sentimentalizer 0.2.2 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e3157d1123401a03ced17de7c55e6115331490aa
-  data.tar.gz: 07869dd69cb3bd464b3d391b35546b70348b6a46
+  metadata.gz: adaa7fcb374f3b8778289f933b001a8878db2b27
+  data.tar.gz: 6fe6763906ebfa20cbec0083f5fa08ce90088811
 SHA512:
-  metadata.gz: be56e07803500a0714e23061e14fb27f06020671cad0c70622219b75907c90e8c897e52360bda6e3f29964047b4737d95fb5592096ea3abcca0c63a93cf8d132
-  data.tar.gz: 458e80553d5b36aa2b068a9dd002c8a7471875e3e5f9284543889b6535f624edcfcb55f0ec1cfd8960e3fc593b9db0f0c44a3acc5624a1dfe953f9ac6fabc810
+  metadata.gz: 26818b295d83d8b0bf2d90cd2ea3f144052b496aaf45710e2593cbb170b3cf57791fc39f4360a8e52e35915b9cde698d473509ec21de883f0e324415ce90ac5f
+  data.tar.gz: cefeae99f73f11bdf590a18e8dcca0e204a8cdd5a624ade0cb1038087bd84ba8dc310048079f50e3480ce230cca080c11e3e63593eaa2f2c75dbe8cb210181b9

data/README.md

@@ -10,7 +10,7 @@ This gem can be used separately or integrated with rails app.
 
 # Codeclimate [![Code Climate](https://codeclimate.com/github/malavbhavsar/sentimentalizer.png)](https://codeclimate.com/github/malavbhavsar/sentimentalizer)
 
-## Instructions for use
+## Instructions for Rails use
 
 1. Install gem using bundler `gem "sentimentalizer"`
 
@@ -23,7 +23,7 @@ Sentimentalizer.analyze('message or tweet or status')
 Sentimentalizer.analyze('message or tweet or status', true)
 ```
 
-4. You will get output like this 
+You will get output like this 
 ```ruby
 Sentimentalizer.analyze('i am so happy')
 => {'text' => 'i am so happy', 'probability' => '0.937', 'sentiment' => ':)' }
@@ -31,6 +31,43 @@ Sentimentalizer.analyze('i am so happy', true)
 => "{\"text\":\"i am so happy\",\"probability\":\"0.937\",\"sentiment\":\":)\"}"
 ```
 
+## Instructions for Vanilla Ruby use
+
+1. Install gem using bundler `gem "sentimentalizer"`
+
+2. Either fire up `irb`, or require it in your project with `require 'sentimentalizer'`
+
+3. Now, you need to train the engine in order to use it
+
+```ruby
+require "sentimentalizer"
+
+Sentimentalizer.setup
+
+# or, wrap it in a class so setup can be automatic
+class Analyzer
+  def initialize
+    Sentimentalizer.setup
+  end
+  
+  def process(phrase)
+    Sentimentalizer.analyze phrase
+  end
+end
+
+# or for json output
+Sentimentalizer.analyze('message or tweet or status', true)
+```
+
+And now you will get output like this 
+```ruby
+analyzer = Analyzer.new
+analyzer.process('i am so happy')
+=> {'text' => 'i am so happy', 'probability' => '0.937', 'sentiment' => ':)' }
+analyzer.process('i am so happy', true)
+=> "{\"text\":\"i am so happy\",\"probability\":\"0.937\",\"sentiment\":\":)\"}"
+```
+
 ## Contributing to sentimentalizer
  
 * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.

data/VERSION

@@ -1 +1 @@
-0.2.2
+0.3.0

data/lib/engine/classifier.rb

@@ -61,6 +61,7 @@ class Classifier
     negative_ratio = negative_count.to_f / negative_total
 
     probability = positive_ratio.to_f / (positive_ratio + negative_ratio)
+    probability = 0 if probability.nan?
 
     ((UNKNOWN_WORD_STRENGTH*UNKNOWN_WORD_PROBABILITY) + (total * probability)) / (UNKNOWN_WORD_STRENGTH+total)
   end

data/lib/engine/corpus.rb

@@ -18,7 +18,7 @@ class Corpus
 
   def load_from_directory directory
     Dir.glob("#{directory}/*.txt") do |entry|
-      IO.foreach(entry) do |line|
+      IO.foreach(entry, encoding: Encoding::UTF_8) do |line|
         add Document.new(line)
       end
     end

data/sentimentalizer.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: sentimentalizer 0.2.2 ruby lib
+# stub: sentimentalizer 0.3.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "sentimentalizer"
-  s.version = "0.2.2"
+  s.version = "0.3.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["malavbhavsar"]
-  s.date = "2014-12-27"
+  s.date = "2016-04-08"
   s.description = "Sentiment analysis with ruby."
   s.email = "malav.bhavsar@gmail.com"
   s.extra_rdoc_files = [

data/spec/sentimentalizer_spec.rb

@@ -4,16 +4,20 @@ describe "Sentimentalizer" do
   before do
     Sentimentalizer.setup
   end
-  
+
   it "will error without a valid input" do
     expect{Sentimentalizer.analyze("")}.to raise_error
   end
-  
+
   it "will return a valid ruby hash with a valid input" do
     Sentimentalizer.analyze("I hate not tests").sentiment.should eq(":(")
   end
-  
+
   it "will return a valid json string with a valid input" do
     JSON.parse(Sentimentalizer.analyze("I hate not tests", true))["sentiment"].should eq(":(")
   end
-end
+
+  it "will assign a probability of .5 in the case of an unknown word" do
+    Sentimentalizer.analyze("a;lsdnzi").overall_probability.should eq(0.5)
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sentimentalizer
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.3.0
 platform: ruby
 authors:
 - malavbhavsar
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-12-27 00:00:00.000000000 Z
+date: 2016-04-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec