outlier-detection-and-quality-assessment

Outlier detection in non-normal tabular data applies IQR-based thresholds across numeric columns to identify anomalous values, while computing skewness and kurtosis to characterize distribution shape and guide preprocessing decisions.

Assessing data quality for skewed datasets involves computing skewness and kurtosis metrics alongside IQR-based outlier detection, which together quantify distribution shape and extreme values to inform automated cleaning workflows.

Yes, automated outlier detection and preprocessing applies IQR-based thresholds across pandas numeric columns, outputting a structured summary and visualization-ready data for downstream ML pipelines.

IQR-based detection calculates interquartile range thresholds to flag extreme values in numeric columns, providing a robust method for non-normal distributions where standard deviation approaches fail.

Yes, outlier detection for non-normal distributions uses IQR-based thresholds and skewness-kurtosis analysis, avoiding normality assumptions to effectively characterize and clean tabular numeric data across domains.