CLN: Assorted typings

pandas/core/algorithms.py

@@ -176,15 +176,14 @@ def _reconstruct_data(values, dtype, original):
     -------
     Index for extension types, otherwise ndarray casted to dtype
     """
-    from pandas import Index
 
     if is_extension_array_dtype(dtype):
         values = dtype.construct_array_type()._from_sequence(values)
     elif is_bool_dtype(dtype):
         values = values.astype(dtype)
 
         # we only support object dtypes bool Index
-        if isinstance(original, Index):
+        if isinstance(original, ABCIndexClass):
             values = values.astype(object)
     elif dtype is not None:
         values = values.astype(dtype)
@@ -833,7 +832,7 @@ def duplicated(values, keep="first"):
     return f(values, keep=keep)
 
 
-def mode(values, dropna=True):
+def mode(values, dropna: bool = True):
     """
     Returns the mode(s) of an array.
 
@@ -1888,7 +1887,7 @@ def searchsorted(arr, value, side="left", sorter=None):
 }
 
 
-def diff(arr, n, axis=0):
+def diff(arr, n: int, axis: int = 0):
     """
     difference of n between self,
     analogous to s-s.shift(n)
@@ -1904,7 +1903,6 @@ def diff(arr, n, axis=0):
     Returns
     -------
     shifted
-
     """
 
     n = int(n)

pandas/core/util/hashing.py

@@ -26,7 +26,7 @@
 _default_hash_key = "0123456789123456"
 
 
-def _combine_hash_arrays(arrays, num_items):
+def _combine_hash_arrays(arrays, num_items: int):
     """
     Parameters
     ----------
@@ -55,7 +55,11 @@ def _combine_hash_arrays(arrays, num_items):
 
 
 def hash_pandas_object(
-    obj, index=True, encoding="utf8", hash_key=None, categorize=True
+    obj,
+    index: bool = True,
+    encoding: str = "utf8",
+    hash_key=None,
+    categorize: bool = True,
 ):
     """
     Return a data hash of the Index/Series/DataFrame.
@@ -179,7 +183,7 @@ def hash_tuples(vals, encoding="utf8", hash_key=None):
     return h
 
 
-def hash_tuple(val, encoding="utf8", hash_key=None):
+def hash_tuple(val, encoding: str = "utf8", hash_key=None):
     """
     Hash a single tuple efficiently
 
@@ -201,7 +205,7 @@ def hash_tuple(val, encoding="utf8", hash_key=None):
     return h
 
 
-def _hash_categorical(c, encoding, hash_key):
+def _hash_categorical(c, encoding: str, hash_key: str):
     """
     Hash a Categorical by hashing its categories, and then mapping the codes
     to the hashes
@@ -239,7 +243,7 @@ def _hash_categorical(c, encoding, hash_key):
     return result
 
 
-def hash_array(vals, encoding="utf8", hash_key=None, categorize=True):
+def hash_array(vals, encoding: str = "utf8", hash_key=None, categorize: bool = True):
     """
     Given a 1d array, return an array of deterministic integers.
 
@@ -317,7 +321,7 @@ def hash_array(vals, encoding="utf8", hash_key=None, categorize=True):
     return vals
 
 
-def _hash_scalar(val, encoding="utf8", hash_key=None):
+def _hash_scalar(val, encoding: str = "utf8", hash_key=None):
     """
     Hash scalar value
 

pandas/tests/groupby/test_categorical.py

@@ -782,7 +782,7 @@ def test_categorical_no_compress():
 
 def test_sort():
 
-    # http://stackoverflow.com/questions/23814368/sorting-pandas-categorical-labels-after-groupby  # noqa: flake8
+    # http://stackoverflow.com/questions/23814368/sorting-pandas-categorical-labels-after-groupby  # noqa: E501
     # This should result in a properly sorted Series so that the plot
     # has a sorted x axis
     # self.cat.groupby(['value_group'])['value_group'].count().plot(kind='bar')