AWS wellarchitected documentation change
Summary
Expanded data preparation guidance with EDA visualization tools, data wrangler tools, and generative AI code tools. Added sub-phase documentation links for data preprocessing and feature engineering.
Security assessment
Focuses on improving data analysis and preparation processes. While data quality impacts model reliability, there's no specific mention of security controls, data protection, or vulnerability mitigation in the changes.
Diff
diff --git a/wellarchitected/latest/machine-learning-lens/data-preparation.md b/wellarchitected/latest/machine-learning-lens/data-preparation.md index aa7c20f33..6bf304131 100644 --- a//wellarchitected/latest/machine-learning-lens/data-preparation.md +++ b//wellarchitected/latest/machine-learning-lens/data-preparation.md @@ -7 +7,11 @@ -ML models are only as good as the data that is used to train them. Ensure that suitable training data is available and is optimized for learning and generalization. Data preparation includes data preprocessing and feature engineering. +ML models are only as good as the data that is used to train them. Verify that suitable training data is available and is optimized for learning and generalization. Data preparation includes data preprocessing and feature engineering. + +A key aspect to understanding data is to identify patterns. These patterns are often not evident with data in tables. Exploratory data analysis (EDA) with visualization tools can assist in quickly gaining a deeper understanding of data. Prepare data using data wrangler tools for interactive data analysis and model building. Employ no-code/low-code, automation, and visual capabilities to improve the productivity and reduce the cost for interactive analysis. Use generative AI code tools. + +###### Sub-phases + + * [Data preprocessing](./data-preprocessing.html) + + * [Feature engineering](./feature-engineering.html) + + @@ -9 +18,0 @@ ML models are only as good as the data that is used to train them. Ensure that s -A key aspect to understanding data is to identify patterns. These patterns are often not evident with data in tables. Exploratory data analysis (EDA) with visualization tools can help in quickly gaining a deeper understanding of data. Prepare data using data wrangler tools for interactive data analysis and model building. Employ no-code/low-code, automation, and visual capabilities to improve the productivity and reduce the cost for interactive analysis.