A scikit-learn compatible neural network library that wraps MLX.
Project description
SKLX
A scikit-learn compatible neural network library that wraps MLX. Highly inspired by skorch.
Examples
import numpy as np
from sklearn.datasets import make_classification
from mlx import nn
from sklx import NeuralNetClassifier
X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)
y = y.astype(np.int64)
class MyModule(nn.Module):
def __init__(self, num_units=10, nonlin=nn.ReLU()):
super().__init__()
self.dense0 = nn.Linear(20, num_units)
self.nonlin = nonlin
self.dropout = nn.Dropout(0.5)
self.dense1 = nn.Linear(num_units, num_units)
self.output = nn.Linear(num_units, 2)
self.softmax = nn.Softmax(dim=-1)
def forward(self, X, **kwargs):
X = self.nonlin(self.dense0(X))
X = self.dropout(X)
X = self.nonlin(self.dense1(X))
X = self.softmax(self.output(X))
return X
net = NeuralNetClassifier(
MyModule,
max_epochs=10,
lr=0.1,
)
net.fit(X, y)
y_proba = net.predict_proba(X)
In an sklearn Pipeline:
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
pipe = Pipeline([
('scale', StandardScaler()),
('net', net),
])
pipe.fit(X, y)
y_proba = pipe.predict_proba(X)
With grid search:
from sklearn.model_selection import GridSearchCV
params = {
'lr': [0.01, 0.02],
'max_epochs': [10, 20],
'module__num_units': [10, 20],
}
gs = GridSearchCV(net, params, refit=False, cv=3, scoring='accuracy', verbose=2)
gs.fit(X, y)
print("best score: {:.3f}, best params: {}".format(gs.best_score_, gs.best_params_))
Future Roadmap
- Completing Feature Parity with Skorch
Pipeline SupportGrid Search Support- Learning Rate Scheduler https://github.com/lazarust/sklx/issues/6
- Scoring https://github.com/lazarust/sklx/issues/7
- Early Stopping https://github.com/lazarust/sklx/issues/8
- Checkpointing https://github.com/lazarust/sklx/issues/9
- Parameter Freezing https://github.com/lazarust/sklx/issues/10
- Progress Bar https://github.com/lazarust/sklx/issues/11
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
sklx-0.0.9.tar.gz
(233.0 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
sklx-0.0.9-py3-none-any.whl
(7.5 kB
view details)
File details
Details for the file sklx-0.0.9.tar.gz.
File metadata
- Download URL: sklx-0.0.9.tar.gz
- Upload date:
- Size: 233.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
89773ac98259c00e0781ad31fd6642be87569112b57454cd5271fb1106f4234b
|
|
| MD5 |
2ae71a564fc74365a5548eefc74b3267
|
|
| BLAKE2b-256 |
ed66dce9d8948a43fe490a454ff0a62fd4900b2c311b760bcea755b07ae94abc
|
Provenance
The following attestation bundles were made for sklx-0.0.9.tar.gz:
Publisher:
python-publish.yml on lazarust/sklx
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
sklx-0.0.9.tar.gz -
Subject digest:
89773ac98259c00e0781ad31fd6642be87569112b57454cd5271fb1106f4234b - Sigstore transparency entry: 829620480
- Sigstore integration time:
-
Permalink:
lazarust/sklx@29796f40d97fc59e8c326b1f197aaa982685e25e -
Branch / Tag:
refs/tags/v0.0.9 - Owner: https://github.com/lazarust
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@29796f40d97fc59e8c326b1f197aaa982685e25e -
Trigger Event:
release
-
Statement type:
File details
Details for the file sklx-0.0.9-py3-none-any.whl.
File metadata
- Download URL: sklx-0.0.9-py3-none-any.whl
- Upload date:
- Size: 7.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3e8f1b1ba2f76a69d5e86c055c94998d17d1dfdb125defc2fd29ce09bc7a023b
|
|
| MD5 |
a57aae1b6b512d94bc2d4b80edc9c6d4
|
|
| BLAKE2b-256 |
5548745fe26f7c709c530cc5a47a38ad2b1bf1f945f9b6cde0aa2bb6279133e1
|
Provenance
The following attestation bundles were made for sklx-0.0.9-py3-none-any.whl:
Publisher:
python-publish.yml on lazarust/sklx
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
sklx-0.0.9-py3-none-any.whl -
Subject digest:
3e8f1b1ba2f76a69d5e86c055c94998d17d1dfdb125defc2fd29ce09bc7a023b - Sigstore transparency entry: 829620494
- Sigstore integration time:
-
Permalink:
lazarust/sklx@29796f40d97fc59e8c326b1f197aaa982685e25e -
Branch / Tag:
refs/tags/v0.0.9 - Owner: https://github.com/lazarust
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@29796f40d97fc59e8c326b1f197aaa982685e25e -
Trigger Event:
release
-
Statement type:
