README.md

Sequential Data Classification

A comprehensive pipeline to analyze Sequential Data with Machine learning algorithm.

Problem description:

• Use industrial data as input to classify output with eight categories.

Outline

• Transforming raw data
• Visualization
• Model
• Simulation
• Summary
• Reference

Transforming raw data

Transform the raw text data into csv file data.

• Code

Visualization

Visualize the raw data in GIF format.

• Code

• Graph

Model

Dynamic Time Warping + K Nearest Neighbors

• Dynamic Time Warping

• K Nearest Neighbors

• Code

Simulation

Build some cross-validation functions to examine the performance of model.

• Code

Summary

• Code

Reference

Montero, P and Vilar, J.A. (2014) TSclust: An R Package for Time Series Clustering. Journal of Statistical Software, http://www.jstatsoft.org/v62/i01/