t_learn 0.1.0.1 → 0.1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 749c02d42d8f70120b364673f13e01e8fcca764e
-  data.tar.gz: 9b476e3d0c694fd77503150190a0a8127af3d9ca
+  metadata.gz: b6597d2b7b9978e0c84e5e87920fb4f3fb765887
+  data.tar.gz: 8c54a272723b8640a8d89e0e8937f84a1ab1a279
 SHA512:
-  metadata.gz: e22afcd74b8809c322eb9f9c9a920705005c1519a5a47e1ae20157934f800f48d5741ffdd804ff6df96ba651e5a87195629e133b3312f8780e6e32853e7b130a
-  data.tar.gz: d4c7e03f7ca8d8b3d75b76c4113e60406124e72b98db21db644546f8440909ea6449efd712e6e103af7ac7e2a9827e26a2a1c9a870cb6d276b8ae522a50231b5
+  metadata.gz: 12134be65f46bbe5d9dec8aaaee3b90c8e3c02f9602f30419a75e7a74cb1c1683ca73725cbcbc081e16918114f357b292e5ceadd5fdd4117de9dcf5ae105641a
+  data.tar.gz: 1198ca3aaa4551929242a30e0afa117676702d26ebccc6d7eda6bcadebbfda9a1fb3a9aa7e2150d257a0f9f9a06ae3c3294cd37b2573a2459206d2b68ebc68b4

data/README.md

@@ -1,6 +1,5 @@
 # TLearn
-
-my machine learning library.
+This is my hobby machine learning library.
 I will add machine learning items.
 
 ## Installation
@@ -20,9 +19,52 @@ Or install it yourself as:
     $ gem install t_learn
 
 ## Usage
-### hop filed net
+
+### simple feedforward_neural_network
+respect for keras.
 
 ``` ruby
+def test_fun(x)
+    return ( x*0.9 ).round(2)
+end
+
+
+model = TLearn::FeedForwardNeuralNetwork.new
+model.add_layer(2)
+model.add_layer(5)
+model.add_layer(1)
+
+x_train = [[0.1, 1.0],[0.2, 1.0], [0.4, 1.0], [0.6, 1.0]]
+
+y_train = [[ test_fun(x_train[0][0]) ], [ test_fun(x_train[1][0]) ],[ test_fun(x_train[2][0]) ],[ test_fun(x_train[3][0]) ]]
+model.fit(x_train, y_train, 500000)
+
+x_test = [[0.1, 1.0],[0.2, 1.0], [0.4, 1.0], [0.6, 1.0]]
+y_test = [[ test_fun(x_train[0][0]) ], [ test_fun(x_train[1][0]) ],[ test_fun(x_train[2][0]) ],[ test_fun(x_train[3][0]) ]]
+
+model.evaluate(x_test, y_test)
+
+```
+
+### result
+.... 
+
+```
+
+x [0.1,  1.0],  y 0.09 ,  output 0.22505163646378912
+x [0.2,  1.0],  y 0.18 ,  output 0.2817288022885251
+x [0.4,  1.0],  y 0.36 ,  output 0.3699200581887254
+x [0.6,  1.0],  y 0.54 ,  output 0.42524180537036876
+
+```
+
+
+### hop filed net
+sample
+``` ruby
+
+require "t_learn"
+
 data = [1.0, 1.0, -1.0, -1.0, 1.0]  # teacher data
 hop_field_net = TLearn::HopFieldNet.new(0.0, data)
 hop_field_net.memorize

data/lib/t_learn/feedforward_neural_network.rb

@@ -0,0 +1,174 @@
+#!/usr/bin/ruby
+# -*- encoding: utf-8 -*-
+
+module TLearn
+
+  #
+  # ==
+  #
+  class FeedForwardNeuralNetwork
+    attr_accessor :layer_list, :layer_size, :link_list, :node_id, :learning_rate
+    def initialize(learning_rate=0.3)
+      @layer_size = 0    #layer iterator
+      @layer_list = Array.new
+      @link_list = Hash.new
+      @node_id = 0
+      @learning_rate = learning_rate
+    end
+
+    def add_layer(node_num)
+      node_list = Array.new()
+      node_num.times do |num|
+        node = Node.new(0.2)
+        node.set_id(@node_id)
+        node_list.push(node)
+        @node_id += 1
+      end
+
+      @layer_list.push(node_list)
+      # connect link
+      if @layer_size != 0  # if not first layer
+        # connect link to @layer_size - 1 layer
+        connect_nodes
+      end
+      @layer_size += 1
+    end
+
+    #
+    # === connect_nodes
+    # 
+    def connect_nodes
+      @layer_list[@layer_size - 1].each do |from_node|
+        @layer_list[@layer_size].each do |to_node|
+          @link_list["#{from_node.id}_#{to_node.id}"] = 0.0
+        end
+      end
+    end
+
+    #
+    # === 
+    #
+    # @param x_train Array
+    # @param y_train Array
+    #
+    def fit(x_train, y_train, epoch)
+      # input teacher_datas
+      epoch.times do 
+        x_train.zip(y_train).each do |x, y|
+          propagation(x)
+          # back_propagation 
+          back_propagation(y)
+        end
+      end
+    end
+
+    def propagation(x)
+      # input data 
+      @layer_list[0].each_with_index do |node, i|
+        node.input (x[i])
+      end
+      @layer_size.times do |layer_num|
+        if layer_num != (@layer_size-1)
+          # puts "layernum #{layer_num}"
+          @layer_list[layer_num + 1].each do |to_node|
+            sum_all_from_node = 0.0
+            @layer_list[layer_num].each do |from_node|
+              sum_all_from_node += @link_list["#{from_node.id}_#{to_node.id}"] * from_node.w
+            end
+            to_node.update_w(sum_all_from_node)
+          end
+        end
+      end
+    end
+
+    #
+    # === 
+    # 
+    # @param y Array teacher_data
+    #
+    def back_propagation(y)
+      delta = {}
+      ( @layer_size - 1).downto(1) do |layer_num|
+        if ( @layer_size - 1) == layer_num   # if output layer
+          @layer_list[layer_num].each_with_index do |to_node, i|
+            @layer_list[layer_num - 1].each do |from_node|
+              delta["#{from_node.id}_#{to_node.id}"] = - calc_err(to_node.w,y[i]) * to_node.w * (1.0 - to_node.w)
+              # puts "delta[#{from_node}_#{to_node}]  #{delta['#{from_node}_#{to_node}']}"
+              delta_weight = -1.0 * @learning_rate * delta["#{from_node.id}_#{to_node.id}"] * to_node.w
+              @link_list["#{from_node.id}_#{to_node.id}"] = @link_list["#{from_node.id}_#{to_node.id}"] + delta_weight ;
+            end
+          end
+        else 
+          @layer_list[layer_num].each do |to_node|
+            @layer_list[layer_num - 1].each do |from_node|
+              delta["#{from_node.id}_#{to_node.id}"] = calc_delta(delta,layer_num, to_node) * to_node.w * (1.0 - to_node.w)
+              delta_weight = -1.0 * @learning_rate * delta["#{from_node.id}_#{to_node.id}"] * to_node.w
+              @link_list["#{from_node.id}_#{to_node.id}"] = @link_list["#{from_node.id}_#{to_node.id}"] + delta_weight 
+            end
+          end
+        end
+      end
+    end
+
+    def calc_err(w, teacher_data)
+      return (teacher_data - w )
+    end
+
+    def calc_delta(delta,layer_i, from_node)
+      sum = 0.0
+      @layer_list[layer_i+1].each do |to_node|
+        sum += delta["#{from_node.id}_#{to_node.id}"] * from_node.w 
+      end
+      return sum
+    end
+
+    def evaluate(x_test, y_test)
+      # compare teacher_datas and output of nn
+      sum = 0.0
+      x_test.zip(y_test).each do |x, y|
+        propagation(x)
+        @layer_list[@layer_size -1].zip(y).each do |output, y_|
+          puts "x #{x}, y #{y_} , output #{output.w}"
+          sum += 1 if output.w == y_
+        end
+      end 
+      return (sum/y_test.size) * 100.0
+    end
+
+    class Node
+      attr_accessor :w,:active_function, :threshold, :id
+      def initialize(w = 0.0, active_function = "sig", threshold = 0.5)
+        @w = w 
+        @threshold = threshold 
+        @active_function = active_function
+      end
+
+      def set_id(id) 
+        @id = id
+      end
+
+      # it can use input fase
+      def input(w)
+        @w = w
+      end
+
+      def update_w(input)
+        # update by sigmoid
+        @w = sigmoid_fun(input)
+      end
+
+      def sigmoid_fun(x, a=1)
+        result= (1.0/(1.0+Math.exp(-1.0 * a * x))) ;
+        return result
+      end
+    end
+  end
+end
+
+
+#
+# 実行用
+#
+if($0 == __FILE__) then
+end
+

data/lib/t_learn/version.rb

@@ -1,3 +1,3 @@
 module TLearn
-  VERSION = "0.1.0.1"
+  VERSION = "0.1.1.0"
 end

data/lib/t_learn.rb

@@ -1,5 +1,6 @@
 require "t_learn/version"
 require "t_learn/hop_field_net"
+require "t_learn/feedforward_neural_network"
 
 module TLearn
   # Your code goes here...

data/t_learn.gemspec

@@ -7,7 +7,7 @@ Gem::Specification.new do |spec|
   spec.name          = "t_learn"
   spec.version       = TLearn::VERSION
   spec.authors       = ["Tcom242242"]
-  spec.email         = ["katsuo242242@gmail.com"]
+  spec.email         = ["okano565656@gmail.com"]
 
   spec.summary       = %q{my machine learning lib}
   spec.description   = %q{my machine learning lib}

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: t_learn
 version: !ruby/object:Gem::Version
-  version: 0.1.0.1
+  version: 0.1.1.0
 platform: ruby
 authors:
 - Tcom242242
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-12-22 00:00:00.000000000 Z
+date: 2016-12-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -54,7 +54,7 @@ dependencies:
         version: '3.0'
 description: my machine learning lib
 email:
-- katsuo242242@gmail.com
+- okano565656@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -71,6 +71,7 @@ files:
 - bin/setup
 - lib/t_learn.rb
 - lib/t_learn/em.rb
+- lib/t_learn/feedforward_neural_network.rb
 - lib/t_learn/hop_field_net.rb
 - lib/t_learn/version.rb
 - t_learn.gemspec