Local variable importance from a global model
Project description
glvi
glvi is a Python module for machine learning built on top of Scikit-learn and is distributed under the MIT license.
glvi was developed by Mr. Li for evaluating variable importance heterogeneity through a global model built on a large time-space scope.
glvi 0.1.4 was not supporting Python 2.7 and Python 3.4. glvi 0.1.4 and later require Python 3.5 or newer.
glvi requires:
- Python (>= 3.5)
- NumPy (>= 1.11.0)
- SciPy (>= 0.17.0)
- Scikit-learn (>= 0.21.0) User installation
If you already have a working installation of numpy, scipy, pandas and scikit-learn, the easiest way to install glvi is using ``pip`` ::
pip install -U glvi
User guide
Compute local variable importance based on decrease in node impurity ::
from glvi import todi
r_t = todi.lovim(500, max_features=0.3, n_jobs=-1)
r_t.fit(train_x, train_y)
local_variable_importance = r_t.compute_feature_importance(X,Y,partition_feature = partition_feature, norm=True,n_jobs=-1)
or compute local variable importance based on decrease in accuracy ::
from glvi import meda
r_m = meda.lovim(500, max_features=0.3, n_jobs=-1)
r_m.fit(train_x, train_y_
local_variable_importance = r_m.compute_feature_importance(X,Y,partition_feature = partition_feature, norm=True,n_jobs=-1)
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
glvi-0.1.7.tar.gz
(6.8 kB
view details)
File details
Details for the file glvi-0.1.7.tar.gz
.
File metadata
- Download URL: glvi-0.1.7.tar.gz
- Upload date:
- Size: 6.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.21.0 setuptools/49.6.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
69803cbc5243e5f3cca9bdcd5214920c7451c49dc1cf89a6f022e8de60a2d23d
|
|
MD5 |
cd14c95e92b204649c7c498057ee3162
|
|
BLAKE2b-256 |
2f7dc6db1f716e3c4ed50246798b792de6ac27f17dfddf50503509b9e059d876
|