Dimensionality Autoencoder
Project description
dim_ae
Dimensionality Reduction Autoencoder built with Keras TF
Package installation
pip install dimae
Usage example
import pandas as pd
import tensorflow as tf
from dimae.autoencoders.autoencoder import AE
df = pd.DataFrame(...)
n_features = df.shape[1]
output_features = 10
ae = AE(n_features, output_features)
batch_size = 8
epochs = 15
dataset = tf.data.Dataset.from_tensor_slices((df.values.astype('float32'), df.values.astype('float32')))
t_dataset = dataset.batch(batch_size)
ae.compile(optimizer = 'adam', loss = 'mse')
ae.fit(t_dataset, epochs = epoches)
encoder = ae.generate_encoder()
encoder.summary()
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
dimae-0.1.4.tar.gz
(3.9 kB
view hashes)
Built Distribution
dimae-0.1.4-py3-none-any.whl
(4.9 kB
view hashes)