spout 0.9.0.beta2 → 0.9.0.rc

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 738f593886806a8cd02c43abb77999efbaa47ef0
-  data.tar.gz: ee1184bd6176e948ddd30dc88ce32c1fa691d4b8
+  metadata.gz: 903443bf7697903d3e8d78462afdf5dfba77df55
+  data.tar.gz: 011b51f8ef1128790ab7f15ebbd6854f03175a56
 SHA512:
-  metadata.gz: 08340a055a4ac3280bc1cf0365bc90a23708dd6092f33d1dbb478a633cb70b0232cce2df1d3e113ed40260f4680d2d37aa432ba7c3bf99a7472ae82f25dfcb9e
-  data.tar.gz: fc1a360a0279b16c0ba51282c00f6b1b0300e8ad210791f1477e9128735bae2a6d818726ae5089c226de2da225623ca6224738363176221538ad749f0e34fcaa
+  metadata.gz: 6c0f00e614dc71910e91102e8ec3c994c88372b42c7977ee7fe860f79b76c83c25ab75e806236a5d5891faac95378fbc1f3dbf0da91adc5a79066c04cd2d9445
+  data.tar.gz: 4d35e2bc0d5e8662c8959ed76d7da8dbbd4e04fe3f864b8a4cea22164cd093c9ba571e2a48a6b486db94795fe19c399bfffe49462ffbe87d1e6795e859145746

data/CHANGELOG.md

@@ -7,6 +7,19 @@
     - Ex: If a dataset exists in folder 0.2.0, then this folder will be used.
     - Ex: If datasets exist in 0.2.0, 0.2.1.beta2, and 0.2.1, then the exact match, 0.2.1.beta2, will be used.
     - Ex: If datasets exist in 0.2.0, 0.2.1.beta1, 0.2.1, and 0.3.0, then the highest match on the minor version is used, in this case 0.2.1.
+  - `spout p` command now uses same syntax as `spout g` command to reference variables
+    - `spout p <variable_id>`
+    - `spout p age --size-sm`
+  - The data dictionary slug can now be specified in the `spout.yml` file:
+    - `slug: my-repo-name`
+    - Setting the slug will allow the `spout export` command to export the data dictionary to `my-repo-name-data-dictionary-0.1.0-variables.csv`, etc.
+  - `spout p` and `spout g` now indicate if the target CSV folder is empty
+  - `spout o` now only calculates averages and outliers for `numeric` and `integer` variables
+- **Testing Changes**
+  - Multi-line assertions now maintain the correct amount of white-space padding
+- **Gem Changes**
+  - Use of Ruby 2.1.3 is now recommended
+  - Updated to simplecov 0.9.1
 
 ## 0.8.0 (June 27, 2014)
 
@@ -71,7 +84,7 @@
     - `spout p --size-sm`
     - `spout p --type-numeric --size-sm`
   - For specific variables the following can be used:
-    - `spout p --id-<variable_id>`
+    - `spout p --id-<variable_id>` **NOTE** changed in v0.9.0
 
 ## 0.6.0 (March 7, 2014)
 

data/README.md

@@ -2,7 +2,7 @@
 
 [![Build Status](https://travis-ci.org/sleepepi/spout.svg?branch=master)](https://travis-ci.org/sleepepi/spout)
 [![Dependency Status](https://gemnasium.com/sleepepi/spout.svg)](https://gemnasium.com/sleepepi/spout)
-[![Code Climate](https://codeclimate.com/github/sleepepi/spout.png)](https://codeclimate.com/github/sleepepi/spout)
+[![Code Climate](https://codeclimate.com/github/sleepepi/spout/badges/gpa.svg)](https://codeclimate.com/github/sleepepi/spout)
 
 Turn your CSV data dictionary into a JSON repository. Collaborate with others to update the data dictionary in JSON format. Generate new Data Dictionary from the JSON repository. Test and validate your data dictionary using built-in tests, or add your own tests and validations.
 
@@ -232,7 +232,7 @@ The following flags can be passed to the `spout pngs` command:
 - `spout p --type-numeric --size-sm`
 
 For specific variables the following can be used:
-  - `spout p --id-<variable_id>`
+  - `spout p <variable_id>`
 
 Generated images are placed in: `./images/`
 

data/lib/spout/commands/coverage.rb

@@ -5,6 +5,7 @@ require 'fileutils'
 require 'spout/helpers/subject_loader'
 require 'spout/models/coverage_result'
 require 'spout/helpers/number_helper'
+require 'spout/helpers/config_reader'
 
 module Spout
   module Commands
@@ -19,10 +20,9 @@ module Spout
         @valid_ids = []
         @number_of_rows = nil
 
-        spout_config = YAML.load_file('.spout.yml')
-        @visit = (spout_config.kind_of?(Hash) ? spout_config['visit'].to_s.strip : '')
+        @config = Spout::Helpers::ConfigReader.new
 
-        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @visit)
+        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @config.visit)
         @subject_loader.load_subjects_from_csvs_part_one! # Not Part Two which is essentially cleaning the data
         @subjects = @subject_loader.subjects
 

data/lib/spout/commands/exporter.rb

@@ -3,12 +3,15 @@ require 'json'
 require 'fileutils'
 require 'colorize'
 
+require 'spout/helpers/config_reader'
+
 module Spout
   module Commands
     class Exporter
       def initialize(standard_version, argv)
         @csv_file = argv[1].to_s
         @standard_version = standard_version
+        @config = Spout::Helpers::ConfigReader.new
         expanded_export!
       end
 
@@ -25,7 +28,7 @@ module Spout
       end
 
       def generic_export(folder, type, keys, include_domain_name = false)
-        export_file = "#{type}.csv"
+        export_file = export_file_name(type)
         puts "      export".colorize( :blue ) + "  #{folder}/#{export_file}"
         CSV.open("#{folder}/#{export_file}", "wb") do |csv|
           if include_domain_name
@@ -49,6 +52,14 @@ module Spout
         end
       end
 
+      def export_file_name(type)
+        if @config.slug == ''
+          "#{type}.csv"
+        else
+          "#{@config.slug}-data-dictionary-#{@standard_version}-#{type}.csv"
+        end
+      end
+
       def generic_folder_path(file, type)
         file.gsub(/#{type}\//, '').split('/')[0..-2].join('/')
       end

data/lib/spout/commands/graphs.rb

@@ -6,6 +6,7 @@ require 'yaml'
 
 require 'spout/helpers/subject_loader'
 require 'spout/helpers/chart_types'
+require 'spout/helpers/config_reader'
 
 module Spout
   module Commands
@@ -13,33 +14,18 @@ module Spout
       def initialize(variables, standard_version)
         @standard_version = standard_version
 
-        spout_config = YAML.load_file('.spout.yml')
+        @config = Spout::Helpers::ConfigReader.new
 
-        @visit = ''
-
-        if spout_config.kind_of?(Hash)
-          @visit = spout_config['visit'].to_s.strip
-
-          chart_variables = if spout_config['charts'].kind_of?(Array)
-            spout_config['charts'].select{|c| c.kind_of?(Hash)}
-          else
-            []
-          end
-        else
-          puts "The YAML file needs to be in the following format:"
-          puts "---\nvisit: visit_variable_name\ncharts:\n- chart: age_variable_name\n  title: Age\n- chart: gender_variable_name\n  title: Gender\n- chart: race_variable_name\n  title: Race\n"
-          return self
-        end
-
-        if Spout::Helpers::ChartTypes::get_json(@visit, 'variable') == nil
-          if @visit == ''
+        if Spout::Helpers::ChartTypes::get_json(@config.visit, 'variable') == nil
+          if @config.visit == ''
             puts "The visit variable in .spout.yml can't be blank."
           else
-            puts "Could not find the following visit variable: #{@visit}"
+            puts "Could not find the following visit variable: #{@config.visit}"
           end
           return self
         end
-        missing_variables = chart_variables.select{|c| Spout::Helpers::ChartTypes::get_json(c['chart'], 'variable') == nil}
+
+        missing_variables = @config.charts.select{|c| Spout::Helpers::ChartTypes::get_json(c['chart'], 'variable') == nil}
         if missing_variables.count > 0
           puts "Could not find the following chart variable#{'s' unless missing_variables.size == 1}: #{missing_variables.join(', ')}"
           return self
@@ -55,20 +41,20 @@ module Spout
 
         @valid_ids = argv_string.split(',').compact.reject{|s| s == ''}
 
-        @chart_variables = chart_variables.unshift( { "chart" => @visit, "title" => 'Histogram' } )
+        @chart_variables = @config.charts.unshift( { "chart" => @config.visit, "title" => 'Histogram' } )
 
         @variable_files = Dir.glob('variables/**/*.json')
 
         t = Time.now
         FileUtils.mkpath "graphs/#{@standard_version}"
 
-        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @visit)
+        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @config.visit)
 
         @subject_loader.load_subjects_from_csvs!
         @subjects = @subject_loader.subjects
         compute_tables_and_charts
 
-        puts "Took #{Time.now - t} seconds."
+        puts "Took #{Time.now - t} seconds." if @subjects.size > 0
       end
 
       def compute_tables_and_charts
@@ -93,7 +79,7 @@ module Spout
             chart_type = chart_type_hash["chart"]
             chart_title = chart_type_hash["title"].downcase.gsub(' ', '-')
 
-            if chart_type == @visit
+            if chart_type == @config.visit
               filtered_subjects = @subjects.select{ |s| s.send(chart_type) != nil }  # and s.send(variable_name) != nil
               if filtered_subjects.count > 0
                 stats[:charts][chart_title] = Spout::Helpers::ChartTypes::chart_histogram(chart_type, filtered_subjects, json, variable_name)
@@ -121,7 +107,7 @@ module Spout
       # [["Visit 1", "1"], ["Visit 2", "2"], ["CVD Outcomes", "3"]]
       def visits
         @visits ||= begin
-          Spout::Helpers::ChartTypes::domain_array(@visit)
+          Spout::Helpers::ChartTypes::domain_array(@config.visit)
         end
       end
 

data/lib/spout/commands/images.rb

@@ -6,6 +6,7 @@ require 'yaml'
 
 require 'spout/helpers/subject_loader'
 require 'spout/helpers/chart_types'
+require 'spout/helpers/config_reader'
 
 module Spout
   module Commands
@@ -22,24 +23,18 @@ module Spout
 
         @number_of_rows = nil
 
-        spout_config = YAML.load_file('.spout.yml')
-
-        @visit = ''
-
-        if spout_config.kind_of?(Hash)
-          @visit = spout_config['visit'].to_s.strip
-        end
+        @config = Spout::Helpers::ConfigReader.new
 
         t = Time.now
         FileUtils.mkpath "graphs/#{@standard_version}"
 
-        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @visit)
+        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @config.visit)
 
         @subject_loader.load_subjects_from_csvs!
         @subjects = @subject_loader.subjects
 
         compute_images
-        puts "Took #{Time.now - t} seconds."
+        puts "Took #{Time.now - t} seconds." if @subjects.size > 0
       end
 
       def compute_images
@@ -60,9 +55,9 @@ module Spout
 
           puts "#{file_index+1} of #{variable_files_count}: #{variable_file.gsub(/(^variables\/|\.json$)/, '').gsub('/', ' / ')}"
 
-          filtered_subjects = @subjects.select{ |s| s.send(@visit) != nil }
+          filtered_subjects = @subjects.select{ |s| s.send(@config.visit) != nil }
 
-          chart_json = Spout::Helpers::ChartTypes::chart_histogram(@visit, filtered_subjects, json, variable_name)
+          chart_json = Spout::Helpers::ChartTypes::chart_histogram(@config.visit, filtered_subjects, json, variable_name)
 
           if chart_json
             File.open(tmp_options_file, "w") do |outfile|

data/lib/spout/commands/outliers.rb

@@ -5,6 +5,7 @@ require 'fileutils'
 require 'spout/helpers/subject_loader'
 require 'spout/models/outlier_result'
 require 'spout/helpers/number_helper'
+require 'spout/helpers/config_reader'
 
 module Spout
   module Commands
@@ -19,10 +20,9 @@ module Spout
         @valid_ids = []
         @number_of_rows = nil
 
-        spout_config = YAML.load_file('.spout.yml')
-        @visit = (spout_config.kind_of?(Hash) ? spout_config['visit'].to_s.strip : '')
+        @config = Spout::Helpers::ConfigReader.new
 
-        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @visit)
+        @subject_loader = Spout::Helpers::SubjectLoader.new(@variable_files, @valid_ids, @standard_version, @number_of_rows, @config.visit)
         @subject_loader.load_subjects_from_csvs!
         @subjects = @subject_loader.subjects
         run_outliers_report!
@@ -35,6 +35,7 @@ module Spout
           Spout::Models::OutlierResult.new(@subjects, method, csv_files)
         end
 
+        @outlier_results.select!{|outlier_result| ['numeric', 'integer'].include?(outlier_result.variable_type) }
         @outlier_results.sort!{|a,b| [a.weight, a.method] <=> [b.weight, b.method]}
 
         @overall_results = @subject_loader.csv_files.collect do |csv_file|

data/lib/spout/helpers/config_reader.rb

@@ -0,0 +1,37 @@
+require 'yaml'
+
+module Spout
+  module Helpers
+    class ConfigReader
+
+      attr_reader :slug, :visit, :charts
+
+
+      def initialize
+        @slug = ''
+        @visit = ''
+        @charts = []
+        parse_yaml_file
+      end
+
+      def parse_yaml_file
+        spout_config = YAML.load_file('.spout.yml')
+
+        if spout_config.kind_of?(Hash)
+          @slug = spout_config['slug'].to_s.strip
+          @visit = spout_config['visit'].to_s.strip
+
+          @charts = if spout_config['charts'].kind_of?(Array)
+            spout_config['charts'].select{|c| c.kind_of?(Hash)}
+          else
+            []
+          end
+        else
+          puts "The YAML file needs to be in the following format:"
+          puts "---\nvisit: visit_variable_name\ncharts:\n- chart: age_variable_name\n  title: Age\n- chart: gender_variable_name\n  title: Gender\n- chart: race_variable_name\n  title: Race\n"
+        end
+      end
+
+    end
+  end
+end

data/lib/spout/helpers/subject_loader.rb

@@ -72,9 +72,9 @@ module Spout
         end
 
         if @csv_directory != @standard_version
-          puts "Using dataset in " + "csvs/#{@csv_directory}/".colorize( :green ) + " for dictionary version " + @standard_version.to_s.colorize( :green ) + "\n\n"
+          puts "#{@csv_files.size == 0 ? 'No CSVs found' : 'Using dataset' } in " + "csvs/#{@csv_directory}/".colorize( :green ) + " for dictionary version " + @standard_version.to_s.colorize( :green ) + "\n\n"
         else
-          puts "Using dataset in " + "csvs/#{@standard_version}/".colorize( :green ) + "\n\n"
+          puts "#{@csv_files.size == 0 ? 'No CSVs found' : 'Using dataset' } in " + "csvs/#{@standard_version}/".colorize( :green ) + "\n\n"
         end
 
       end

data/lib/spout/models/outlier_result.rb

@@ -4,7 +4,7 @@ require 'spout/helpers/json_loader'
 module Spout
   module Models
     class OutlierResult
-      attr_reader :csv_files, :method, :major_outliers, :minor_outliers, :outliers, :weight, :units, :display_name, :median
+      attr_reader :csv_files, :method, :major_outliers, :minor_outliers, :outliers, :weight, :units, :display_name, :median, :variable_type
 
       def initialize(subjects, method, csv_files)
         @values = subjects.collect(&method.to_sym)
@@ -24,6 +24,7 @@ module Spout
         variable = Spout::Helpers::JsonLoader::get_variable(method)
         @units = (variable.kind_of?(Hash) ? variable['units'] : nil)
         @display_name = (variable.kind_of?(Hash) ? variable['display_name'] : nil)
+        @variable_type = (variable.kind_of?(Hash) ? variable['type'] : nil)
         @median = @values.median
       end
 

data/lib/spout/templates/ruby-version

@@ -1 +1 @@
-ruby-2.1.2
+ruby-2.1.3

data/lib/spout/templates/spout.yml

@@ -1,2 +1,3 @@
+# slug: myrepo
 visit: visit
 charts: []

data/lib/spout/templates/travis.yml

@@ -1,3 +1,3 @@
 language: ruby
 rvm:
-  - 2.1.2
+  - 2.1.3

data/lib/spout/tests.rb

@@ -41,7 +41,7 @@ module Minitest
           print "    #{test.name}"
           puts
           print "             "
-          print test.failure
+          print test.failure.to_s.gsub("\n", "\n             ")
           puts
           puts
         end

data/lib/spout/version.rb

@@ -3,7 +3,7 @@ module Spout
     MAJOR = 0
     MINOR = 9
     TINY = 0
-    BUILD = "beta2" # nil, "pre", "rc", "rc2"
+    BUILD = "rc" # nil, "pre", "rc", "rc2"
 
     STRING = [MAJOR, MINOR, TINY, BUILD].compact.join('.')
   end

data/lib/spout.rb

@@ -45,8 +45,8 @@ module Spout
     argv = argv.last(argv.size - 1)
     require 'spout/commands/images'
     types         = flag_values(argv, 'type')
-    variable_ids  = flag_values(argv, 'id')
     sizes         = flag_values(argv, 'size')
+    variable_ids  = non_flag_values(argv)
     Spout::Commands::Images.new(types, variable_ids, sizes, standard_version, argv)
   end
 
@@ -111,4 +111,8 @@ EOT
     flags.select{|f| f =~ /^--#{param}-/}.collect{|f| f[(param.size + 3)..-1]}
   end
 
+  def self.non_flag_values(flags)
+    flags.reject{|f| f =~ /^--/}
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: spout
 version: !ruby/object:Gem::Version
-  version: 0.9.0.beta2
+  version: 0.9.0.rc
 platform: ruby
 authors:
 - Remo Mueller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-25 00:00:00.000000000 Z
+date: 2014-09-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -118,6 +118,7 @@ files:
 - lib/spout/commands/project_generator.rb
 - lib/spout/helpers/array_statistics.rb
 - lib/spout/helpers/chart_types.rb
+- lib/spout/helpers/config_reader.rb
 - lib/spout/helpers/iterators.rb
 - lib/spout/helpers/json_loader.rb
 - lib/spout/helpers/number_helper.rb
@@ -185,7 +186,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: 1.3.1
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.1
 signing_key: 
 specification_version: 4
 summary: Turn your CSV data dictionary into a JSON repository. Collaborate with others