Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Reproduction attempt #2

Closed
nuest opened this issue Oct 31, 2019 · 1 comment
Closed

Reproduction attempt #2

nuest opened this issue Oct 31, 2019 · 1 comment

Comments

@nuest
Copy link
Contributor

nuest commented Oct 31, 2019

Thanks for providing data and code together with your article! I've attempted a reproduction as part of a manuscript under development, and was partly successful, which is really great. 馃帀

(and thanks for already fixing the license, #1)

Here is what I achieved and the changes I made and how far I got. I worked with the file Data Analysis and Visualization.R, as I was unsure about the differences between it and the Markdown file.

  • add a few lines of code to download the data at the start
  • make some educated guesses to fix non-existing objects: X10, USA2
  • make an educated guess to use file Input-Data/usa_trt_varnames_plots_0913.csv instead of the missing usa_trt_varnames.csv
  • moved CHECK MULTICOLLINEARITY code down so that usa.trt.cl is found (created later in the script
  • make number of runs and iterations configurable, so that I had some results with much smaller waiting time > I don't really worry about the actual results right now, just want to make sure the code runs, I'm happy to run the long analysis (parallelize it?) when the code works.
  • load library cluster so that silhouette() is available
  • added a guess where US_tract_2010.shp could be downloaded
  • try to fix deprecated ggplot2 function usage
  • add a gitignore file, ignoring some R-specific stuff but also the data folders
  • fixed a minor typo in the readme, replace some placeholders there, apply common Markdown formatting, fix headline formatting

You can see the changes in this comparison: master...nuest:master

Results

I have a dendogram (of course looks different because of smaller number of runs)!

image

I have Figure 10 (sort of) !

image

I have another figure that looks quite bad...

image

I look forward to your comments regarding the changes. It would be great if you could help resolving some of the guesses I had to make.

@geoss
Copy link
Owner

geoss commented Oct 31, 2019

DO you want to send a pull request? That'll make it easy for me to review changes. Thanks. -SS

@geoss geoss closed this as completed Oct 31, 2019
@nuest nuest mentioned this issue Nov 4, 2019
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants