change: Update tests

Author: Dewen Qi

src/sagemaker/workflow/pipeline_context.py

@@ -105,7 +105,7 @@ def _intercept_create_request(self, request: Dict, create, func_name: str = None
         else:
             self.context = request
 
-    def init_model_step_arguments(self, model):
+    def init_step_arguments(self, model):
         """Create a `_ModelStepArguments` (if not exist) as pipeline context
 
         Args:
@@ -161,7 +161,7 @@ def wrapper(*args, **kwargs):
                 UserWarning,
             )
             if run_func.__name__ in ["register", "create"]:
-                args[0].sagemaker_session.init_model_step_arguments(args[0])
+                args[0].sagemaker_session.init_step_arguments(args[0])
                 run_func(*args, **kwargs)
                 context = args[0].sagemaker_session.context
                 args[0].sagemaker_session.context = None

src/sagemaker/workflow/steps.py

@@ -420,15 +420,15 @@ def __init__(
 
         self._properties = Properties(path=f"Steps.{name}", shape_name="DescribeModelOutput")
 
-        if not self.step_args:
-            warnings.warn(
-                (
-                    "We are deprecating the instantiation of CreateModelStep using "
-                    "`Model` and a list of `CreateModelInput`. "
-                    "Instead, the new interface simply uses step_args."
-                ),
-                DeprecationWarning,
-            )
+        # TODO: add public document link here once ready
+        warnings.warn(
+            (
+                "We are deprecating the use of CreateModelStep. "
+                "Instead, please use the ModelStep, which simply takes in the step arguments "
+                "generated by model.create()."
+            ),
+            DeprecationWarning,
+        )
 
     @property
     def arguments(self) -> RequestType:

tests/data/xgboost_abalone/inference.py

@@ -0,0 +1,60 @@
+#  Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License").
+#  You may not use this file except in compliance with the License.
+#  A copy of the License is located at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  or in the "license" file accompanying this file. This file is 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 os
+import pickle as pkl
+
+import numpy as np
+import sagemaker_xgboost_container.encoder as xgb_encoders
+
+
+def model_fn(model_dir):
+    """
+    Deserialize and return fitted model.
+    """
+    model_file = "xgboost-model"
+    booster = pkl.load(open(os.path.join(model_dir, model_file), "rb"))
+    return booster
+
+
+def input_fn(request_body, request_content_type):
+    """
+    The SageMaker XGBoost model server receives the request data body and the content type,
+    and invokes the `input_fn`.
+    Return a DMatrix (an object that can be passed to predict_fn).
+    """
+    if request_content_type == "text/libsvm":
+        return xgb_encoders.libsvm_to_dmatrix(request_body)
+    else:
+        raise ValueError("Content type {} is not supported.".format(request_content_type))
+
+
+def predict_fn(input_data, model):
+    """
+    SageMaker XGBoost model server invokes `predict_fn` on the return value of `input_fn`.
+    Return a two-dimensional NumPy array where the first columns are predictions
+    and the remaining columns are the feature contributions (SHAP values) for that prediction.
+    """
+    prediction = model.predict(input_data)
+    feature_contribs = model.predict(input_data, pred_contribs=True, validate_features=False)
+    output = np.hstack((prediction[:, np.newaxis], feature_contribs))
+    return output
+
+
+def output_fn(predictions, content_type):
+    """
+    After invoking predict_fn, the model server invokes `output_fn`.
+    """
+    if content_type == "text/csv":
+        return ",".join(str(x) for x in predictions[0])
+    else:
+        raise ValueError("Content type {} is not supported.".format(content_type))

tests/data/xgboost_abalone/xgb_model.tar.gz

@@ -26,9 +26,7 @@
 from botocore.exceptions import WaiterError
 
 import tests
-from sagemaker.parameter import IntegerParameter
 from sagemaker.tensorflow import TensorFlow, TensorFlowModel
-from sagemaker.tuner import HyperparameterTuner
 from tests.integ.retry import retries
 from sagemaker.drift_check_baselines import DriftCheckBaselines
 from sagemaker import (
@@ -50,7 +48,7 @@
 from sagemaker.workflow.parameters import ParameterInteger, ParameterString
 from sagemaker.workflow.pipeline import Pipeline
 from sagemaker.workflow.step_collections import RegisterModel
-from sagemaker.workflow.steps import CreateModelStep, ProcessingStep, TrainingStep, TuningStep
+from sagemaker.workflow.steps import CreateModelStep, ProcessingStep, TrainingStep
 from sagemaker.xgboost import XGBoostModel
 from sagemaker.xgboost import XGBoost
 from sagemaker.workflow.conditions import (
@@ -848,124 +846,3 @@ def test_model_registration_with_tensorflow_model_with_pipeline_model(
             pipeline.delete()
         except Exception as error:
             logging.error(error)
-
-
-def test_tuning_single_algo_with_create_model(
-    sagemaker_session,
-    role,
-    cpu_instance_type,
-    pipeline_name,
-    region_name,
-):
-    base_dir = os.path.join(DATA_DIR, "pytorch_mnist")
-    entry_point = os.path.join(base_dir, "mnist.py")
-    input_path = sagemaker_session.upload_data(
-        path=os.path.join(base_dir, "training"),
-        key_prefix="integ-test-data/pytorch_mnist/training",
-    )
-    inputs = TrainingInput(s3_data=input_path)
-
-    instance_count = ParameterInteger(name="InstanceCount", default_value=1)
-    instance_type = ParameterString(name="InstanceType", default_value="ml.m5.xlarge")
-
-    pytorch_estimator = PyTorch(
-        entry_point=entry_point,
-        role=role,
-        framework_version="1.5.0",
-        py_version="py3",
-        instance_count=instance_count,
-        instance_type=instance_type,
-        sagemaker_session=sagemaker_session,
-        enable_sagemaker_metrics=True,
-        max_retry_attempts=3,
-    )
-
-    min_batch_size = ParameterInteger(name="MinBatchSize", default_value=64)
-    max_batch_size = ParameterInteger(name="MaxBatchSize", default_value=128)
-    hyperparameter_ranges = {
-        "batch-size": IntegerParameter(min_batch_size, max_batch_size),
-    }
-    tuner = HyperparameterTuner(
-        estimator=pytorch_estimator,
-        objective_metric_name="test:acc",
-        objective_type="Maximize",
-        hyperparameter_ranges=hyperparameter_ranges,
-        metric_definitions=[{"Name": "test:acc", "Regex": "Overall test accuracy: (.*?);"}],
-        max_jobs=2,
-        max_parallel_jobs=2,
-    )
-    step_tune = TuningStep(
-        name="my-tuning-step",
-        tuner=tuner,
-        inputs=inputs,
-    )
-    best_model = Model(
-        image_uri=pytorch_estimator.training_image_uri(),
-        model_data=step_tune.get_top_model_s3_uri(
-            top_k=0,
-            s3_bucket=sagemaker_session.default_bucket(),
-        ),
-        sagemaker_session=sagemaker_session,
-        role=role,
-    )
-    model_inputs = CreateModelInput(
-        instance_type="ml.m5.large",
-        accelerator_type="ml.eia1.medium",
-    )
-    step_best_model = CreateModelStep(
-        name="1st-model",
-        model=best_model,
-        inputs=model_inputs,
-    )
-
-    second_best_model = Model(
-        image_uri=pytorch_estimator.training_image_uri(),
-        model_data=step_tune.get_top_model_s3_uri(
-            top_k=1,
-            s3_bucket=sagemaker_session.default_bucket(),
-        ),
-        sagemaker_session=sagemaker_session,
-        role=role,
-        entry_point=entry_point,
-        source_dir=base_dir,
-    )
-    step_second_best_model = CreateModelStep(
-        name="2nd-best-model",
-        model=second_best_model,
-        inputs=model_inputs,
-    )
-    pipeline = Pipeline(
-        name=pipeline_name,
-        parameters=[instance_count, instance_type, min_batch_size, max_batch_size],
-        steps=[step_tune, step_best_model, step_second_best_model],
-        sagemaker_session=sagemaker_session,
-    )
-
-    try:
-        response = pipeline.create(role)
-        create_arn = response["PipelineArn"]
-        assert re.match(
-            rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}",
-            create_arn,
-        )
-
-        execution = pipeline.start(parameters={})
-        assert re.match(
-            rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}/execution/",
-            execution.arn,
-        )
-        try:
-            execution.wait(delay=30, max_attempts=60)
-        except WaiterError:
-            pass
-        execution_steps = execution.list_steps()
-
-        for step in execution_steps:
-            assert not step.get("FailureReason", None)
-            assert step["StepStatus"] == "Succeeded"
-        assert len(execution_steps) == 3
-    finally:
-        try:
-            pipeline.delete()
-        except Exception:
-            pass