| :py:mod:`tests.system.providers.amazon.aws.example_sagemaker` |
| ============================================================= |
| |
| .. py:module:: tests.system.providers.amazon.aws.example_sagemaker |
| |
| |
| Module Contents |
| --------------- |
| |
| |
| Functions |
| ~~~~~~~~~ |
| |
| .. autoapisummary:: |
| |
| tests.system.providers.amazon.aws.example_sagemaker.set_up |
| tests.system.providers.amazon.aws.example_sagemaker.delete_ecr_repository |
| tests.system.providers.amazon.aws.example_sagemaker.delete_logs |
| |
| |
| |
| Attributes |
| ~~~~~~~~~~ |
| |
| .. autoapisummary:: |
| |
| tests.system.providers.amazon.aws.example_sagemaker.DAG_ID |
| tests.system.providers.amazon.aws.example_sagemaker.ROLE_ARN_KEY |
| tests.system.providers.amazon.aws.example_sagemaker.KNN_IMAGE_URI_KEY |
| tests.system.providers.amazon.aws.example_sagemaker.sys_test_context_task |
| tests.system.providers.amazon.aws.example_sagemaker.DATASET |
| tests.system.providers.amazon.aws.example_sagemaker.SAMPLE_SIZE |
| tests.system.providers.amazon.aws.example_sagemaker.PREPROCESS_SCRIPT_TEMPLATE |
| tests.system.providers.amazon.aws.example_sagemaker.test_context |
| tests.system.providers.amazon.aws.example_sagemaker.test_run |
| |
| |
| .. py:data:: DAG_ID |
| :annotation: = example_sagemaker |
| |
| |
| |
| .. py:data:: ROLE_ARN_KEY |
| :annotation: = ROLE_ARN |
| |
| |
| |
| .. py:data:: KNN_IMAGE_URI_KEY |
| :annotation: = KNN_IMAGE_URI |
| |
| |
| |
| .. py:data:: sys_test_context_task |
| |
| |
| |
| |
| .. py:data:: DATASET |
| :annotation: = Multiline-String |
| |
| .. raw:: html |
| |
| <details><summary>Show Value</summary> |
| |
| .. code-block:: text |
| :linenos: |
| |
| |
| 5.1,3.5,1.4,0.2,Iris-setosa |
| 4.9,3.0,1.4,0.2,Iris-setosa |
| 7.0,3.2,4.7,1.4,Iris-versicolor |
| 6.4,3.2,4.5,1.5,Iris-versicolor |
| 4.9,2.5,4.5,1.7,Iris-virginica |
| 7.3,2.9,6.3,1.8,Iris-virginica |
| |
| |
| .. raw:: html |
| |
| </details> |
| |
| |
| |
| .. py:data:: SAMPLE_SIZE |
| |
| |
| |
| |
| .. py:data:: PREPROCESS_SCRIPT_TEMPLATE |
| :annotation: = Multiline-String |
| |
| .. raw:: html |
| |
| <details><summary>Show Value</summary> |
| |
| .. code-block:: text |
| :linenos: |
| |
| |
| import boto3 |
| import numpy as np |
| import pandas as pd |
| |
| def main(): |
| # Load the Iris dataset from {input_path}/input.csv, split it into train/test |
| # subsets, and write them to {output_path}/ for the Processing Operator. |
| |
| columns = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'] |
| iris = pd.read_csv('{input_path}/input.csv', names=columns) |
| |
| # Process data |
| iris['species'] = iris['species'].replace({{'Iris-virginica': 0, 'Iris-versicolor': 1, 'Iris-setosa': 2}}) |
| iris = iris[['species', 'sepal_length', 'sepal_width', 'petal_length', 'petal_width']] |
| |
| # Split into test and train data |
| iris_train, iris_test = np.split( |
| iris.sample(frac=1, random_state=np.random.RandomState()), [int(0.7 * len(iris))] |
| ) |
| |
| # Remove the "answers" from the test set |
| iris_test.drop(['species'], axis=1, inplace=True) |
| |
| # Write the splits to disk |
| iris_train.to_csv('{output_path}/train.csv', index=False, header=False) |
| iris_test.to_csv('{output_path}/test.csv', index=False, header=False) |
| |
| print('Preprocessing Done.') |
| |
| if __name__ == "__main__": |
| main() |
| |
| |
| |
| .. raw:: html |
| |
| </details> |
| |
| |
| |
| .. py:function:: set_up(env_id, knn_image_uri, role_arn) |
| |
| |
| .. py:function:: delete_ecr_repository(repository_name) |
| |
| |
| .. py:function:: delete_logs(env_id) |
| |
| |
| .. py:data:: test_context |
| |
| |
| |
| |
| .. py:data:: test_run |
| |
| |
| |
| |