inductive bias learning
Project description
IBLM:Inductive Bias Learning Models
What is IBLM?
IBLM (Inductive Bias Learning) is a new machine learning modeling method that uses LLM to infer the structure of the model itself from the data set and outputs it as Python code. The learned model (code model) can be used as a machine learning model to predict a new dataset.
How to Use
Setting
- Installation
pip install iblm
- OpenAI API key settings
os.environ["OPENAI_API_KEY"] = "OPENAI_API_KEY"
Binary classification
- Model Definition
from iblm import IBLMClassifier
# Load LLM via LangChain. (GPT-4 recommended)
llm_model = OpenAI(temperature=0, model_name = 'gpt-4')
params = {'columns_name': True}
iblm = IBLMClassifier(llm_model = llm_model, params=params)
- Model Learning
file_path = 'Specify the directory to output python files.'
model = iblm.fit(x_train, y_train, model_name = 'model_name', file_path=file_path)
- Model Predictions
y_proba = iblm.predict(x_test)
Notebooks
Use the link below to try it out immediately on Google colab.
Supported Models
Currently, the recommended model is GPT-4
Contributor
Backstory
This idea is based on langchain-tools, which was created in an attempt to make LLM learn LightGBM.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
iblm-0.1.45.tar.gz
(6.3 kB
view hashes)
Built Distribution
iblm-0.1.45-py3-none-any.whl
(10.8 kB
view hashes)