Skip to main content

Time-dependent Canonical Correlation Analysis

Project description

Time-dependent Canonical Correlation Analysis

Canonical Correlation Analysis is a technique in multivariate data analysis for finding correlation and pairs of vectors that maximizes the correlation between a set of paired variables. Many important problems involve recoding time-dependent observations. In order to understand the coupling dynamics between the two sources, spot trends, detect anomalies, in this paper, we introduce the time-dependent canonical correlation analysis (TDCCA), a method of inferring time-dependent canonical vectors of paired variables.

Getting Started

We provide both simulation examples used in our paper. The main computation algorithm is not added into the class method for the convenience of algorithm development for multi-view data. The package saves all the analysis to the given folder and saves the preprocessed data into the hdf5 file. The parallel computing with multi-cores is also allowed and tested in Linux system. This package also provides other algorithms to optimize the function, including cvxpy naive optimization, cvxpy naive admm optimization and two other admm algorithms. For details, see the admm_computation.py file. However, these functions have not been tested thoroughly.

These instructions will get you a copy of the project up running on your local machine for development and testing purposes.

This package is also published in pypi. For a quick installation, try

pip install tdcca 

Prerequisites

What things you need to install the software and how to install them

See setup.py for details of packages requirements. 

Installing from GitHub

Download the packages by using git clone https://github.com/xuefeicao/tdcca.git

python setup.py install

If you experience problems related to installing the dependency Matplotlib on OSX, please see https://matplotlib.org/faq/osx_framework.html

Intro to our package

After installing our package locally, try to import tdcca in your python environment and learn about package's function. Note: our package name in pypi is tdcca. It is recommended that users scale the data before running our package.

from tdcca import *
help(multi_sim)

Examples

The examples subfolder includes simulations provided in the paper. 

Running the tests

The test has been conducted in both Linux and Mac Os.

Built With

  • Python 2.7

Compatibility

  • Python 2.7

Authors

License

This project is licensed under the MIT License - see the LICENSE file for details

Project details


Release history Release notifications

Download files

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

Files for tdcca, version 0.0.0
Filename, size File type Python version Upload date Hashes
Filename, size tdcca-0.0.0-py2-none-any.whl (20.3 kB) File type Wheel Python version py2 Upload date Hashes View hashes
Filename, size tdcca-0.0.0.tar.gz (19.5 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page