categorize 0.0.6 → 0.0.7
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 +8 -8
- data/lib/categorize/models/cluster.rb +7 -5
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,15 +1,15 @@
|
|
|
1
1
|
---
|
|
2
2
|
!binary "U0hBMQ==":
|
|
3
3
|
metadata.gz: !binary |-
|
|
4
|
-
|
|
4
|
+
YmI4NmJiZjFkYjJjY2ZkNTFjMGQyM2RhNTM2MjJhYTQ3MmQ2Nzc4Zg==
|
|
5
5
|
data.tar.gz: !binary |-
|
|
6
|
-
|
|
6
|
+
ZGMwZmU4YTgyY2ZkZjFjNTljNmQwNmE2MTdkMmRlMWRlYjc1NjlmOA==
|
|
7
7
|
!binary "U0hBNTEy":
|
|
8
8
|
metadata.gz: !binary |-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
9
|
+
YzBkOTQwNjVhMGEzM2MyZDA3YTlhNjZmYTNiZWFlNjgwOTFlMGM2YjhlMjRm
|
|
10
|
+
NzUzMjFlNzE0ZTc0NThhOTBjY2E0ZjcwMzgzOThhNDg3NGQ0ZmI4MzY4MjM4
|
|
11
|
+
NTJlZmJjNTg1Y2I2ZDNjNmIzOTcxMTVhMDFmYTc2ODYxYTc1Yjk=
|
|
12
12
|
data.tar.gz: !binary |-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
13
|
+
YmQ4YjFhOTBjMzIwZWEwM2ZjNGM3NzczYjFhYWU5MjM2NmI2NDMxMTU0ZDI4
|
|
14
|
+
NzU4ZDc3NGVlNjE1MzRjNTZhOTdiZDU3OWY4OWE4NDkxNDgwZTE1NWUyOThi
|
|
15
|
+
NmQ1ZjI2MGRkMjk3YjY3YmY4NzczM2VkYTljOTk3YmY1ZWI1MmQ=
|
|
@@ -18,9 +18,11 @@ module Categorize
|
|
|
18
18
|
end
|
|
19
19
|
|
|
20
20
|
def build_categories(clusters)
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
end
|
|
21
|
+
cluster_indices = clusters.map do |cluster|
|
|
22
|
+
cluster.data_items.map { |v| @vectors.index(v) }
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
clusters_to_records = Hash[(0...@num_clusters).zip(cluster_indices)]
|
|
24
26
|
|
|
25
27
|
@query_terms ||= @query.split.map(&:downcase)
|
|
26
28
|
|
|
@@ -31,9 +33,9 @@ module Categorize
|
|
|
31
33
|
end
|
|
32
34
|
|
|
33
35
|
records = clusters_to_records.values
|
|
34
|
-
# merge duplicate labeled categories
|
|
35
|
-
categories_records = []
|
|
36
36
|
|
|
37
|
+
# merge categories with the same label
|
|
38
|
+
categories_records = []
|
|
37
39
|
categories.each_with_index do |category, i|
|
|
38
40
|
if j = categories[0...i].index(category) && categories_records[j]
|
|
39
41
|
categories_records[j].last + records.shift
|