movieDB 0.2.2 → 0.2.4

data/lib/movieDB/base.rb

@@ -3,14 +3,13 @@ require 'MovieDB/status_checker'
 require 'MovieDB/movie_error'
 
 module MovieDB #:nodoc
-# MoviesDB v0.1.x is not a datastore gem. Rather, it is a high-level statistical software that performs
-# mathematical computations for analyzing film data from imdb.  
-# In a nut shell, it is a solution to the common problem of deducing logical hypothesis based off data sets.
-  
+# MoviesDB is not a datastore gem. Rather, it is a high-level statistical software that performs
+# mathematical computations for analyzing film data from imdb.
+# It is a solution to the common problem of deducing logical hypothesis based off movie data.
   class Base
     include StatusChecker
     include MovieError
   end
-
 end
 $:.unshift File.expand_path('..', __FILE__)
+

data/lib/movieDB/data_analysis.rb

@@ -1,18 +1,15 @@
 require 'MovieDB'
 
 module MovieDB
-
-  ##
-  # Analysing, inspecting, cleaning, transforming and modeling data.
-
+  # Analyzing, inspecting, cleaning, transforming and modeling data.
+  #
   class DataAnalysis < MovieDB::Movie
     module AnalysisOfVariance
       module LeastSquares
         module Statistic
-
           def basic_statistic (directory_name)
             open_spreadsheet(directory_name)
-            
+
             if check_imdb_count == true
                puts "*"*41
                puts "* A minimum of 2 Imdb id's are required *"
@@ -29,76 +26,58 @@ module MovieDB
             @book = Spreadsheet.open File.join('reports', directory_name)
             @sheet = @book.worksheet(0)
 
-            ##
-            # Add document formatting
+            title_format = Spreadsheet::Format.new :color => :blue, :weight => :bold, :size => 13
 
-            title_format = Spreadsheet::Format.new :color => :blue,
-                                 :weight => :bold,
-                                 :size => 13
-
-           @sheet.column(22).width = "worldwide_gross".length
+            @sheet.column(22).width = "worldwide_gross".length
           end
 
           def check_imdb_count
             @sheet.rows.count - 1 == 1
           end
 
-          def perform_computation          
-
+          def perform_computation
+          # Perform computation on the data collected.
+          # TODO: Need to use coefficienct statistical formula.
+          # Calculate median as an example but COD formula must be used.
+          # Mean is commonly called as average. Mean or Average is defined as the sum of
+          # all the given elements divided by the total number of elements.
+          #
+          # Range is the difference between the highest and the lowest values in a
+          # frequency distribution.
+          #
+          # Mode is the most frequently occurring value in a frequency distribution.
+          #
+          # Calculate Standard Deviation.
+          # Standard deviation is a statistical measure of spread or variability.
+          #
+          # The standard deviation is the root mean square (RMS) deviation of the
+          # values from their arithmetic mean.
             total_columns = 22
             @column = []
-            @row_count = @sheet.rows.count
 
-            ##
-            # Use this total column count to make it dynamic
-            #total_columns = @column_count = @sheet.column_count
+            @row_count = @sheet.rows.count
 
             1.upto(total_columns) do |c|
-              @column = [] # set instance variable to an empty array
-
-              ##
-              # loop through to collect all elements
-              # The returned array includes both strings and integers elements
+              @column = []
 
               @sheet.each_with_index do |row, i|
                 @column << @sheet[i, 0 + c ]
               end
 
-              @column.shift # delete the string header from the array
-              @column.compact! # delete nil from the array
-              row_count = @sheet.rows.count
-
-              ##
-              # Perform computation on the data collected
-              # TODO: Need to use coefficienct statistical formula
-              # Calculate median as an example but COD formula must be used
+              @column.shift
+              @column.compact!
 
+              row_count = @sheet.rows.count
 
-              if @column.all? {|i| (1..99999999999).include? (i)}
-
+              if @column.all? { |i| (1..99999999999).include? (i) }
                 n = @column.count
                     @column.sort!
 
-                ##
-                # Mean is commonly called as average.Mean or Average is defined as the sum of 
-                # all the given elements divided by the total number of elements.
-                #
-                # Range is the difference between the highest and the lowest values in a 
-                # frequency distribution.
-                #
-                # Mode is the most frequently occurring value in a frequency distribution.
-
-                @mean = @column.sum/n # Find the mean
-                @range = @column.max - @column.min # Find the range
+                @mean = @column.sum / n
+                @range = @column.max - @column.min
 
                 freq = @column.inject(Hash.new(0)) { |h, v| h[v] += 1; h }
-                @mode =  @column.sort_by { |v| freq[v]}.last # Find the mode
-
-                ##
-                # Calculate Standard Deviation 
-                # Standard deviation is a statistical measure of spread or variability.
-                # The standard deviation is the root mean square (RMS) deviation of the
-                # values from their arithmetic mean.
+                @mode =  @column.sort_by { |v| freq[v] }.last # Find the mode
 
                 @column_squared = []
                 @column.each do |col|
@@ -107,15 +86,15 @@ module MovieDB
 
                 @sum_of_column = @column.sum
                 @sum_of_column_squared = @column_squared.sum
-                @standard_dev = Math.sqrt((@sum_of_column_squared -((@sum_of_column)*(@sum_of_column)/n))/(n-1))
+                @standard_dev = Math.sqrt((@sum_of_column_squared - ((@sum_of_column) * (@sum_of_column) / n)) / (n - 1))
 
                  if n.odd?
-                   index = (n + 1)/2
-                   @median = @column[index - 1] # Subtract -1 to reduce index value since array start with an index 0.
+                   index = (n + 1) / 2
+                   @median = @column[index - 1]
                  else
-                   middle_index = n/2
+                   middle_index = n / 2
                    right_index = middle_index + 1
-                   @median = (@column[middle_index - 1] + @column[right_index - 1])/2
+                   @median = (@column[middle_index - 1] + @column[right_index - 1]) / 2
                  end
 
               else
@@ -126,9 +105,6 @@ module MovieDB
                 @standard_dev = "N/A"
               end
 
-              ##
-              # Insert results into spreadsheet cell
-
               @sheet[@row_count + 2, 0 ] =  "Mean"
               @sheet[@row_count + 2, 0 + c ] = @mean
 
@@ -143,7 +119,6 @@ module MovieDB
 
               @sheet[@row_count + 6, 0 ] =  "Standard Deviation"
               @sheet[@row_count + 6, 0 + c ] =  @standard_dev
-
             end
           end
 
@@ -155,13 +130,16 @@ module MovieDB
           end
 
           def insert_data_to_existing_xls_file
-
             filename = ("#{report_name}.xls")
             @book.write File.join('reports', filename)
             return filename
           end
         end
-        module Coefficient_Of_Determination; end
+
+        module Coefficient_Of_Determination
+         # TODO: Add code.
+        end
+
         module Discrete_Least_Squares_Meshless_Method; end
         module Explained_Sum_Of_Squares; end
         module Fraction_Of_Variance_Unexplained; end
@@ -192,12 +170,10 @@ module MovieDB
       module Variable_Kernel_Density_Estimation; end
     end
 
-    ##
-    # primarily EDA is for seeing what the data can 
-    # tell us beyond the formal modeling or hypothesis testing task
-    # The output will be a visual material
-
     module ExploratoryDataAnalysis
+    # primarily EDA is for seeing what the data can
+    # tell us beyond the formal modeling or hypothesis testing task.
+    # The output will be a visual material.
       module Data_Reduction; end
       module Table_Diagonalization; end
       module Configural_Frequency_Analysis; end
@@ -216,12 +192,12 @@ module MovieDB
     module RegressionAnalysis
       module Choice_Modelling; end
 
-      module Generalized_Linear_Model 
-        module Binomial_Regression; end        
-        module Generalized_Additive_Model; end        
-        module Linear_Probability_Model; end        
-        module Poisson_Regression; end        
-        module Zero_Inflated_Model; end           
+      module Generalized_Linear_Model
+        module Binomial_Regression; end
+        module Generalized_Additive_Model; end
+        module Linear_Probability_Model; end
+        module Poisson_Regression; end
+        module Zero_Inflated_Model; end
       end
 
       module Nonparametric_Regression; end
@@ -251,23 +227,19 @@ module MovieDB
     end
   end
 
-  ##
-  #TODO: All Mathetical Calculations go here.
-
   class ExportData
     def write_spreadsheet (data, data_analysis_name)
-    
       begin data_analysis.is_a? String
         @data_analysis_name = data_analysis_name.split.join.gsub('_', ' ').downcase.to_s
         case data_analysis_name
-          when "coefficient of determination"
-            write_coefficient_of_determination 
-          when  "discrete least squares meshless method"
-            write_discrete_least_squares_meshless_method
-          when "discrete least squares meshless method"
-            write_discrete_least_squares_meshless_method
-          else
-          end
+        when "coefficient of determination"
+          write_coefficient_of_determination
+        when  "discrete least squares meshless method"
+          write_discrete_least_squares_meshless_method
+        when "discrete least squares meshless method"
+          write_discrete_least_squares_meshless_method
+        else
+        end
       rescue
         raise ArgumentError, 'invalid attribute'
       end
@@ -275,12 +247,10 @@ module MovieDB
 
     def write_coefficient_of_determination
       book = Spreadsheet::Workbook.new
+
       sheet1 = book.create_worksheet name: "Data Analysis: #{@data_analysis_name}"
       sheet1.row(0).concat %w{title released_date worldwide_gross}
 
-      # Loop through the data to collect  all values. 
-      # Then values into array
-
       data.each_with_index do |value, index|
         sheet1[1, index] = "#{value}"
       end

data/lib/movieDB/data_export.rb

@@ -1,13 +1,14 @@
 require "spreadsheet"
 require "MovieDB"
-  
+
   # This module will write xls document to file
   #
-  # Usage @book = Spreadsheet::Workbook.new
-
+  # Usage
+  #
+  #    @book = Spreadsheet::Workbook.new
 module MovieDB
   class DataExport < MovieDB::Movie
-    class  << self 
+    class  << self
       #TODO: Check the data analysis(DA) name. Write a define_method and include the DA.
 
       def export_movie_data
@@ -17,12 +18,11 @@ module MovieDB
       end
 
       def create_spreadsheet_file
-        directory_name = ('reports')
+        directory_name = 'reports'
         create_directory(directory_name)
         Spreadsheet.client_encoding = 'UTF-8'
         @book = Spreadsheet::Workbook.new
-        @sheet = @book.create_worksheet name: "Data Analysis: #{$DATA_ANALYSIS_NAME}" # the analysis nameshould be an input
-
+        @sheet = @book.create_worksheet name: "Data Analysis: #{$DATA_ANALYSIS_NAME}" # the analysis name should be an input
       end
 
       def create_directory(directory_name)
@@ -37,26 +37,25 @@ module MovieDB
       def create_spreadsheet_header
         @sheet.row(0).concat $IMDB_ATTRIBUTES_HEADERS
 
-        title_format = Spreadsheet::Format.new :color => :blue,
-                                         :weight => :bold,
-                                         :size => 13
-
+        title_format = Spreadsheet::Format.new :color => :blue, :weight => :bold, :size => 13
         float_format = Spreadsheet::Format.new :number_format => "0.00"
 
         @sheet.row(0).default_format = title_format
+
         @sheet.column(1).default_format = float_format
         @sheet.column(16).default_format = float_format
         @sheet.column(22).default_format = float_format
       end
 
-      # Loop through array of and array imbd data. Each row has the 
+      # Loop through array of and array imbd data. Each row has the
       # the information about the film/movie
       # The Data is obtained from MovieDB::Movie
       # example
-      # catching fire |
+      #
+      #   Film: catching fire
       def create_spreadsheet_body
-       $IMDB_ATTRIBUTES_HEADERS.each do |header|
-        case header
+        $IMDB_ATTRIBUTES_HEADERS.each do |header|
+          case header
           when 'title' then spreadsheet_body_text_data("title")
           when 'cast_members' then spreadsheet_body_count_data("cast_members")
           when 'cast_characters' then spreadsheet_body_count_data("cast_characters")
@@ -86,19 +85,19 @@ module MovieDB
       end
 
       def spreadsheet_body_text_data(header_title)
-        @e_t = element_title = MovieDB::Movie.instance_eval{filter_movie_attr(header_title)}.flatten
+        @e_t = element_title = MovieDB::Movie.instance_eval { filter_movie_attr(header_title) }.flatten
 
         element_title.each_with_index do |element2, i|
           element_array = element_title[(i)].split('   ',)
-          @sheet.row(1 + i).concat element_array 
+          @sheet.row(1 + i).concat element_array
         end
       end
 
       def spreadsheet_body_count_data(header_title)
-         element_cast = MovieDB::Movie.instance_eval{filter_movie_attr(header_title)}
+        element_cast = MovieDB::Movie.instance_eval { filter_movie_attr(header_title) }
 
-         0.upto(@e_t.length - 1) do |i|
-           element_array = []
+        0.upto(@e_t.length - 1) do |i|
+          element_array = []
 
           element_array << element_cast[i].length
           @sheet.row(1 + i).concat element_array
@@ -106,7 +105,7 @@ module MovieDB
       end
 
       def spreadsheet_body_numeric_data(header_title)
-        @e_t = element_title = MovieDB::Movie.instance_eval{filter_movie_attr(header_title)}
+        @e_t = element_title = MovieDB::Movie.instance_eval { filter_movie_attr(header_title) }
 
         element_title.each_with_index do |element2, i|
           element_array = element_title[(i)]

data/lib/movieDB/data_process.rb

@@ -5,6 +5,7 @@ module MovieDB
     PATH_AOV = MovieDB::DataAnalysis::AnalysisOfVariance::LeastSquares
     extend PATH_AOV::Statistic
     extend PATH_AOV::Coefficient_Of_Determination
+
     include PATH_AOV::Explained_Sum_Of_Squares
     include PATH_AOV::Fraction_Of_Variance_Unexplained
     include PATH_AOV::Gauss_Newton_Algorithm

data/lib/movieDB/genres/en.txt

@@ -26,4 +26,3 @@ Talk-Show
 Thriller
 War
 Western
-

data/lib/movieDB/person.rb

@@ -1,20 +1,19 @@
 require 'rubygems'
 require 'time'
-
-  ##
-  # Create an actor instance and return the values  for 
-  # actor = MovieDB::Actor.instance_eval{create_with_info("Brittany Murphy", "F", "1977-11-10", "2009-12-20")}
-  # actor = MovieDB::Actor.instance_eval{create_with_info("George Clooney", "M", "1961-05-06", nil)}
-  #   # Name
-  #   # actor_name = actor.map(&:name) #=> ["Brittany Murphy"]
-  #
-  #   # Alive?
-  #   # actor_name = actor.map(&:alive?) #=> [false, true]
-  #
-  #   # Age
-  #   # actor_name = actor.map(&:age) #=> [32, 52]
-  #
-
+# Create an actor instance and return the values for the actor variable.
+#
+#    actor = MovieDB::Actor.instance_eval{create_with_info("Brittany Murphy", "F", "1977-11-10", "2009-12-20")}
+#    actor = MovieDB::Actor.instance_eval{create_with_info("George Clooney", "M", "1961-05-06", nil)}
+
+#  Example to find the actor name:
+#
+#    actor_name = actor.map(&:name) #=> ["Brittany Murphy"]
+#
+#  Example to see if an actoyre is alive:
+#    actor_name = actor.map(&:alive?) #=> [false, true]
+#
+#   Example to find an actor's age:
+#     actor_name = actor.map(&:age) #=> [32, 52]
 module MovieDB
   class Person
     attr_accessor :name, :gender, :birth_date, :death_date, :birthplace
@@ -49,27 +48,28 @@ module MovieDB
         person.gender = gender
         person.birth_date = birth_date
         person.death_date = death_date
+
         return @person_DS << person
       end
 
       def filter_person(attr)
        attr = attr.to_sym
-       raise ArgumentError, "#{attr} can only be name or age" if !attr == :age && :name
+       raise ArgumentError "#{attr} can only be name or age" if !attr == :age && :name
+
        return @person_DS.select{|s| s.alive?}.map(&attr)
       end
 
-  ##
-  # Returns a random parameter integer between min to max, 
-  # rather than a float between min to max.(Ruby 2.0.0)
-  #
-
+      # Returns a random parameter integer between min to max,
+      # rather than a float between min to max.(Ruby 2.0.0)
       def sample_attr(attr)
         randgen = Object.new
         attr_array = self.instance_eval{filter_person(attr)}
         attr_array.sample(random: randgen)
       end
     end
+
     private_class_method :create_with_info, :filter_person
+
   end
 
   class Actor < Person
@@ -85,7 +85,8 @@ module MovieDB
     end
 
     def actor_actress_gender(person)
-      case when person.gender == 'F'
+      case
+      when person.gender == 'F'
         return "actress"
       when person.gender == "M"
         return "actor"
@@ -95,23 +96,22 @@ module MovieDB
     end
 
     class << self
-
       def filter_actor_alive(attr)
        attr = attr.to_sym
-       raise ArgumentError, "#{attr} can only be name or age" if !attr == :age && :name
+       raise ArgumentError "#{attr} can only be name or age" if !attr == :age && :name
+
        return @person_DS.select{|s| s.alive?}.map(&"#{attr.to_sym}")
       end
 
       def filter_actor_deceased(actor)
-       return @person_DS.select{|s| !s.alive?}.map{|m| "#{m.age}"} if attr == "age"
-       return @person_DS.select{|s| !s.alive?}.map{|m| "#{m.name}"} if attr == "name"
+       return @person_DS.select{ |s| !s.alive?}.map{ |m| "#{m.age}" } if attr == "age"
+       return @person_DS.select{ |s| !s.alive?}.map{ |m| "#{m.name}" } if attr == "name"
       end
 
     end
   end
 
   class Writer < Person
-
     attr_accessor :published_work
     alias :published? :published_work
 
@@ -123,7 +123,6 @@ module MovieDB
   end
 
   class Director < Person
-
     attr_accessor :filmography
 
     def initialize(filmography = [])