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 details)
Built Distribution
File details
Details for the file lstm_preprocess-0.3.0.tar.gz
.
File metadata
- Download URL: lstm_preprocess-0.3.0.tar.gz
- Upload date:
- Size: 1.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.2 tqdm/4.60.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6f8eb8fa2c2347bdcc5343df16440d48f39c84adf7c1f8385625ea96d547b1f8 |
|
MD5 | 398b16073b0f7b77ee0bf1eac28ddeaa |
|
BLAKE2b-256 | 0e02029d8da782edbb822ca152f3700bf8fc7a54b88d66d281681905a634cab3 |
File details
Details for the file lstm_preprocess-0.3.0-py3-none-any.whl
.
File metadata
- Download URL: lstm_preprocess-0.3.0-py3-none-any.whl
- Upload date:
- Size: 1.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.2 tqdm/4.60.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a5675200c50aa4c2c7cee6c8d978b2d2214c5feae6f53ee89d55d25af405a17b |
|
MD5 | 4261bce24671fb9f8e27de25a32bbe38 |
|
BLAKE2b-256 | f7cbad31276265b373772bd42acd3b918b58e24ad10f6095adc30286804bf764 |