Fix kmeans max_iterations hyperparameter (aws#199)

Author: ChoiByungWook

CHANGELOG.rst

@@ -2,13 +2,18 @@
 CHANGELOG
 =========
 
+1.3.dev1
+========
+
+* bug-fix: Estimators: Change max_iterations hyperparameter key for KMeans
+
 1.3.0
-=======
+=====
 
 * feature: Add chainer
 
 1.2.5
-========
+=====
 
 * bug-fix: Change module names to string type in __all__
 * feature: Save training output files in local mode

src/sagemaker/amazon/kmeans.py

@@ -28,7 +28,7 @@ class KMeans(AmazonAlgorithmEstimatorBase):
 
     k = hp('k', gt(1), 'An integer greater-than 1', int)
     init_method = hp('init_method', isin('random', 'kmeans++'), 'One of "random", "kmeans++"', str)
-    max_iterations = hp('local_lloyd_max_iterations', gt(0), 'An integer greater-than 0', int)
+    max_iterations = hp('local_lloyd_max_iter', gt(0), 'An integer greater-than 0', int)
     tol = hp('local_lloyd_tol', (ge(0), le(1)), 'An float in [0, 1]', float)
     num_trials = hp('local_lloyd_num_trials', gt(0), 'An integer greater-than 0', int)
     local_init_method = hp('local_lloyd_init_method', isin('random', 'kmeans++'), 'One of "random", "kmeans++"', str)

tests/integ/test_kmeans.py

@@ -41,14 +41,27 @@ def test_kmeans(sagemaker_session):
                         k=10, sagemaker_session=sagemaker_session, base_job_name='test-kmeans')
 
         kmeans.init_method = 'random'
-        kmeans.max_iterators = 1
+        kmeans.max_iterations = 1
         kmeans.tol = 1
         kmeans.num_trials = 1
         kmeans.local_init_method = 'kmeans++'
         kmeans.half_life_time_size = 1
         kmeans.epochs = 1
         kmeans.center_factor = 1
 
+        assert kmeans.hyperparameters() == dict(
+            init_method=kmeans.init_method,
+            local_lloyd_max_iter=str(kmeans.max_iterations),
+            local_lloyd_tol=str(kmeans.tol),
+            local_lloyd_num_trials=str(kmeans.num_trials),
+            local_lloyd_init_method=kmeans.local_init_method,
+            half_life_time_size=str(kmeans.half_life_time_size),
+            epochs=str(kmeans.epochs),
+            extra_center_factor=str(kmeans.center_factor),
+            k=str(kmeans.k),
+            force_dense='True',
+        )
+
         kmeans.fit(kmeans.record_set(train_set[0][:100]))
 
     endpoint_name = name_from_base('kmeans')
@@ -80,14 +93,27 @@ def test_async_kmeans(sagemaker_session):
                         k=10, sagemaker_session=sagemaker_session, base_job_name='test-kmeans')
 
         kmeans.init_method = 'random'
-        kmeans.max_iterators = 1
+        kmeans.max_iterations = 1
         kmeans.tol = 1
         kmeans.num_trials = 1
         kmeans.local_init_method = 'kmeans++'
         kmeans.half_life_time_size = 1
         kmeans.epochs = 1
         kmeans.center_factor = 1
 
+        assert kmeans.hyperparameters() == dict(
+            init_method=kmeans.init_method,
+            local_lloyd_max_iter=str(kmeans.max_iterations),
+            local_lloyd_tol=str(kmeans.tol),
+            local_lloyd_num_trials=str(kmeans.num_trials),
+            local_lloyd_init_method=kmeans.local_init_method,
+            half_life_time_size=str(kmeans.half_life_time_size),
+            epochs=str(kmeans.epochs),
+            extra_center_factor=str(kmeans.center_factor),
+            k=str(kmeans.k),
+            force_dense='True',
+        )
+
         kmeans.fit(kmeans.record_set(train_set[0][:100]), wait=False)
         training_job_name = kmeans.latest_training_job.name
 

tests/unit/test_kmeans.py

@@ -74,15 +74,15 @@ def test_all_hyperparameters(sagemaker_session):
     assert kmeans.hyperparameters() == dict(
         k=str(ALL_REQ_ARGS['k']),
         init_method='random',
-        local_lloyd_max_iterations='3',
+        local_lloyd_max_iter='3',
         local_lloyd_tol='0.5',
         local_lloyd_num_trials='5',
         local_lloyd_init_method='kmeans++',
         half_life_time_size='0',
         epochs='10',
         extra_center_factor='2',
         eval_metrics='[\'msd\', \'ssd\']',
-        force_dense='True'
+        force_dense='True',
     )