From c84b7e9e3986cc0dd0c3050a60e5722cf066a386 Mon Sep 17 00:00:00 2001
From: jbrockmendel <jbrockmendel@gmail.com>
Date: Mon, 13 Apr 2020 13:42:42 -0700
Subject: [PATCH] CLN: remove tuple kludge in CategoricalDtype.__hash__

---
 pandas/core/dtypes/dtypes.py | 40 +++++++++++++++---------------------
 pandas/core/util/hashing.py  |  2 --
 2 files changed, 16 insertions(+), 26 deletions(-)

diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
index 8fe2b3c60d6d0..0224895774c8e 100644
--- a/pandas/core/dtypes/dtypes.py
+++ b/pandas/core/dtypes/dtypes.py
@@ -482,31 +482,23 @@ def _hash_categories(categories, ordered: Ordered = True) -> int:
         from pandas.core.util.hashing import (
             hash_array,
             _combine_hash_arrays,
-            hash_tuples,
         )
-        from pandas.core.dtypes.common import is_datetime64tz_dtype, DT64NS_DTYPE
-
-        if len(categories) and isinstance(categories[0], tuple):
-            # assumes if any individual category is a tuple, then all our. ATM
-            # I don't really want to support just some of the categories being
-            # tuples.
-            categories = list(categories)  # breaks if a np.array of categories
-            cat_array = hash_tuples(categories)
-        else:
-            if categories.dtype == "O":
-                if len({type(x) for x in categories}) != 1:
-                    # TODO: hash_array doesn't handle mixed types. It casts
-                    # everything to a str first, which means we treat
-                    # {'1', '2'} the same as {'1', 2}
-                    # find a better solution
-                    hashed = hash((tuple(categories), ordered))
-                    return hashed
-
-            if is_datetime64tz_dtype(categories.dtype):
-                # Avoid future warning.
-                categories = categories.astype(DT64NS_DTYPE)
-
-            cat_array = hash_array(np.asarray(categories), categorize=False)
+
+        if categories.dtype == "O":
+            if len({type(x) for x in categories}) != 1:
+                # TODO: hash_array doesn't handle mixed types. It casts
+                # everything to a str first, which means we treat
+                # {'1', '2'} the same as {'1', 2}
+                # find a better solution
+                hashed = hash((tuple(categories), ordered))
+                return hashed
+
+        if isinstance(categories.dtype, DatetimeTZDtype):
+            # Avoid future warning.
+            categories = categories.astype("datetime64[ns]")
+
+        cat_array = hash_array(np.asarray(categories), categorize=False)
+
         if ordered:
             cat_array = np.vstack(
                 [cat_array, np.arange(len(cat_array), dtype=cat_array.dtype)]
diff --git a/pandas/core/util/hashing.py b/pandas/core/util/hashing.py
index d9c8611c94cdb..e9d2bc2aa22b0 100644
--- a/pandas/core/util/hashing.py
+++ b/pandas/core/util/hashing.py
@@ -289,8 +289,6 @@ def hash_array(
 
     # First, turn whatever array this is into unsigned 64-bit ints, if we can
     # manage it.
-    elif isinstance(dtype, np.bool):
-        vals = vals.astype("u8")
     elif issubclass(dtype.type, (np.datetime64, np.timedelta64)):
         vals = vals.view("i8").astype("u8", copy=False)
     elif issubclass(dtype.type, np.number) and dtype.itemsize <= 8: