src
Hepatitis C Prediction Package
This package provides machine learning tools for Hepatitis C classification using PyTorch neural networks with an interactive Streamlit interface.
Modules
data
Data loading, preprocessing, and dataset creation utilities.
Contains HepatitisDataset class for PyTorch data loading.
models
Neural network model definitions (HepatitisNet with residual connections).
Includes model saving/loading and evaluation utilities.
train
Training utilities and ModelTrainer class for model training workflows.
visualization
Plotting and visualization functions for data exploration and results.
Quick Start
>>> from src.data import load_raw_data, clean_data, prepare_features, HepatitisDataset
>>> from src.models import HepatitisNet, evaluate_model, save_model, load_model
>>> from src.train import ModelTrainer
>>> from torch.utils.data import DataLoader
>>>
>>> # Load and prepare data
>>> data = load_raw_data()
>>> cleaned_data, encoder = clean_data(data)
>>> X, y, imputer = prepare_features(cleaned_data)
>>>
>>> # Create dataset
>>> dataset = HepatitisDataset(X_train, y_train)
>>> train_loader = DataLoader(dataset, batch_size=32, shuffle=True)
>>>
>>> # Create and train model
>>> model = HepatitisNet(input_size=12, hidden_sizes=[128, 64, 32])
>>> trainer = ModelTrainer(model, device='cuda')
>>> history = trainer.train(train_loader, val_loader, epochs=50)
Authors
- Endika Aguirre (https://github.com/Ninjalice)
- Igor Vons (https://github.com/Yngvine)
- Wassim Bouzarhoun (https://github.com/Krypto02)
License
MIT License - See LICENSE file for details.
Repository
https://github.com/Ninjalice/HEPATITIS_C_MODEL
Documentation
1""" 2Hepatitis C Prediction Package 3 4This package provides machine learning tools for Hepatitis C classification 5using PyTorch neural networks with an interactive Streamlit interface. 6 7Modules 8------- 9data 10 11 Data loading, preprocessing, and dataset creation utilities. 12 Contains HepatitisDataset class for PyTorch data loading. 13 14models 15 16 Neural network model definitions (HepatitisNet with residual connections). 17 Includes model saving/loading and evaluation utilities. 18 19train 20 21 Training utilities and ModelTrainer class for model training workflows. 22 23visualization 24 25 Plotting and visualization functions for data exploration and results. 26 27Quick Start 28----------- 29>>> from src.data import load_raw_data, clean_data, prepare_features, HepatitisDataset 30>>> from src.models import HepatitisNet, evaluate_model, save_model, load_model 31>>> from src.train import ModelTrainer 32>>> from torch.utils.data import DataLoader 33>>> 34>>> # Load and prepare data 35>>> data = load_raw_data() 36>>> cleaned_data, encoder = clean_data(data) 37>>> X, y, imputer = prepare_features(cleaned_data) 38>>> 39>>> # Create dataset 40>>> dataset = HepatitisDataset(X_train, y_train) 41>>> train_loader = DataLoader(dataset, batch_size=32, shuffle=True) 42>>> 43>>> # Create and train model 44>>> model = HepatitisNet(input_size=12, hidden_sizes=[128, 64, 32]) 45>>> trainer = ModelTrainer(model, device='cuda') 46>>> history = trainer.train(train_loader, val_loader, epochs=50) 47 48Authors 49------- 50- Endika Aguirre (https://github.com/Ninjalice) 51- Igor Vons (https://github.com/Yngvine) 52- Wassim Bouzarhoun (https://github.com/Krypto02) 53 54License 55------- 56MIT License - See [LICENSE](https://github.com/Ninjalice/HEPATITIS_C_MODEL/blob/main/LICENSE) file for details. 57 58Repository 59---------- 60https://github.com/Ninjalice/HEPATITIS_C_MODEL 61 62Documentation 63------------- 64https://ninjalice.github.io/HEPATITIS_C_MODEL/src.html 65""" 66 67__version__ = "0.1.0" 68__author__ = "Ninjalice" 69__license__ = "MIT" 70 71# Control what modules are exposed by this package 72__all__ = [ 73 "data", 74 "models", 75 "train", 76 "visualization" 77]