Comments (3)
Minimal breaking example. Data set:
purple-seed-stain , normal gt-norm upper-areas 80-89 abnorm no-yellow-halos w-s-marg lt-1/8 absent absent absent norm no absent tan absent absent absent none absent diseased colored absent norm absent norm , num_501
purple-seed-stain , normal lt-norm whole-field lt-80 abnorm no-yellow-halos w-s-marg lt-1/8 absent absent absent abnorm yes absent tan absent absent absent none absent diseased colored absent norm absent norm , num_502
Test set:
charcoal-rot , normal gt-norm whole-field lt-80 abnorm absent dna dna absent absent absent abnorm yes absent tan absent absent absent black present norm dna absent norm absent norm , test_item
Bad output:
Analogical Set
Total Frequency = 196608
+-------------------+---------+--------+------------+
| Class | Item | Score | Percentage |
+-------------------+---------+--------+------------+
| purple-seed-stain | num_501 | 49152 | 25.000% |
| purple-seed-stain | num_502 | 147456 | 75.000% |
+-------------------+---------+--------+------------+
Statistical Summary
+-------------------+--------+------------+
| Class | Score | Percentage |
+-------------------+--------+------------+
| purple-seed-stain | 131072 | 66.667% |
+-------------------+--------+------------+
| Total | 196608 | |
+-------------------+--------+------------+
Expected result:
Statistical Summary
purple-seed-stain 327680 100.000%
------
327680
Analogical Set
Total Frequency = 327680
purple-seed-stain num_501 49152 15.000%
purple-seed-stain num_502 278528 85.000%
from algorithm-am.
Broke before 2.38. Obviously I need to add extensive testing for accuracy. I always accepted that matching accuracy of the finnverb dataset was good enough, but that's really laziness.
from algorithm-am.
Bad commit:
commit 336cbde30e7c82f1fa8d0655b026a7591a725bf4
Author: Nathan Glenn <[email protected]>
Date: Sun Feb 9 17:51:46 2014 -0800
add carry_pointer macro
I don't really like how this macro looks; it's not very transparent to
me. However, this allows us to gather all of the carrying logic into
one place.
from algorithm-am.
Related Issues (20)
- allow comments in data files HOT 1
- sort results by order of probability
- give a warning for commas in a nocommas format file
- output version with help in analogize.pl
- AM::classify should die if test_item is undef or the wrong type
- add detailed tests of statistical results
- document data sets
- improve analogize documentation HOT 1
- Dataset/Item creation API request
- add to_str method to Item
- scores should contain all classes
- change comment to ID
- rename homogeneous variable in gangs
- percentage format change and accessor
- InstallGuide plugin didn't work HOT 1
- R and/or Python versions HOT 5
- move dzil smoke test to GitHub action HOT 1
- intermittent failure of finnverb test HOT 1
- improve logging
- non-ASCII characters scrambled in output
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from algorithm-am.