo
@@ -914,7 +914,7 @@ def maybe_infer_to_datetimelike(value, convert_dates=False):
 
     v = value
 
-    if not is_list_like(v, strict=False):
+    if not is_list_like(v):
         v = [v]
     v = np.array(v, copy=False)
 

diff --git a/pandas/core/dtypes/common.py b/pandas/core/dtypes/common.py
@@ -327,8 +327,8 @@ def is_offsetlike(arr_or_obj):
     """
     if isinstance(arr_or_obj, ABCDateOffset):
         return True
-    elif (is_list_like(arr_or_obj, strict=False) and len(arr_or_obj)
-          and is_object_dtype(arr_or_obj)):
+    elif (is_list_like(arr_or_obj) and len(arr_or_obj) and
+          is_object_dtype(arr_or_obj)):
         return all(isinstance(x, ABCDateOffset) for x in arr_or_obj)
     return False
 

diff --git a/pandas/core/dtypes/inference.py b/pandas/core/dtypes/inference.py
@@ -4,10 +4,10 @@
 import numpy as np
 from numbers import Number
 from pandas import compat
-from pandas.compat import (PY2, string_types, text_type,
+from pandas.compat import (PY2, PY36, string_types, text_type,
                            string_and_binary_types, re_type)
 from pandas._libs import lib
-import warnings
+from collections import abc, OrderedDict
 
 is_bool = lib.is_bool
 
@@ -248,7 +248,7 @@ def is_re_compilable(obj):
         return True
 
 
-def is_list_like(obj, strict=None):
+def is_list_like(obj):
     """
     Check if the object is list-like.
 
@@ -260,8 +260,6 @@ def is_list_like(obj, strict=None):
     Parameters
     ----------
     obj : The object to check.
-    strict : boolean, default None
-        Whether `set` should be counted as list-like
 
     Returns
     -------
@@ -285,21 +283,38 @@ def is_list_like(obj, strict=None):
     >>> is_list_like(np.array(2)))
     False
     """
-    if strict is None and isinstance(obj, set):
-        # only raise warning if necessary
-        warnings.warn('is_list_like will in the future return False for sets. '
-                      'To keep the previous behavior, pass `strict=False`. To '
-                      'adopt the future behavior and silence this warning, '
-                      'pass `strict=True`', FutureWarning)
-    strict = False if strict is None else strict
-
-    list_like = (isinstance(obj, compat.Iterable)
-                 # we do not count strings/unicode/bytes as set-like
-                 and not isinstance(obj, string_and_binary_types)
-                 # exclude zero-dimensional numpy arrays, effectively scalars
-      
57AE
           and not (isinstance(obj, np.ndarray) and obj.ndim == 0))
-    return list_like and (not strict or not isinstance(obj, set))
 
+    return (isinstance(obj, compat.Iterable) and
+            # we do not count strings/unicode/bytes as list-like
+            not isinstance(obj, string_and_binary_types) and
+            # exclude zero-dimensional numpy arrays, effectively scalars
+            not (isinstance(obj, np.ndarray) and obj.ndim == 0))
+
+
+def is_ordered_list_like(obj):
+    """
+    Check if the object is list-like and has a defined order
+
+    Works like :meth:`is_list_like` but excludes sets (as well as unordered
+    `dict` before Python 3.6)
+
+    Note that iterators can not be inspected for order - this check will return
+    True but it is up to the user to make sure that their iterators are
+    generated in an ordered way.
+
+    Parameters
+    ----------
+    obj : The object to check.
+
+    Returns
+    -------
+    is_ordered_list_like : bool
+        Whether `obj` is an ordered list-like
+    """
+    list_like = is_list_like(obj)
+    unordered_dict = not PY36 and (isinstance(obj, dict)
+                                   and not isinstance(obj, OrderedDict))
+    return list_like and not unordered_dict and not isinstance(obj, abc.Set)
 
 def is_array_like(obj):
     """
@@ -331,7 +346,7 @@ def is_array_like(obj):
     False
     """
 
-    return is_list_like(obj, strict=False) and hasattr(obj, "dtype")
+    return is_list_like(obj) and hasattr(obj, "dtype")
 
 
 def is_nested_list_like(obj):
@@ -374,9 +389,8 @@ def is_nested_list_like(obj):
     --------
     is_list_like
     """
-    return (is_list_like(obj, strict=False) and hasattr(obj, '__len__')
-            and len(obj) > 0 and all(is_list_like(item, strict=False)
-                                     for item in obj))
+    return (is_list_like(obj) and hasattr(obj, '__len__') and
+            len(obj) > 0 and all(is_list_like(item) for item in obj))
 
 
 def is_dict_like(obj):

diff --git a/pandas/core/dtypes/missing.py b/pandas/core/dtypes/missing.py
@@ -464,7 +464,7 @@ def _infer_fill_value(val):
     element to provide proper block construction
     """
 
-    if not is_list_like(val, strict=False):
+    if not is_list_like(val):
         val = [val]
     val = np.array(val, copy=False)
     if is_datetimelike(val):

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -421,8 +421,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
             if not isinstance(data, compat.Sequence):
                 data = list(data)
             if len(data) > 0:
-                if (is_list_like(data[0], strict=False)
-                        and getattr(data[0], 'ndim', 1) == 1):
+                if is_list_like(data[0]) and getattr(data[0], 'ndim', 1) == 1:
                     if is_named_tuple(data[0]) and columns is None:
                         columns = data[0]._fields
                     arrays, columns = _to_arrays(data, columns, dtype=dtype)
@@ -2791,8 +2790,7 @@ def __getitem__(self, key):
 
         # We are left with two options: a single key, and a collection of keys,
         # We interpret tuples as collections only for non-MultiIndex
-        is_single_key = (isinstance(key, tuple)
-                         or not is_list_like(key, strict=False))
+        is_single_key = isinstance(key, tuple) or not is_list_like(key)
 
         if is_single_key:
             if self.columns.nlevels > 1:
@@ -3154,9 +3152,9 @@ def select_dtypes(self, include=None, exclude=None):
         5  False  2.0
         """
 
-        if not is_list_like(include, strict=False):
+        if not is_list_like(include):
             include = (include,) if include is not None else ()
-        if not is_list_like(exclude, strict=False):
+        if not is_list_like(exclude):
             exclude = (exclude,) if exclude is not None else ()
 
         selection = tuple(map(frozenset, (include, exclude)))
@@ -3281,7 +3279,7 @@ def _ensure_valid_index(self, value):
         passed value
         """
         # GH5632, make sure that we are a Series convertible
-        if not len(self.index) and is_list_like(value, strict=False):
+        if not len(self.index) and is_list_like(value):
             try:
                 value = Series(value)
             except (ValueError, NotImplementedError, TypeError):
@@ -7663,7 +7661,7 @@ def isin(self, values):
                                  "a duplicate axis.")
             return self.eq(values.reindex_like(self))
         else:
-            if not is_list_like(values, strict=False):
+            if not is_list_like(values):
                 raise TypeError("only list-like or dict-like objects are "
                                 "allowed to be passed to DataFrame.isin(), "
                                 "you passed a "
@@ -7733,7 +7731,7 @@ def extract_index(data):
             elif isinstance(v, dict):
                 have_dicts = True
                 indexes.append(list(v.keys()))
-            elif is_list_like(v, strict=False) and getattr(v, 'ndim', 1) == 1:
+            elif is_list_like(v) and getattr(v, 'ndim', 1) == 1:
                 have_raw_arrays = True
                 raw_lengths.append(len(v))
 
@@ -7776,8 +7774,7 @@ def convert(v):
         # this is equiv of np.asarray, but does object conversion
         # and platform dtype preservation
         try:
-            if (is_list_like(values[0], strict=False)
-                    or hasattr(values[0], 'len')):
+            if is_list_like(values[0]) or hasattr(values[0], 'len'):
                 values = np.array([convert(v) for v in values])
             elif isinstance(values[0], np.ndarray) and values[0].ndim == 0:
                 # GH#21861