earth 0.11.10 → 0.11.11

data/Gemfile

@@ -2,6 +2,10 @@ source :rubygems
 
 gemspec :path => '.'
 
+group :development do
+  gem 'guard'
+end
+
 if RUBY_VERSION < "1.9"
   gem 'fastercsv'
 end

data/Guardfile

@@ -0,0 +1,35 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec', :version => 2 do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+
+  # Rails example
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^app/models/(.+)\.rb$})                           { |m| "spec/models/#{m[1]}_spec.rb" }
+  watch(%r{^app/controllers(.+)\.rb$})                           { |m| "spec/controllers/#{m[1]}_spec.rb" }
+  watch(%r{^app/(.*)(\.erb|\.haml)$})                 { |m| "spec/#{m[1]}#{m[2]}_spec.rb" }
+  watch(%r{^lib/(.+)\.rb$})                           { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch(%r{^app/controllers/(.+)_(controller)\.rb$})  { |m| ["spec/routing/#{m[1]}_routing_spec.rb", "spec/#{m[2]}s/#{m[1]}_#{m[2]}_spec.rb", "spec/acceptance/#{m[1]}_spec.rb"] }
+  watch(%r{^spec/support/(.+)\.rb$})                  { "spec" }
+  watch('spec/spec_helper.rb')                        { "spec" }
+  watch('config/routes.rb')                           { "spec/routing" }
+  watch('app/controllers/application_controller.rb')  { "spec/controllers" }
+  # Capybara request specs
+  watch(%r{^app/views/(.+)/.*\.(erb|haml)$})          { |m| "spec/requests/#{m[1]}_spec.rb" }
+end
+
+
+guard 'bundler' do
+  watch('Gemfile')
+  # Uncomment next line if Gemfile contain `gemspec' command
+  # watch(/^.+\.gemspec/)
+end
+
+guard 'cucumber' do
+  watch(%r{^features/.+\.feature$})
+  watch(%r{^features/support/.+$})          { 'features' }
+  watch(%r{^features/step_definitions/(.+)_steps\.rb$}) { |m| Dir[File.join("**/#{m[1]}.feature")][0] || 'features' }
+end

data/README.markdown

@@ -2,47 +2,121 @@
 
 Earth is a collection of data models that represent various things found here on Earth, such as pet breeds, kinds of rail travel, zip codes, and Petroleum Administration for Defense Districts.
 
-The data that these models represent can be pulled from http://data.brighterplanet.com
+The data that these models represent can be pulled from preconfigured authoritative sources.
 
 ## Usage
 
-    require 'earth'
-    Earth.init :automobile, :locality
-    ft = AutomobileFuel.first
-    ...
+``` ruby
+require 'earth'
+Earth.init :automobile, :locality
+ft = AutomobileFuel.first
+# ...
+```
 
 `Earth.init` loads desired "data domains" as well as any supporting classes and plugins that each data model needs. A "data domain" is a grouping of related data models. For instance, all automobile-related data is in the `:automobile` domain.
 
+### Domains
+
+<table>
+  <thead>
+  <tr>
+    <th>Domain</th>
+    <th>Models</th>
+  </tr>
+  </thead>
+  <tbody>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/air"><code>:air</code></a></td>
+    <td>Aircraft, Airline, Airport ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/automobile"><code>:automobile</code></a></td>
+    <td>AutomobileFuel, AutomobileMake, AutomobileModel ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/bus"><code>:bus</code></a></td>
+    <td>BusClass, BusFuel ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/computation"><code>:computation</code></a></td>
+    <td>ComputationCarrier, ComputationCarrierInstanceClass ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/diet"><code>:diet</code></a></td>
+    <td>DietClass, FoodGroup ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/fuel"><code>:fuel</code></a></td>
+    <td>Fuel, FuelPrice, GreenhouseGas ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/hospitality"><code>:hospitality</code></a></td>
+    <td>LodgingClass, CommercialBuildingEnergyConsumptionSurveyResponse ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/industry"><code>:industry</code></a></td>
+    <td>Industry, CbecsEnergyIntensity ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/locality"><code>:locality</code></a></td>
+    <td>CensusDivision, Country, ZipCode ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/pet"><code>:pet</code></a></td>
+    <td>Breed, Gender, Species ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/rail"><code>:rail</code></a></td>
+    <td>RailClass, RailFuel, RailCompany ...</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/residence"><code>:residence</code></a></td>
+    <td>Urbanity, ResidenceClass, AirConditionerUse</td>
+  </tr>
+  <tr>
+    <td><a href="https://github.com/brighterplanet/earth/tree/master/lib/earth/shipping"><code>:shipping</code></a></td>
+    <td>Carrier, ShipmentMode ...</td>
+  </tr>
+  </tbody>
+</table>
+    
+
 ### Data storage
 
 You can store Earth data in any relational database. On your very first run, you will need to create the tables for data each model. This is done using minirecord with the `apply_schemas` option:
 
-    require 'activerecord'
-    ActiveRecord::Base.establish_connection :adapter => ...   # Not needed if using Rails
+``` ruby
+require 'activerecord'
+ActiveRecord::Base.establish_connection :adapter => ...   # Not needed if using Rails
 
-    require 'earth'
-    Earth.init :all, :apply_schemas => true
+require 'earth'
+Earth.init :all, :apply_schemas => true
+```
 
 ### Pulling data from data.brighterplanet.com
 
-By default, Earth will pull data from data.brighterplanet.com. Simply call `run_data_miner!` on whichever data model class you need. If there are any Earth classes that the chosen class depends on, they will be downloaded as well automatically:
+By default, Earth will pull data from [data.brighterplanet.com](http://data.brighterplanet.com), which continuously (and transparently) refreshes its data from authoritative sources. Simply call `#run_data_miner!` on whichever data model class you need. If there are any Earth classes that the chosen class depends on, they will be downloaded as well automatically:
 
-    require 'earth'
-    Earth.init :locality
-    ZipCode.run_data_miner!
+``` ruby
+require 'earth'
+Earth.init :locality
+ZipCode.run_data_miner!
+```
 
 ### Pulling data from the original sources
 
-If you'd like to pull data directly from the source, e.g. Automobile data from EPA's sources, simply require the data\_miner file for the desired domain:
+If you'd like to bypass the [data.brighterplanet.com](http://data.brighterplanet.com) proxy and pull data directly from authoritative sources (*e.g.,* automobile data from EPA), simply require the `data\_miner` file for the desired domain:
 
-    require 'earth'
-    Earth.init :automobile
+``` ruby
+require 'earth'
+Earth.init :automobile
 
-    require 'earth/automobile/data_miner'
-    AutomobileMake.run_data_miner!
+require 'earth/automobile/data_miner'
+AutomobileMake.run_data_miner!
+```
 
 ## Collaboration cycle 
-Brighter Planet vigorously encourages collaborative improvement of its emitter libraries. Collaboration requires a (free) GitHub account.
+Brighter Planet vigorously encourages collaborative improvement.
 
 ### You
 1.  Fork the earth repository on GitHub.
@@ -57,4 +131,4 @@ Brighter Planet vigorously encourages collaborative improvement of its emitter l
 1.  Ensure tests pass.
 1.  Review changes for scientific accuracy.
 1.  Merge changes to master repository and publish.
-1.  Direct production environment to use new emitter version.
+1.  Direct production environment to use new library version.

data/Rakefile

@@ -6,6 +6,10 @@ require 'bueller'
 Bueller::Tasks.new
 
 task :console do
+  require 'earth'
+  logger = Logger.new('log/test.log')
+  DataMiner.logger = ActiveRecord::Base.logger = logger
+  ActiveRecord::Base.establish_connection :adapter => 'postgresql', :database => 'test_earth'
   Earth.init :all
 
   require 'irb'

data/earth.gemspec

@@ -5,7 +5,7 @@ require "earth/version"
 Gem::Specification.new do |s|
   s.name        = "earth"
   s.version     = Earth::VERSION
-  s.date = "2012-01-26"
+  s.date = "2012-02-15"
   s.platform    = Gem::Platform::RUBY
   s.authors = ["Seamus Abshere", "Derek Kastner", "Andy Rossmeissl"]
   s.email = %q{andy@rossmeissl.net}
@@ -27,26 +27,28 @@ Gem::Specification.new do |s|
   s.require_paths = ["lib"]
   s.rubygems_version = %q{1.3.7}
   
-  s.add_runtime_dependency 'data_miner', '>=1.3'
-  s.add_runtime_dependency 'to_regexp'
+  s.add_runtime_dependency 'activerecord'
+  s.add_runtime_dependency 'activesupport'
   s.add_runtime_dependency 'cohort_scope'
-  s.add_runtime_dependency 'table_warnings', '>=0.0.6'
-  s.add_runtime_dependency 'remote_table', '>=1.3.0'
+  s.add_runtime_dependency 'conversions'
+  s.add_runtime_dependency 'data_miner', '>=1.3'
   s.add_runtime_dependency 'falls_back_on'
   s.add_runtime_dependency 'fixed_width-multibyte'
-  s.add_runtime_dependency 'geokit'
   s.add_runtime_dependency 'fuzzy_match', '>=1.1.0'
-  s.add_runtime_dependency 'weighted_average', '>=1.0.2'
+  s.add_runtime_dependency 'geokit'
   s.add_runtime_dependency 'mini_record-compat' # need https://github.com/DAddYE/mini_record/pull/7
-  s.add_runtime_dependency 'activesupport'
-  s.add_runtime_dependency 'activerecord'
-  s.add_development_dependency 'bundler'
+  s.add_runtime_dependency 'remote_table', '>=1.3.0'
+  s.add_runtime_dependency 'table_warnings', '>=0.0.6'
+  s.add_runtime_dependency 'to_regexp'
+  s.add_runtime_dependency 'weighted_average', '>=1.0.2'
   s.add_development_dependency 'bueller'
+  s.add_development_dependency 'bundler'
+  s.add_development_dependency 'charisma'
   s.add_development_dependency 'cucumber'
+  s.add_development_dependency 'mysql' # for bin/earth_tester.rb
+  s.add_development_dependency 'pg'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'rdoc'
   s.add_development_dependency 'rspec'
   s.add_development_dependency 'sqlite3-ruby'
-  s.add_development_dependency 'mysql' # for bin/earth_tester.rb
-  s.add_development_dependency 'pg'
 end

data/lib/earth/air/aircraft.rb

@@ -1,5 +1,5 @@
 class Aircraft < ActiveRecord::Base
-  set_primary_key :icao_code
+  self.primary_key = "icao_code"
   
   # Fuzzy association with FlightSegment
   cache_fuzzy_match_with :flight_segments, :primary_key => :description, :foreign_key => :aircraft_description
@@ -141,4 +141,4 @@ class Aircraft < ActiveRecord::Base
   col :b, :type => :float
   col :b_units
   col :fuel_use_specificity
-end
+end

data/lib/earth/air/aircraft_instance.rb

@@ -1,5 +1,5 @@
 class AircraftInstance < ActiveRecord::Base
-  set_primary_key :id
+  self.primary_key = "id"
   
   col :id
   col :registration
@@ -8,4 +8,4 @@ class AircraftInstance < ActiveRecord::Base
   col :airline_name
   add_index :registration
   add_index :serial_number
-end
+end

data/lib/earth/air/aircraft_instance_seat_class.rb

@@ -1,5 +1,5 @@
 class AircraftInstanceSeatClass < ActiveRecord::Base
-  set_primary_key :row_hash
+  self.primary_key = "row_hash"
   
   col :row_hash
   col :seat_class_name
@@ -10,4 +10,4 @@ class AircraftInstanceSeatClass < ActiveRecord::Base
   col :seat_width, :type => :float
   col :seat_width_units
   add_index :aircraft_instance_id
-end
+end

data/lib/earth/air/airline.rb

@@ -1,8 +1,8 @@
 class Airline < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
   col :bts_code
   col :iata_code
   col :icao_code
-end
+end

data/lib/earth/air/airport.rb

@@ -2,7 +2,7 @@ require ::File.join(Earth.vendor_dir, 'geokit-rails', 'lib', 'geokit-rails')
 require 'earth/locality'
 
 class Airport < ActiveRecord::Base
-  set_primary_key :iata_code
+  self.primary_key = "iata_code"
   
   belongs_to :country, :foreign_key => 'country_iso_3166_code', :primary_key => 'iso_3166_code'
   
@@ -17,4 +17,4 @@ class Airport < ActiveRecord::Base
   col :country_iso_3166_code
   col :latitude, :type => :float
   col :longitude, :type => :float
-end
+end

data/lib/earth/air/bts_aircraft.rb

@@ -1,5 +1,5 @@
 class BtsAircraft < ActiveRecord::Base
-  set_primary_key :bts_code
+  self.primary_key = "bts_code"
   col :bts_code
   col :description
-end
+end

data/lib/earth/air/flight_distance_class.rb

@@ -1,5 +1,5 @@
 class FlightDistanceClass < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   def self.find_by_distance(distance)
     first :conditions => arel_table[:min_distance].lteq(distance.to_f).and(arel_table[:max_distance].gt(distance.to_f))

data/lib/earth/air/flight_distance_class_seat_class.rb

@@ -1,5 +1,5 @@
 class FlightDistanceClassSeatClass < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   falls_back_on :name => 'fallback',
                 :multiplier => 1.0

data/lib/earth/air/flight_seat_class.rb

@@ -1,5 +1,5 @@
 class FlightSeatClass < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
 end

data/lib/earth/air/flight_segment.rb

@@ -1,7 +1,7 @@
 require 'earth/locality'
 
 class FlightSegment < ActiveRecord::Base
-  set_primary_key :row_hash
+  self.primary_key = "row_hash"
   
   extend CohortScope
   self.minimum_cohort_size = 1

data/lib/earth/automobile/automobile_fuel.rb

@@ -1,7 +1,7 @@
 require 'earth/fuel'
 
 class AutomobileFuel < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   has_many :type_fuel_year_ages, :class_name => 'AutomobileTypeFuelYearAge', :foreign_key => 'fuel_common_name', :primary_key => 'distance_key'
   has_many :type_fuel_years,     :class_name => 'AutomobileTypeFuelYear',    :foreign_key => 'fuel_common_name', :primary_key => 'ef_key'

data/lib/earth/automobile/automobile_make.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMake < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
   col :fuel_efficiency, :type => :float

data/lib/earth/automobile/automobile_make_model.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMakeModel < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name # make + model
   col :make_name

data/lib/earth/automobile/automobile_make_model_year.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMakeModelYear < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   # Need this so Automobile and AutomobileTrip can do characteristics[:make_model_year].automobile_fuel
   belongs_to :automobile_fuel, :foreign_key => 'fuel_code', :primary_key => 'code'

data/lib/earth/automobile/automobile_make_model_year_variant.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMakeModelYearVariant < ActiveRecord::Base
-  set_primary_key :row_hash
+  self.primary_key = "row_hash"
   
   # It looks like synthesizing a unique name would require including pretty much every column from the FEGs
   # (e.g. creeper gear, automatic vs automatic with lockup, feedback fuel system, etc.)

data/lib/earth/automobile/automobile_make_year.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMakeYear < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
   col :make_name

data/lib/earth/automobile/automobile_make_year_fleet.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileMakeYearFleet < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
   col :make_name

data/lib/earth/automobile/automobile_model.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileModel < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   col :name
 end

data/lib/earth/automobile/automobile_size_class.rb

@@ -1,6 +1,6 @@
 require 'earth/fuel'
 class AutomobileSizeClass < ActiveRecord::Base
-  set_primary_key :name
+  self.primary_key = "name"
   
   # FIXME TODO clean up size class in MakeModelYearVariant, derive size class for MakeModelYear, and calculate this from MakeModelYear
   falls_back_on :hybrid_fuel_efficiency_city_multiplier => 1.651, # https://brighterplanet.sifterapp.com/issue/667