Metadata-Version: 2.1
Name: icgc-survival
Version: 0.2.2
Summary: A framework for survival prediction and analysis of ICGC datasets
Home-page: https://github.com/julianspaeth/icgc-survival
Author: Julian Späth
Author-email: spaethju@posteo.de
License: MIT License
Download-URL: https://github.com/julianspaeth/icgc-survival/archive/v0.1.tar.gz
Keywords: survival-analysis,survival-prediction,machine-learning,random-survival-forest,icgc
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Topic :: Software Development :: Build Tools
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Description-Content-Type: text/markdown
Requires-Dist: requests
Requires-Dist: pandas
Requires-Dist: lifelines
Requires-Dist: numpy
Requires-Dist: random-survival-forest

# Random Survival Forest

The ICGC-survival package provides an easy oppurtinity to perform survival prediction on ICGC datasets.

## Installation
```sh
$ pip install icgc-survival
```

## Contribute

- Source Code: https://github.com/julianspaeth/icgc-survival

## Getting Started

```python
>>> from download_helper import login, download_file_by_project
>>> from feature_creator import extract_gene_affected_counts
>>> from label_creator import extract_survival_labels

>>> token = login(username, password)
>>> df = download_file_by_project(token=token, filetype="simple_somatic_mutation", release=28, project_code="ALL-US")
>>> ssm_gene_affected_counts = extract_gene_affected_counts(df)
>>> labels, features = extract_survival_labels(ssm_gene_affected_counts, donors)

>>> x, x_test, y, y_test = train_test_split(features, labels, shuffle=True, test_size=0.33, random_state=10)
...
```

## Support

If you are having issues or feedback, please let me know.

julian.spaeth@student.uni-tuebinden.de

## License
MIT

