segment_ruby 0.1.1 → 0.1.2

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.
Files changed (16) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +2 -0
  3. data/data/segment_ruby/test_bigram/2_frequencies.tsv +10 -0
  4. data/data/segment_ruby/test_bigram/2_total.tsv +1 -0
  5. data/data/segment_ruby/test_bigram/frequencies.tsv +10 -0
  6. data/data/segment_ruby/test_bigram/total.tsv +1 -0
  7. data/data/segment_ruby/test_unigram/frequencies.tsv +10 -0
  8. data/data/segment_ruby/test_unigram/total.tsv +1 -0
  9. data/data/segment_ruby/us_names/2_frequencies.tsv.save +0 -0
  10. data/data/segment_ruby/us_names/2_total.tsv.save +1 -0
  11. data/data/segment_ruby/us_names/README.md +15 -0
  12. data/data/segment_ruby/us_names/frequencies.tsv +78637 -0
  13. data/data/segment_ruby/us_names/total.tsv +1 -0
  14. data/lib/segment_ruby/version.rb +1 -1
  15. data/lib/segment_ruby.rb +3 -3
  16. metadata +13 -2
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 26ffd5e24afa505dec8c31cac0cad0cecafc27bb
4
- data.tar.gz: 4171510ada22f97967654a976da3c014b5fab121
3
+ metadata.gz: a44ebf20192579cea4c945942fb1275614ccd4cf
4
+ data.tar.gz: 59fc1cd835d97ca68459dccfd9f3b61d44667292
5
5
  SHA512:
6
- metadata.gz: fcf6a77d8778367c64563d09be67080b935282250fc625cdb2169ea9f461a0dea2a04ef47a400b7f70ed4f2745c534cd5600b3eb13b9b94285aaf6eb65609348
7
- data.tar.gz: c7868ead403e68c2154016150456676269376b136dce0de73c30370ce168e27abf839335a46c4854af037a155238241c79ef89a172163055dc16651ef95e5bfa
6
+ metadata.gz: 0d422443d5be858b3b328d40f3dd174372971aa7364d84118d436d4381b03d815906883bb66fc4fba16a2804a8f7ad509c47c41ed8c979cc0c8b0277bfd91e64
7
+ data.tar.gz: cd72e99abe2f9b59a6c2dcafcfedc912702aa46621c7086506191fe8cd06a0177d71fd5dbd8df99caf5aaf730cfb6aea9917f7e57708a6859003a02646958847
data/.gitignore CHANGED
@@ -7,3 +7,5 @@
7
7
  /pkg/
8
8
  /spec/reports/
9
9
  /tmp/
10
+ tags
11
+ .tags*
data/data/segment_ruby/test_bigram/2_frequencies.tsv ADDED
@@ -0,0 +1,10 @@
1
+ of the 4090128330
2
+ , and 2800837645
3
+ in the 2053960926
4
+ , the 1364701650
5
+ to the 1358602774
6
+ and the 894974339
7
+ , " 792712997
8
+ on the 769237885
9
+ ) . 693102993
10
+ . " 686861045
data/data/segment_ruby/test_bigram/2_total.tsv ADDED
@@ -0,0 +1 @@
1
+ 431675447550
data/data/segment_ruby/test_bigram/frequencies.tsv ADDED
@@ -0,0 +1,10 @@
1
+ , 27957346221
2
+ the 23688414489
3
+ . 19194317252
4
+ of 15342397280
5
+ and 11021132912
6
+ to 9494905988
7
+ in 7611765281
8
+ a 7083003595
9
+ " 4430963121
10
+ is 4139526351
data/data/segment_ruby/test_bigram/total.tsv ADDED
@@ -0,0 +1 @@
1
+ 468285774779
data/data/segment_ruby/test_unigram/frequencies.tsv ADDED
@@ -0,0 +1,10 @@
1
+ , 27957346221
2
+ the 23688414489
3
+ . 19194317252
4
+ of 15342397280
5
+ and 11021132912
6
+ to 9494905988
7
+ in 7611765281
8
+ a 7083003595
9
+ " 4430963121
10
+ is 4139526351
data/data/segment_ruby/test_unigram/total.tsv ADDED
@@ -0,0 +1 @@
1
+ 468285774779
data/data/segment_ruby/us_names/2_frequencies.tsv.save ADDED
File without changes
data/data/segment_ruby/us_names/README.md ADDED
@@ -0,0 +1,15 @@
1
+ # US names
2
+
3
+ These frequencies from from US 2013 Social Security Death Master Index.
4
+ First and last names were lowercased, all spaces were removed, and
5
+ then frequencies were counted.
6
+
7
+ For example:
8
+
9
+ - "Jane" was counted as both a first and as a last name.
10
+ - The first name "Mary Ann" had spaces removed, and so was counted along
11
+ with "MaryAnn"
12
+ - Variants such as "O'Reilly" and "OReilly" were _not_ merged (Although "O Reilly" and "OReilly" were merged).
13
+
14
+ The original data comes from the US Social Security Agency; the data was
15
+ provided by [Tom Alciere](http://cancelthesefunerals.com/).