lancetnic 1.2.0

A tool for working with text data

LANCETNIC 1.2.0

The LANCETNIC library is a tool for working with text data: learning, analysis, and inference.

Tasks to be solved:

• Binary classification (spam/not spam; patient is sick/not sick; loan approved/refusal, etc.)

🚀 Installing:

Install with CUDA

To work with the GPU, it is recommended to install PyTorch with CUDA support (OPTIONAL):

pip install torch==2.5.1+cu124 torchaudio==2.5.1+cu124 torchvision==0.20.1+cu124 --index-url https://download.pytorch.org/whl/cu124

Then install lancetnic:

pip install lancetnic

👥 Autors

• Lancet52

📄 Documentation

Документация на русском

Documentation in English

Quick start

Training:

from lancetnic.models import LancetBC
from lancetnic import Binary

model = Binary()
model.train(model_name=LancetBC, # A model for binary classification
            train_path="train.csv", # The path to the training dataset
            val_path="val.csv", # Path to the validation dataset
            num_epochs=50 # Number of training epochs
            )
            

Inferece:

from lancetnic import Predictor
pred=Predictor()
prediction=pred.predict(model_path="best_model.pt",
             text="Your text"
             )

print(prediction)