Skip to content

Latest commit

 

History

18 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

Machine Learning Assignment

coursera John Hopkins - October 2017

Executive Summary

Results

  • Initial pml-training.csv data was randomly partitioned 60%/20%/20% into Training, Testing & Validation for Cross Validation
  • Out of Sample Error was determined using Accuracy metric - 98% on Testing and 99% on Validation

Pre- Processing

  • Reduced the columns from 160 to 59 by removing those which had greater than 20% missing values
  • Best fit model was found using unstandardised data and removing some variables that were highly correlated with others
  • Also tried standardising (centre & scale) and PCA to compress predictors but this actually gave lower Accuracy in the model

About

coursera John Hopkins Machine Learning Assignment

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages