dgaff_ml 0.0.4 → 0.0.5

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ZmVmMWMxYWU2ZjM1NWMzOTRjNWVkNDY1OGE1MmJkYjU0MmMyM2Y0NQ==
+    YjcyMDhhYThjMmM2OWNmZWM2Y2Y4Mzk0ZWE1YzBjOGYxNzA4NTkzZg==
   data.tar.gz: !binary |-
-    Y2NmMTQ4NjVjYzNkMzE2ZTgwNmE5Y2NiYTNhOGQxZDAwODA2Mjg3ZQ==
+    Yzg1YzYwY2Y4N2Y1MjMzZGUxZDhjZTBmNzBiNWE4ZTgzZjc4ODkwZA==
 SHA512:
   metadata.gz: !binary |-
-    MTk0Y2ZhNTA3OTJlY2U2ZDI5ZjRhMjllYjg4YjBkMjUxZWQ0ZjAyZDIxZDZh
-    NzIwNjM3NDgyM2ZiOTBkZDZlNzkzY2JlNGQwNWFhMzUwNDBkMWJjNzIxYzkw
-    NWMwMGVmZDc2MTVhMjk2NjE5MTI3OWJlMzZlNDEyOTFkZGE4ZjA=
+    YWRhNWEyMDY5ODc2M2RkNTE3ZGRjODNjNTdmZThlOGRkNjNjODM1NDIyMmEx
+    NjJkYzBiOGNkMWJmMDk0ZGEzOWNlZTVhZjA3ZTI2OGJhZjQzYzMxMTEwOGRl
+    NjBmMjU5ZWQ1MGVmNDRjOGFjZGU3YTRkNTQwOGY0ZmIzMTRiNjI=
   data.tar.gz: !binary |-
-    YjNmZjk0ZGFlNDc5YjRhN2ZkYTA0MmJmNjBmZmUwYWZmOWU3MWI0NjdkOTg5
-    YmFhNzgzNzVlZjEzNmEwNWNmNzVhM2M5MzlkNjAzZTI4MmYwZDgzZjJjYjhj
-    MmQxMTFlY2IwZDkxMzEwY2QxYTIyMTQ0NGFjNWM4YjljODFiZjU=
+    ZDcyYTdhNzg0YzYxMjZhZWQyYzFlZTI3YWY1OTdjYmU5ZThlNDUwOWY1Nzg4
+    NDJmYTlkNmJlZDI3YjExOWZkY2Q0NmM4ODEzZDNhMDYwODI1Y2I4MzM0MjRm
+    MmZmMDVkNWVlNzM4MjZlYTlhYjZlMWFkNTE0ZDc5OTQ1OGE1YWM=

data/dgaff_ml/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/dgaff_ml/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in dgaff_ml.gemspec
+gemspec

data/dgaff_ml/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2017 Devin Gaffney
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/dgaff_ml/README.md

@@ -0,0 +1,31 @@
+# DgaffMl
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'dgaff_ml'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install dgaff_ml
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/dgaff_ml/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/dgaff_ml/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/dgaff_ml/dgaff_ml.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'dgaff_ml/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "dgaff_ml"
+  spec.version       = DgaffMl::VERSION
+  spec.authors       = ["Devin Gaffney"]
+  spec.email         = ["itsme@devingaffney.com"]
+  spec.summary       = %q{TODO: Write a short summary. Required.}
+  spec.description   = %q{TODO: Write a longer description. Optional.}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/dgaff_ml/lib/dgaff_ml/version.rb

@@ -0,0 +1,3 @@
+module DgaffMl
+  VERSION = "0.0.1"
+end

data/dgaff_ml/lib/dgaff_ml.rb

@@ -0,0 +1,5 @@
+require "dgaff_ml/version"
+
+module DgaffMl
+  # Your code goes here...
+end

data/lib/dgaff_ml/client.rb

@@ -7,17 +7,37 @@ class DGaffML
     def initialize(user_id)
       @user = DGaffML::Request.login(user_id)
     end
-    
+
+    def datasets
+      DGaffML::Request.datasets(@user["id"]).collect{|d| DGaffML::Dataset.new(self, d)}
+    end
+
+    def dataset(dataset_id)
+      DGaffML::Dataset.new(self, DGaffML::Request.dataset(@user["id"], dataset_id))
+    end
+
+    def export_model(dataset_id)
+      DGaffML::Model.new(self, DGaffML::Request.export_model(@user["id"], dataset_id))
+    end
+
     def models
-      DGaffML::Request.datasets(@user["id"])
+      DGaffML::Request.models(@user["id"]).collect{|m| DGaffML::Model.new(self, m)}
     end
 
-    def model(dataset_id)
-      DGaffML::Model.new(self, DGaffML::Request.dataset(@user["id"], dataset_id))
+    def model(model_id)
+      DGaffML::Model.new(self, DGaffML::Request.model(@user["id"], model_id))
     end
-    
+
     def predict(dataset_id, obs)
       DGaffML::Request.predict(@user["id"], dataset_id, obs)
     end
+    
+    def apply_to_new_dataset(model_id, filepath, prediction_column)
+      DGaffML::Dataset.new(self, DGaffML::Request.apply_to_new_dataset(@user["id"], model_id, filepath, prediction_column))
+    end
+    
+    def new_dataset(filepath, prediction_column)
+      DGaffML::Dataset.new(self,DGaffML::Request.new_dataset(@user["id"], filepath, prediction_column))
+    end
   end
 end

data/lib/dgaff_ml/dataset.rb

@@ -0,0 +1,118 @@
+class DGaffML
+  class Dataset
+    attr_accessor :dataset
+    def initialize(client, dataset_response)
+      @client = client
+      @dataset = dataset_response
+      @dataset_id = @dataset["id"]
+      @user_id = @dataset["user_id"]
+    end
+    
+    def predict(obs)
+      predictions = @client.predict(@dataset_id, translate_obs(obs))
+      if self.dataset["conversion_pipeline"].keys.include?("label")
+        return predictions.collect{|x| self.dataset["conversion_pipeline"]["label"][x]}
+      else
+        return predictions
+      end
+    end
+    
+    def translate_obs(obs)
+      dataset_keys = (self.dataset["conversion_pipeline"].keys-["label", "internal_headers"]).sort_by(&:to_i)
+      dataset_classes = dataset_keys.collect{|k| self.dataset["col_classes"][k.to_i]}
+      translated_rows = []
+      obs.each do |row|
+        translated_row = []
+        row.each_with_index do |el, i|
+          translated_row << cast_val(el, dataset_classes[i])
+        end
+        translated_rows << translated_row
+      end
+      self.convert(translated_rows, dataset_keys, dataset_classes)
+    end
+
+    def convert(rows, dataset_keys, dataset_classes)
+      transposed = rows.transpose
+      detexted = []
+      labels = []
+      transposed.each_with_index do |col, i|
+        if dataset_classes[i] == "Phrase" || dataset_classes[i] == "Text"
+          self.dataset["conversion_pipeline"][dataset_keys[i]]["unique_terms"].each do |term|
+            counted = []
+            col.each do |row|
+              row = [row.to_s] if row.nil?
+              counted << row.count(term)
+            end
+            detexted << counted
+          end
+        elsif dataset_classes[i] == "Categorical"
+          counted = []
+          col.each do |val|
+            counted << self.dataset["conversion_pipeline"][dataset_keys[i]]["unique_terms"].index(val.to_s)
+          end
+          detexted << counted
+        else
+          conversion_pipeline = self.dataset["conversion_pipeline"][dataset_keys[i]]
+          replaced = col.collect{|r| r||conversion_pipeline["average"]}
+          dist = conversion_pipeline["max"]-conversion_pipeline["min"]
+          detexted << replaced
+          detexted << replaced.collect{|r| (r-conversion_pipeline["min"]).to_f/dist} if dist > 0
+          detexted << replaced.collect{|r| (r-conversion_pipeline["average"]).to_f/conversion_pipeline["stdev"]} if conversion_pipeline["stdev"] > 0
+          detexted << replaced.collect{|r| r.abs}
+        end
+      end
+      return detexted.transpose
+    end
+
+    def clean_str(string)
+      string.
+      gsub(/[^A-Za-z0-9(),!?\'\`]/, " ").
+      gsub("  ", " ").
+      gsub("\'s", " \'s").
+      gsub("", "").
+      gsub("\'ve", " \'ve").
+      gsub("n\'t", " n\'t").
+      gsub("\'re", " \'re").
+      gsub("\'d", " \'d").
+      gsub("\'ll", " \'ll").
+      gsub(",", " , ").
+      gsub("!", " ! ").
+      gsub("\(", " \\( ").
+      gsub("\)", " \\) ").
+      gsub(" \\\(  \\\(  \\\( ", " \(\(\( ").
+      gsub(" \\\)  \\\)  \\\) ", " \)\)\) ").
+      gsub("\?", " \? ").
+      gsub(/\s{2,}/, " ").
+      gsub(Regexp.new("http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"), "<URL/>").
+      gsub("www", " ").
+      gsub("com", " ").
+      gsub("org", " ").
+      strip.
+      downcase
+    end
+    
+    def cast_val(value, directive)
+      if directive == "Integer"
+        return value.to_i
+      elsif directive == "Float"
+        return value.to_f
+      elsif directive == "Time"
+        if value.length == 10 and value.scan(/\d/).count == 10
+          return Time.at(value).to_i
+        elsif value.length == 13 and value.scan(/\d/).count == 13
+          return Time.at(value).to_i
+        else
+          return Chronic.parse(value).to_i
+        end
+      elsif directive == "Text" or directive == "Phrase"
+        return clean_str(value).split(" ").collect{|word| Stemmer::stem_word(word)}
+      elsif directive == "Categorical"
+        return value
+      end
+    end
+    
+    def export_model
+      @client.export_model(@dataset_id)
+    end
+  end
+end

data/lib/dgaff_ml/model.rb

@@ -1,114 +1,15 @@
 class DGaffML
   class Model
-    attr_accessor :model
+    attr_accessor :dataset
     def initialize(client, model_response)
       @client = client
       @model = model_response
-      @dataset_id = @model["id"]
+      @model_id = @model["id"]
       @user_id = @model["user_id"]
     end
     
-    def predict(obs)
-      predictions = @client.predict(@dataset_id, translate_obs(obs))
-      if self.model["conversion_pipeline"].keys.include?("label")
-        return predictions.collect{|x| self.model["conversion_pipeline"]["label"][x]}
-      else
-        return predictions
-      end
-    end
-    
-    def translate_obs(obs)
-      model_keys = (self.model["conversion_pipeline"].keys-["label", "internal_headers"]).sort_by(&:to_i)
-      model_classes = model_keys.collect{|k| self.model["col_classes"][k.to_i]}
-      translated_rows = []
-      obs.each do |row|
-        translated_row = []
-        row.each_with_index do |el, i|
-          translated_row << cast_val(el, model_classes[i])
-        end
-        translated_rows << translated_row
-      end
-      self.convert(translated_rows, model_keys, model_classes)
-    end
-
-    def convert(rows, model_keys, model_classes)
-      transposed = rows.transpose
-      detexted = []
-      labels = []
-      transposed.each_with_index do |col, i|
-        if model_classes[i] == "Phrase" || model_classes[i] == "Text"
-          self.model["conversion_pipeline"][model_keys[i]]["unique_terms"].each do |term|
-            counted = []
-            col.each do |row|
-              row = [row.to_s] if row.nil?
-              counted << row.count(term)
-            end
-            detexted << counted
-          end
-        elsif model_classes[i] == "Categorical"
-          counted = []
-          col.each do |val|
-            counted << self.model["conversion_pipeline"][model_keys[i]]["unique_terms"].index(val.to_s)
-          end
-          detexted << counted
-        else
-          conversion_pipeline = self.model["conversion_pipeline"][model_keys[i]]
-          replaced = col.collect{|r| r||conversion_pipeline["average"]}
-          dist = conversion_pipeline["max"]-conversion_pipeline["min"]
-          detexted << replaced
-          detexted << replaced.collect{|r| (r-conversion_pipeline["min"]).to_f/dist} if dist > 0
-          detexted << replaced.collect{|r| (r-conversion_pipeline["average"]).to_f/conversion_pipeline["stdev"]} if conversion_pipeline["stdev"] > 0
-          detexted << replaced.collect{|r| r.abs}
-        end
-      end
-      return detexted.transpose
-    end
-
-    def clean_str(string)
-      string.
-      gsub(/[^A-Za-z0-9(),!?\'\`]/, " ").
-      gsub("  ", " ").
-      gsub("\'s", " \'s").
-      gsub("", "").
-      gsub("\'ve", " \'ve").
-      gsub("n\'t", " n\'t").
-      gsub("\'re", " \'re").
-      gsub("\'d", " \'d").
-      gsub("\'ll", " \'ll").
-      gsub(",", " , ").
-      gsub("!", " ! ").
-      gsub("\(", " \\( ").
-      gsub("\)", " \\) ").
-      gsub(" \\\(  \\\(  \\\( ", " \(\(\( ").
-      gsub(" \\\)  \\\)  \\\) ", " \)\)\) ").
-      gsub("\?", " \? ").
-      gsub(/\s{2,}/, " ").
-      gsub(Regexp.new("http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"), "<URL/>").
-      gsub("www", " ").
-      gsub("com", " ").
-      gsub("org", " ").
-      strip.
-      downcase
-    end
-    
-    def cast_val(value, directive)
-      if directive == "Integer"
-        return value.to_i
-      elsif directive == "Float"
-        return value.to_f
-      elsif directive == "Time"
-        if value.length == 10 and value.scan(/\d/).count == 10
-          return Time.at(value).to_i
-        elsif value.length == 13 and value.scan(/\d/).count == 13
-          return Time.at(value).to_i
-        else
-          return Chronic.parse(value).to_i
-        end
-      elsif directive == "Text" or directive == "Phrase"
-        return clean_str(value).split(" ").collect{|word| Stemmer::stem_word(word)}
-      elsif directive == "Categorical"
-        return value
-      end
+    def apply_to_new_dataset(filepath, prediction_column)
+      @client.apply_to_new_dataset(@model_id, filepath, prediction_column)
     end
   end
 end

data/lib/dgaff_ml/request.rb

@@ -3,11 +3,15 @@ class DGaffML
     def self.hostname
       "http://machinelearning.devingaffney.com"
     end
-    
+
     def self.login(user_id)
       JSON.parse(RestClient.get(hostname+"/api/#{user_id}").body)
     end
     
+    def self.new_dataset(user_id, filepath, prediction_column)
+      JSON.parse(RestClient.post(hostname+"/api/#{user_id}/new_dataset", {filesize: File.open(filepath).size/1024.0/1024, filename: filepath.split("/").last, csv_data: CSV.read(filepath).to_json, prediction_column: prediction_column}).body)
+    end
+
     def self.dataset(user_id, dataset_id)
       JSON.parse(RestClient.get(hostname+"/api/#{user_id}/dataset/#{dataset_id}").body)
     end
@@ -16,8 +20,25 @@ class DGaffML
       JSON.parse(RestClient.get(hostname+"/api/#{user_id}/datasets").body)
     end
     
+    def self.export_model(user_id, dataset_id)
+      JSON.parse(RestClient.get(hostname+"/api/#{user_id}/dataset/#{dataset_id}/export_model").body)
+    end
+
+    def self.model(user_id, model_id)
+      JSON.parse(RestClient.get(hostname+"/api/#{user_id}/model/#{model_id}").body)
+    end
+
+    def self.models(user_id)
+      JSON.parse(RestClient.get(hostname+"/api/#{user_id}/models").body)
+    end
+
+    def self.apply_to_new_dataset(user_id, model_id, filepath, prediction_column)
+      JSON.parse(RestClient.post(hostname+"/api/#{user_id}/model/#{model_id}/apply_to_new_dataset", {filesize: File.open(filepath).size/1024.0/1024, filename: filepath.split("/").last, csv_data: CSV.read(filepath).to_json, prediction_column: prediction_column}).body)
+    end
+
     def self.predict(user_id, dataset_id, obs)
       JSON.parse(RestClient.post(hostname+"/api/#{user_id}/predict/#{dataset_id}", {data: obs.to_json}).body)
     end
+
   end
 end

data/lib/dgaff_ml/version.rb

@@ -1,3 +1,3 @@
 module DgaffMl
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

data/lib/dgaff_ml.rb

@@ -1,5 +1,7 @@
+require 'csv'
 require "dgaff_ml/version"
 require File.expand_path('../dgaff_ml/client', __FILE__)
+require File.expand_path('../dgaff_ml/dataset', __FILE__)
 require File.expand_path('../dgaff_ml/model', __FILE__)
 require File.expand_path('../dgaff_ml/request', __FILE__)
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dgaff_ml
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Devin Gaffney
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-10-27 00:00:00.000000000 Z
+date: 2017-11-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -93,9 +93,18 @@ files:
 - README.md
 - Rakefile
 - dgaff_ml.gemspec
+- dgaff_ml/.gitignore
+- dgaff_ml/Gemfile
+- dgaff_ml/LICENSE.txt
+- dgaff_ml/README.md
+- dgaff_ml/Rakefile
+- dgaff_ml/dgaff_ml.gemspec
+- dgaff_ml/lib/dgaff_ml.rb
+- dgaff_ml/lib/dgaff_ml/version.rb
 - echo.py
 - lib/dgaff_ml.rb
 - lib/dgaff_ml/client.rb
+- lib/dgaff_ml/dataset.rb
 - lib/dgaff_ml/model.rb
 - lib/dgaff_ml/request.rb
 - lib/dgaff_ml/version.rb