Skip to main content

Pliable Lasso

Project description

===============================

Author: Stephen Anthony Rose

Original paper: [https://arxiv.org/abs/1712.00484]

```
pip install plasso
```

Abstract
--------

We propose a generalization of the lasso that allows the model coefficients to vary as a function of a general set of modifying variables. These modifiers might be variables such as gender, age or time. The paradigm is quite general, with each lasso coefficient modified by a sparse linear function of the modifying variables Z. The model is estimated in a hierarchical fashion to control the degrees of freedom and avoid overfitting. The modifying variables may be observed, observed only in the training set, or unobserved overall. There are connections of our proposal to varying coefficient models and high-dimensional interaction models. We present a computationally efficient algorithm for its optimization, with exact screening rules to facilitate application to large numbers of predictors. The method is illustrated on a number of different simulated and real examples.

Example
-------

```python
from plasso import PliableLasso

# Input data looks just like sklearn except an extra matrix Z
y = target_data()
x = data() # Main effects data
z = modifying_data() # Data used to modify the estimate coefficients for X

# Fit model
model = PliableLasso()
model.fit(x, z, y)

# Cool things to do afterwards
y_hat = model.predict(x, z)

```

Check out the `example.py` file to see more ways to use it.

Installation / Usage
--------------------

To install use pip:

$ pip install plasso


Or clone the repo:

$ git clone https://github.com/arose13/PliableLasso.git
$ python setup.py install

Also for large data sets I recommend install `pytorch`

Contributing
------------

Me (Stephen Anthony Rose)

If you want to add and improve things be my guest.

Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

plasso-1.20190329.1200.tar.gz (12.7 kB view details)

Uploaded Source

File details

Details for the file plasso-1.20190329.1200.tar.gz.

File metadata

  • Download URL: plasso-1.20190329.1200.tar.gz
  • Upload date:
  • Size: 12.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.9.1 tqdm/4.28.1 CPython/3.6.6

File hashes

Hashes for plasso-1.20190329.1200.tar.gz
Algorithm Hash digest
SHA256 d346534fd041ceca7f1f594023e6400727695e642833f674c2ec3b6c06524a68
MD5 12ddee86accd29133ed73443cc8c4abb
BLAKE2b-256 2e90c0b41fc7c69b8f1a7b6d39e396090e0a6f267d41efc1a95e1a8248edb253

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page