ai4r 1.12 → 1.13

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. data/README.rdoc +7 -12
  2. data/examples/classifiers/simple_linear_regression_example.csv +159 -0
  3. data/examples/classifiers/simple_linear_regression_example.rb +15 -0
  4. data/examples/clusterers/clusterer_example.rb +56 -0
  5. data/examples/neural_network/backpropagation_example.rb +2 -1
  6. data/lib/ai4r.rb +3 -1
  7. data/lib/ai4r/classifiers/id3.rb +6 -2
  8. data/lib/ai4r/classifiers/multilayer_perceptron.rb +1 -1
  9. data/lib/ai4r/classifiers/naive_bayes.rb +24 -21
  10. data/lib/ai4r/classifiers/simple_linear_regression.rb +118 -0
  11. data/lib/ai4r/clusterers/average_linkage.rb +3 -3
  12. data/lib/ai4r/clusterers/bisecting_k_means.rb +2 -2
  13. data/lib/ai4r/clusterers/centroid_linkage.rb +3 -3
  14. data/lib/ai4r/clusterers/clusterer.rb +0 -11
  15. data/lib/ai4r/clusterers/complete_linkage.rb +3 -3
  16. data/lib/ai4r/clusterers/diana.rb +2 -2
  17. data/lib/ai4r/clusterers/k_means.rb +123 -21
  18. data/lib/ai4r/clusterers/median_linkage.rb +3 -3
  19. data/lib/ai4r/clusterers/single_linkage.rb +4 -4
  20. data/lib/ai4r/clusterers/ward_linkage.rb +4 -4
  21. data/lib/ai4r/clusterers/ward_linkage_hierarchical.rb +48 -0
  22. data/lib/ai4r/clusterers/weighted_average_linkage.rb +3 -3
  23. data/lib/ai4r/data/data_set.rb +12 -3
  24. data/lib/ai4r/data/proximity.rb +22 -0
  25. data/lib/ai4r/neural_network/backpropagation.rb +26 -15
  26. data/test/classifiers/id3_test.rb +12 -0
  27. data/test/classifiers/multilayer_perceptron_test.rb +1 -1
  28. data/test/classifiers/naive_bayes_test.rb +18 -18
  29. data/test/classifiers/simple_linear_regression_test.rb +37 -0
  30. data/test/clusterers/k_means_test.rb +75 -8
  31. data/test/clusterers/ward_linkage_hierarchical_test.rb +81 -0
  32. data/test/data/data_set_test.rb +8 -0
  33. data/test/data/proximity_test.rb +7 -1
  34. metadata +96 -55
data/README.rdoc CHANGED
@@ -1,7 +1,6 @@
1
1
  = Introduction
2
2
 
3
- This project aims to produce ruby implementations of
4
- algorithms covering several Artificial intelligence fields.
3
+ This project aims to produce ruby implementations of algorithms covering several Artificial intelligence fields.
5
4
 
6
5
  = Where can I find the lastest code and info on this project?
7
6
 
@@ -11,13 +10,13 @@ http://www.ai4r.org
11
10
 
12
11
  1. Install the gem:
13
12
 
14
- gem install ai4r
13
+ gem install ai4r
15
14
 
16
15
  2. Include require statements in your code:
17
16
 
18
17
  require "rubygems"
19
18
  require "ai4r"
20
-
19
+
21
20
  = More Info
22
21
 
23
22
  * AI4R Project site: http://www.ai4r.org
@@ -31,14 +30,10 @@ If you have questions or constructive comments about this project send it to me:
31
30
  = Contributors
32
31
 
33
32
  This project was created and is maintained by {Sergio Fierens}[https://github.com/SergioFierens].
34
- There are other (great and absolutely cool) people who have donated time and code to make this project better, including:
35
-
36
- * {Thomas Kern}[https://github.com/thomaskern]
37
- * {Luis Parravicini}[https://github.com/luisparravicini]
38
- * {Kevin Menard}[https://github.com/nirvdrum]
33
+ There are other (great and absolutely cool) people who have donated time and code to make this project better. You can check out the complete AI4R contributors list: http://github.com/SergioFierens/ai4r/graphs/contributors.
39
34
 
40
35
  = Disclaimer
41
36
 
42
- This software is provided "as is" and without any express or implied warranties,
43
- including, without limitation, the implied warranties of merchantibility and
44
- fitness for a particular purpose.
37
+ This software is provided "as is" and without any express or implied warranties,
38
+ including, without limitation, the implied warranties of merchantibility and
39
+ fitness for a particular purpose.
data/examples/classifiers/simple_linear_regression_example.csv ADDED
@@ -0,0 +1,159 @@
1
+ symboling,normalized-losses,wheel-base,length,width,height,curb-weight,engine-size,bore,stroke,compression-ratio,horsepower,peak-rpm,city-mpg,highway-mpg,class
2
+ 2,164,99.8,176.6,66.2,54.3,2337,109,3.19,3.4,10,102,5500,24,30,13950
3
+ 2,164,99.4,176.6,66.4,54.3,2824,136,3.19,3.4,8,115,5500,18,22,17450
4
+ 1,158,105.8,192.7,71.4,55.7,2844,136,3.19,3.4,8.5,110,5500,19,25,17710
5
+ 1,158,105.8,192.7,71.4,55.9,3086,131,3.13,3.4,8.3,140,5500,17,20,23875
6
+ 2,192,101.2,176.8,64.8,54.3,2395,108,3.5,2.8,8.8,101,5800,23,29,16430
7
+ 0,192,101.2,176.8,64.8,54.3,2395,108,3.5,2.8,8.8,101,5800,23,29,16925
8
+ 0,188,101.2,176.8,64.8,54.3,2710,164,3.31,3.19,9,121,4250,21,28,20970
9
+ 0,188,101.2,176.8,64.8,54.3,2765,164,3.31,3.19,9,121,4250,21,28,21105
10
+ 2,121,88.4,141.1,60.3,53.2,1488,61,2.91,3.03,9.5,48,5100,47,53,5151
11
+ 1,98,94.5,155.9,63.6,52,1874,90,3.03,3.11,9.6,70,5400,38,43,6295
12
+ 0,81,94.5,158.8,63.6,52,1909,90,3.03,3.11,9.6,70,5400,38,43,6575
13
+ 1,118,93.7,157.3,63.8,50.8,1876,90,2.97,3.23,9.41,68,5500,37,41,5572
14
+ 1,118,93.7,157.3,63.8,50.8,1876,90,2.97,3.23,9.4,68,5500,31,38,6377
15
+ 1,118,93.7,157.3,63.8,50.8,2128,98,3.03,3.39,7.6,102,5500,24,30,7957
16
+ 1,148,93.7,157.3,63.8,50.6,1967,90,2.97,3.23,9.4,68,5500,31,38,6229
17
+ 1,148,93.7,157.3,63.8,50.6,1989,90,2.97,3.23,9.4,68,5500,31,38,6692
18
+ 1,148,93.7,157.3,63.8,50.6,1989,90,2.97,3.23,9.4,68,5500,31,38,7609
19
+ -1,110,103.3,174.6,64.6,59.8,2535,122,3.34,3.46,8.5,88,5000,24,30,8921
20
+ 3,145,95.9,173.2,66.3,50.2,2811,156,3.6,3.9,7,145,5000,19,24,12964
21
+ 2,137,86.6,144.6,63.9,50.8,1713,92,2.91,3.41,9.6,58,4800,49,54,6479
22
+ 2,137,86.6,144.6,63.9,50.8,1819,92,2.91,3.41,9.2,76,6000,31,38,6855
23
+ 1,101,93.7,150,64,52.6,1837,79,2.91,3.07,10.1,60,5500,38,42,5399
24
+ 1,101,93.7,150,64,52.6,1940,92,2.91,3.41,9.2,76,6000,30,34,6529
25
+ 1,101,93.7,150,64,52.6,1956,92,2.91,3.41,9.2,76,6000,30,34,7129
26
+ 0,110,96.5,163.4,64,54.5,2010,92,2.91,3.41,9.2,76,6000,30,34,7295
27
+ 0,78,96.5,157.1,63.9,58.3,2024,92,2.92,3.41,9.2,76,6000,30,34,7295
28
+ 0,106,96.5,167.5,65.2,53.3,2236,110,3.15,3.58,9,86,5800,27,33,7895
29
+ 0,106,96.5,167.5,65.2,53.3,2289,110,3.15,3.58,9,86,5800,27,33,9095
30
+ 0,85,96.5,175.4,65.2,54.1,2304,110,3.15,3.58,9,86,5800,27,33,8845
31
+ 0,85,96.5,175.4,62.5,54.1,2372,110,3.15,3.58,9,86,5800,27,33,10295
32
+ 0,85,96.5,175.4,65.2,54.1,2465,110,3.15,3.58,9,101,5800,24,28,12945
33
+ 1,107,96.5,169.1,66,51,2293,110,3.15,3.58,9.1,100,5500,25,31,10345
34
+ 0,145,113,199.6,69.6,52.8,4066,258,3.63,4.17,8.1,176,4750,15,19,32250
35
+ 1,104,93.1,159.1,64.2,54.1,1890,91,3.03,3.15,9,68,5000,30,31,5195
36
+ 1,104,93.1,159.1,64.2,54.1,1900,91,3.03,3.15,9,68,5000,31,38,6095
37
+ 1,104,93.1,159.1,64.2,54.1,1905,91,3.03,3.15,9,68,5000,31,38,6795
38
+ 1,113,93.1,166.8,64.2,54.1,1945,91,3.03,3.15,9,68,5000,31,38,6695
39
+ 1,113,93.1,166.8,64.2,54.1,1950,91,3.08,3.15,9,68,5000,31,38,7395
40
+ 1,129,98.8,177.8,66.5,53.7,2385,122,3.39,3.39,8.6,84,4800,26,32,8845
41
+ 0,115,98.8,177.8,66.5,55.5,2410,122,3.39,3.39,8.6,84,4800,26,32,8495
42
+ 1,129,98.8,177.8,66.5,53.7,2385,122,3.39,3.39,8.6,84,4800,26,32,10595
43
+ 0,115,98.8,177.8,66.5,55.5,2410,122,3.39,3.39,8.6,84,4800,26,32,10245
44
+ 0,115,98.8,177.8,66.5,55.5,2425,122,3.39,3.39,8.6,84,4800,26,32,11245
45
+ 0,118,104.9,175,66.1,54.4,2670,140,3.76,3.16,8,120,5000,19,27,18280
46
+ -1,93,110,190.9,70.3,56.5,3515,183,3.58,3.64,21.5,123,4350,22,25,25552
47
+ -1,93,110,190.9,70.3,58.7,3750,183,3.58,3.64,21.5,123,4350,22,25,28248
48
+ 0,93,106.7,187.5,70.3,54.9,3495,183,3.58,3.64,21.5,123,4350,22,25,28176
49
+ -1,93,115.6,202.6,71.7,56.3,3770,183,3.58,3.64,21.5,123,4350,22,25,31600
50
+ 3,142,96.6,180.3,70.5,50.8,3685,234,3.46,3.1,8.3,155,4750,16,18,35056
51
+ 2,161,93.7,157.3,64.4,50.8,1918,92,2.97,3.23,9.4,68,5500,37,41,5389
52
+ 2,161,93.7,157.3,64.4,50.8,1944,92,2.97,3.23,9.4,68,5500,31,38,6189
53
+ 2,161,93.7,157.3,64.4,50.8,2004,92,2.97,3.23,9.4,68,5500,31,38,6669
54
+ 1,161,93,157.3,63.8,50.8,2145,98,3.03,3.39,7.6,102,5500,24,30,7689
55
+ 3,153,96.3,173,65.4,49.4,2370,110,3.17,3.46,7.5,116,5500,23,30,9959
56
+ 3,153,96.3,173,65.4,49.4,2328,122,3.35,3.46,8.5,88,5000,25,32,8499
57
+ 1,125,96.3,172.4,65.4,51.6,2365,122,3.35,3.46,8.5,88,5000,25,32,6989
58
+ 1,125,96.3,172.4,65.4,51.6,2405,122,3.35,3.46,8.5,88,5000,25,32,8189
59
+ 1,125,96.3,172.4,65.4,51.6,2403,110,3.17,3.46,7.5,116,5500,23,30,9279
60
+ -1,137,96.3,172.4,65.4,51.6,2403,110,3.17,3.46,7.5,116,5500,23,30,9279
61
+ 1,128,94.5,165.3,63.8,54.5,1889,97,3.15,3.29,9.4,69,5200,31,37,5499
62
+ 1,128,94.5,165.3,63.8,54.5,2017,103,2.99,3.47,21.9,55,4800,45,50,7099
63
+ 1,128,94.5,165.3,63.8,54.5,1918,97,3.15,3.29,9.4,69,5200,31,37,6649
64
+ 1,122,94.5,165.3,63.8,54.5,1938,97,3.15,3.29,9.4,69,5200,31,37,6849
65
+ 1,103,94.5,170.2,63.8,53.5,2024,97,3.15,3.29,9.4,69,5200,31,37,7349
66
+ 1,128,94.5,165.3,63.8,54.5,1951,97,3.15,3.29,9.4,69,5200,31,37,7299
67
+ 1,128,94.5,165.6,63.8,53.3,2028,97,3.15,3.29,9.4,69,5200,31,37,7799
68
+ 1,122,94.5,165.3,63.8,54.5,1971,97,3.15,3.29,9.4,69,5200,31,37,7499
69
+ 1,103,94.5,170.2,63.8,53.5,2037,97,3.15,3.29,9.4,69,5200,31,37,7999
70
+ 2,168,95.1,162.4,63.8,53.3,2008,97,3.15,3.29,9.4,69,5200,31,37,8249
71
+ 0,106,97.2,173.4,65.2,54.7,2324,120,3.33,3.47,8.5,97,5200,27,34,8949
72
+ 0,106,97.2,173.4,65.2,54.7,2302,120,3.33,3.47,8.5,97,5200,27,34,9549
73
+ 0,128,100.4,181.7,66.5,55.1,3095,181,3.43,3.27,9,152,5200,17,22,13499
74
+ 0,108,100.4,184.6,66.5,56.1,3296,181,3.43,3.27,9,152,5200,17,22,14399
75
+ 0,108,100.4,184.6,66.5,55.1,3060,181,3.43,3.27,9,152,5200,19,25,13499
76
+ 3,194,91.3,170.7,67.9,49.7,3071,181,3.43,3.27,9,160,5200,19,25,17199
77
+ 3,194,91.3,170.7,67.9,49.7,3139,181,3.43,3.27,7.8,200,5200,17,23,19699
78
+ 1,231,99.2,178.5,67.9,49.7,3139,181,3.43,3.27,9,160,5200,19,25,18399
79
+ 0,161,107.9,186.7,68.4,56.7,3020,120,3.46,3.19,8.4,97,5000,19,24,11900
80
+ 0,161,107.9,186.7,68.4,56.7,3197,152,3.7,3.52,21,95,4150,28,33,13200
81
+ 0,161,107.9,186.7,68.4,56.7,3075,120,3.46,2.19,8.4,95,5000,19,24,15580
82
+ 0,161,107.9,186.7,68.4,56.7,3252,152,3.7,3.52,21,95,4150,28,33,16900
83
+ 0,161,107.9,186.7,68.4,56.7,3075,120,3.46,3.19,8.4,97,5000,19,24,16630
84
+ 0,161,107.9,186.7,68.4,56.7,3252,152,3.7,3.52,21,95,4150,28,33,17950
85
+ 0,161,108,186.7,68.3,56,3130,134,3.61,3.21,7,142,5600,18,24,18150
86
+ 1,119,93.7,157.3,63.8,50.8,1918,90,2.97,3.23,9.4,68,5500,37,41,5572
87
+ 1,119,93.7,157.3,63.8,50.8,2128,98,3.03,3.39,7.6,102,5500,24,30,7957
88
+ 1,154,93.7,157.3,63.8,50.6,1967,90,2.97,3.23,9.4,68,5500,31,38,6229
89
+ 1,154,93.7,167.3,63.8,50.8,1989,90,2.97,3.23,9.4,68,5500,31,38,6692
90
+ 1,154,93.7,167.3,63.8,50.8,2191,98,2.97,3.23,9.4,68,5500,31,38,7609
91
+ -1,74,103.3,174.6,64.6,59.8,2535,122,3.35,3.46,8.5,88,5000,24,30,8921
92
+ 3,186,94.5,168.9,68.3,50.2,2778,151,3.94,3.11,9.5,143,5500,19,27,22018
93
+ 3,150,99.1,186.6,66.5,56.1,2658,121,3.54,3.07,9.31,110,5250,21,28,11850
94
+ 2,104,99.1,186.6,66.5,56.1,2695,121,3.54,3.07,9.3,110,5250,21,28,12170
95
+ 3,150,99.1,186.6,66.5,56.1,2707,121,2.54,2.07,9.3,110,5250,21,28,15040
96
+ 2,104,99.1,186.6,66.5,56.1,2758,121,3.54,3.07,9.3,110,5250,21,28,15510
97
+ 3,150,99.1,186.6,66.5,56.1,2808,121,3.54,3.07,9,160,5500,19,26,18150
98
+ 2,104,99.1,186.6,66.5,56.1,2847,121,3.54,3.07,9,160,5500,19,26,18620
99
+ 2,83,93.7,156.9,63.4,53.7,2050,97,3.62,2.36,9,69,4900,31,36,5118
100
+ 2,83,93.7,157.9,63.6,53.7,2120,108,3.62,2.64,8.7,73,4400,26,31,7053
101
+ 2,83,93.3,157.3,63.8,55.7,2240,108,3.62,2.64,8.7,73,4400,26,31,7603
102
+ 0,102,97.2,172,65.4,52.5,2145,108,3.62,2.64,9.5,82,4800,32,37,7126
103
+ 0,102,97.2,172,65.4,52.5,2190,108,3.62,2.64,9.5,82,4400,28,33,7775
104
+ 0,102,97.2,172,65.4,52.5,2340,108,3.62,2.64,9,94,5200,26,32,9960
105
+ 0,102,97,172,65.4,54.3,2385,108,3.62,2.64,9,82,4800,24,25,9233
106
+ 0,102,97,172,65.4,54.3,2510,108,3.62,2.64,7.7,111,4800,24,29,11259
107
+ 0,89,97,173.5,65.4,53,2290,108,3.62,2.64,9,82,4800,28,32,7463
108
+ 0,89,97,173.5,65.4,53,2455,108,3.62,2.64,9,94,5200,25,31,10198
109
+ 0,85,96.9,173.6,65.4,54.9,2420,108,3.62,2.64,9,82,4800,23,29,8013
110
+ 0,85,96.9,173.6,65.4,54.9,2650,108,3.62,2.64,7.7,111,4800,23,23,11694
111
+ 1,87,95.7,158.7,63.6,54.5,1985,92,3.05,3.03,9,62,4800,35,39,5348
112
+ 1,87,95.7,158.7,63.6,54.5,2040,92,3.05,3.03,9,62,4800,31,38,6338
113
+ 1,74,95.7,158.7,63.6,54.5,2015,92,3.05,3.03,9,62,4800,31,38,6488
114
+ 0,77,95.7,169.7,63.6,59.1,2280,92,3.05,3.03,9,62,4800,31,37,6918
115
+ 0,81,95.7,169.7,63.6,59.1,2290,92,3.05,3.03,9,62,4800,27,32,7898
116
+ 0,91,95.7,169.7,63.6,59.1,3110,92,3.05,3.03,9,62,4800,27,32,8778
117
+ 0,91,95.7,166.3,64.4,53,2081,98,3.19,3.03,9,70,4800,30,37,6938
118
+ 0,91,95.7,166.3,64.4,52.8,2109,98,3.19,3.03,9,70,4800,30,37,7198
119
+ 0,91,95.7,166.3,64.4,53,2275,110,3.27,3.35,22.5,56,4500,34,36,7898
120
+ 0,91,95.7,166.3,64.4,52.8,2275,110,3.27,3.35,22.5,56,4500,38,47,7788
121
+ 0,91,95.7,166.3,64.4,53,2094,98,3.19,3.03,9,70,4800,38,47,7738
122
+ 0,91,95.7,166.3,64.4,52.8,2122,98,3.19,3.03,9,70,4800,28,34,8358
123
+ 0,91,95.7,166.3,64.4,52.8,2140,98,3.19,3.03,9,70,4800,28,34,9258
124
+ 1,168,94.5,168.7,64,52.6,2169,98,3.19,3.03,9,70,4800,29,34,8058
125
+ 1,168,94.5,168.7,64,52.6,2204,98,3.19,3.03,9,70,4800,29,34,8238
126
+ 1,168,94.5,168.7,64,52.6,2265,98,3.24,3.08,9.4,112,6600,26,29,9298
127
+ 1,168,94.5,168.7,64,52.6,2300,98,3.24,3.08,9.4,112,6600,26,29,9538
128
+ 2,134,98.4,176.2,65.6,52,2540,146,3.62,3.5,9.3,116,4800,24,30,8449
129
+ 2,134,98.4,176.2,65.6,52,2536,146,3.62,3.5,9.3,116,4800,24,30,9639
130
+ 2,134,98.4,176.2,65.6,52,2551,146,3.62,3.5,9.3,116,4800,24,30,9989
131
+ 2,134,98.4,176.2,65.6,52,2679,146,3.62,3.5,9.3,116,4800,24,30,11199
132
+ 2,134,98.4,176.2,65.6,52,2714,146,3.62,3.5,9.3,116,4800,24,30,11549
133
+ 2,134,98.4,176.2,65.6,53,2975,146,3.62,3.5,9.3,116,4800,24,30,17669
134
+ -1,65,102.4,175.6,66.5,54.9,2326,122,3.31,3.54,8.7,92,4200,29,34,8948
135
+ -1,65,102.4,175.6,66.5,54.9,2480,110,3.27,3.35,22.5,73,4500,30,33,10698
136
+ -1,65,102.4,175.6,66.5,53.9,2414,122,3.31,3.54,8.7,92,4200,27,32,9988
137
+ -1,65,102.4,175.6,66.5,54.9,2414,122,3.31,3.54,8.7,92,4200,27,32,10898
138
+ -1,65,102.4,175.6,66.5,53.9,2458,122,3.31,3.54,8.7,92,4200,27,32,11248
139
+ 3,197,102.9,183.5,67.7,52,2976,171,3.27,3.35,9.3,161,5200,20,24,16558
140
+ 3,197,102.9,183.5,67.7,52,3016,171,3.27,3.35,9.3,161,5200,19,24,15998
141
+ -1,90,104.5,187.8,66.5,54.1,3131,171,3.27,3.35,9.2,156,5200,20,24,15690
142
+ 2,122,97.3,171.7,65.5,55.7,2261,97,3.01,3.4,23,52,4800,37,46,7775
143
+ 2,122,97.3,171.7,65.5,55.7,2209,109,3.19,3.4,9,85,5250,27,34,7975
144
+ 2,94,97.3,171.7,65.5,55.7,2264,97,3.01,3.4,23,52,4800,37,46,7995
145
+ 2,94,97.3,171.7,65.5,55.7,2212,109,3.19,3.4,9,85,5250,27,34,8195
146
+ 2,94,97.3,171.7,65.5,55.7,2275,109,3.19,3.4,9,85,5250,27,34,8495
147
+ 2,94,97.3,171.7,65.5,55.7,2319,97,3.01,3.4,23,68,4500,37,42,9495
148
+ 2,94,97.3,171.7,65.5,55.7,2300,109,3.19,3.4,10,100,5500,26,32,9995
149
+ 3,256,94.5,165.7,64,51.4,2221,109,3.19,3.4,8.5,90,5500,24,29,9980
150
+ -2,103,104.3,188.8,67.2,56.2,2912,141,3.78,3.15,9.5,114,5400,23,28,12940
151
+ -1,74,104.3,188.8,67.2,57.5,3034,141,3.78,3.15,9.5,114,5400,23,28,13415
152
+ -2,103,104.3,188.8,67.2,56.2,2935,141,3.78,3.15,9.5,114,5400,24,28,15985
153
+ -1,74,104.3,188.8,67.2,57.5,3042,141,3.78,3.15,9.5,114,5400,24,28,16515
154
+ -2,103,104.3,188.8,67.2,56.2,3045,130,3.62,3.15,7.5,162,5100,17,22,18420
155
+ -1,74,104.3,188.8,67.2,57.5,3157,130,3.62,3.15,7.5,162,5100,17,22,18950
156
+ -1,95,109.1,188.8,68.9,55.5,2952,141,3.78,3.15,9.5,114,5400,23,28,16845
157
+ -1,95,109.1,188.8,68.8,55.5,3049,141,3.78,3.15,8.7,160,5300,19,25,19045
158
+ -1,95,109.1,188.8,68.9,55.5,3012,173,3.58,2.87,8.8,134,5500,18,23,21485
159
+ -1,95,109.1,188.8,68.9,55.5,3217,145,3.01,3.4,23,106,4800,26,27,22470
data/examples/classifiers/simple_linear_regression_example.rb ADDED
@@ -0,0 +1,15 @@
1
+ require File.dirname(__FILE__) + '/../../lib/ai4r/classifiers/simple_linear_regression'
2
+ require File.dirname(__FILE__) + '/../../lib/ai4r/data/data_set'
3
+ require 'benchmark'
4
+
5
+ include Ai4r::Classifiers
6
+ include Ai4r::Data
7
+
8
+ data_set = DataSet.new
9
+ data_set.parse_csv_with_labels File.dirname(__FILE__) + "/simple_linear_regression_example.csv"
10
+
11
+ r = SimpleLinearRegression.new.build data_set
12
+ p r.eval([-1,95,109.1,188.8,68.9,55.5,3062,141,3.78,3.15,9.5,114,5400,19,25])
13
+
14
+ # => 11662.949367088606
15
+ #Actual price 22625
data/examples/clusterers/clusterer_example.rb ADDED
@@ -0,0 +1,56 @@
1
+ # Author:: Sergio Fierens (implementation)
2
+ # License:: MPL 1.1
3
+ # Project:: ai4r
4
+ # Url:: http://www.ai4r.org/
5
+ #
6
+ # You can redistribute it and/or modify it under the terms of
7
+ # the Mozilla Public License version 1.1 as published by the
8
+ # Mozilla Foundation at http://www.mozilla.org/MPL/MPL-1.1.txt
9
+
10
+ # In this example we group results from a post-training survey into 4 groups.
11
+ # The Diana algorithm is used, but you can try other algorithms by changing
12
+ # the word "Diana" by "KMeans", "AverageLinkage", or any other cluster implementation.
13
+ # The cluster API is the same, so you can play around and observe different results.
14
+
15
+ require 'rubygems'
16
+ require 'ai4r'
17
+ include Ai4r::Data
18
+ include Ai4r::Clusterers
19
+
20
+ # 5 Questions on a post training survey
21
+ questions = [ "The material covered was appropriate for someone with my level of knowledge of the subject.",
22
+ "The material was presented in a clear and logical fashion",
23
+ "There was sufficient time in the session to cover the material that was presented",
24
+ "The instructor was respectful of students",
25
+ "The instructor provided good examples"]
26
+
27
+ # Answers to each question go from 1 (bad) to 5 (excellent)
28
+ # The answers array has an element per survey complemented.
29
+ # Each survey completed is in turn an array with the answer of each question.
30
+ answers = [ [ 1, 2, 3, 2, 2], # Answers of person 1
31
+ [ 5, 5, 3, 2, 2], # Answers of person 2
32
+ [ 1, 2, 3, 2, 2], # Answers of person 3
33
+ [ 1, 2, 2, 2, 2], # ...
34
+ [ 1, 2, 5, 5, 2],
35
+ [ 3, 3, 3, 3, 3],
36
+ [ 1, 2, 3, 2, 2],
37
+ [ 3, 2, 3, 5, 5],
38
+ [ 3, 3, 3, 5, 2],
39
+ [ 4, 4, 3, 1, 1],
40
+ [ 5, 5, 5, 5, 5],
41
+ [ 4, 2, 4, 2, 1],
42
+ [ 4, 4, 5, 5, 5],
43
+ [ 4, 4, 3, 2, 2],
44
+ [ 2, 2, 3, 2, 3],
45
+ [ 3, 3, 3, 1, 1]] # Answers of person 16
46
+
47
+ data_set = DataSet.new(:data_items => answers, :data_labels => questions)
48
+
49
+ # Let's group answers in 4 groups
50
+ clusterer = Diana.new.build(data_set, 4)
51
+
52
+ clusterer.clusters.each_with_index do |cluster, index|
53
+ puts "Group #{index+1}"
54
+ p cluster.data_items
55
+ end
56
+
data/examples/neural_network/backpropagation_example.rb CHANGED
@@ -16,7 +16,8 @@ require 'benchmark'
16
16
  times = Benchmark.measure do
17
17
 
18
18
  srand 1
19
-
19
+
20
+ # creating network with 256 input-neurons, 3-neurons and 0 hidden layers
20
21
  net = Ai4r::NeuralNetwork::Backpropagation.new([256, 3])
21
22
 
22
23
  tr_input = TRIANGLE.flatten.collect { |input| input.to_f / 5.0}
data/lib/ai4r.rb CHANGED
@@ -14,6 +14,7 @@ require File.dirname(__FILE__) + "/ai4r/clusterers/weighted_average_linkage"
14
14
  require File.dirname(__FILE__) + "/ai4r/clusterers/centroid_linkage"
15
15
  require File.dirname(__FILE__) + "/ai4r/clusterers/median_linkage"
16
16
  require File.dirname(__FILE__) + "/ai4r/clusterers/ward_linkage"
17
+ require File.dirname(__FILE__) + "/ai4r/clusterers/ward_linkage_hierarchical"
17
18
  require File.dirname(__FILE__) + "/ai4r/clusterers/diana"
18
19
  # Classifiers
19
20
  require File.dirname(__FILE__) + "/ai4r/classifiers/classifier"
@@ -30,4 +31,5 @@ require File.dirname(__FILE__) + "/ai4r/neural_network/hopfield"
30
31
  # Genetic Algorithms
31
32
  require File.dirname(__FILE__) + "/ai4r/genetic_algorithm/genetic_algorithm"
32
33
  # SOM
33
- require File.dirname(__FILE__) + "/ai4r/som/som"
34
+ require File.dirname(__FILE__) + "/ai4r/som/som"
35
+
data/lib/ai4r/classifiers/id3.rb CHANGED
@@ -280,7 +280,7 @@ module Ai4r
280
280
 
281
281
  def value(data)
282
282
  value = data[@index]
283
- return rule_not_found if !@values.include?(value)
283
+ return ErrorNode.new.value(data) if !@values.include?(value)
284
284
  return nodes[@values.index(value)].value(data)
285
285
  end
286
286
 
@@ -313,9 +313,13 @@ module Ai4r
313
313
  end
314
314
  end
315
315
 
316
+ class ModelFailureError < StandardError
317
+ default_message = "There was not enough information during training to do a proper induction for this data element."
318
+ end
319
+
316
320
  class ErrorNode #:nodoc: all
317
321
  def value(data)
318
- raise "There was not enough information during training to do a proper induction for this data element."
322
+ raise ModelFailureError, "There was not enough information during training to do a proper induction for the data element #{data}."
319
323
  end
320
324
  def get_rules
321
325
  return []
data/lib/ai4r/classifiers/multilayer_perceptron.rb CHANGED
@@ -47,7 +47,7 @@ module Ai4r
47
47
  :hidden_layers => "Hidden layer structure. E.g. [8, 6] will generate " +
48
48
  "2 hidden layers with 8 and 6 neurons each. By default []",
49
49
  :training_iterations => "How many times the training should be " +
50
- "repeated. By default: 1000",
50
+ "repeated. By default: 500",
51
51
  :active_node_value => "Default: 1",
52
52
  :inactive_node_value => "Default: 0"
53
53
 
data/lib/ai4r/classifiers/naive_bayes.rb CHANGED
@@ -57,8 +57,8 @@ module Ai4r
57
57
 
58
58
  class NaiveBayes < Classifier
59
59
 
60
- parameters_info :m => "Default value is set to 0. It may be set to a value greater than " +
61
- "0 when the size of the dataset is relatively small"
60
+ parameters_info :m => 'Default value is set to 0. It may be set to a value greater than ' +
61
+ '0 when the size of the dataset is relatively small'
62
62
 
63
63
  def initialize
64
64
  @m = 0
@@ -75,7 +75,7 @@ module Ai4r
75
75
  # b.eval(["Red", "SUV", "Domestic"])
76
76
  # => 'No'
77
77
  def eval(data)
78
- prob = @class_prob.map {|cp| cp}
78
+ prob = @class_prob.dup
79
79
  prob = calculate_class_probabilities_for_entry(data, prob)
80
80
  index_to_klass(prob.index(prob.max))
81
81
  end
@@ -90,27 +90,28 @@ module Ai4r
90
90
  # b.get_probability_map(["Red", "SUV", "Domestic"])
91
91
  # => {"Yes"=>0.4166666666666667, "No"=>0.5833333333333334}
92
92
  def get_probability_map(data)
93
- prob = @class_prob.map {|cp| cp}
93
+ prob = @class_prob.dup
94
94
  prob = calculate_class_probabilities_for_entry(data, prob)
95
95
  prob = normalize_class_probability prob
96
96
  probability_map = {}
97
97
  prob.each_with_index { |p, i| probability_map[index_to_klass(i)] = p }
98
- return probability_map
98
+
99
+ probability_map
99
100
  end
100
101
 
101
102
  # counts values of the attribute instances and calculates the probability of the classes
102
103
  # and the conditional probabilities
103
104
  # Parameter data has to be an instance of CsvDataSet
104
105
  def build(data)
105
- raise "Error instance must be passed" unless data.is_a?(DataSet)
106
- raise "Data should not be empty" if data.data_items.length == 0
106
+ raise 'Error instance must be passed' unless data.is_a?(Ai4r::Data::DataSet)
107
+ raise 'Data should not be empty' if data.data_items.length == 0
107
108
 
108
109
  initialize_domain_data(data)
109
110
  initialize_klass_index
110
111
  initialize_pc
111
112
  calculate_probabilities
112
113
 
113
- return self
114
+ self
114
115
  end
115
116
 
116
117
  private
@@ -128,25 +129,27 @@ module Ai4r
128
129
  # probability of every attribute in condition to a specific class
129
130
  # this is repeated for every class
130
131
  def calculate_class_probabilities_for_entry(data, prob)
131
- prob.each_with_index do |prob_entry, prob_index|
132
+ 0.upto(prob.length - 1) do |prob_index|
132
133
  data.each_with_index do |att, index|
133
134
  next if value_index(att, index).nil?
134
135
  prob[prob_index] *= @pcp[index][value_index(att, index)][prob_index]
135
136
  end
136
137
  end
138
+
139
+ prob
137
140
  end
138
141
 
139
142
  # normalises the array of probabilities so the sum of the array equals 1
140
143
  def normalize_class_probability(prob)
141
144
  prob_sum = sum(prob)
142
145
  prob_sum > 0 ?
143
- prob.map {|prob_entry| prob_entry / prob_sum } :
146
+ prob.map { |prob_entry| prob_entry / prob_sum } :
144
147
  prob
145
148
  end
146
149
 
147
150
  # sums an array up; returns a number of type Float
148
151
  def sum(array)
149
- array.inject(0.0){|b, i| b+i}
152
+ array.inject(0.0) { |b, i| b + i }
150
153
  end
151
154
 
152
155
  # returns the name of the class when the index is found
@@ -160,7 +163,7 @@ module Ai4r
160
163
  @klass_index[dl] = index
161
164
  end
162
165
 
163
- @data_labels.each_with_index do |dl, index|
166
+ 0.upto(@data_labels.length - 1) do |index|
164
167
  @values[index] = {}
165
168
  @domains[index].each_with_index do |d, d_index|
166
169
  @values[index][d] = d_index
@@ -180,19 +183,19 @@ module Ai4r
180
183
 
181
184
  # builds an array of the form:
182
185
  # array[attributes][values][classes]
183
- def build_array(dl, index)
186
+ def build_array(index)
184
187
  domains = Array.new(@domains[index].length)
185
- domains.map do |p1|
186
- pl = Array.new @klasses.length, 0
188
+ domains.map do
189
+ Array.new @klasses.length, 0
187
190
  end
188
191
  end
189
192
 
190
193
  # initializes the two array for storing the count and conditional probabilities of
191
194
  # the attributes
192
195
  def initialize_pc
193
- @data_labels.each_with_index do |dl, index|
194
- @pcc << build_array(dl, index)
195
- @pcp << build_array(dl, index)
196
+ 0.upto(@data_labels.length - 1) do |index|
197
+ @pcc << build_array(index)
198
+ @pcp << build_array(index)
196
199
  end
197
200
  end
198
201
 
@@ -200,7 +203,7 @@ module Ai4r
200
203
  # certain attribute and the assigned class.
201
204
  # In addition to that, it also calculates the conditional probabilities and values
202
205
  def calculate_probabilities
203
- @klasses.each {|dl| @class_counts[klass_index(dl)] = 0}
206
+ @klasses.each { |dl| @class_counts[klass_index(dl)] = 0 }
204
207
 
205
208
  calculate_class_probabilities
206
209
  count_instances
@@ -220,7 +223,7 @@ module Ai4r
220
223
  # counts the instances of a certain value of a certain attribute and the assigned class
221
224
  def count_instances
222
225
  @data_items.each do |item|
223
- @data_labels.each_with_index do |dl, dl_index|
226
+ 0.upto(@data_labels.length - 1) do |dl_index|
224
227
  @pcc[dl_index][value_index(item[dl_index], dl_index)][klass_index(item.klass)] += 1
225
228
  end
226
229
  end
@@ -231,7 +234,7 @@ module Ai4r
231
234
  @pcc.each_with_index do |attributes, a_index|
232
235
  attributes.each_with_index do |values, v_index|
233
236
  values.each_with_index do |klass, k_index|
234
- @pcp[a_index][v_index][k_index] = (klass.to_f + @m * @class_prob[k_index]) / (@class_counts[k_index] + @m).to_f
237
+ @pcp[a_index][v_index][k_index] = (klass.to_f + @m * @class_prob[k_index]) / (@class_counts[k_index] + @m)
235
238
  end
236
239
  end
237
240
  end