movieDB 0.1.9 → 0.1.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5f17c2732790f64b960010075a59107de517385d
-  data.tar.gz: b5058e6ec52a4c1affe409c93dcdd51c9ccc6625
+  metadata.gz: d50cca9ba4a8eab49599c8fd2dbe0ab856993d34
+  data.tar.gz: 0f8f434ce0c78e6b4604cc326717b75373777818
 SHA512:
-  metadata.gz: 35b23f1af4dcbdf9a705e3651e22b5af4cdda3b15b93b68ead37ffe5f7d880cf868df71a011f3f1d2f3ba197adce5d7fc8b4c4126623321bab960a4b2ef5ee44
-  data.tar.gz: 168741faaff822022c26a4e083b66099034bb50a5bdc346bc55349da545ccef6d81d4ef8abc33d1c061fc7d70b73a6facafb247ea052d4ef65983521b049be63
+  metadata.gz: aba42600c6385faa6383be3e23eae5fa604349de78c2d607d38d6ac34ceaf91239d14db5bb652f14c16c879973acba335617ef9e3e9537bb8e6b46af9e0ee713
+  data.tar.gz: 7b2f064cd6dbc380a1f798923b6ba6428af2b4d161a3421c92eaab1d348a636d5419c17a75577a350fe075133f004f98bc7c456567bc22968c14f4ebdb3c53d6

data/README.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-Although the name suggests a datastore gem, MovieDB is actually a ruby wrapper that inspects, cleans, transform and model imdb data and provides useful data analysis information, suggesting conclusion.  The objective is provide a tool that will help movie/film producers make decisions based on archival imdb data.
+Although the name suggests a datastore gem, MovieDB is actually a ruby wrapper that inspects, cleans, transform and model imdb data and provides useful data analysis information, suggesting conclusion.  The objective and usage is to provide a tool that can aide movie/film producers make statistical decisions based off archival imdb data.
 
 Basic functions and Data Analysis:
 * Data Analysis
@@ -35,7 +35,7 @@ Or install it yourself as:
    
     > require 'MovieDB/data_export'
 
-    > MovieDB::Movie.clear_data_store  #IMPORTANT: Returns and empty array
+    > MovieDB::Movie.clear_data_store  **ONLY IF YOUR WANT TO EMPTY YOUR DATASTORE (ARRAY)
   
     > MovieDB::Movie.send(:get_multiple_imdb_movie_data, "2024544", "1800241", "0791314")
 
@@ -43,9 +43,9 @@ Or install it yourself as:
 
 ## Exported Document
 
-The excel document is stored in the reports directory.
+The exported movie data is stored in your reports directory.
 
-    $ cd /reports/data_analysis_20131203.xls
+    $ cd /reports/imdb_raw_data_20131216.xls
 
 ## Usage - Data Analysis
 

data/lib/movieDB.rb

@@ -179,7 +179,7 @@ unless defined? MovieDB::Movie
                   movie_info.poster = Array.new << @movie_data.poster
                   movie_info.rating = Array.new << @movie_data.rating
                   movie_info.votes = Array.new << @movie_data.votes
-                  movie_info.mpaa_rating = Array.new << @movie_data.mpaa_rating == [nil] ? ["No Ratings"] : [@movie_data.mpaa_rating]
+                  movie_info.mpaa_rating = Array.new << @movie_data.mpaa_rating == [nil] ? ["Not Rated"] : [@movie_data.mpaa_rating]
                   movie_info.tagline = Array.new << @movie_data.tagline
                   movie_info.year = Array.new << @movie_data.year
                   movie_info.release_date = Array.new << @movie_data.release_date

data/lib/movieDB/base.rb

@@ -3,9 +3,9 @@ require 'MovieDB/status_checker'
 require 'MovieDB/movie_error'
 
 module MovieDB #:nodoc
-# MoviesDB v0.1.x is not a datastore gem. Rather is performs mathematical computations for analyzing film data from imdb.  can manage the data store of pre-production, production and final film releases.
-# Its a solution to the common problem of building a multi-database that utilizes both SQL and NoSQL
-# combined features to increase speed and performance for reading records.
+# 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.
   
   class Base
     include StatusChecker

data/lib/movieDB/data_analysis.rb

@@ -9,11 +9,55 @@ module MovieDB
     module AnalysisOfVariance
       module LeastSquares
         module Coefficient_Of_Determination
-         def cod
-           @headers = %w(title x_value y_value)
-           #return @headers
-           #'my coefficiency'
-         end
+          def coefficient_of_determination (directory_name)
+            open_spreadsheet(directory_name)
+            perform_computation
+            insert_data_to_existing_xls_file
+          end
+
+          def open_spreadsheet(directory_name)
+            @book = Spreadsheet.open File.join('reports', directory_name)
+            @sheet = @book.worksheet(0)
+          end
+
+          def perform_computation
+            @col_0 = []
+
+            @sheet.each_with_index do |row, i|
+              @col_0 << @sheet[i, 1]
+            end
+
+            ##
+            # Perform computation on the data collected
+            # TODO: Need to use coefficienct statistical formula
+            # Calculate median as an example but COD formula must be used
+
+            drop_header = @col_0.shift
+
+            row_count = @sheet.rows.count
+            column_count = @sheet.columns[0].count
+
+            @data_processing = @col_0.inject do |sum, n|
+              (sum + n)/(row_count-1)
+            end
+          end
+
+          def report_name
+            module_nesting = Module.nesting[0].to_s.gsub('::', ' ').split()
+            count = module_nesting.size
+            @data_analysis_name = module_nesting[count - 1]
+            @data_analysis_name << '_' <<  "#{Time.now.to_s.gsub(':', '').gsub('-', '').gsub(' ', '').split('')[0..9].join}"
+          end
+
+          def insert_data_to_existing_xls_file
+            filename = ("#{report_name}.xls")
+            #@book.worksheet(0).insert_row(4, [@data_processing ])
+            @sheet[5, 1] = @data_processing
+            @sheet.row(6).push "Median", @data_processing 
+
+            @book.write File.join('reports', filename)
+            return filename
+          end
         end
         module Discrete_Least_Squares_Meshless_Method; end
         module Explained_Sum_Of_Squares; end
@@ -23,7 +67,7 @@ module MovieDB
         module Lack_Of_Fit_Sum_Of_Squares; end
         module Least_Squares_Support_Vector_Machine; end
         module Mean_Squared_Error; end
-        module Moving_Least_Squares; end
+        module Moving_Least_Sqares; end
         module Non_Linear_Iterative_Partial_Least_Squares; end
         module Non_Linear_Least_Squares; end
         module Ordinary_Least_Squares; end

data/lib/movieDB/data_export.rb

@@ -1,5 +1,4 @@
 require "spreadsheet"
-require "MovieDB/data_analysis"
 require "MovieDB"
   
   # This module will write xls document to file
@@ -8,25 +7,6 @@ require "MovieDB"
 
 module MovieDB
   class DataExport < MovieDB::Movie
-    PATH_AOV = MovieDB::DataAnalysis::AnalysisOfVariance::LeastSquares
-    include 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
-    include PATH_AOV::Iteratively_Reweighted_Least_Squares
-    include PATH_AOV::Lack_Of_Fit_Sum_Of_Squares
-    include PATH_AOV::Least_Squares_Support_Vector_Machine
-    include PATH_AOV::Mean_Squared_Error
-    include PATH_AOV::Moving_Least_Squares
-    include PATH_AOV::Non_Linear_Iterative_Partial_Least_Squares
-    include PATH_AOV::Non_Linear_Least_Squares
-    include PATH_AOV::Ordinary_Least_Squares
-    include PATH_AOV::Partial_Least_Squares_Regression
-    include PATH_AOV::Partition_Of_Sums_Of_Squares
-    include PATH_AOV::Residual_Sum_Of_Squares
-    include PATH_AOV::Total_Least_Squares
-    include PATH_AOV::Total_Sum_Of_Squares
-
     class  << self 
       #TODO: Check the data analysis(DA) name. Write a define_method and include the DA.
 
@@ -57,10 +37,15 @@ module MovieDB
       def create_spreadsheet_header
         @sheet.row(0).concat $IMDB_ATTRIBUTES_HEADERS
 
-        format = Spreadsheet::Format.new :color => :blue,
-                         :weight => :bold,
-                         :size => 18
-        @sheet.row(0).default_format = format
+        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
       end
 
       # Loop through array of and array imbd data. Each row has the 
@@ -90,8 +75,10 @@ module MovieDB
           when 'rating' then spreadsheet_body_numeric_data("rating")
           when 'votes' then spreadsheet_body_numeric_data("votes")
           when 'mpaa_rating' then spreadsheet_body_numeric_data("mpaa_rating")
+          when 'tagline' then spreadsheet_body_text_data("tagline")
           when 'year' then spreadsheet_body_numeric_data("year")
           when 'release_date' then spreadsheet_body_numeric_data("release_date")
+          else
           end
         end
       end
@@ -99,7 +86,7 @@ module MovieDB
       def spreadsheet_body_text_data(header_title)
         @e_t = element_title = MovieDB::Movie.instance_eval{filter_movie_attr(header_title)}.flatten
 
-        element_title.each_with_index do |element2,i|
+        element_title.each_with_index do |element2, i|
           element_array = element_title[(i)].split('   ',)
           @sheet.row(1 + i).concat element_array 
         end
@@ -119,7 +106,7 @@ module MovieDB
       def spreadsheet_body_numeric_data(header_title)
         @e_t = element_title = MovieDB::Movie.instance_eval{filter_movie_attr(header_title)}
 
-        element_title.each_with_index do |element2,i|
+        element_title.each_with_index do |element2, i|
           element_array = element_title[(i)]
           @sheet.row(1 + i).concat element_array
         end

data/lib/movieDB/data_process.rb

@@ -0,0 +1,24 @@
+require 'MovieDB/data_analysis'
+
+module MovieDB
+  class DataProcess
+    PATH_AOV = MovieDB::DataAnalysis::AnalysisOfVariance::LeastSquares
+    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
+    include PATH_AOV::Iteratively_Reweighted_Least_Squares
+    include PATH_AOV::Lack_Of_Fit_Sum_Of_Squares
+    include PATH_AOV::Least_Squares_Support_Vector_Machine
+    include PATH_AOV::Mean_Squared_Error
+    include PATH_AOV::Non_Linear_Iterative_Partial_Least_Squares
+    include PATH_AOV::Non_Linear_Least_Squares
+    include PATH_AOV::Ordinary_Least_Squares
+    include PATH_AOV::Partial_Least_Squares_Regression
+    include PATH_AOV::Partition_Of_Sums_Of_Squares
+    include PATH_AOV::Residual_Sum_Of_Squares
+    include PATH_AOV::Total_Least_Squares
+    include PATH_AOV::Total_Sum_Of_Squares
+  end
+end
+

data/lib/movieDB/version.rb

@@ -1,3 +1,3 @@
 module MovieDB
-  VERSION = "0.1.9"
+  VERSION = "0.1.10"
 end

data/spec/{data_analysis_spec.rb → data_process_spec.rb}

@@ -1,45 +1,50 @@
 require 'spec_helper'
 
-describe MovieDB::DataAnalysis do
+describe MovieDB::DataProcess do
 
   describe "#AnalysisOfVariance" do
    describe "#LeastSquares" do
      describe "#Coefficient_Of_Determination" do
-        let(:cof) {MovieDB::DataAnalysis::AnalysisOfVariance::LeastSquares::Coefficient_Of_Determination.cod}
-      
+        let(:cod) {MovieDB::DataProcess}
+        #let(:cod) {MovieDB::DataProcess.analyze_cod(imdb_raw_data_2013121820.xls)}
+
         it "should return the cof" do
-         cof.send(:cod).should == []
+         cod.send(:coefficient_of_determination, 'imdb_raw_data_2013121911.xls').should == []
         end 
+
+        it "raise error if file does not exist" do
+
+        end
      end
-     
+
      describe "#Discrete_Least_Squares_Meshless_Method" do
       pending
      end
-     
+
      describe "#Explained_Sum_Of_Squares" do
       pending
-     end
-     
+     end 
+
      describe "#Fraction_Of_Variance_Unexplained" do
       pending
      end
-     
+
      describe "#Gauss_Newton_Algorithm" do
       pending
      end
-     
+
      describe "#Iteratively_Reweighted_Least_Squares" do
       pending
      end
-     
+
      describe "#Lack_Of_Fit_Sum_Of_Squares" do
       pending
      end
-     
+
      describe "#Least_Squares_Support_Vector_Machine" do
       pending
      end
-     
+
      describe "#Mean_Squared_Error" do
       pending
      end

data/spec/spec_helper.rb

@@ -5,7 +5,7 @@ require 'MovieDB/base'
 require "MovieDB/person"
 require 'MovieDB/status_checker'
 require 'MovieDB/movie_error'
-require "MovieDB/data_analysis"
+require "MovieDB/data_process"
 require "MovieDB/data_export"
 
 RSpec.configure do |config|

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: movieDB
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.1.10
 platform: ruby
 authors:
 - Albert_McKeever
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-18 00:00:00.000000000 Z
+date: 2013-12-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -154,6 +154,7 @@ files:
 - lib/movieDB/base.rb
 - lib/movieDB/data_analysis.rb
 - lib/movieDB/data_export.rb
+- lib/movieDB/data_process.rb
 - lib/movieDB/genre_parser.rb
 - lib/movieDB/genres/en.txt
 - lib/movieDB/movie_error.rb
@@ -163,9 +164,13 @@ files:
 - movieDB.gemspec
 - npm-debug.log
 - reports/.DS_Store
+- reports/Coefficient_Of_Determination_2013121918.xls
+- reports/add.xls
+- reports/imdb_raw_data_2013121911.xls
+- reports/imdb_raw_data_2013121912.xls
 - spec/.DS_Store
-- spec/data_analysis_spec.rb
 - spec/data_export_spec.rb
+- spec/data_process_spec.rb
 - spec/movieDB_spec.rb
 - spec/person_spec.rb
 - spec/spec_helper.rb
@@ -195,8 +200,8 @@ specification_version: 4
 summary: Movie/Film Statistic and Data Analysis
 test_files:
 - spec/.DS_Store
-- spec/data_analysis_spec.rb
 - spec/data_export_spec.rb
+- spec/data_process_spec.rb
 - spec/movieDB_spec.rb
 - spec/person_spec.rb
 - spec/spec_helper.rb