data_mining 0.0.1 → 0.0.2
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.
- checksums.yaml +4 -4
- data/lib/data_mining/dbscan.rb +14 -2
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 974c994068ee3cf5b01c62f5b406f5ae327d17d3
|
|
4
|
+
data.tar.gz: e95b21a5a62291a3342b32b2b16db1ba31ae9e99
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e81c069008ec95bcc3598b29437890a497917b33e3a873dacbca64265f98681b5f1f8e2484c7fe893597d09837574a35fc846c049cd68c33e159d17c78b5abd2
|
|
7
|
+
data.tar.gz: b51412c6449a85a22ca5258d2731847abea52a498202bc12f6e4167c1ad28989f60e634c015e0f19409dde655b026a2dd20b5d3eb492f3b1ddbc9db83d9faeef
|
data/lib/data_mining/dbscan.rb
CHANGED
|
@@ -4,7 +4,7 @@ module DataMining
|
|
|
4
4
|
# Find clusters and outliers
|
|
5
5
|
#
|
|
6
6
|
# Example:
|
|
7
|
-
# >> input = [[:p1, 1], [:p2, 2], [:p3, 10]]
|
|
7
|
+
# >> input = [[:p1, [1,1]], [:p2, [2,1]], [:p3, [10,11]]]
|
|
8
8
|
# >> radius = 3
|
|
9
9
|
# >> min_points = 2
|
|
10
10
|
# >> dbscan = DataMining::DBScan.cluster(input, radius, min_points)
|
|
@@ -96,9 +96,21 @@ module DataMining
|
|
|
96
96
|
end
|
|
97
97
|
|
|
98
98
|
def neighbors?(p1, p2)
|
|
99
|
-
|
|
99
|
+
fail ArgumentError, 'Wrong point coordinates' unless valid_points?(p1, p2)
|
|
100
|
+
return true if p1 != p2 && euclidean_distance(p1, p2).abs <= @radius
|
|
100
101
|
false
|
|
101
102
|
end
|
|
103
|
+
|
|
104
|
+
def valid_points?(p1, p2)
|
|
105
|
+
return false if p1.value.length != p2.value.length
|
|
106
|
+
(p1.value + p2.value).all? { |x| x.is_a? Numeric }
|
|
107
|
+
end
|
|
108
|
+
|
|
109
|
+
def euclidean_distance(p1, p2)
|
|
110
|
+
p1 = p1.value
|
|
111
|
+
p2 = p2.value
|
|
112
|
+
Math.sqrt(p1.each_with_index.inject(0) { |sum, (v, i)| sum + ((v - p2[i])**2) })
|
|
113
|
+
end
|
|
102
114
|
end
|
|
103
115
|
end
|
|
104
116
|
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: data_mining
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Manuel Stuefer
|
|
@@ -19,7 +19,7 @@ files:
|
|
|
19
19
|
- lib/data_mining.rb
|
|
20
20
|
- lib/data_mining/dbscan.rb
|
|
21
21
|
- lib/data_mining/point.rb
|
|
22
|
-
homepage:
|
|
22
|
+
homepage: https://github.com/mstuefer/data_mining
|
|
23
23
|
licenses:
|
|
24
24
|
- MIT
|
|
25
25
|
metadata: {}
|