te_rex 0.0.5 → 0.0.10
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/te_rex/bayes.rb +11 -5
- data/lib/te_rex/version.rb +1 -1
- data/lib/te_rex.rb +7 -0
- data/test/test_helper.rb +9 -0
- data/test/test_modules/refund.rb +0 -1
- data/test/test_modules/unknown.rb +1 -0
- metadata +19 -23
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 41cbaf3893f705db1f366bdf247e0882971d860b
|
4
|
+
data.tar.gz: 909c02dd6578c76bdc5ec7ae4cab8f3b7cedd8d1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b9878b1e86ec13e17dd892abc4c615e1e369f692ea020413f121687af8b70c50a597557f7f36674f2a87464657edd62edd9f4ca62ab901fe3e042d98443180b8
|
7
|
+
data.tar.gz: 08a16cf36d77697253a56147fc3903f505ef5c09ebbfa7eb6f03474e44f87418a29a8c4640c8a46fb242cc441a39e193fa57bb9a8218653095eec9b3c519451e
|
data/lib/te_rex/bayes.rb
CHANGED
@@ -6,10 +6,15 @@ module TeRex
|
|
6
6
|
class Bayes
|
7
7
|
|
8
8
|
attr_accessor :category_counts, :total_words
|
9
|
+
attr_reader :messages
|
9
10
|
|
11
|
+
# categories = [{:tag => "Thing1", :msg => "Thing1 message"}, {:tag => "Thing2", :msg => "Thing2 message"}]
|
12
|
+
# initialize({:tag => "Refund", :msg => "You'll get a refund"}, {:tag => "Nonrefund", :msg => "You won't get a refund"})
|
10
13
|
def initialize(*categories)
|
11
|
-
@clasif = Hash.new
|
12
|
-
|
14
|
+
@clasif = Hash.new
|
15
|
+
@messages = Hash.new
|
16
|
+
categories.each {|cat| @clasif[TeRex::Format.category_term(cat[:tag])] = Hash.new}
|
17
|
+
categories.each {|cat| @messages[cat[:tag]] = cat[:msg]}
|
13
18
|
@total_words = 0
|
14
19
|
@category_counts = Hash.new(0)
|
15
20
|
end
|
@@ -18,7 +23,7 @@ module TeRex
|
|
18
23
|
category = TeRex::Format.category_term(ctgry)
|
19
24
|
@category_counts[category] += 1
|
20
25
|
|
21
|
-
BayesData.index_frequency(text).each do |word, count|
|
26
|
+
BayesData.index_frequency(text).each do |word, count|
|
22
27
|
@clasif[category][word] ||= 0
|
23
28
|
@clasif[category][word] += count
|
24
29
|
|
@@ -46,7 +51,8 @@ module TeRex
|
|
46
51
|
end
|
47
52
|
|
48
53
|
def classify(text)
|
49
|
-
(classifications(text).sort_by{|a| -a[1]})[0][0]
|
54
|
+
tag = (classifications(text).sort_by{|a| -a[1]})[0][0]
|
55
|
+
[tag, @messages[tag]]
|
50
56
|
end
|
51
57
|
|
52
58
|
def categories
|
@@ -59,7 +65,7 @@ module TeRex
|
|
59
65
|
@clasif.each_pair do |term,val|
|
60
66
|
cc = self.category_counts[term]
|
61
67
|
train_ratio = (@total_words/cc).to_f
|
62
|
-
tmp << [(train_ratio
|
68
|
+
tmp << [(train_ratio >= max_threshold), term, "description" => {"training_ratio" => "#{train_ratio}", "threshold" => "#{max_threshold}", "category_counts" => "#{cc}", "total_words" => "#{@total_words}"}]
|
63
69
|
end
|
64
70
|
tmp
|
65
71
|
end
|
data/lib/te_rex/version.rb
CHANGED
data/lib/te_rex.rb
CHANGED
data/test/test_helper.rb
ADDED
data/test/test_modules/refund.rb
CHANGED
@@ -25,7 +25,6 @@ module TeRex
|
|
25
25
|
"- 12 NOON HOTEL TIME DAY OF ARRIVAL TO AVOID BILLING OF 1NT ROOM AND TAX OR FORFEITURE OF DEPOSIT",
|
26
26
|
"RESERVATIONS MUST BE CANCELLED BY 1600/4PM DAY OF ARRIVAL LOCAL HOTEL TIME TO AVOID A PENALTY OF ONE NIGHT ROOM AND TAX CHARGE. NOTE- INDIVIDUAL PLANS MAY VARY. PLEASE READ INDIVIDUAL DISPLAY FOR MORE INFORMATION. **50.00USD EARLY DEPARTURE FEE** .",
|
27
27
|
"- RESERVATIONS BOOKED 8 DAYS OR MORE PRIOR TO ARRIVAL MUST BE CANCELLED 7 DAYS PRIOR TO ARRIVAL TO RECEIVE REFUND - RESERVATIONS BOOKED WITHIN 7 DAYS OF ARRIVAL FORFEIT DEPOSIT OF 3 NIGHTS ROOM AND TAX",
|
28
|
-
"ALL RESERVATIONS MUST BE CANCELLED 24 HOURS PRIOR TO HOST TIME UNLESS DEPOSIT REQUIRED IF THIS RESERVATION HAS BEEN MADE ELECTRONICALLY PLEASE CANCEL IT ELECTRONICALLY TO AVOID CONFUSION AND A NO SHOW BILL POLICY SUBJECT TO CHANGE .",
|
29
28
|
"PLEASE REFER TO RATE DETAILS AT THE TIME OF BOOKING FOR CANCELLATION POLICY. PLEASE NOTE THAT POLICY IS SUBJECT TO CHANGES WITHOUT NOTICE."
|
30
29
|
]
|
31
30
|
end
|
@@ -3,6 +3,7 @@ module TeRex
|
|
3
3
|
UNKNOWN = [
|
4
4
|
"The cancellation policy will be determined when the rate is validated.",
|
5
5
|
"-CANCEL POLICY MAY VARY BY DAY OF WEEK AND SEASON. THE MOST ACCURATE CANCEL POLICY IS ADVISED DURING BOOKING PROCESS. IN CASE OF A NO-SHOW THE CREDIT CARD WILL BE CHARGED ONE NIGHT STAY. OUR SYSTEM ACKNOWLEDGES ALL PROPERLY CANCELED RESERVATIONS BY RETURNING A CANCELLATION NUMBER. DO NOT ASSUME YOUR RESERVATION IS CANCELED IF YOU HAVE NOT RECEIVED A CANCELLATION NUMBER IN YOUR PNR OR BOOKING FILE. IF YOU DO NOT RECEIVE A CANCELLATION NUMBER, PLEASE CALL THE CHOICE GDS DEPARTMENT AT 1-866-953-4570",
|
6
|
+
"CANCELLATION DEADLINES MAY VARY BY DATES OF ARRIVAL/ SPECIAL EVENTS OR BY RATE PLAN. PLEASE READ THE RATE RULES FOR YOUR RESERVATION FOR THE EXACT DEADLINE. FAILURE TO CANCEL WITHIN THE DEADLINE WILL RESULT IN A CANCELLATION FEE THAT COULD RANGE FROM 1 NIGHT UP TO THE TOTAL AMOUNT OF STAY. NON REFUNDABLE RATES CANNOT BE CANCELLED AND ARE SUBJECT TO FULL AMOUNT OF STAY PENALTY. -EARLY CHECKOUT POLICY -NO CHARGE FOR EARLY DEPARTURE AS LONG AS THE GUEST CHECKS OUT BY 12PM EASTERN STANDARD TIME -EXCEPTIONS MAY APPLY DURING SPECIAL EVENTS OR CONVENTIONS - SEE RATE RULES.",
|
6
7
|
"-14JAN02 - END - CANCEL POLICIES VARY BY HOTEL. SINCE A HOTEL CAN SET A CANCELLATION POLICY OF UP TO 30 DAYS IN ADVANCE, PLEASE REVIEW POLICY PRIOR TO BOOKING TO AVOID POSSIBLE CHARGE."
|
7
8
|
]
|
8
9
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: te_rex
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.10
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Joshua Bowles
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-
|
11
|
+
date: 2014-11-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: fast-stemmer
|
@@ -111,65 +111,59 @@ dependencies:
|
|
111
111
|
- !ruby/object:Gem::Version
|
112
112
|
version: 0.10.1
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
|
-
name: pry-
|
114
|
+
name: pry-rescue
|
115
115
|
requirement: !ruby/object:Gem::Requirement
|
116
116
|
requirements:
|
117
117
|
- - "~>"
|
118
118
|
- !ruby/object:Gem::Version
|
119
|
-
version: '
|
119
|
+
version: '1.4'
|
120
120
|
- - ">="
|
121
121
|
- !ruby/object:Gem::Version
|
122
|
-
version:
|
122
|
+
version: 1.4.1
|
123
123
|
type: :development
|
124
124
|
prerelease: false
|
125
125
|
version_requirements: !ruby/object:Gem::Requirement
|
126
126
|
requirements:
|
127
127
|
- - "~>"
|
128
128
|
- !ruby/object:Gem::Version
|
129
|
-
version: '
|
129
|
+
version: '1.4'
|
130
130
|
- - ">="
|
131
131
|
- !ruby/object:Gem::Version
|
132
|
-
version:
|
132
|
+
version: 1.4.1
|
133
133
|
- !ruby/object:Gem::Dependency
|
134
|
-
name: pry-
|
134
|
+
name: pry-stack_explorer
|
135
135
|
requirement: !ruby/object:Gem::Requirement
|
136
136
|
requirements:
|
137
137
|
- - "~>"
|
138
138
|
- !ruby/object:Gem::Version
|
139
|
-
version: '
|
139
|
+
version: '0.4'
|
140
140
|
- - ">="
|
141
141
|
- !ruby/object:Gem::Version
|
142
|
-
version:
|
142
|
+
version: 0.4.9.1
|
143
143
|
type: :development
|
144
144
|
prerelease: false
|
145
145
|
version_requirements: !ruby/object:Gem::Requirement
|
146
146
|
requirements:
|
147
147
|
- - "~>"
|
148
148
|
- !ruby/object:Gem::Version
|
149
|
-
version: '
|
149
|
+
version: '0.4'
|
150
150
|
- - ">="
|
151
151
|
- !ruby/object:Gem::Version
|
152
|
-
version:
|
152
|
+
version: 0.4.9.1
|
153
153
|
- !ruby/object:Gem::Dependency
|
154
|
-
name:
|
154
|
+
name: simplecov
|
155
155
|
requirement: !ruby/object:Gem::Requirement
|
156
156
|
requirements:
|
157
|
-
- - "~>"
|
158
|
-
- !ruby/object:Gem::Version
|
159
|
-
version: '0.4'
|
160
157
|
- - ">="
|
161
158
|
- !ruby/object:Gem::Version
|
162
|
-
version: 0
|
159
|
+
version: '0'
|
163
160
|
type: :development
|
164
161
|
prerelease: false
|
165
162
|
version_requirements: !ruby/object:Gem::Requirement
|
166
163
|
requirements:
|
167
|
-
- - "~>"
|
168
|
-
- !ruby/object:Gem::Version
|
169
|
-
version: '0.4'
|
170
164
|
- - ">="
|
171
165
|
- !ruby/object:Gem::Version
|
172
|
-
version: 0
|
166
|
+
version: '0'
|
173
167
|
description: Simple text processing for small data sets.
|
174
168
|
email:
|
175
169
|
- jbowayles@gmail.com
|
@@ -190,12 +184,13 @@ files:
|
|
190
184
|
- test/alpha_num_test.rb
|
191
185
|
- test/bayes_data_test.rb
|
192
186
|
- test/sparse_bayes_test.rb
|
187
|
+
- test/test_helper.rb
|
193
188
|
- test/test_modules/nonrefund.rb
|
194
189
|
- test/test_modules/partrefund.rb
|
195
190
|
- test/test_modules/refund.rb
|
196
191
|
- test/test_modules/unknown.rb
|
197
192
|
- test/trained_bayes_test.rb
|
198
|
-
homepage:
|
193
|
+
homepage: https://github.com/jbowles/te_rex
|
199
194
|
licenses:
|
200
195
|
- MIT
|
201
196
|
metadata: {}
|
@@ -215,7 +210,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
215
210
|
version: '0'
|
216
211
|
requirements: []
|
217
212
|
rubyforge_project:
|
218
|
-
rubygems_version: 2.
|
213
|
+
rubygems_version: 2.2.2
|
219
214
|
signing_key:
|
220
215
|
specification_version: 4
|
221
216
|
summary: Basic NLP stuff for small data sets. Naive Bayes classification and corpora
|
@@ -224,6 +219,7 @@ test_files:
|
|
224
219
|
- test/alpha_num_test.rb
|
225
220
|
- test/bayes_data_test.rb
|
226
221
|
- test/sparse_bayes_test.rb
|
222
|
+
- test/test_helper.rb
|
227
223
|
- test/test_modules/nonrefund.rb
|
228
224
|
- test/test_modules/partrefund.rb
|
229
225
|
- test/test_modules/refund.rb
|