From bd409b6d509f684f88039779cf970e32e5fe29b4 Mon Sep 17 00:00:00 2001
From: Ignacio Quintero <rignacio@amazon.com>
Date: Mon, 22 Jan 2018 16:58:40 -0800
Subject: [PATCH 1/4] Add data_type to hyperparameters

When we describe a training job the data type of the hyper parameters is
lost because we use a dict[str, str]. This adds a new optional field to
Hyperparameter so that we can convert the datatypes at runtime.
---
 .../amazon/factorization_machines.py          | 48 +++++++-------
 src/sagemaker/amazon/hyperparameter.py        |  3 +-
 src/sagemaker/amazon/kmeans.py                | 18 ++---
 src/sagemaker/amazon/linear_learner.py        | 65 ++++++++++---------
 src/sagemaker/amazon/pca.py                   |  8 +--
 tests/unit/test_hyperparameter.py             | 19 +++++-
 6 files changed, 90 insertions(+), 71 deletions(-)

diff --git a/src/sagemaker/amazon/factorization_machines.py b/src/sagemaker/amazon/factorization_machines.py
index 5340fa11f0..6c1aa0e8ac 100644
--- a/src/sagemaker/amazon/factorization_machines.py
+++ b/src/sagemaker/amazon/factorization_machines.py
@@ -23,34 +23,34 @@ class FactorizationMachines(AmazonAlgorithmEstimatorBase):
 
     repo = 'factorization-machines:1'
 
-    num_factors = hp('num_factors', (gt(0), isint), 'An integer greater than zero')
+    num_factors = hp('num_factors', (gt(0), isint), 'An integer greater than zero', int)
     predictor_type = hp('predictor_type', isin('binary_classifier', 'regressor'),
-                        'Value "binary_classifier" or "regressor"')
-    epochs = hp('epochs', (gt(0), isint), "An integer greater than 0")
-    clip_gradient = hp('clip_gradient', isnumber, "A float value")
-    eps = hp('eps', isnumber, "A float value")
-    rescale_grad = hp('rescale_grad', isnumber, "A float value")
-    bias_lr = hp('bias_lr', (ge(0), isnumber), "A non-negative float")
-    linear_lr = hp('linear_lr', (ge(0), isnumber), "A non-negative float")
-    factors_lr = hp('factors_lr', (ge(0), isnumber), "A non-negative float")
-    bias_wd = hp('bias_wd', (ge(0), isnumber), "A non-negative float")
-    linear_wd = hp('linear_wd', (ge(0), isnumber), "A non-negative float")
-    factors_wd = hp('factors_wd', (ge(0), isnumber), "A non-negative float")
+                        'Value "binary_classifier" or "regressor"', str)
+    epochs = hp('epochs', (gt(0), isint), "An integer greater than 0", int)
+    clip_gradient = hp('clip_gradient', isnumber, "A float value", float)
+    eps = hp('eps', isnumber, "A float value", float)
+    rescale_grad = hp('rescale_grad', isnumber, "A float value", float)
+    bias_lr = hp('bias_lr', (ge(0), isnumber), "A non-negative float", float)
+    linear_lr = hp('linear_lr', (ge(0), isnumber), "A non-negative float", float)
+    factors_lr = hp('factors_lr', (ge(0), isnumber), "A non-negative float", float)
+    bias_wd = hp('bias_wd', (ge(0), isnumber), "A non-negative float", float)
+    linear_wd = hp('linear_wd', (ge(0), isnumber), "A non-negative float", float)
+    factors_wd = hp('factors_wd', (ge(0), isnumber), "A non-negative float", float)
     bias_init_method = hp('bias_init_method', isin('normal', 'uniform', 'constant'),
-                          'Value "normal", "uniform" or "constant"')
-    bias_init_scale = hp('bias_init_scale', (ge(0), isnumber), "A non-negative float")
-    bias_init_sigma = hp('bias_init_sigma', (ge(0), isnumber), "A non-negative float")
-    bias_init_value = hp('bias_init_value', isnumber, "A float value")
+                          'Value "normal", "uniform" or "constant"', str)
+    bias_init_scale = hp('bias_init_scale', (ge(0), isnumber), "A non-negative float", float)
+    bias_init_sigma = hp('bias_init_sigma', (ge(0), isnumber), "A non-negative float", float)
+    bias_init_value = hp('bias_init_value', isnumber, "A float value", float)
     linear_init_method = hp('linear_init_method', isin('normal', 'uniform', 'constant'),
-                            'Value "normal", "uniform" or "constant"')
-    linear_init_scale = hp('linear_init_scale', (ge(0), isnumber), "A non-negative float")
-    linear_init_sigma = hp('linear_init_sigma', (ge(0), isnumber), "A non-negative float")
-    linear_init_value = hp('linear_init_value', isnumber, "A float value")
+                            'Value "normal", "uniform" or "constant"', str)
+    linear_init_scale = hp('linear_init_scale', (ge(0), isnumber), "A non-negative float", float)
+    linear_init_sigma = hp('linear_init_sigma', (ge(0), isnumber), "A non-negative float", float)
+    linear_init_value = hp('linear_init_value', isnumber, "A float value", float)
     factors_init_method = hp('factors_init_method', isin('normal', 'uniform', 'constant'),
-                             'Value "normal", "uniform" or "constant"')
-    factors_init_scale = hp('factors_init_scale', (ge(0), isnumber), "A non-negative float")
-    factors_init_sigma = hp('factors_init_sigma', (ge(0), isnumber), "A non-negative float")
-    factors_init_value = hp('factors_init_value', isnumber, "A float value")
+                             'Value "normal", "uniform" or "constant"', str)
+    factors_init_scale = hp('factors_init_scale', (ge(0), isnumber), "A non-negative float", float)
+    factors_init_sigma = hp('factors_init_sigma', (ge(0), isnumber), "A non-negative float", float)
+    factors_init_value = hp('factors_init_value', isnumber, "A float value", float)
 
     def __init__(self, role, train_instance_count, train_instance_type,
                  num_factors, predictor_type,
diff --git a/src/sagemaker/amazon/hyperparameter.py b/src/sagemaker/amazon/hyperparameter.py
index 0d86191474..e34b1bcff7 100644
--- a/src/sagemaker/amazon/hyperparameter.py
+++ b/src/sagemaker/amazon/hyperparameter.py
@@ -16,7 +16,7 @@ class Hyperparameter(object):
     """An algorithm hyperparameter with optional validation. Implemented as a python
     descriptor object."""
 
-    def __init__(self, name, validate=lambda _: True, validation_message=""):
+    def __init__(self, name, validate=lambda _: True, validation_message="", data_type=str):
         """Args:
             name (str): The name of this hyperparameter
             validate (callable[object]->[bool]): A validation function or list of validation functions.
@@ -27,6 +27,7 @@ def __init__(self, name, validate=lambda _: True, validation_message=""):
         self.validation = validate
         self.validation_message = validation_message
         self.name = name
+        self.data_type = data_type
         try:
             iter(self.validation)
         except TypeError:
diff --git a/src/sagemaker/amazon/kmeans.py b/src/sagemaker/amazon/kmeans.py
index d3fb5d670e..bc1fb4456b 100644
--- a/src/sagemaker/amazon/kmeans.py
+++ b/src/sagemaker/amazon/kmeans.py
@@ -23,15 +23,15 @@ class KMeans(AmazonAlgorithmEstimatorBase):
 
     repo = 'kmeans:1'
 
-    k = hp('k', (gt(1), isint), 'An integer greater-than 1')
-    init_method = hp('init_method', isin('random', 'kmeans++'), 'One of "random", "kmeans++"')
-    max_iterations = hp('local_lloyd_max_iterations', (gt(0), isint), 'An integer greater-than 0')
-    tol = hp('local_lloyd_tol', (gt(0), isint), 'An integer greater-than 0')
-    num_trials = hp('local_lloyd_num_trials', (gt(0), isint), 'An integer greater-than 0')
-    local_init_method = hp('local_lloyd_init_method', isin('random', 'kmeans++'), 'One of "random", "kmeans++"')
-    half_life_time_size = hp('half_life_time_size', (ge(0), isint), 'An integer greater-than-or-equal-to 0')
-    epochs = hp('epochs', (gt(0), isint), 'An integer greater-than 0')
-    center_factor = hp('extra_center_factor', (gt(0), isint), 'An integer greater-than 0')
+    k = hp('k', (gt(1), isint), '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), isint), 'An integer greater-than 0', int)
+    tol = hp('local_lloyd_tol', (gt(0), isint), 'An integer greater-than 0', int)
+    num_trials = hp('local_lloyd_num_trials', (gt(0), isint), 'An integer greater-than 0', int)
+    local_init_method = hp('local_lloyd_init_method', isin('random', 'kmeans++'), 'One of "random", "kmeans++"', str)
+    half_life_time_size = hp('half_life_time_size', (ge(0), isint), 'An integer greater-than-or-equal-to 0', int)
+    epochs = hp('epochs', (gt(0), isint), 'An integer greater-than 0', int)
+    center_factor = hp('extra_center_factor', (gt(0), isint), 'An integer greater-than 0', int)
 
     def __init__(self, role, train_instance_count, train_instance_type, k, init_method=None,
                  max_iterations=None, tol=None, num_trials=None, local_init_method=None,
diff --git a/src/sagemaker/amazon/linear_learner.py b/src/sagemaker/amazon/linear_learner.py
index af336a8e6b..b78394cdad 100644
--- a/src/sagemaker/amazon/linear_learner.py
+++ b/src/sagemaker/amazon/linear_learner.py
@@ -27,40 +27,41 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
 
     binary_classifier_model_selection_criteria = hp('binary_classifier_model_selection_criteria',
                                                     isin('accuracy', 'f1', 'precision_at_target_recall',
-                                                         'recall_at_target_precision', 'cross_entropy_loss'))
-    target_recall = hp('target_recall', (gt(0), lt(1)), "A float in (0,1)")
-    target_precision = hp('target_precision', (gt(0), lt(1)), "A float in (0,1)")
-    positive_example_weight_mult = hp('positive_example_weight_mult', gt(0), "A float greater than 0")
-    epochs = hp('epochs', (gt(0), isint), "An integer greater-than 0")
+                                                         'recall_at_target_precision', 'cross_entropy_loss'),
+                                                    data_type=str)
+    target_recall = hp('target_recall', (gt(0), lt(1)), "A float in (0,1)", float)
+    target_precision = hp('target_precision', (gt(0), lt(1)), "A float in (0,1)", float)
+    positive_example_weight_mult = hp('positive_example_weight_mult', gt(0), "A float greater than 0", float)
+    epochs = hp('epochs', (gt(0), isint), "An integer greater-than 0", int)
     predictor_type = hp('predictor_type', isin('binary_classifier', 'regressor'),
-                        'One of "binary_classifier" or "regressor"')
-    use_bias = hp('use_bias', isbool, "Either True or False")
-    num_models = hp('num_models', (gt(0), isint), "An integer greater-than 0")
-    num_calibration_samples = hp('num_calibration_samples', (gt(0), isint), "An integer greater-than 0")
-    init_method = hp('init_method', isin('uniform', 'normal'), 'One of "uniform" or "normal"')
-    init_scale = hp('init_scale', (gt(-1), lt(1)), 'A float in (-1, 1)')
-    init_sigma = hp('init_sigma', (gt(0), lt(1)), 'A float in (0, 1)')
-    init_bias = hp('init_bias', isnumber, 'A number')
-    optimizer = hp('optimizer', isin('sgd', 'adam', 'auto'), 'One of "sgd", "adam" or "auto')
+                        'One of "binary_classifier" or "regressor"', str)
+    use_bias = hp('use_bias', isbool, "Either True or False", bool)
+    num_models = hp('num_models', (gt(0), isint), "An integer greater-than 0", int)
+    num_calibration_samples = hp('num_calibration_samples', (gt(0), isint), "An integer greater-than 0", int)
+    init_method = hp('init_method', isin('uniform', 'normal'), 'One of "uniform" or "normal"', str)
+    init_scale = hp('init_scale', (gt(-1), lt(1)), 'A float in (-1, 1)', float)
+    init_sigma = hp('init_sigma', (gt(0), lt(1)), 'A float in (0, 1)', float)
+    init_bias = hp('init_bias', isnumber, 'A number', float)
+    optimizer = hp('optimizer', isin('sgd', 'adam', 'auto'), 'One of "sgd", "adam" or "auto', str)
     loss = hp('loss', isin('logistic', 'squared_loss', 'absolute_loss', 'auto'),
-              '"logistic", "squared_loss", "absolute_loss" or"auto"')
-    wd = hp('wd', (gt(0), lt(1)), 'A float in (0,1)')
-    l1 = hp('l1', (gt(0), lt(1)), 'A float in (0,1)')
-    momentum = hp('momentum', (gt(0), lt(1)), 'A float in (0,1)')
-    learning_rate = hp('learning_rate', (gt(0), lt(1)), 'A float in (0,1)')
-    beta_1 = hp('beta_1', (gt(0), lt(1)), 'A float in (0,1)')
-    beta_2 = hp('beta_1', (gt(0), lt(1)), 'A float in (0,1)')
-    bias_lr_mult = hp('bias_lr_mult', gt(0), 'A float greater-than 0')
-    bias_wd_mult = hp('bias_wd_mult', gt(0), 'A float greater-than 0')
-    use_lr_scheduler = hp('use_lr_scheduler', isbool, 'A boolean')
-    lr_scheduler_step = hp('lr_scheduler_step', (gt(0), isint), 'An integer greater-than 0')
-    lr_scheduler_factor = hp('lr_scheduler_factor', (gt(0), lt(1)), 'A float in (0,1)')
-    lr_scheduler_minimum_lr = hp('lr_scheduler_minimum_lr', gt(0), 'A float greater-than 0')
-    normalize_data = hp('normalize_data', isbool, 'A boolean')
-    normalize_label = hp('normalize_label', isbool, 'A boolean')
-    unbias_data = hp('unbias_data', isbool, 'A boolean')
-    unbias_label = hp('unbias_label', isbool, 'A boolean')
-    num_point_for_scalar = hp('num_point_for_scalar', (isint, gt(0)), 'An integer greater-than 0')
+              '"logistic", "squared_loss", "absolute_loss" or"auto"', str)
+    wd = hp('wd', (gt(0), lt(1)), 'A float in (0,1)', float)
+    l1 = hp('l1', (gt(0), lt(1)), 'A float in (0,1)', float)
+    momentum = hp('momentum', (gt(0), lt(1)), 'A float in (0,1)', float)
+    learning_rate = hp('learning_rate', (gt(0), lt(1)), 'A float in (0,1)', float)
+    beta_1 = hp('beta_1', (gt(0), lt(1)), 'A float in (0,1)', float)
+    beta_2 = hp('beta_1', (gt(0), lt(1)), 'A float in (0,1)', float)
+    bias_lr_mult = hp('bias_lr_mult', gt(0), 'A float greater-than 0', float)
+    bias_wd_mult = hp('bias_wd_mult', gt(0), 'A float greater-than 0', float)
+    use_lr_scheduler = hp('use_lr_scheduler', isbool, 'A boolean', bool)
+    lr_scheduler_step = hp('lr_scheduler_step', (gt(0), isint), 'An integer greater-than 0', int)
+    lr_scheduler_factor = hp('lr_scheduler_factor', (gt(0), lt(1)), 'A float in (0,1)', float)
+    lr_scheduler_minimum_lr = hp('lr_scheduler_minimum_lr', gt(0), 'A float greater-than 0', float)
+    normalize_data = hp('normalize_data', isbool, 'A boolean', bool)
+    normalize_label = hp('normalize_label', isbool, 'A boolean', bool)
+    unbias_data = hp('unbias_data', isbool, 'A boolean', bool)
+    unbias_label = hp('unbias_label', isbool, 'A boolean', bool)
+    num_point_for_scalar = hp('num_point_for_scalar', (isint, gt(0)), 'An integer greater-than 0', int)
 
     def __init__(self, role, train_instance_count, train_instance_type, predictor_type='binary_classifier',
                  binary_classifier_model_selection_criteria=None, target_recall=None, target_precision=None,
diff --git a/src/sagemaker/amazon/pca.py b/src/sagemaker/amazon/pca.py
index 7a23f60c7c..19271c43e8 100644
--- a/src/sagemaker/amazon/pca.py
+++ b/src/sagemaker/amazon/pca.py
@@ -25,13 +25,13 @@ class PCA(AmazonAlgorithmEstimatorBase):
     DEFAULT_MINI_BATCH_SIZE = 500
 
     num_components = hp(name='num_components', validate=lambda x: x > 0 and isinstance(x, int),
-                        validation_message='Value must be an integer greater than zero')
+                        validation_message='Value must be an integer greater than zero', data_type=int)
     algorithm_mode = hp(name='algorithm_mode', validate=lambda x: x in ['regular', 'stable', 'randomized'],
-                        validation_message='Value must be one of "regular", "stable", "randomized"')
+                        validation_message='Value must be one of "regular", "stable", "randomized"', data_type=str)
     subtract_mean = hp(name='subtract_mean', validate=lambda x: isinstance(x, bool),
-                       validation_message='Value must be a boolean')
+                       validation_message='Value must be a boolean', data_type=bool)
     extra_components = hp(name='extra_components', validate=lambda x: x >= 0 and isinstance(x, int),
-                          validation_message="Value must be an integer greater than or equal to 0")
+                          validation_message="Value must be an integer greater than or equal to 0", data_type=int)
 
     def __init__(self, role, train_instance_count, train_instance_type, num_components,
                  algorithm_mode=None, subtract_mean=None, extra_components=None, **kwargs):
diff --git a/tests/unit/test_hyperparameter.py b/tests/unit/test_hyperparameter.py
index c168f3275e..69fc248e53 100644
--- a/tests/unit/test_hyperparameter.py
+++ b/tests/unit/test_hyperparameter.py
@@ -18,7 +18,7 @@ class Test(object):
 
     blank = Hyperparameter(name="some-name")
     elizabeth = Hyperparameter(name='elizabeth')
-    validated = Hyperparameter(name="validated", validate=lambda value: value > 55)
+    validated = Hyperparameter(name="validated", validate=lambda value: value > 55, data_type=int)
 
 
 def test_blank_access():
@@ -55,3 +55,20 @@ def test_validated():
     x.validated = 66
     with pytest.raises(ValueError):
         x.validated = 23
+
+
+def test_data_type():
+    x = Test()
+    x.validated = 66
+    assert type(x.validated) == Test.__dict__["validated"].data_type
+
+
+def test_from_string():
+    x = Test()
+    value = 65
+
+    x.validated = value
+    from_api = str(value)
+
+    x.validated = Test.__dict__["validated"].data_type(from_api)
+    assert x.validated == value

From 6834806cabe4bf2da3cf7949d81bb84303ee765b Mon Sep 17 00:00:00 2001
From: Ignacio Quintero <rignacio@amazon.com>
Date: Tue, 23 Jan 2018 14:25:17 -0800
Subject: [PATCH 2/4] Enforce a HP Type when setting its value.

instead of validating with isinstance() cast the hp value to the type it
is meant to be. This enforces a "strongly typed" value. When we
deserialize from the API string responses it becomes easier to deal with
too.
---
 src/sagemaker/amazon/amazon_estimator.py      |  4 +-
 .../amazon/factorization_machines.py          | 42 +++++++++----------
 src/sagemaker/amazon/hyperparameter.py        |  4 +-
 src/sagemaker/amazon/kmeans.py                | 16 +++----
 src/sagemaker/amazon/linear_learner.py        | 24 +++++------
 src/sagemaker/amazon/pca.py                   |  7 ++--
 6 files changed, 49 insertions(+), 48 deletions(-)

diff --git a/src/sagemaker/amazon/amazon_estimator.py b/src/sagemaker/amazon/amazon_estimator.py
index 9ed28c1894..9fbdb8b631 100644
--- a/src/sagemaker/amazon/amazon_estimator.py
+++ b/src/sagemaker/amazon/amazon_estimator.py
@@ -28,8 +28,8 @@ class AmazonAlgorithmEstimatorBase(EstimatorBase):
     """Base class for Amazon first-party Estimator implementations. This class isn't intended
     to be instantiated directly."""
 
-    feature_dim = hp('feature_dim', (validation.isint, validation.gt(0)))
-    mini_batch_size = hp('mini_batch_size', (validation.isint, validation.gt(0)))
+    feature_dim = hp('feature_dim', validation.gt(0), data_type=int)
+    mini_batch_size = hp('mini_batch_size', validation.gt(0), data_type=int)
 
     def __init__(self, role, train_instance_count, train_instance_type, data_location=None, **kwargs):
         """Initialize an AmazonAlgorithmEstimatorBase.
diff --git a/src/sagemaker/amazon/factorization_machines.py b/src/sagemaker/amazon/factorization_machines.py
index 6c1aa0e8ac..66972316ac 100644
--- a/src/sagemaker/amazon/factorization_machines.py
+++ b/src/sagemaker/amazon/factorization_machines.py
@@ -13,7 +13,7 @@
 from sagemaker.amazon.amazon_estimator import AmazonAlgorithmEstimatorBase, registry
 from sagemaker.amazon.common import numpy_to_record_serializer, record_deserializer
 from sagemaker.amazon.hyperparameter import Hyperparameter as hp  # noqa
-from sagemaker.amazon.validation import gt, isin, isint, ge, isnumber
+from sagemaker.amazon.validation import gt, isin, ge
 from sagemaker.predictor import RealTimePredictor
 from sagemaker.model import Model
 from sagemaker.session import Session
@@ -23,34 +23,34 @@ class FactorizationMachines(AmazonAlgorithmEstimatorBase):
 
     repo = 'factorization-machines:1'
 
-    num_factors = hp('num_factors', (gt(0), isint), 'An integer greater than zero', int)
+    num_factors = hp('num_factors', gt(0), 'An integer greater than zero', int)
     predictor_type = hp('predictor_type', isin('binary_classifier', 'regressor'),
                         'Value "binary_classifier" or "regressor"', str)
-    epochs = hp('epochs', (gt(0), isint), "An integer greater than 0", int)
-    clip_gradient = hp('clip_gradient', isnumber, "A float value", float)
-    eps = hp('eps', isnumber, "A float value", float)
-    rescale_grad = hp('rescale_grad', isnumber, "A float value", float)
-    bias_lr = hp('bias_lr', (ge(0), isnumber), "A non-negative float", float)
-    linear_lr = hp('linear_lr', (ge(0), isnumber), "A non-negative float", float)
-    factors_lr = hp('factors_lr', (ge(0), isnumber), "A non-negative float", float)
-    bias_wd = hp('bias_wd', (ge(0), isnumber), "A non-negative float", float)
-    linear_wd = hp('linear_wd', (ge(0), isnumber), "A non-negative float", float)
-    factors_wd = hp('factors_wd', (ge(0), isnumber), "A non-negative float", float)
+    epochs = hp('epochs', gt(0), "An integer greater than 0", int)
+    clip_gradient = hp('clip_gradient', (), "A float value", float)
+    eps = hp('eps', (), "A float value", float)
+    rescale_grad = hp('rescale_grad', (), "A float value", float)
+    bias_lr = hp('bias_lr', ge(0), "A non-negative float", float)
+    linear_lr = hp('linear_lr', ge(0), "A non-negative float", float)
+    factors_lr = hp('factors_lr', ge(0), "A non-negative float", float)
+    bias_wd = hp('bias_wd', ge(0), "A non-negative float", float)
+    linear_wd = hp('linear_wd', ge(0), "A non-negative float", float)
+    factors_wd = hp('factors_wd', ge(0), "A non-negative float", float)
     bias_init_method = hp('bias_init_method', isin('normal', 'uniform', 'constant'),
                           'Value "normal", "uniform" or "constant"', str)
-    bias_init_scale = hp('bias_init_scale', (ge(0), isnumber), "A non-negative float", float)
-    bias_init_sigma = hp('bias_init_sigma', (ge(0), isnumber), "A non-negative float", float)
-    bias_init_value = hp('bias_init_value', isnumber, "A float value", float)
+    bias_init_scale = hp('bias_init_scale', ge(0), "A non-negative float", float)
+    bias_init_sigma = hp('bias_init_sigma', ge(0), "A non-negative float", float)
+    bias_init_value = hp('bias_init_value', (), "A float value", float)
     linear_init_method = hp('linear_init_method', isin('normal', 'uniform', 'constant'),
                             'Value "normal", "uniform" or "constant"', str)
-    linear_init_scale = hp('linear_init_scale', (ge(0), isnumber), "A non-negative float", float)
-    linear_init_sigma = hp('linear_init_sigma', (ge(0), isnumber), "A non-negative float", float)
-    linear_init_value = hp('linear_init_value', isnumber, "A float value", float)
+    linear_init_scale = hp('linear_init_scale', ge(0), "A non-negative float", float)
+    linear_init_sigma = hp('linear_init_sigma', ge(0), "A non-negative float", float)
+    linear_init_value = hp('linear_init_value', (), "A float value", float)
     factors_init_method = hp('factors_init_method', isin('normal', 'uniform', 'constant'),
                              'Value "normal", "uniform" or "constant"', str)
-    factors_init_scale = hp('factors_init_scale', (ge(0), isnumber), "A non-negative float", float)
-    factors_init_sigma = hp('factors_init_sigma', (ge(0), isnumber), "A non-negative float", float)
-    factors_init_value = hp('factors_init_value', isnumber, "A float value", float)
+    factors_init_scale = hp('factors_init_scale', ge(0), "A non-negative float", float)
+    factors_init_sigma = hp('factors_init_sigma', ge(0), "A non-negative float", float)
+    factors_init_value = hp('factors_init_value', (), "A float value", float)
 
     def __init__(self, role, train_instance_count, train_instance_type,
                  num_factors, predictor_type,
diff --git a/src/sagemaker/amazon/hyperparameter.py b/src/sagemaker/amazon/hyperparameter.py
index e34b1bcff7..5607194659 100644
--- a/src/sagemaker/amazon/hyperparameter.py
+++ b/src/sagemaker/amazon/hyperparameter.py
@@ -36,9 +36,10 @@ def __init__(self, name, validate=lambda _: True, validation_message="", data_ty
     def validate(self, value):
         if value is None:  # We allow assignment from None, but Nones are not sent to training.
             return
+
         for valid in self.validation:
             if not valid(value):
-                error_message = "Invalid hyperparameter value {}".format(value)
+                error_message = "Invalid hyperparameter value {} for {}".format(value, self.name)
                 if self.validation_message:
                     error_message = error_message + ". Expecting: " + self.validation_message
                 raise ValueError(error_message)
@@ -51,6 +52,7 @@ def __get__(self, obj, objtype):
 
     def __set__(self, obj, value):
         """Validate the supplied value and set this hyperparameter to value"""
+        value = self.data_type(value)
         self.validate(value)
         if '_hyperparameters' not in dir(obj):
             obj._hyperparameters = dict()
diff --git a/src/sagemaker/amazon/kmeans.py b/src/sagemaker/amazon/kmeans.py
index bc1fb4456b..020f496d8f 100644
--- a/src/sagemaker/amazon/kmeans.py
+++ b/src/sagemaker/amazon/kmeans.py
@@ -13,7 +13,7 @@
 from sagemaker.amazon.amazon_estimator import AmazonAlgorithmEstimatorBase, registry
 from sagemaker.amazon.common import numpy_to_record_serializer, record_deserializer
 from sagemaker.amazon.hyperparameter import Hyperparameter as hp  # noqa
-from sagemaker.amazon.validation import gt, isin, isint, ge
+from sagemaker.amazon.validation import gt, isin, ge
 from sagemaker.predictor import RealTimePredictor
 from sagemaker.model import Model
 from sagemaker.session import Session
@@ -23,15 +23,15 @@ class KMeans(AmazonAlgorithmEstimatorBase):
 
     repo = 'kmeans:1'
 
-    k = hp('k', (gt(1), isint), 'An integer greater-than 1', int)
+    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), isint), 'An integer greater-than 0', int)
-    tol = hp('local_lloyd_tol', (gt(0), isint), 'An integer greater-than 0', int)
-    num_trials = hp('local_lloyd_num_trials', (gt(0), isint), 'An integer greater-than 0', int)
+    max_iterations = hp('local_lloyd_max_iterations', gt(0), 'An integer greater-than 0', int)
+    tol = hp('local_lloyd_tol', gt(0), 'An integer greater-than 0', int)
+    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)
-    half_life_time_size = hp('half_life_time_size', (ge(0), isint), 'An integer greater-than-or-equal-to 0', int)
-    epochs = hp('epochs', (gt(0), isint), 'An integer greater-than 0', int)
-    center_factor = hp('extra_center_factor', (gt(0), isint), 'An integer greater-than 0', int)
+    half_life_time_size = hp('half_life_time_size', ge(0), 'An integer greater-than-or-equal-to 0', int)
+    epochs = hp('epochs', gt(0), 'An integer greater-than 0', int)
+    center_factor = hp('extra_center_factor', gt(0), 'An integer greater-than 0', int)
 
     def __init__(self, role, train_instance_count, train_instance_type, k, init_method=None,
                  max_iterations=None, tol=None, num_trials=None, local_init_method=None,
diff --git a/src/sagemaker/amazon/linear_learner.py b/src/sagemaker/amazon/linear_learner.py
index b78394cdad..d59ea3eea3 100644
--- a/src/sagemaker/amazon/linear_learner.py
+++ b/src/sagemaker/amazon/linear_learner.py
@@ -13,7 +13,7 @@
 from sagemaker.amazon.amazon_estimator import AmazonAlgorithmEstimatorBase, registry
 from sagemaker.amazon.common import numpy_to_record_serializer, record_deserializer
 from sagemaker.amazon.hyperparameter import Hyperparameter as hp  # noqa
-from sagemaker.amazon.validation import isin, gt, lt, isint, isbool, isnumber
+from sagemaker.amazon.validation import isin, gt, lt, isbool
 from sagemaker.predictor import RealTimePredictor
 from sagemaker.model import Model
 from sagemaker.session import Session
@@ -32,16 +32,16 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
     target_recall = hp('target_recall', (gt(0), lt(1)), "A float in (0,1)", float)
     target_precision = hp('target_precision', (gt(0), lt(1)), "A float in (0,1)", float)
     positive_example_weight_mult = hp('positive_example_weight_mult', gt(0), "A float greater than 0", float)
-    epochs = hp('epochs', (gt(0), isint), "An integer greater-than 0", int)
+    epochs = hp('epochs', gt(0), "An integer greater-than 0", int)
     predictor_type = hp('predictor_type', isin('binary_classifier', 'regressor'),
                         'One of "binary_classifier" or "regressor"', str)
     use_bias = hp('use_bias', isbool, "Either True or False", bool)
-    num_models = hp('num_models', (gt(0), isint), "An integer greater-than 0", int)
-    num_calibration_samples = hp('num_calibration_samples', (gt(0), isint), "An integer greater-than 0", int)
+    num_models = hp('num_models', gt(0), "An integer greater-than 0", int)
+    num_calibration_samples = hp('num_calibration_samples', gt(0), "An integer greater-than 0", int)
     init_method = hp('init_method', isin('uniform', 'normal'), 'One of "uniform" or "normal"', str)
     init_scale = hp('init_scale', (gt(-1), lt(1)), 'A float in (-1, 1)', float)
     init_sigma = hp('init_sigma', (gt(0), lt(1)), 'A float in (0, 1)', float)
-    init_bias = hp('init_bias', isnumber, 'A number', float)
+    init_bias = hp('init_bias', (), 'A number', float)
     optimizer = hp('optimizer', isin('sgd', 'adam', 'auto'), 'One of "sgd", "adam" or "auto', str)
     loss = hp('loss', isin('logistic', 'squared_loss', 'absolute_loss', 'auto'),
               '"logistic", "squared_loss", "absolute_loss" or"auto"', str)
@@ -53,15 +53,15 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
     beta_2 = hp('beta_1', (gt(0), lt(1)), 'A float in (0,1)', float)
     bias_lr_mult = hp('bias_lr_mult', gt(0), 'A float greater-than 0', float)
     bias_wd_mult = hp('bias_wd_mult', gt(0), 'A float greater-than 0', float)
-    use_lr_scheduler = hp('use_lr_scheduler', isbool, 'A boolean', bool)
-    lr_scheduler_step = hp('lr_scheduler_step', (gt(0), isint), 'An integer greater-than 0', int)
+    use_lr_scheduler = hp('use_lr_scheduler', (), 'A boolean', bool)
+    lr_scheduler_step = hp('lr_scheduler_step', gt(0), 'An integer greater-than 0', int)
     lr_scheduler_factor = hp('lr_scheduler_factor', (gt(0), lt(1)), 'A float in (0,1)', float)
     lr_scheduler_minimum_lr = hp('lr_scheduler_minimum_lr', gt(0), 'A float greater-than 0', float)
-    normalize_data = hp('normalize_data', isbool, 'A boolean', bool)
-    normalize_label = hp('normalize_label', isbool, 'A boolean', bool)
-    unbias_data = hp('unbias_data', isbool, 'A boolean', bool)
-    unbias_label = hp('unbias_label', isbool, 'A boolean', bool)
-    num_point_for_scalar = hp('num_point_for_scalar', (isint, gt(0)), 'An integer greater-than 0', int)
+    normalize_data = hp('normalize_data', (), 'A boolean', bool)
+    normalize_label = hp('normalize_label', (), 'A boolean', bool)
+    unbias_data = hp('unbias_data', (), 'A boolean', bool)
+    unbias_label = hp('unbias_label', (), 'A boolean', bool)
+    num_point_for_scalar = hp('num_point_for_scalar', gt(0), 'An integer greater-than 0', int)
 
     def __init__(self, role, train_instance_count, train_instance_type, predictor_type='binary_classifier',
                  binary_classifier_model_selection_criteria=None, target_recall=None, target_precision=None,
diff --git a/src/sagemaker/amazon/pca.py b/src/sagemaker/amazon/pca.py
index 19271c43e8..48f99c04d1 100644
--- a/src/sagemaker/amazon/pca.py
+++ b/src/sagemaker/amazon/pca.py
@@ -24,13 +24,12 @@ class PCA(AmazonAlgorithmEstimatorBase):
 
     DEFAULT_MINI_BATCH_SIZE = 500
 
-    num_components = hp(name='num_components', validate=lambda x: x > 0 and isinstance(x, int),
+    num_components = hp(name='num_components', validate=lambda x: x > 0,
                         validation_message='Value must be an integer greater than zero', data_type=int)
     algorithm_mode = hp(name='algorithm_mode', validate=lambda x: x in ['regular', 'stable', 'randomized'],
                         validation_message='Value must be one of "regular", "stable", "randomized"', data_type=str)
-    subtract_mean = hp(name='subtract_mean', validate=lambda x: isinstance(x, bool),
-                       validation_message='Value must be a boolean', data_type=bool)
-    extra_components = hp(name='extra_components', validate=lambda x: x >= 0 and isinstance(x, int),
+    subtract_mean = hp(name='subtract_mean', validation_message='Value must be a boolean', data_type=bool)
+    extra_components = hp(name='extra_components', validate=lambda x: x >= 0,
                           validation_message="Value must be an integer greater than or equal to 0", data_type=int)
 
     def __init__(self, role, train_instance_count, train_instance_type, num_components,

From c50b06a75c08c8a73af230751854ec8f60d9e7c7 Mon Sep 17 00:00:00 2001
From: Ignacio Quintero <rignacio@amazon.com>
Date: Tue, 23 Jan 2018 16:50:46 -0800
Subject: [PATCH 3/4] Fix broken unit tests

My previous commit broke a couple of unit tests. This fixes them.
---
 src/sagemaker/amazon/hyperparameter.py | 2 +-
 tests/unit/test_hyperparameter.py      | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/sagemaker/amazon/hyperparameter.py b/src/sagemaker/amazon/hyperparameter.py
index 5607194659..a3ac76367c 100644
--- a/src/sagemaker/amazon/hyperparameter.py
+++ b/src/sagemaker/amazon/hyperparameter.py
@@ -52,7 +52,7 @@ def __get__(self, obj, objtype):
 
     def __set__(self, obj, value):
         """Validate the supplied value and set this hyperparameter to value"""
-        value = self.data_type(value)
+        value = None if value is None else self.data_type(value)
         self.validate(value)
         if '_hyperparameters' not in dir(obj):
             obj._hyperparameters = dict()
diff --git a/tests/unit/test_hyperparameter.py b/tests/unit/test_hyperparameter.py
index 69fc248e53..db7ed3f64c 100644
--- a/tests/unit/test_hyperparameter.py
+++ b/tests/unit/test_hyperparameter.py
@@ -16,7 +16,7 @@
 
 class Test(object):
 
-    blank = Hyperparameter(name="some-name")
+    blank = Hyperparameter(name="some-name", data_type=int)
     elizabeth = Hyperparameter(name='elizabeth')
     validated = Hyperparameter(name="validated", validate=lambda value: value > 55, data_type=int)
 
@@ -70,5 +70,5 @@ def test_from_string():
     x.validated = value
     from_api = str(value)
 
-    x.validated = Test.__dict__["validated"].data_type(from_api)
+    x.validated = from_api
     assert x.validated == value

From 59ac007315b47d9df1db99b17dc6102c747f5785 Mon Sep 17 00:00:00 2001
From: Ignacio Quintero <rignacio@amazon.com>
Date: Wed, 24 Jan 2018 10:40:07 -0800
Subject: [PATCH 4/4] Remove unused validation functions

isint() isbool() etc are no longer used.
---
 src/sagemaker/amazon/linear_learner.py | 4 ++--
 src/sagemaker/amazon/validation.py     | 6 ------
 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/src/sagemaker/amazon/linear_learner.py b/src/sagemaker/amazon/linear_learner.py
index d59ea3eea3..d1d9dd6cb8 100644
--- a/src/sagemaker/amazon/linear_learner.py
+++ b/src/sagemaker/amazon/linear_learner.py
@@ -13,7 +13,7 @@
 from sagemaker.amazon.amazon_estimator import AmazonAlgorithmEstimatorBase, registry
 from sagemaker.amazon.common import numpy_to_record_serializer, record_deserializer
 from sagemaker.amazon.hyperparameter import Hyperparameter as hp  # noqa
-from sagemaker.amazon.validation import isin, gt, lt, isbool
+from sagemaker.amazon.validation import isin, gt, lt
 from sagemaker.predictor import RealTimePredictor
 from sagemaker.model import Model
 from sagemaker.session import Session
@@ -35,7 +35,7 @@ class LinearLearner(AmazonAlgorithmEstimatorBase):
     epochs = hp('epochs', gt(0), "An integer greater-than 0", int)
     predictor_type = hp('predictor_type', isin('binary_classifier', 'regressor'),
                         'One of "binary_classifier" or "regressor"', str)
-    use_bias = hp('use_bias', isbool, "Either True or False", bool)
+    use_bias = hp('use_bias', (), "Either True or False", bool)
     num_models = hp('num_models', gt(0), "An integer greater-than 0", int)
     num_calibration_samples = hp('num_calibration_samples', gt(0), "An integer greater-than 0", int)
     init_method = hp('init_method', isin('uniform', 'normal'), 'One of "uniform" or "normal"', str)
diff --git a/src/sagemaker/amazon/validation.py b/src/sagemaker/amazon/validation.py
index ff3259be8f..ede48cc9b3 100644
--- a/src/sagemaker/amazon/validation.py
+++ b/src/sagemaker/amazon/validation.py
@@ -10,7 +10,6 @@
 # distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
 # ANY KIND, either express or implied. See the License for the specific
 # language governing permissions and limitations under the License.
-import numbers
 
 
 def gt(minimum):
@@ -41,8 +40,3 @@ def istype(expected):
     def validate(value):
         return isinstance(value, expected)
     return validate
-
-
-isint = istype(int)
-isbool = istype(bool)
-isnumber = istype(numbers.Number)  # noqa