Constrained linear regression in scikit-learn style
Project description
constrained-linear-regression
This is a Python implementation of constrained linear regression in scikit-learn style. The current version supports upper and lower bound for each slope coefficient.
It was developed after this question https://stackoverflow.com/questions/50410037
Installation:
pip install constrained-linear-regression
You can use this model, for example, if you want all coefficients to be non-negative:
from constrained_linear_regression import ConstrainedLinearRegression
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression
X, y = load_boston(return_X_y=True)
model = ConstrainedLinearRegression(nonnegative=True)
model.fit(X, y)
print(model.intercept_)
print(model.coef_)
The output will be like
-36.99292986145538
[0. 0.05286515 0. 4.12512386 0. 8.04017956
0. 0. 0. 0. 0. 0.02273805
0. ]
You can also impose arbitrary bounds for any coefficients you choose
model = ConstrainedLinearRegression()
min_coef = np.repeat(-np.inf, X.shape[1])
min_coef[0] = 0
min_coef[4] = -1
max_coef = np.repeat(4, X.shape[1])
max_coef[3] = 2
model.fit(X, y, max_coef=max_coef, min_coef=min_coef)
print(model.intercept_)
print(model.coef_)
The output will be
24.060175576410515
[ 0. 0.04504673 -0.0354073 2. -1. 4.
-0.01343263 -1.17231216 0.2183103 -0.01375266 -0.7747823 0.01122374
-0.56678676]
You can also set coefficients lasso
and ridge
if you want to apply the
corresponding penalties. For lasso
, however, the output might not be exactly
equal to the result of sklearn.linear_model.Lasso
due to the difference
in the optimization algorithm.
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
Built Distribution
File details
Details for the file constrained_linear_regression-0.0.5.tar.gz
.
File metadata
- Download URL: constrained_linear_regression-0.0.5.tar.gz
- Upload date:
- Size: 6.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/7.1.0 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f7a8721d4cbe5b5a5a450c01c728bb25ae9b7efde39a6ff2ec4b36c5af432e85 |
|
MD5 | 9235e043c72cdbf2313f3f89071eadba |
|
BLAKE2b-256 | f60b12aa3fdadf40e1c9f1bc3a6c53ceab193c7ba01c51a7b995d2aca7fd8a78 |
Provenance
File details
Details for the file constrained_linear_regression-0.0.5-py3-none-any.whl
.
File metadata
- Download URL: constrained_linear_regression-0.0.5-py3-none-any.whl
- Upload date:
- Size: 7.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/7.1.0 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e628b340a920beb50294f6c6f50ff993e602b259f3c7eeb9b15889f23c10bfaa |
|
MD5 | fa4b785d04446a933107391a4417d969 |
|
BLAKE2b-256 | 5d829d7f62455227d7631e267ceead8d99ea08a1216684446c1a2051a14def1a |