A package for quick&dirty DNN
Project description
QuickNN
An implementation sklearn-like of FeedForward Neural Networks for quick applications. It can handle categorical variables with one-hot-encoding(OHE) method batch-wise as well as continuous variables.
Example
from quicknn import QuickNN
# load X_train, X_test, y_train, y_test
qdnn = QuickNN(list_neurons=[100, 100, 1])
qnn.fit(X_train, y_train)
y_pred = qnn.predict(X_test)
Installing
$ pip install quicknn
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
quicknn-1.0.2.tar.gz
(5.9 kB
view hashes)
Built Distributions
Close
Hashes for quicknn-1.0.2-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a1e75844ffb5d73a6488c7b1e9c27394afe37d766672797d64568a365f24f9c7 |
|
MD5 | 97a29bc05c0e2fe75141566cacf7cedd |
|
BLAKE2b-256 | dec349dd8274ec70d2e4a0879799728b80457e01ec227b95e9e12f4f605583ea |