atqy
253 lines
15 KiB
Plaintext
253 lines
15 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Algorithms\n"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"---\n",
|
|
"\n",
|
|
"This notebook's CI test result for us-west-2 is as follows. CI test results in other regions can be found at the end of the notebook. \n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"\n",
|
|
"Examples on how to use SageMaker's built-in algorithms."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Image Processing\n",
|
|
"---\n",
|
|
"\n",
|
|
"SageMaker provides algorithms that are used for image processing.\n",
|
|
"\n",
|
|
"### Image Classification\n",
|
|
"* [Using SageMaker Image Classification with Amazon Elastic Inference](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-fulltraining-elastic-inference.ipynb)\n",
|
|
"* [Image classification training with image format](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-lst-format.ipynb)\n",
|
|
"* [End-to-End Incremental Training Image Classification Example](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-incremental-training-highlevel.ipynb)\n",
|
|
"* [Image classification training with image format demo](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-lst-format-highlevel.ipynb)\n",
|
|
"* [Image classification transfer learning demo](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-transfer-learning.ipynb)\n",
|
|
"* [Image classification transfer learning demo (SageMaker SDK)](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-transfer-learning-highlevel.ipynb)\n",
|
|
"* [End-to-End Multiclass Image Classification Example](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-fulltraining.ipynb)\n",
|
|
"* [End-to-End Multiclass Image Classification Example with SageMaker SDK and SageMaker Neo](../introduction_to_amazon_algorithms/imageclassification_caltech/Image-classification-fulltraining-highlevel.ipynb)\n",
|
|
"* [Image classification multi-label classification](../introduction_to_amazon_algorithms/imageclassification_mscoco_multi_label/Image-classification-multilabel-lst.ipynb)\n",
|
|
"\n",
|
|
"### Object Detection\n",
|
|
"* [Amazon SageMaker Object Detection for Bird Species](../introduction_to_amazon_algorithms/object_detection_birds/object_detection_birds.ipynb)\n",
|
|
"\n",
|
|
"### Semantic Segmentation\n",
|
|
"* [Amazon SageMaker Semantic Segmentation Algorithm](../introduction_to_amazon_algorithms/semantic_segmentation_pascalvoc/semantic_segmentation_pascalvoc.ipynb)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Text Processing\n",
|
|
"---\n",
|
|
"\n",
|
|
"SageMaker provides algorithms that are tailored to the analysis of texts and documents used in natural language processing and translation.\n",
|
|
"\n",
|
|
"### BlazingText\n",
|
|
"\n",
|
|
"* [Text Classification using SageMaker BlazingText](../introduction_to_amazon_algorithms/blazingtext_text_classification_dbpedia/blazingtext_text_classification_dbpedia.ipynb)\n",
|
|
"* [Learning Word2Vec Subword Representations using BlazingText](../introduction_to_amazon_algorithms/blazingtext_word2vec_subwords_text8/blazingtext_word2vec_subwords_text8.ipynb)\n",
|
|
"* [Learning Word2Vec Word Representations using BlazingText](../introduction_to_amazon_algorithms/blazingtext_word2vec_text8/blazingtext_word2vec_text8.ipynb)\n",
|
|
"\n",
|
|
"### Latent Dirichlet Allocation (LDA) \n",
|
|
"\n",
|
|
"* [An Introduction to SageMaker LDA](../introduction_to_amazon_algorithms/lda_topic_modeling/LDA-Introduction.ipynb)\n",
|
|
"\n",
|
|
"### Neural Topic Model (NTM)\n",
|
|
"\n",
|
|
"* [Amazon SageMaker Neural Topic Model now supports auxiliary vocabulary channel, new topic evaluation metrics, and training subsampling](../scientific_details_of_algorithms/ntm_topic_modeling/ntm_wikitext.ipynb)\n",
|
|
"* [Introduction to Basic Functionality of NTM](../introduction_to_amazon_algorithms/ntm_synthetic/ntm_synthetic.ipynb)\n",
|
|
"* [An Introduction to SageMaker Neural Topic Model](../introduction_to_applying_machine_learning/ntm_20newsgroups_topic_modeling/ntm_20newsgroups_topic_model.ipynb)\n",
|
|
"\n",
|
|
"### Seq2Seq\n",
|
|
"\n",
|
|
"* [Machine Translation English-German Example Using SageMaker Seq2Seq](../introduction_to_amazon_algorithms/seq2seq_translation_en-de/SageMaker-Seq2Seq-Translation-English-German.ipynb)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Time Series Processing\n",
|
|
"---\n",
|
|
"\n",
|
|
"SageMaker DeepAR algorithm is useful for processing time series data.\n",
|
|
"\n",
|
|
"### DeepAR\n",
|
|
"\n",
|
|
"* [Time series forecasting with DeepAR - Synthetic data](../introduction_to_amazon_algorithms/deepar_synthetic/deepar_synthetic.ipynb)\n",
|
|
"* [SageMaker/DeepAR demo on electricity dataset](../introduction_to_amazon_algorithms/deepar_electricity/DeepAR-Electricity.ipynb)\n",
|
|
"* [Predicting driving speed violations with the Amazon SageMaker DeepAR algorithm](../introduction_to_applying_machine_learning/deepar_chicago_traffic_violations/deepar_chicago_traffic_violations.ipynb)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Supervised Learning Algorithms\n",
|
|
"---\n",
|
|
"\n",
|
|
"Amazon SageMaker provides several built-in general purpose algorithms that can be used for either classification or regression problems.\n",
|
|
"\n",
|
|
"### Factorization Machines\n",
|
|
"\n",
|
|
"* [An Introduction to Factorization Machines with MNIST](../introduction_to_amazon_algorithms/factorization_machines_mnist/factorization_machines_mnist.ipynb)\n",
|
|
"\n",
|
|
"### k-Nearest Neighbors (kNN)\n",
|
|
"\n",
|
|
"* [Multi-Class Classification using Amazon SageMaker k-Nearest-Neighbors (kNN)](../introduction_to_amazon_algorithms/k_nearest_neighbors_covtype/k_nearest_neighbors_covtype.ipynb)\n",
|
|
"\n",
|
|
"### Linear Learner\n",
|
|
"\n",
|
|
"* [An Introduction to Linear Learner with MNIST](../introduction_to_amazon_algorithms/linear_learner_mnist/linear_learner_mnist.ipynb)\n",
|
|
"* [Train Linear Learner model using File System Data Source](../introduction_to_amazon_algorithms/linear_learner_mnist/linear_learner_mnist_with_file_system_data_source.ipynb)\n",
|
|
"* [Build multiclass classifiers with Amazon SageMaker linear learner](../scientific_details_of_algorithms/linear_learner_multiclass_classification/linear_learner_multiclass_classification.ipynb)\n",
|
|
"* [Fairness Linear Learner in SageMaker](../introduction_to_applying_machine_learning/fair_linear_learner/fair_linear_learner.ipynb)\n",
|
|
"\n",
|
|
"### XGBoost\n",
|
|
"\n",
|
|
"#### Basic\n",
|
|
"* [Multiclass classification with Amazon SageMaker XGBoost algorithm](../introduction_to_amazon_algorithms/xgboost_mnist/xgboost_mnist.ipynb)\n",
|
|
"* [Regression with Amazon SageMaker XGBoost algorithm](../introduction_to_amazon_algorithms/xgboost_abalone/xgboost_abalone.ipynb)\n",
|
|
"* [Customer Churn Prediction with XGBoost](../introduction_to_applying_machine_learning/xgboost_customer_churn/xgboost_customer_churn.ipynb)\n",
|
|
"\n",
|
|
"#### Advanced\n",
|
|
"\n",
|
|
"* [Train and deploy a regression model with the Amazon SageMaker XGBoost Algorithm using Script Mode](../introduction_to_amazon_algorithms/xgboost_abalone/xgboost_abalone_dist_script_mode.ipynb)\n",
|
|
"* [Regression with Amazon SageMaker XGBoost (Parquet input)](../introduction_to_amazon_algorithms/xgboost_abalone/xgboost_parquet_input_training.ipynb)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Unsupervised Learning Algorithms\n",
|
|
"---\n",
|
|
"\n",
|
|
"Amazon SageMaker provides several built-in algorithms that can be used for a variety of unsupervised learning tasks such as clustering, dimension reduction, pattern recognition, and anomaly detection.\n",
|
|
"\n",
|
|
"\n",
|
|
"### IP Insights\n",
|
|
"\n",
|
|
"* [An Introduction to the Amazon SageMaker IP Insights Algorithm](../introduction_to_amazon_algorithms/ipinsights_login/ipinsights-tutorial.ipynb)\n",
|
|
"\n",
|
|
"### K-means\n",
|
|
"* [Analyze US census data for population segmentation using Amazon SageMaker](../introduction_to_applying_machine_learning/US-census_population_segmentation_PCA_Kmeans/sagemaker-countycensusclustering.ipynb)\n",
|
|
"* [End-to-End Example with Amazon SageMaker K-Means](../sagemaker-python-sdk/1P_kmeans_highlevel/kmeans_mnist.ipynb)\n",
|
|
"* [End-to-End Example with Amazon SageMaker K-Means using SageMaker API](../sagemaker-python-sdk/1P_kmeans_lowlevel/kmeans_mnist_lowlevel.ipynb)\n",
|
|
"\n",
|
|
"### Principle Component Analysis (PCA)\n",
|
|
"\n",
|
|
"* [An Introduction to PCA with MNIST](../introduction_to_amazon_algorithms/pca_mnist/pca_mnist.ipynb)\n",
|
|
"\n",
|
|
"### Random Cut Forest (RCF)\n",
|
|
"\n",
|
|
"* [An Introduction to SageMaker Random Cut Forests](../introduction_to_amazon_algorithms/random_cut_forest/random_cut_forest.ipynb)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Feature Engineering\n",
|
|
"---\n",
|
|
"\n",
|
|
"### Object2Vec\n",
|
|
"\n",
|
|
"* [Document Embedding with Amazon SageMaker Object2Vec](../introduction_to_applying_machine_learning/object2vec_document_embedding/object2vec_document_embedding.ipynb)\n",
|
|
"* [An Introduction to SageMaker ObjectToVec model for MovieLens recommendation](../introduction_to_amazon_algorithms/object2vec_movie_recommendation/object2vec_movie_recommendation.ipynb)\n",
|
|
"* [An Introduction to SageMaker ObjectToVec model for sequence-sequence embedding](../introduction_to_amazon_algorithms/object2vec_sentence_similarity/object2vec_sentence_similarity.ipynb)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Notebook CI Test Results\n",
|
|
"\n",
|
|
"This notebook was tested in multiple regions. The test results are as follows, except for us-west-2 which is shown at the top of the notebook.\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"instance_type": "ml.t3.medium",
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (Data Science 3.0)",
|
|
"language": "python",
|
|
"name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/sagemaker-data-science-310-v1"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|