Tabular Checks

Distribution

• Train Test Feature Drift
• Train Test Label Drift
• Train Test Prediction Drift
• Whole Dataset Drift

Integrity

• New Category
• Conflicting Labels
• Data Duplicates
• Dominant Frequency Change
• Is Single Value
• Mixed Data Types
• Mixed Nulls
• New Label
• Outlier Sample Detection
• Special Characters
• String Length Out Of Bounds
• String Mismatch
• String Mismatch Comparison

Methodology

• Boosting Overfit
• Datasets Size Comparison
• Date Train Validation Leakage Duplicates
• Date Train Validation Leakage Overlap
• Identifier Leakage
• Index Leakage
• Model Inference Time
• Single Feature Contribution
• Single Feature Contribution Train Test
• Train Test Samples Mix
• Unused Features

Overview

• Columns Info
• Model Info

Performance

• Calibration Score
• Confusion Matrix Report
• Model Error Analysis
• Multi Model Performance Report
• Performance Report
• Regression Error Distribution
• Regression Systematic Error
• ROC Report
• Segment Performance
• Simple Model Comparison

previous

H2O

next

Train Test Feature Drift