Clean up data files, remove old example data

Authored by kqr on Jul 30 2019, 10:36 AM.

Description

Clean up data files, remove old example data

Summary:
We had to switch from CSV-with-semicolons-as-delimiters to
CSV-with-actual-commas-as-delimiters because Weka does not want to read the
former. I also manually recoded some of the data to UTF-8, so there may be some
weird characters in there still. I can still not figure out what encoding Excel
used when exporting the file...

Test Plan:
Run the program, pick the menu alternatives. I get output similar to

CHOOSE METHOD WITH A NUMBER

  1. Train data
  2. Generate people
  3. Exit

2
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Female)
Observation(id=01801307, count=1, Gender=Female)
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Male)
Observation(id=01801307, count=1, Gender=Female)
Observation(id=01801307, count=1, Gender=Male)

CHOOSE METHOD WITH A NUMBER

  1. Train data
  2. Generate people
  3. Exit

1

Results

Correctly Classified Instances 40 100 %
Incorrectly Classified Instances 0 0 %
Kappa statistic 1
Mean absolute error 0.0358
Root mean squared error 0.0551
Relative absolute error 117.4501 %
Root relative squared error 153.8336 %
Total Number of Instances 40

Reviewers: kqr, skruttet

Reviewed By: skruttet

Differential Revision: https://dev.xkqr.org/D10

Details

Committed
Christoffer Stjernlöf <christoffer@loop54.com>Jul 30 2019, 10:36 AM
Pushed
kqrJul 30 2019, 10:36 AM
Reviewer
skruttet
Differential Revision
D10: Clean up data files, remove old example data
Parents
rMLVP490207af400a: Add /target to .gitignore
Branches
Unknown
Tags
Unknown
References
HEAD -> master
Christoffer Stjernlöf <christoffer@loop54.com> committed rMLVP06ffcd7a88cd: Clean up data files, remove old example data (authored by kqr).Jul 30 2019, 10:36 AM