AWS wellarchitected documentation change
Summary
Updated figure numbering, image alt text, and minor wording changes in data preprocessing strategies (e.g., 'prevent' to 'block', 'helps' to 'assists'). Formatting adjustments for consistency in bullet points.
Security assessment
Changes are editorial improvements and formatting adjustments without introducing new security content. Mentions of data leakage prevention and bias mitigation were already present; wording changes do not alter security implications.
Diff
diff --git a/wellarchitected/latest/machine-learning-lens/data-preprocessing.md b/wellarchitected/latest/machine-learning-lens/data-preprocessing.md index 4d643808c..aba62c418 100644 --- a//wellarchitected/latest/machine-learning-lens/data-preprocessing.md +++ b//wellarchitected/latest/machine-learning-lens/data-preprocessing.md @@ -9 +9 @@ Data preprocessing puts data into the right shape and quality for training. Ther - + @@ -11 +11 @@ Data preprocessing puts data into the right shape and quality for training. Ther -_Figure 10: Data processing main components_ +_Figure 9: Data preprocessing main components_ @@ -13 +13 @@ _Figure 10: Data processing main components_ -The data preprocessing strategies listed in Figure 10 can be expanded as the following: +The data preprocessing strategies listed in Figure 9 can be expanded as the following: @@ -15 +15 @@ The data preprocessing strategies listed in Figure 10 can be expanded as the fol - * **Clean** (**replace, impute, remove outliers and duplicates)** \- Remove outliers and duplicates, replace inaccurate or irrelevant data, and correct missing data using imputation techniques that will minimize bias as part of data cleaning. + * **Clean (replace, impute, remove outliers and duplicates):** Remove outliers and duplicates, replace inaccurate or irrelevant data, and correct missing data using imputation techniques that will minimize bias as part of data cleaning. @@ -17 +17 @@ The data preprocessing strategies listed in Figure 10 can be expanded as the fol - * **Partition** \- To prevent ML models from overfitting and to evaluate a trained model accurately, randomly split data into train, validate, and test sets. Data leakage can happen when information from hold-out test dataset leaks into the training data. One way to avoid data leakage is to remove duplicates before splitting the data. + * **Partition:** To block ML models from overfitting and to evaluate a trained model accurately, randomly split data into train, validate, and test sets. Data leakage can happen when information from hold-out test dataset leaks into the training data. One way to avoid data leakage is to remove duplicates before splitting the data. @@ -19 +19 @@ The data preprocessing strategies listed in Figure 10 can be expanded as the fol - * **Scale (normalize, standardize)** \- Normalization is a scaling technique in machine learning that is applied during data preparation to change the values of numeric columns in the dataset to use a common scale. This technique helps ensure that each feature of the machine learning model has equal feature importance when they have different ranges. Normalized numeric features will have values in the range of [0,1]. Standardized numeric features will have a mean of 0 and standard deviation of 1. Standardization helps in handling outliers. + * **Scale (normalize, standardize):** Normalization is a scaling technique in machine learning that is applied during data preparation to change the values of numeric columns in the dataset to use a common scale. This technique assists to verify that each feature of the machine learning model has equal feature importance when they have different ranges. Normalized numeric features will have values in the range of [0,1]. Standardized numeric features will have a mean of 0 and standard deviation of 1. Standardization assists in handling outliers. @@ -21 +21 @@ The data preprocessing strategies listed in Figure 10 can be expanded as the fol - * **Unbias, balance (detection & mitigation)** \- Detecting and mitigating bias helps avoid inaccurate model results. Biases are imbalances in the accuracy of predictions across different groups, such as age or income bracket. Biases can come from the data or algorithm used to train your model. + * **Unbias, balance (detection and mitigation):** Detecting and mitigating bias assists to avoid inaccurate model results. Biases are imbalances in the accuracy of predictions across different groups, such as age or income bracket. Biases can come from the data or algorithm used to train your model. @@ -23 +23 @@ The data preprocessing strategies listed in Figure 10 can be expanded as the fol - * **Augment** \- Data augmentation increases the amount of data artificially by synthesizing new data from existing data. Data augmentation can help regularize and reduce overfitting. + * **Augment:** Data augmentation increases the amount of data artificially by synthesizing new data from existing data. Data augmentation can assist to regularize and reduce overfitting.