This package provides fundamental operation on reshaping dataframes for Keras LSTM input
Project description
This is a tool used to reshape dataset in pandas for Keras LSTM model
This module provides a single function that converts a multivariate time series dataframe into a supervised learning - style dataframe by flattening and shifting each series along a given lagging period. For example, when one tries to use keras on a 2-D tensor of shape (total_time_steps, num_features), it's required to reshape the tensor into a 3-D tensor of input_shape (num_features, time_steps, batch_size)
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
lstm_preprocess-0.3.0.tar.gz
(1.4 kB
view hashes)
Built Distribution
Close
Hashes for lstm_preprocess-0.3.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a5675200c50aa4c2c7cee6c8d978b2d2214c5feae6f53ee89d55d25af405a17b |
|
MD5 | 4261bce24671fb9f8e27de25a32bbe38 |
|
BLAKE2b-256 | f7cbad31276265b373772bd42acd3b918b58e24ad10f6095adc30286804bf764 |