From 28451006c489ac72cfb1deb43b1c05024d8cf746 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 10 Sep 2020 18:44:18 -0700
Subject: [PATCH 1/2] PERF: CategoricalDtype.__eq__

---
 pandas/core/dtypes/dtypes.py | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
index e321fdd9b3a9b..9bbed0ec2f236 100644
--- a/pandas/core/dtypes/dtypes.py
+++ b/pandas/core/dtypes/dtypes.py
@@ -375,12 +375,28 @@ def __eq__(self, other: Any) -> bool:
             # but same order is not necessary.  There is no distinction between
             # ordered=False and ordered=None: CDT(., False) and CDT(., None)
             # will be equal if they have the same categories.
-            if (
-                self.categories.dtype == other.categories.dtype
-                and self.categories.equals(other.categories)
-            ):
+            left = self.categories
+            right = other.categories
+            if not left.dtype == right.dtype:
+                return False
+
+            if len(left) != len(right):
+                return False
+
+            if self.categories.equals(other.categories):
                 # Check and see if they happen to be identical categories
                 return True
+
+            if left.dtype != object:
+                # Faster than calculating hash
+                indexer = left.get_indexer(right)
+                # Because left and right have the same length and are unique,
+                #  `indexer` not having any -1s implies that there is a
+                #  bijection between `left` and `right`.
+                return (indexer != -1).all()
+
+            # With object-dtype we need a comparison that identifies
+            #  e.g. int(2) as distinct from float(2)
             return hash(self) == hash(other)
 
     def __repr__(self) -> str_type:

From 0091f5fcd7cfeee43219f3fa282883f627991fcd Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Sat, 12 Sep 2020 14:41:58 -0700
Subject: [PATCH 2/2] comment

---
 pandas/core/dtypes/dtypes.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
index 9bbed0ec2f236..2e5dc15131e70 100644
--- a/pandas/core/dtypes/dtypes.py
+++ b/pandas/core/dtypes/dtypes.py
@@ -377,6 +377,8 @@ def __eq__(self, other: Any) -> bool:
             # will be equal if they have the same categories.
             left = self.categories
             right = other.categories
+
+            # GH#36280 the ordering of checks here is for performance
             if not left.dtype == right.dtype:
                 return False