-
Notifications
You must be signed in to change notification settings - Fork 130
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit 966aa2e
Showing
12 changed files
with
635 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,18 @@ | ||
= Decision Tree | ||
|
||
A ruby library which implements ID3 (information gain) algorithm for decision tree learning. Currently, continuous and discrete datasets can be learned. | ||
|
||
- Discrete model assumes unique labels & can be graphed and converted into a png for visual analysis | ||
- Continuous looks at all possible values for a variable and iteratively chooses the best threshold between all possible assignments. This results in a binary tree which is partitioned by the threshold at every step. (e.g. temperate > 20C) | ||
|
||
== Features | ||
- ID3 algorithms for continuous and discrete cases, with support for incosistent datasets. | ||
- Graphviz component to visualize the learned tree (http://rockit.sourceforge.net/subprojects/graphr/) | ||
- Support for multiple, and symbolic outputs and graphing of continuos trees. | ||
- Returns default value when no branches are suitable for input | ||
|
||
== Implementation | ||
- Ruleset is a class that trains an ID3Tree with 2/3 of the training data, converts it into a set of rules and prunes the rules with the remaining 1/3 of the training data (in a C4.5 way). | ||
- Bagging is a bagging-based trainer (quite obvious), which trains 10 Ruleset trainers and when predicting chooses the best output based on voting. | ||
|
||
Blog post with explanation & examples: http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
require 'rubygems' | ||
require 'decisiontree' | ||
include DecisionTree | ||
|
||
# ---Continuous----------------------------------------------------------------------------------------- | ||
|
||
# Read in the training data | ||
training, attributes = [], nil | ||
File.open('data/continuous-training.txt','r').each_line { |line| | ||
data = line.strip.chomp('.').split(',') | ||
attributes ||= data | ||
training.push(data.collect {|v| (v == 'healthy') || (v == 'colic') ? (v == 'healthy' ? 1 : 0) : v.to_f}) | ||
} | ||
|
||
# Remove the attribute row from the training data | ||
training.shift | ||
|
||
# Instantiate the tree, and train it based on the data (set default to '1') | ||
dec_tree = ID3Tree.new(attributes, training, 1, :continuous) | ||
dec_tree.train | ||
|
||
#---- Test the tree.... | ||
|
||
# Read in the test cases | ||
# Note: omit the attribute line (first line), we know the labels from the training data | ||
test = [] | ||
File.open('data/continuous-test.txt','r').each_line { |line| | ||
data = line.strip.chomp('.').split(',') | ||
test.push(data.collect {|v| (v == 'healthy') || (v == 'colic') ? (v == 'healthy' ? 1 : 0) : v.to_f}) | ||
} | ||
|
||
# Let the tree predict the output and compare it to the true specified value | ||
test.each { |t| predict = dec_tree.predict(t); puts "Predict: #{predict} ... True: #{t.last}"} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
4.60000,139.00000,101.00000,28.80000,7.64000,13.80000,265.06000,1.50000,0.60000,60.00000,12.00000,40.00000,40.00000,3.52393,0.20000,17.61965,healthy. | ||
4.30000,139.00000,101.00000,26.20000,3.61000,16.10000,518.74103,1.90000,0.01000,68.00000,12.00000,38.00000,36.00000,5.70834,0.20000,28.54170,healthy. | ||
4.20000,139.00000,101.00000,29.20000,4.96000,13.00000,265.06000,2.10000,0.50000,62.00000,12.00000,39.00000,44.00000,3.44906,0.20000,17.24530,healthy. | ||
4.40000,141.00000,103.00000,28.30000,12.65000,14.10000,197.60699,2.20000,0.10000,66.00000,12.00000,32.00000,44.00000,3.30135,0.20000,16.50675,healthy. | ||
4.50000,136.00000,101.00000,26.10000,3.27000,13.40000,300.61499,1.40000,0.01000,68.00000,16.00000,33.00000,50.00000,6.94524,0.70000,9.92177,healthy. | ||
4.30000,151.00000,112.00000,21.90000,42.66000,21.40000,613.52301,11.50000,172.89999,68.00000,26.00000,63.00000,92.00000,2.69917,0.50000,5.39834,colic. | ||
3.00000,145.00000,103.00000,22.30000,83.93000,22.70000,476.97101,43.40000,139.50000,86.00000,60.00000,67.00000,68.00000,2.73668,0.20000,13.68340,colic. | ||
3.40000,134.00000,98.00000,25.90000,90.15000,13.50000,265.06000,2.10000,1.30000,66.00000,20.00000,40.00000,52.00000,3.13565,0.50000,6.27130,colic. | ||
2.90000,136.00000,92.00000,34.70000,5.81000,12.20000,243.71800,4.20000,22.80000,61.00000,20.00000,41.00000,48.00000,3.20928,0.20000,16.04640,colic. | ||
3.80000,140.00000,99.00000,28.20000,88.92000,16.60000,695.82800,7.00000,2.60000,60.00000,28.00000,49.00000,80.00000,1.67106,0.50000,3.34212,colic. | ||
3.70000,143.00000,105.00000,21.60000,93.67000,20.10000,265.06000,4.60000,38.80000,68.00000,16.00000,43.00000,48.00000,3.51757,0.50000,7.03514,colic. | ||
3.70000,142.00000,103.00000,27.00000,100.24000,15.70000,386.71301,2.30000,0.01000,85.00000,40.00000,45.00000,48.00000,2.81077,0.50000,5.62154,colic. | ||
3.20000,138.00000,99.00000,29.80000,80.77000,12.40000,224.11301,2.30000,3.90000,61.00000,24.00000,37.00000,40.00000,3.32568,0.50000,6.65136,colic. |
Oops, something went wrong.