{"id":24680,"library":"tabicl","title":"TabICL","description":"TabICL (Tabular In-Context Learning) is a state-of-the-art tabular foundation model for few-shot and zero-shot learning on tabular data. Current version 2.1.1, actively maintained.","status":"active","version":"2.1.1","language":"python","source_language":"en","source_url":"https://github.com/autogluon/tabicd","tags":["tabular","foundation model","few-shot","machine learning","deep learning"],"install":[{"cmd":"pip install tabicl","lang":"bash","label":"Install from PyPI"}],"dependencies":[{"reason":"TabICL requires PyTorch for model inference and training.","package":"torch","optional":false},{"reason":"Used for data loading and preprocessing.","package":"pandas","optional":false}],"imports":[{"wrong":"from tabicl import TabICL","symbol":"TabICLClassifier","correct":"from tabicl import TabICLClassifier"},{"wrong":"from tabicl import TabICL","symbol":"TabICLRegressor","correct":"from tabicl import TabICLRegressor"},{"wrong":"from tabicl import TabICL","symbol":"InferenceConfig","correct":"from tabicl import InferenceConfig"}],"quickstart":{"code":"import pandas as pd\nfrom tabicl import TabICL\n\n# Load or create a pandas DataFrame with your data\n# data = pd.read_csv('your_data.csv')\n\n# Initialize the model\nmodel = TabICL(pretrained=True)\n\n# Example: predict on a dataset (adjust as per your task)\n# predictions = model.predict(data)\nprint('TabICL model loaded successfully')","lang":"python","description":"Basic usage of TabICL for tabular data prediction."},"warnings":[{"fix":"Ensure Python 3.10+ and upgrade PyTorch to 2.0+. Do not install older tabicl versions.","message":"TabICL v2.x requires Python >=3.10 and PyTorch >=2.0. Older versions (1.x) are incompatible and use different APIs.","severity":"breaking","affected_versions":">=2.0.0"},{"fix":"Impute missing values before passing data. Use pandas .fillna() or similar.","message":"TabICL expects data in pandas DataFrame format with no missing values. NaN or None will cause silent errors or poor performance.","severity":"gotcha","affected_versions":"All"}],"env_vars":null,"search_vec":"'2.1.1':32 'activ':33 'art':14 'context':6 'current':30 'data':29 'deep':43 'few-shot':19,38 'foundat':16,36 'in-context':4 'learn':7,26,42,44 'machin':41 'maintain':34 'model':17,37 'shot':21,25,40 'state':11 'state-of-the-art':10 'tabicl':1,2 'tabular':3,15,28,35 'version':31 'zero':24 'zero-shot':23","created_at":"2026-05-01T08:14:21.664005+00:00","updated_at":"2026-05-01T08:14:21.664005+00:00","problems":null,"ecosystem":"pypi","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":"2.1.1","cli_name":"","cli_version":null,"type":"library","homepage":null,"github":null,"docs":null,"changelog":null,"pypi":"https://pypi.org/project/tabicl/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["ai-ml","data"],"base_url":null,"auth_type":null,"provenance":{"verified_status":"passing","verified_at":"2026-07-03","last_verified":"2026-07-03","next_check":"2026-08-02","install_tag":null}}