moneyball 0.0.1.alpha → 0.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0a01481cc7fd30de73d170270013ab6848e86873
-  data.tar.gz: 9dff51bfbcd2688a676b798f1b42fc0dddcc1367
+  metadata.gz: 7f39378b88ae0c5a200beb76783c60706afd65ec
+  data.tar.gz: f114082afb54865c8b46754c2660317361c948fc
 SHA512:
-  metadata.gz: 58e2e3ff6d953767ca0e236e7101941d2237241b95ca3896d570f2547890f9aa5f9aea1810ef1fc569b43b382b5fdeb2ecb1643acea443666a7f214dc93424b2
-  data.tar.gz: 6190298eb57b643bbbb7acf35d0910d6940f14d1069d5df29c27767dcbc7db1f29a28f44ae9902c9b1b1856b6c31e2495706be822b425b09b68bd200af8d2665
+  metadata.gz: 8c38fede0049073f02ded2636e7a70c86f1d52aa58b0c3e4e4780321c35309675f4321489b531d6308a4280567c455053a7a041f1eea1fe1ff69036d8989617f
+  data.tar.gz: 0227f09c11bd500e0b5d25cf70572145b9088b52f6adae422c9161e66a0ef5fe2c8eda50f3867fe8d56b380354bc55afdf7b6e499f0f5ecf797bf30f5e9601d6

data/.gitignore

@@ -7,3 +7,4 @@
 /pkg/
 /spec/reports/
 /tmp/
+*.gem

data/.travis.yml

@@ -1,3 +1,4 @@
 language: ruby
 rvm:
-  - 2.2.2
+  - 2.2.0
+  - ruby-head

data/README.md

@@ -1,8 +1,11 @@
+[![Code Climate](https://codeclimate.com/github/geoffharcourt/moneyball/badges/gpa.svg)](https://codeclimate.com/github/geoffharcourt/moneyball)
 # Moneyball
+[![Build Status](https://travis-ci.org/geoffharcourt/moneyball.svg?branch=master)](https://travis-ci.org/geoffharcourt/moneyball)
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/moneyball`. To experiment with that code, run `bin/console` for an interactive prompt.
-
-TODO: Delete this and the text above, and describe your gem
+Moneyball parses MLB Gameday's play-by-play information to pull useful
+quantitative and qualitative information out of the data feed. Moneyball can
+determine where a batted ball was hit, the general classification of the batted
+ball, and stat line information from the plate appearance.
 
 ## Installation
 
@@ -22,7 +25,23 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+`Moneyball::Parser` takes a Nokogiri XML node.
+
+```ruby
+raw_xml = '<atbat event="Strikeout" des="Ty Cobb strikes out swinging."></atbat>'
+nokogiri_node = Nokogiri::XML(raw_xml).search("atbat").first
+stats = Moneyball::Parser.new(nokogiri_node).stats
+
+stats.slice(:pa, :ab, :h, :k) # => { pa: 1, ab: 1, h: 0, k: 1 }
+```
+
+`Moneyball::BattedBallLocationExtractor` and `Moneyball::BattedBallTypeExtractor` take a string from the play-by-play summary.
+
+```ruby
+summary = "Billy Hamilton hits a fly ball home run (22) to deep center field."
+Moneyball::BattedBallTypeExtractor.new(summary).categorize # => "Line drive"
+Moneyball::BattedBallLocationExtractor.new(summary).categorize # => "CF"
+```
 
 ## Development
 
@@ -32,8 +51,16 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
 
 ## Contributing
 
+This is a work in progress! I have been using pieces of this code in private projects, but it's time for the saber community to get a crack at improving this code.
+
+Any contributions should come with tests (we use RSpec) and a well documented PR. If you have a specific event from the Gameday feed that prompted your pull request, please reference it in your PR.
+
+Here's how to contribute!
 1. Fork it ( https://github.com/[my-github-username]/moneyball/fork )
 2. Create your feature branch (`git checkout -b my-new-feature`)
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create a new Pull Request
+
+## License
+Moneyball is © 2015 Geoff Harcourt. It is free software, and may be redistributed under the terms specified in the LICENSE file.

data/Rakefile

@@ -1 +1,7 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+require File.expand_path("../lib/moneyball/version", __FILE__)
+
+RSpec::Core::RakeTask.new('spec')
+
+task default: :spec

data/lib/moneyball.rb

@@ -1,5 +1,9 @@
 require "nokogiri"
+
 require "moneyball/version"
+require "moneyball/parser"
+require "moneyball/batted_ball_location_extractor"
+require "moneyball/batted_ball_type_extractor"
 
 module Moneyball
   # Your code goes here...

data/lib/moneyball/batted_ball_location_extractor.rb

@@ -0,0 +1,72 @@
+module Moneyball
+  class BattedBallLocationExtractor
+    def initialize(event_description)
+      @event_description = event_description
+    end
+
+    def classification
+      case
+      when event_description.match(deflected_by_regex("first baseman")) then "1B"
+      when event_description.match(deflected_by_regex("second baseman")) then "2B"
+      when event_description.match(deflected_by_regex("third baseman")) then "3B"
+      when event_description.match(deflected_by_regex("shortstop")) then "SS"
+      when event_description.match(unassisted_regex("first baseman")) then "1B"
+      when event_description.match(unassisted_regex("second baseman")) then "2B"
+      when event_description.match(unassisted_regex("third baseman")) then "3B"
+      when event_description.match(unassisted_regex("shortstop")) then "SS"
+      when event_description.match(infielder_regex("catcher")) then "C"
+      when event_description.match(infielder_regex("first baseman")) then "1B"
+      when event_description.match(infielder_regex("second baseman")) then "2B"
+      when event_description.match(infielder_regex("third baseman")) then "3B"
+      when event_description.match(infielder_regex("shortstop")) then "SS"
+      when event_description.match(infielder_regex("pitcher")) then "P"
+      when event_description.match(outfielder_regex("left")) then "LF"
+      when event_description.match(outfielder_regex("center")) then "CF"
+      when event_description.match(outfielder_regex("right")) then "RF"
+      when event_description.match(flies_into_sacrifice_double_play_regex("left"))
+        "LF"
+      when event_description.match(flies_into_sacrifice_double_play_regex("center"))
+        "CF"
+      when event_description.match(flies_into_sacrifice_double_play_regex("right"))
+        "RF"
+      when event_description.match(/(caught stealing|fan interference|hit by pitch|reaches on catcher interference|strikes out|out on strikes|walks)/)
+        nil
+      when event_description.match(/(passed ball|wild pitch).+out at/) then nil
+      when event_description.match(/picks off/) then nil
+      when event_description.match(/\AThrowing error by/) then nil
+      when event_description.match(/\A(\w+ challenged([A-Za-z\s\(\)\-\,])+\:)?([A-Za-z]|\s)+(, Jr.)? out at /)
+        nil
+      when event_description.match(/ (doubles|hits a home run|singles|triples)\.\s+\Z/) then nil
+      else
+        raise "No match for batted ball location on '#{event_description}'"
+        nil
+      end
+    end
+
+    protected
+
+    attr_reader :event_description
+
+    private
+
+    def deflected_by_regex(position)
+      /deflected by #{position}/
+    end
+
+    def infielder_regex(position)
+      /(ball to|bunt(,| to)|fielded by|(F|f)ielding error by|fly to|line drive to|reaches on a (force attempt, )?missed catch error by [A-Za-z\s\.]+, assist to|out( sharply| softly)? ?(,| to)|play,|pop up to|reaches on a(n)? (fielding |throwing )?error by|reaches on a force attempt, throwing error by|bunt\.\s+Throwing error by|pops into a double play in foul territory,) ?#{position}/
+    end
+
+    def outfielder_regex(position)
+      /((ground|fly) ball|drive|fielding error|flies into a double play|fly|grand slam( \(\d?\))|lines into a double play|out)( sharply| softly)?(,| by| down the| to) #{position}(-field line)?/
+    end
+
+    def flies_into_sacrifice_double_play_regex(position)
+      /flies into a sacrifice double play(,| to) #{position} fielder/
+    end
+
+    def unassisted_regex(position)
+      /#{position}[A-Za-z\s]+unassisted/
+    end
+  end
+end

data/lib/moneyball/batted_ball_type_extractor.rb

@@ -0,0 +1,48 @@
+module Moneyball
+  class BattedBallTypeExtractor
+    def initialize(event_description)
+      @event_description = event_description
+    end
+
+    def classification
+      case
+      when event_description.match(/line(s)? (drive|into|out)/)
+        "Line drive"
+      when event_description.match(/fl(ies|y) (ball|out)/)
+        "Fly ball"
+      when event_description.match(/sacrifice fly/)
+        "Fly ball"
+      when event_description.match(/flies into a/)
+        "Fly ball"
+      when event_description.match(/ground(s)?( (ball|into|out)|, fielded)/)
+        "Ground ball"
+      when event_description.match(/fielder's choice/)
+        "Ground ball"
+      when event_description.match(/((hits|out on) a sacrifice|ground) bunt/)
+        "Ground ball"
+      when event_description.match(/reaches on a(n)? ((fielding |missed catch |throwing )?error|force attempt)/)
+        "Ground ball"
+      when event_description.match(/pop(s)? (into a(n)? (unassisted )?double play|(into a force )?out|up)/)
+        "Pop up"
+      when event_description.match(/(grand slam|home run)/)
+        "Fly ball"
+      when event_description.match(/(\AThrowing error|catcher interference|caught stealing|fan interference|hit by pitch|strikes out|out on strikes|walks)/)
+        nil
+      when event_description.match(/(passed ball|wild pitch).+out at/) then nil
+      when event_description.match(/picks off/) then nil
+      when event_description.match(/\A(\w+ challenged ([A-Za-z]|\s|\(|\)|\-|\,)+\:)?([A-Za-z]|\s)+(, Jr.)? out at /)
+        nil
+      when event_description.match(/ triples\.\s+\Z/) then nil
+      when event_description.match(/ doubles\.\s+\Z/) then nil
+      when event_description.match(/ singles\.\s+\Z/) then nil
+      else
+        raise "No match for batted ball type on '#{event_description}'"
+        nil
+      end
+    end
+
+    protected
+
+    attr_reader :event_description
+  end
+end

data/lib/moneyball/parser.rb

@@ -0,0 +1,214 @@
+module Moneyball
+  class Parser
+    def initialize(node)
+      @node = node
+    end
+
+    def stats
+      {
+        pa: pa,
+        ab: ab,
+        h: h,
+        h_1b: h_1b,
+        h_2b: h_2b,
+        h_3b: h_3b,
+        hr: hr,
+        bb: bb,
+        ibb: ibb,
+        k: k,
+        roe: roe,
+        gidp: gidp,
+        dp: dp,
+        tp: tp,
+        hbp: hbp,
+        sf: sf,
+        sh: sh,
+        fc: fc,
+        bi: bi,
+        ci: ci,
+        fi: fi,
+        r: r,
+        rbi: rbi
+      }
+    end
+
+    protected
+
+    attr_reader :node
+
+    private
+
+    def batter_id
+      @batter_id ||= node.attribute("batter").value
+    end
+
+    def r
+      @r = node.search("runner[id='#{batter_id}'][score='T']").any? ? 1 : 0
+    end
+
+    def rbi
+      @r = node.search("runner[rbi='T']").count
+    end
+
+    def event_value
+      @event_value ||= node.attribute("event").value
+    end
+
+    def event_matches(regex)
+      if event_value.match(regex)
+        1
+      else
+        0
+      end
+    end
+
+    def any_outcomes_occurred(outcomes)
+      if outcomes.any? { |outcome| outcome == 1 }
+        1
+      else
+        0
+      end
+    end
+
+    def ab
+      @ab ||= any_outcomes_occurred([
+        h,
+        k,
+        batted_out,
+        double_play,
+        tp,
+        roe,
+        force_out,
+        fc,
+        bi,
+        fi
+      ])
+    end
+
+    def bi
+      @bi ||= event_matches(/Batter Interference/)
+    end
+
+    def bb
+      @bb ||= event_matches(/Walk/)
+    end
+
+    def ibb
+      @ibb ||= event_matches(/(I|i)ntent(ional)? (W|w)alk/)
+    end
+
+    def ci
+      @ci ||= event_matches(/Catcher Interference/)
+    end
+
+    def gidp
+      @gidp ||= event_matches(/((G|g)rounded (I|i)nto|Sacrifice Bunt) DP/)
+    end
+
+    def dp
+      @dp ||= any_outcomes_occurred([gidp, double_play, sacrifice_double_play])
+    end
+
+    def tp
+      @tp ||= event_matches(/(T|t)riple (P|p)lay/)
+    end
+
+    def sacrifice_double_play
+      @sacrifice_double_play ||= event_matches(/Sac (Bunt|Fly) DP/)
+    end
+
+    def double_play
+      @double_play ||= event_matches(/((D|d)ouble (P|p)lay| - DP)/)
+    end
+
+    def fc
+      @fc ||= event_matches(/Fielders Choice( Out)?/)
+    end
+
+    def fi
+      @fi ||= event_matches(/Fan (I|i)nterference/)
+
+      if @fi
+        parse_hit_from_description
+      end
+
+      @fi
+    end
+
+    def h
+      @h ||= any_outcomes_occurred([h_1b, h_2b, h_3b, hr])
+    end
+
+    def hbp
+      @hbp ||= event_matches(/Hit By Pitch/)
+    end
+
+    def h_1b
+      @h_1b ||= event_matches(/(S|s)ingle/)
+    end
+
+    def h_2b
+      @h_2b ||= event_matches(/(D|d)ouble\Z/)
+    end
+
+    def h_3b
+      @h_3b ||= event_matches(/(T|t)riple?\Z/)
+    end
+
+    def hr
+      @hr ||= event_matches(/(H|h)ome (R|r)un/)
+    end
+
+    def k
+      @k ||= event_matches(/(S|s)trikeout/)
+    end
+
+    def batted_out
+      @batter_out ||= event_matches(/(Fly|Ground|Line|Pop)( )?(O|o)ut|Grounded Into DP/)
+    end
+
+    def force_out
+      @force_out ||= event_matches(/Forceout/)
+    end
+
+    def pa
+      @pa ||= if !event_value.match(/Runner Out/)
+        1
+      else
+        0
+      end
+    end
+
+    def roe
+      @reached_on_error ||= event_matches(/Field Error/)
+    end
+
+    def sf
+      @sf ||= event_matches(/Sac Fly/)
+    end
+
+    def sh
+      @sh ||= event_matches(/Sac(rifice)? Bunt/)
+    end
+
+    def parse_hit_from_description
+      description = node.attribute("des").value
+
+      if description.match(/singles/)
+        @h = 1
+        @h_1b = 1
+      elsif description.match(/doubles/)
+        @h = 1
+        @h_2b = 1
+      elsif description.match(/ground-rule double/)
+        @h = 1
+        @h_2b = 1
+      elsif description.match(/triples/)
+        @h = 1
+        @h_3b = 1
+      elsif description.match(/hits a sacrifice bunt/) && description.match(/error/)
+        @roe = 1
+      end
+    end
+  end
+end

data/lib/moneyball/version.rb

@@ -1,3 +1,3 @@
 module Moneyball
-  VERSION = "0.0.1.alpha"
+  VERSION = "0.0.1"
 end

data/moneyball.gemspec

@@ -9,26 +9,18 @@ Gem::Specification.new do |spec|
   spec.authors       = ["Geoff Harcourt"]
   spec.email         = ["geoff.harcourt@gmail.com"]
 
-  spec.summary       = %q{Parse quantitative information out of baseball play-by-play descriptions.}
-  spec.description   = %q{Moneyball parses the descriptions of plays from Gameday XML and turns the natural language into statistics for research purposes.}
+  spec.summary       = %q{A parser for Gameday XML play descriptions.}
+  spec.description   = %q{Moneyball parses Gameday play-by-play descriptions and extracts usable data from plain English summaries of plays.}
   spec.homepage      = "https://github.com/geoffharcourt/moneyball"
   spec.license       = "MIT"
 
-  # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
-  # delete this section to allow pushing this gem to any host.
-  # if spec.respond_to?(:metadata)
-  #   spec.metadata['allowed_push_host'] = ": set to 'http://mygemserver.com'"
-  # else
-  #   raise "rubygems 2.0 or newer is required to protect against public gem pushes."
-  # end
-
   spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.add_development_dependency "bundler", "~> 1.9"
-  spec.add_development_dependency "rake", "~> 10.0"
-
   spec.add_dependency "nokogiri"
+
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.2.0"
 end

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: moneyball
 version: !ruby/object:Gem::Version
-  version: 0.0.1.alpha
+  version: 0.0.1
 platform: ruby
 authors:
 - Geoff Harcourt
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-05-14 00:00:00.000000000 Z
+date: 2015-05-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.9'
-  type: :development
+        version: '0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.9'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -39,21 +39,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '10.0'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
+        version: 3.2.0
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
-description: Moneyball parses the descriptions of plays from Gameday XML and turns
-  the natural language into statistics for research purposes.
+        version: 3.2.0
+description: Moneyball parses Gameday play-by-play descriptions and extracts usable
+  data from plain English summaries of plays.
 email:
 - geoff.harcourt@gmail.com
 executables: []
@@ -65,12 +65,15 @@ files:
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
-- LICENSE.txt
+- LICENSE
 - README.md
 - Rakefile
 - bin/console
 - bin/setup
 - lib/moneyball.rb
+- lib/moneyball/batted_ball_location_extractor.rb
+- lib/moneyball/batted_ball_type_extractor.rb
+- lib/moneyball/parser.rb
 - lib/moneyball/version.rb
 - moneyball.gemspec
 homepage: https://github.com/geoffharcourt/moneyball
@@ -88,13 +91,13 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.4.7
 signing_key: 
 specification_version: 4
-summary: Parse quantitative information out of baseball play-by-play descriptions.
+summary: A parser for Gameday XML play descriptions.
 test_files: []