Skip to main content

Time Series Analysis for Simulation of Technological Processes

Project description

[![ru](https://img.shields.io/badge/lang-ru-red.svg)](README.ru.md)

# Time Series Anomaly detection based on Deep Learning

TSAD is a Python module created for solving Anomaly Detection problems with time series data. The module is based on deep learning techniques.

The main meaning of this module are:

  1. Forecast a multivariate Time Series (TS) one point ahead (Also works for univariate TS)

  2. Compute residuals between forecast and true values

  3. Apply analysis of residuals (default is Hoteling Statics)

  4. Plot and return anomalies

This module allows forecast multi-step ahead both multivariate and univariate time series also.

As forecasting algorithms were implemented or will be implemented:

  • A simple one-layer LSTM network (LSTM)

  • A two-layer LSTM network (DeepLSTM)

  • A bi-directional LSTM network (BLSTM)

  • LSTM encoder-decoder (EncDec-AD)

  • LSTM autoencoder (LSTM-AE);

  • Convolutional LSTM network (ConvLSTM)

  • Convolutional Bi-directional LSTM network (CBLSTM)

  • Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED)

Actually, the possibility of the module allows you to use any own forecasting algorithm, computer of residuals, or evaluator of residuals.

#### Documentation

https://tsad.readthedocs.io/

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

tsad-0.19.4-py3-none-any.whl (81.2 kB view details)

Uploaded Python 3

File details

Details for the file tsad-0.19.4-py3-none-any.whl.

File metadata

  • Download URL: tsad-0.19.4-py3-none-any.whl
  • Upload date:
  • Size: 81.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.10.11

File hashes

Hashes for tsad-0.19.4-py3-none-any.whl
Algorithm Hash digest
SHA256 69feefa56fe6cd0457d1ed8c932a7aebe043770125a7c5a9e6caf058880c5e4d
MD5 f3c9babada5136d45934c75a603b917b
BLAKE2b-256 dbe9eb62b9c568677bf735fef5e30a7462fe91618184674d53cd7908d71321d6

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page