2.4.0

What's Changed

🐛 Fixes

• fix argn.predict_proba with context data #254
• fix argn.predict column order #255
• fix pre-commit hook #260

📦 Packaging

• upgrade PyTorch to 2.9.1 and vLLM 0.12.0 #250
• update CUDA image to version 13.0.2 #252
• release 2.4.0 #261

Full Changelog: 2.3.3...2.4.0

2.3.3

What's Changed

🐛 Fixes

• adjust assignment to prevent pandas warning #247

📦 Uncategorized

• release 2.3.3 #248

Full Changelog: 2.3.2...2.3.3

2.3.2

What's Changed

🐛 Fixes

• predict proba with flexible genration disabled #245

📦 Uncategorized

• release 2.3.2 #246

Full Changelog: 2.3.1...2.3.2

2.3.1

What's Changed

🚀 Features

• log likelihood #240
• allow custom trn_val_split logic #239

📦 Uncategorized

• release 2.3.1 #243

Full Changelog: 2.3.0...2.3.1

2.2.0

What's Changed

🚀 Features

• return model marginal probabilities via argn.predict_proba #236

📦 Uncategorized

• release 2.2.0 #237

Full Changelog: 2.1.0...2.2.0

2.1.0

What's Changed

🚀 Features

• predict_proba as dataframe with class names #234

📦 Uncategorized

• release 2.1.0 #235

Full Changelog: 2.0.1...2.1.0

2.0.1

What's Changed

🐛 Fixes

• type casting in ANALYZE/ENCODE steps for TABULAR_NUMERIC_DISCRETE columns #226
• do not set_random_state for the same pid #227

📦 Uncategorized

• refine README #228
• release 2.0.1 #229

Full Changelog: 2.0.0...2.0.1

2.0.0

What's Changed

🚀 Features

• sklearn-compatible interfaces for TabularARGN and LanguageModel #219

📦 Uncategorized

• revise README #223
• release 2.0.0 #225

Full Changelog: 1.7.1...2.0.0

1.7.1

What's Changed

🚀 Features

• deprecate max epochs cap #216

📦 Uncategorized

• release 1.7.1 #217

Full Changelog: 1.7.0...1.7.1

1.7.0

What's Changed

🚀 Features

• allow Conditional Generation for columns, that have imputation enabled and are seeded as NULLs #206

📦 Uncategorized

• release 1.7.0 #212

Full Changelog: 1.6.1...1.7.0