{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Data Science Tech Brief By HackerNoon","title":"How I Decoded My Apple Watch Metrics: Taking a Look At The Raw Numbers (Part 2)","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/e0488ba2\"></iframe>","width":"100%","height":180,"duration":219,"description":"\n        This story was originally published on HackerNoon at: https://hackernoon.com/how-i-decoded-my-apple-watch-metrics-taking-a-look-at-the-raw-numbers-part-2.\nLearn how to parse Apple Health XML & GPX files. A technical guide to \"streaming\" large CDA files and extracting workout kinematics using Python.\nCheck more stories related to data-science at: https://hackernoon.com/c/data-science.\n            You can also check exclusive content about #data-science, #python-notebook, #python, #apple-watch, #apple-health, #prediction-delta, #health-data, #apple-wearable-data,  and more.\nThis story was written by: @farzon. Learn more about this writer by checking @farzon's about page,\n            and for more stories, please visit hackernoon.com.\nExporting Apple Health data results in massive, messy XML files that are difficult to process. By using a \"streaming\" parser to filter specific LOINC codes and extracting GPS kinematics from GPX files, I converted 300MB of raw records into clean CSVs. This structured data is now ready to be fed into a custom machine learning model to reverse-engineer VO2 Max.\n        \n        ","thumbnail_url":"https://img.transistorcdn.com/8VxAgS1Ll3FJEERcAdhFdqqXJMnE7OfD2RUvrjauLt0/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxMjY4LzE2ODM1/ODI1ODUtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}