{"version":1,"pages":[{"id":"-LbIjUyTTTBbe185Y5B-","title":"Welcome to Sparkitecture!","pathname":"/","siteSpaceId":"sitesp_6r4PD","description":""},{"id":"-Ln_piGISRAU_yqgJVZ0","title":"Azure Storage","pathname":"/cloud-service-integration/azure-storage","siteSpaceId":"sitesp_6r4PD","description":"Storage is a managed service in Azure that provides highly available, secure, durable, scalable, and redundant storage for your data. Azure Storage includes both Blobs, Data Lake Store, and others.","breadcrumbs":[{"label":"Cloud Service Integration"}]},{"id":"-Lq7WbPTYesbavqG2E1U","title":"Azure SQL Data Warehouse / Synapse","pathname":"/cloud-service-integration/azure-sql-data-warehouse","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Cloud Service Integration"}]},{"id":"-Ln_pf1efI9sORhN1IuT","title":"Azure Data Factory","pathname":"/cloud-service-integration/azure-data-factory","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Cloud Service Integration"}]},{"id":"-LqWAS8DrHc1NGEj0KHJ","title":"Reading and Writing Data","pathname":"/data-preparation/reading-and-writing-data","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Data Preparation"}]},{"id":"-Ljvk8dtHAbZrf9e-cnj","title":"Shaping Data with Pipelines","pathname":"/data-preparation/shaping-data-with-pipelines","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Data Preparation"}]},{"id":"-Lq7_NLO4iMG8OVfK9Pf","title":"Other Common Tasks","pathname":"/data-preparation/other-common-tasks","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Data Preparation"}]},{"id":"-Ljvk6_lgP8jjpd9tQFX","title":"About Spark MLlib","pathname":"/machine-learning/about-spark-mllib","siteSpaceId":"sitesp_6r4PD","description":"MLlib is Apache Spark's scalable machine learning library.","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-LjvlJszmLN1irQks-s3","title":"Classification","pathname":"/machine-learning/classification","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-LjvlRUrgX50zUkDEixi","title":"Logistic Regression","pathname":"/machine-learning/classification/logistic-regression","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Classification"}]},{"id":"-Ljvl_nruWB2f8Co39RG","title":"Naïve Bayes","pathname":"/machine-learning/classification/naive-bayes","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Classification"}]},{"id":"-LjvmCXEBYb9k64T2hXr","title":"Decision Tree","pathname":"/machine-learning/classification/decision-tree","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Classification"}]},{"id":"-LjvmJAyE-6MgnPnh03q","title":"Random Forest","pathname":"/machine-learning/classification/random-forest","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Classification"}]},{"id":"-LqbnJRfQhtkVmVoylSN","title":"Gradient-Boosted Trees","pathname":"/machine-learning/classification/gradient-boosted-trees","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Classification"}]},{"id":"-LjvlMvNz57aCEvIm0Gp","title":"Regression","pathname":"/machine-learning/regression","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-LjvlStbMlKWewuUOgFs","title":"Linear Regression","pathname":"/machine-learning/regression/linear-regression","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Regression"}]},{"id":"-LqH66n__v_oZdC6wcmt","title":"Decision Tree","pathname":"/machine-learning/regression/decision-tree","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Regression"}]},{"id":"-LqH66naPWjUsASNFEx9","title":"Random Forest","pathname":"/machine-learning/regression/random-forest","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Regression"}]},{"id":"-LqfbUGQ6RCI3sD7dY0J","title":"Gradient-Boosted Trees","pathname":"/machine-learning/regression/gradient-boosted-trees","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"},{"label":"Regression"}]},{"id":"-Lq7WI8yA9SkrxAjb4Jq","title":"MLflow","pathname":"/machine-learning/mlflow","siteSpaceId":"sitesp_6r4PD","description":"MLflow is an open source library by the Databricks team designed for managing the machine learning lifecycle. It allows for the creation of projects, tracking of metrics, and model versioning.","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-Lq7VUNU0eVDQ7bO_hbP","title":"Feature Importance","pathname":"/machine-learning/feature-importance","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-Lq7Tm51crucT_7EB3dA","title":"Model Saving and Loading","pathname":"/machine-learning/model-saving-and-loading","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-Lq7a59-VvLIcl-4c3bz","title":"Model Evaluation","pathname":"/machine-learning/model-evaluation","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"-Lq7OD2GfPetUOuRK5iu","title":"Structured Streaming","pathname":"/streaming-data/structured-streaming","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Streaming Data"}]},{"id":"-LjvkQXlclJer9F-iuGY","title":"API Serving","pathname":"/operationalization/api-serving","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Operationalization"}]},{"id":"-Lq7XIWiQ5WeZQGjmeII","title":"Batch Scoring","pathname":"/operationalization/batch-scoring","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Operationalization"}]},{"id":"-LqkqMrmfQPv_uyIDW70","title":"Text Data Preparation","pathname":"/natural-language-processing/data-preparation","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Natural Language Processing"}]},{"id":"-LqkrZXtMxPGpcZZeses","title":"Model Evaluation","pathname":"/natural-language-processing/model-evaluation","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Natural Language Processing"}]},{"id":"-MBZXkETZh2M5UaLdtrd","title":"Glow","pathname":"/bioinformatics-and-genomics/glow","siteSpaceId":"sitesp_6r4PD","description":"","breadcrumbs":[{"label":"Bioinformatics and Genomics"}]}]}