From db0e1700c888fd96eed43b8ffcafd4efa456a2b1 Mon Sep 17 00:00:00 2001
From: Vincent Roseberry <rosbo@google.com>
Date: Fri, 27 Nov 2020 22:14:14 +0000
Subject: [PATCH 1/2] Install bayesian-optimization from pip archive & add
 tests

---
 Dockerfile              |  2 +-
 tests/test_bayes_opt.py | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_bayes_opt.py

diff --git a/Dockerfile b/Dockerfile
index 2e8c5d3b..a930bd6c 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -196,7 +196,7 @@ RUN pip install mpld3 && \
     pip install missingno && \
     pip install pandas-profiling && \
     pip install s2sphere && \
-    pip install git+https://github.com/fmfn/BayesianOptimization.git && \
+    pip install bayesian-optimization && \
     pip install matplotlib-venn && \
     pip install pyldavis && \
     pip install mlxtend && \
diff --git a/tests/test_bayes_opt.py b/tests/test_bayes_opt.py
new file mode 100644
index 00000000..99af8aea
--- /dev/null
+++ b/tests/test_bayes_opt.py
@@ -0,0 +1,32 @@
+import unittest
+
+from bayes_opt import BayesianOptimization
+
+
+class TestBayesOpt(unittest.TestCase):
+    def test_optimize(self):
+        # Bounded region of parameter space
+        pbounds = {'x': (2, 4), 'y': (-3, 3)}
+
+        optimizer = BayesianOptimization(
+            f=black_box_function,
+            pbounds=pbounds,
+            random_state=1,
+        )
+
+        optimizer.maximize(
+            init_points=2,
+            n_iter=1,
+        )       
+
+        self.assertAlmostEqual(-7, optimizer.max['target'], places=0) # compares using 0 decimal
+    
+
+def black_box_function(x, y):
+    """Function with unknown internals we wish to maximize.
+
+    This is just serving as an example, for all intents and
+    purposes think of the internals of this function, i.e.: the process
+    which generates its output values, as unknown.
+    """
+    return -x ** 2 - (y - 1) ** 2 + 1
\ No newline at end of file

From 4c68822ea4d931db052337621fa588522e4dd696 Mon Sep 17 00:00:00 2001
From: Vincent Roseberry <rosbo@google.com>
Date: Fri, 27 Nov 2020 22:18:39 +0000
Subject: [PATCH 2/2] install openslide & category-encoders from pip archive

---
 Dockerfile                      | 6 ++----
 tests/test_category_encoders.py | 8 ++++----
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index a930bd6c..a92ca383 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -283,8 +283,7 @@ RUN pip install --upgrade cython && \
     pip install fasttext && \
     apt-get install -y libhunspell-dev && pip install hunspell && \
     pip install annoy && \
-    # Need to use CountEncoder from category_encoders before it's officially released
-    pip install git+https://github.com/scikit-learn-contrib/categorical-encoding.git && \
+    pip install category_encoders && \
     # google-cloud-automl 2.0.0 introduced incompatible API changes, need to pin to 1.0.1
     pip install google-cloud-automl==1.0.1 && \
     # Newer version crashes (latest = 1.14.0) when running tensorflow.
@@ -347,8 +346,7 @@ RUN pip install bcolz && \
     pip install --upgrade Pillow && \
     # Install openslide and its python binding
     apt-get install -y openslide-tools && \
-    # b/152402322 install latest from pip once is in: https://github.com/openslide/openslide-python/pull/76
-    pip install git+git://github.com/rosbo/openslide-python.git@fix-setup && \
+    pip install openslide-python && \
     pip install ptyprocess && \
     pip install Pygments && \
     pip install pyparsing && \
diff --git a/tests/test_category_encoders.py b/tests/test_category_encoders.py
index 54d6024e..4aced160 100644
--- a/tests/test_category_encoders.py
+++ b/tests/test_category_encoders.py
@@ -1,12 +1,12 @@
 import unittest
 
+from category_encoders import CountEncoder
+import pandas as pd
+
+
 ## Need to make sure we have CountEncoder available from the category_encoders library
 class TestCategoryEncoders(unittest.TestCase):
     def test_count_encoder(self):
-
-        from category_encoders import CountEncoder
-        import pandas as pd
-
         encoder = CountEncoder(cols="data")
 
         data = pd.DataFrame([1, 2, 3, 1, 4, 5, 3, 1], columns=["data"])