markov_chains 0.1.0 → 0.1.1
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/markov_chains/dictionary.rb +28 -26
- data/lib/markov_chains/version.rb +2 -2
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 2a5502df6fbd5d786c29c3c73eeccc2aadf024a8
|
|
4
|
+
data.tar.gz: ad36913b85e82c09e51e2d4737554c3b05a05f6a
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: f9a1b39ef2e706d7228f610c05100cd98faf8d60fe03bc26193fe7b0700952a09b791da004986488e327644582b9386518ce6fd9c0964e354756ac42e0896387
|
|
7
|
+
data.tar.gz: 9de8d90926e2bb63ff65f34bed0d826c4081829946c1aa013c614c5d696b290c4cb4ab758e411c89fbcce1098a74bcf1e183ac0cd18dd5a4265fa964642d9fa0
|
|
@@ -28,32 +28,6 @@ module MarkovChains
|
|
|
28
28
|
sentences = text.split seps
|
|
29
29
|
sentences.each_slice(2) { |s,t| process_sentence(s.strip,t) }
|
|
30
30
|
end
|
|
31
|
-
|
|
32
|
-
# Processes a single sentence with terminator
|
|
33
|
-
#
|
|
34
|
-
# @example Process a sentence
|
|
35
|
-
# process_sentence("It is sunny today", "!")
|
|
36
|
-
#
|
|
37
|
-
# @param [String] sentence to process
|
|
38
|
-
# @param [Character] sentence terminator
|
|
39
|
-
#
|
|
40
|
-
private def process_sentence(sentence, terminator)
|
|
41
|
-
# Consider phrases/words/clauses separators when splitting
|
|
42
|
-
seps = "([,;:])"
|
|
43
|
-
|
|
44
|
-
# Split <sentence> into words
|
|
45
|
-
words = sentence.gsub(/[^#{seps}\w'\s]/, "").gsub(/(#{seps})\s+/, '\1').split(/\s+|#{seps}/)
|
|
46
|
-
words << terminator
|
|
47
|
-
|
|
48
|
-
# Add <@order> start words to the list
|
|
49
|
-
@start_words << words[0, @order]
|
|
50
|
-
|
|
51
|
-
# Add the words to the frequency hash <words_for>
|
|
52
|
-
until words.size < @order + 1 do
|
|
53
|
-
(@words_for[words[0, @order]] ||= []) << words[@order]
|
|
54
|
-
words.shift
|
|
55
|
-
end
|
|
56
|
-
end
|
|
57
31
|
|
|
58
32
|
# Returns a word based on the likelihood of it appearing after the input array of words
|
|
59
33
|
#
|
|
@@ -79,5 +53,33 @@ module MarkovChains
|
|
|
79
53
|
def get_start_words
|
|
80
54
|
@start_words.sample
|
|
81
55
|
end
|
|
56
|
+
|
|
57
|
+
private
|
|
58
|
+
|
|
59
|
+
# Processes a single sentence with terminator
|
|
60
|
+
#
|
|
61
|
+
# @example Process a sentence
|
|
62
|
+
# process_sentence("It is sunny today", "!")
|
|
63
|
+
#
|
|
64
|
+
# @param [String] sentence to process
|
|
65
|
+
# @param [Character] sentence terminator
|
|
66
|
+
#
|
|
67
|
+
def process_sentence(sentence, terminator)
|
|
68
|
+
# Consider phrases/words/clauses separators when splitting
|
|
69
|
+
seps = "([,;:])"
|
|
70
|
+
|
|
71
|
+
# Split <sentence> into words
|
|
72
|
+
words = sentence.gsub(/[^#{seps}\w'\s]/, "").gsub(/(#{seps})\s+/, '\1').split(/\s+|#{seps}/)
|
|
73
|
+
words << terminator
|
|
74
|
+
|
|
75
|
+
# Add <@order> start words to the list
|
|
76
|
+
@start_words << words[0, @order]
|
|
77
|
+
|
|
78
|
+
# Add the words to the frequency hash <words_for>
|
|
79
|
+
until words.size < @order + 1 do
|
|
80
|
+
(@words_for[words[0, @order]] ||= []) << words[@order]
|
|
81
|
+
words.shift
|
|
82
|
+
end
|
|
83
|
+
end
|
|
82
84
|
end
|
|
83
85
|
end
|
|
@@ -1,3 +1,3 @@
|
|
|
1
1
|
module MarkovChains
|
|
2
|
-
VERSION = '0.1.
|
|
3
|
-
end
|
|
2
|
+
VERSION = '0.1.1'
|
|
3
|
+
end
|