bstats 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2ed7bce6b33ac9e017f6c4687fdfc01916ee9548
+  data.tar.gz: 013caea171c873a166ba53dc6519ebd9a4215110
+SHA512:
+  metadata.gz: f91e8469424b27379b0267fd299463ce3f69e0dd83b70be5f17867abf157464d81fae2573308b0068a0e81d03b1ba17722666254173f03e1734c01ac5b7c37ee
+  data.tar.gz: 0e50363c7cab885e707bd236a4bc75d6ab4e548e82fb76a2785ca48e7706ce602d6ac612a00b878bc3a7a1fcc6bb6c321607a4df22e54608aa1a9ec89564525b

data/Gemfile

@@ -0,0 +1,8 @@
+source 'https://rubygems.org'
+gem 'activerecord', '~> 4.1.6'
+gem 'sqlite3', '~> 1.3.9'
+
+group :test do
+	gem 'rspec'
+	gem 'rspec-activemodel-mocks'
+end

data/README.md

@@ -0,0 +1,21 @@
+# ruby-baseball-stats
+A ruby gem that takes a couple CSVs and does a bit of numbers crunching to generate a few statistics.
+## How To Install
+First, the gem depends on a few other libraries:
+* Active Record
+* SQLite3
+* RSpec (only needed if running the tests from source)
+If you already have those, great, just install the gem and go. If not, there's a Gemfile in the source you can use with Bundler to get all the needed dependencies. Alternately, just install the gems individually, that works too.
+### Installing The Gem
+Just like any other local gem:
+`sudo gem install bstats-1.0.0.gem`
+## Running The Script
+It comes pre-loaded with the stats and players needed to determine the stat winners, so after installing you can just run `bstats` from anywhere and see the results.
+### Loading New Data
+To load in new player and statistical data, run `sudo bstats import` from a directory containing the 'Master-small.csv' and 'Batting-07-12.csv' files.
+
+## TODO List
+* Import needs work:
+** Move DB out of /Library/Ruby/Gems into user writable space so that 'sudo' isn't needed to write to it
+** Allow more dynamic command line management, like filenames (OptionParser)
+* Data model addresses immediate requirements only, could be broken out for more granular and performant data analysis

data/bin/bstats

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/bstats.rb'

data/db/db_config.rb

@@ -0,0 +1,8 @@
+require 'active_record'
+require 'sqlite3'
+I18n.enforce_available_locales = false
+db_file =  File.join(File.dirname(__FILE__), 'temp.db')
+ActiveRecord::Base.establish_connection(
+  :adapter => 'sqlite3',
+  :database => db_file
+)

data/db/migrate/create_player_batting_stats_table.rb

@@ -0,0 +1,33 @@
+require_relative '../db_config'
+
+class CreatePlayerBattingStatsTable < ActiveRecord::Migration
+
+  def up
+    create_table :player_batting_stats do |t|
+      t.string  :external_id
+      t.string  :year
+      t.string  :league
+      t.string  :team_id
+      t.integer :games,               :default => 0
+      t.integer :at_bats,             :default => 0
+      t.integer :runs,                :default => 0
+      t.integer :hits,                :default => 0
+      t.integer :doubles,             :default => 0
+      t.integer :triples,             :default => 0
+      t.integer :home_runs,           :default => 0
+      t.integer :runs_batted_in,      :default => 0
+      t.integer :stolen_bases,        :default => 0
+      t.integer :caught_stealing,     :default => 0
+      t.decimal :batting_average,     :default => 0.0,  :precision => 1, :scale => 3
+      t.decimal :slugging_percentage, :default => 0.0,  :precision => 1, :scale => 3
+    end
+  end 
+
+  def down
+    drop_table :player_batting_stats if table_exists?(:player_batting_stats)
+  end
+
+  def self.table_exists?(name)
+    ActiveRecord::Base.connection.tables.include?(name)
+  end
+end

data/db/migrate/create_players_table.rb

@@ -0,0 +1,21 @@
+require_relative '../db_config'
+
+class CreatePlayersTable < ActiveRecord::Migration
+
+  def up
+    create_table :players do |t|
+      t.string  :external_id
+      t.integer :birth_year
+      t.string  :first_name
+      t.string  :last_name
+    end
+  end 
+
+  def down
+    drop_table :players if table_exists?(:players)
+  end
+
+  def self.table_exists?(name)
+    ActiveRecord::Base.connection.tables.include?(name)
+  end
+end

data/lib/bstats.rb

@@ -0,0 +1,45 @@
+require_relative 'bstats/player'
+require_relative 'bstats/player_batting_stat'
+require_relative 'bstats/data_persistence'
+require_relative 'bstats/number_crunch'
+
+begin
+	if ARGV[0] == 'import'
+		dp = BStats::DataPersistence.new()
+	 	dp.teardown_db()
+	 	dp.initialize_db()
+	 	puts "Importing data..."
+	 	player_file = File.join(Dir.pwd, 'Master-small.csv')
+	 	stats_file = File.join(Dir.pwd, 'Batting-07-12.csv')
+		BStats::Player.import_csv(player_file)
+		BStats::PlayerBattingStat.import_csv(stats_file)
+	end
+
+	ba_winner = BStats::NumberCrunch.most_improved_batting_average(from_year=2009, to_year=2010)
+	puts "Most Improved Batting Average (2009-2010):"
+	puts "\tName: #{ba_winner}"
+	puts "\tBatting Average Improvement: #{ba_winner.percent_improved}"
+
+
+	puts "\r\n2007 Oakland A's Slugging Percentage:"
+	puts "Name\t\t\tSlugging Percentage"
+	BStats::NumberCrunch.team_slugging_percentage('OAK', 2007).each do |stat|
+		puts "#{stat.player.last_name}, #{stat.player.first_name}\t\t#{'%.3f' % stat.slugging_percentage}"
+	end
+
+	al11 = BStats::NumberCrunch.triple_crown_winner('AL', 2011)
+	puts "2011 AL Triple Crown Winner: #{al11}"
+	nl11 = BStats::NumberCrunch.triple_crown_winner('NL', 2011)
+	puts "2011 NL Triple Crown Winner: #{nl11}"
+	al12 = BStats::NumberCrunch.triple_crown_winner('AL', 2012)
+	puts "2012 AL Triple Crown Winner: #{al12}"
+	nl12 = BStats::NumberCrunch.triple_crown_winner('NL', 2012)
+	puts "2012 NL Triple Crown Winner: #{nl12}"
+
+rescue Errno::ENOENT => e
+	puts "Files needed to import aren't in the directory calling this script. Include 'Master-small.csv' and 'Batting-07-12.csv' in the directory from which you execute this script."
+rescue Exception => e
+	puts e.class
+	puts e.inspect
+	puts e.backtrace
+end

data/lib/bstats/batting_average_winner.rb

@@ -0,0 +1,11 @@
+require_relative 'winner'
+
+module BStats
+	class BattingAverageWinner < Winner
+		attr_writer :percent_improved
+
+		def percent_improved
+			@percent_improved || 0
+		end
+	end
+end

data/lib/bstats/data_persistence.rb

@@ -0,0 +1,16 @@
+require_relative '../../db/migrate/create_players_table'
+require_relative '../../db/migrate/create_player_batting_stats_table'
+
+module BStats
+	class DataPersistence
+		def initialize_db()
+			CreatePlayersTable.migrate(:up)
+			CreatePlayerBattingStatsTable.migrate(:up)
+		end
+
+		def teardown_db()
+			CreatePlayersTable.migrate(:down)
+			CreatePlayerBattingStatsTable.migrate(:down)
+		end
+	end
+end

data/lib/bstats/number_crunch.rb

@@ -0,0 +1,57 @@
+require_relative '../../lib/bstats/player'
+require_relative '../../lib/bstats/player_batting_stat'
+require_relative 'winner'
+require_relative 'batting_average_winner'
+
+module BStats
+	class NumberCrunch
+		def self.most_improved_batting_average(from_year, to_year, min_at_bats=200)
+			winner = BattingAverageWinner.new()
+			get_grouped_at_bats(from_year, min_at_bats).each do |y1stat|
+				get_grouped_at_bats(to_year, min_at_bats).each do | y2stat |
+					if ((y2stat.hits_sum.to_f / y2stat.at_bats_sum.to_f) - (y1stat.hits_sum.to_f / y1stat.at_bats_sum.to_f)) > winner.percent_improved
+						winner.percent_improved = ((y2stat.hits_sum.to_f / y2stat.at_bats_sum.to_f) - (y1stat.hits_sum.to_f / y1stat.at_bats_sum.to_f)).round(3)
+						winner.player = y2stat.player
+					end
+				end
+			end
+			return winner
+		end
+
+		def self.team_slugging_percentage(team_id, year)
+			PlayerBattingStat.where("team_id = ? AND year = ?", team_id, year)
+		end
+
+		def self.triple_crown_winner(league, year, min_at_bats=400)
+			winner = Winner.new()
+			btwinner = get_batting_title_winner(league, year, min_at_bats)
+			home_run_king = get_home_run_king(league, year, min_at_bats)
+			if btwinner.external_id == home_run_king.external_id
+				most_rbis = get_most_rbis(league, year, min_at_bats)
+				if btwinner.external_id == most_rbis.external_id
+					winner.player = btwinner.player
+				end
+			end
+			return winner
+		end
+
+		private
+
+		def self.get_grouped_at_bats(year, min_at_bats=200)
+			PlayerBattingStat.select(:id, :external_id, :year, "SUM(at_bats) as at_bats_sum", "SUM(hits) as hits_sum").where("year = ?", year).group(:external_id).having("sum(at_bats) >= ?", min_at_bats)
+		end
+
+		def self.get_batting_title_winner(league, year, min_at_bats)
+			PlayerBattingStat.where("league = ? AND year = ? AND at_bats >= ?", league, year, min_at_bats).order('batting_average DESC').first
+		end
+
+		def self.get_home_run_king(league, year, min_at_bats)
+			PlayerBattingStat.where("league = ? AND year = ? AND at_bats >= ?", league, year, min_at_bats).order('home_runs DESC').first
+		end
+
+		def self.get_most_rbis(league, year, min_at_bats)
+			PlayerBattingStat.where("league = ? AND year = ? AND at_bats >= ?", league, year, min_at_bats).order('runs_batted_in DESC').first
+		end
+	end
+end
+

data/lib/bstats/player.rb

@@ -0,0 +1,22 @@
+require_relative '../../db/db_config'
+require 'csv'
+
+module BStats
+	class Player < ActiveRecord::Base
+		has_many :player_batting_stats, :class_name => 'PlayerBattingStat', :foreign_key => 'external_id', :primary_key => 'external_id'
+
+		validates :external_id, presence: true
+		validates :birth_year, numericality: true
+
+		def self.import_csv(file)
+			CSV.foreach(file, headers: true) do |row|
+				player = Player.new()
+				player.external_id = row['playerID'].to_s
+				player.birth_year = row['birthYear'].to_i
+				player.first_name = row['nameFirst'].to_s
+				player.last_name = row['nameLast'].to_s
+				player.save
+			end
+		end
+	end
+end

data/lib/bstats/player_batting_stat.rb

@@ -0,0 +1,47 @@
+require_relative '../../db/db_config'
+require 'csv'
+
+module BStats
+	class PlayerBattingStat < ActiveRecord::Base
+		belongs_to :player, :class_name => "Player", :foreign_key => 'external_id', :primary_key => 'external_id'
+
+		validates :external_id, presence: true
+		validates :games, :at_bats, :runs, :hits, :doubles, :triples, :home_runs, :runs_batted_in, :stolen_bases, :caught_stealing, numericality: true
+
+		def self.import_csv(file)
+			begin
+				CSV.foreach(file, headers: true) do |row|
+					stat = PlayerBattingStat.new()
+					stat.external_id = row['playerID'].to_s
+					stat.year = row['yearID'].to_s
+					stat.league = row['league'].to_s
+					stat.team_id = row['teamID'].to_s
+					stat.games = row['G'].to_i
+					stat.at_bats = row['AB'].to_i
+					stat.runs = row['R'].to_i
+					stat.hits = row['H'].to_i
+					stat.doubles = row['2B'].to_i
+					stat.triples = row['3B'].to_i
+					stat.home_runs = row['HR'].to_i
+					stat.runs_batted_in = row['RBI'].to_i
+					stat.stolen_bases = row['SB'].to_i
+					stat.caught_stealing = row['CS'].to_i
+					stat.batting_average = self.calculate_batting_average(stat.hits, stat.at_bats)
+					stat.slugging_percentage = self.calculate_slugging_percentage(stat.hits, stat.doubles, stat.triples, stat.home_runs, stat.at_bats)
+					stat.save
+				end
+			rescue CSV::MalformedCSVError => e
+				# certain csv's have file endings that the CSV library doesn't like. Windows may or may not have something to do with that
+				# TODO: log file ending failure
+			end
+		end
+
+		def self.calculate_batting_average(hits, at_bats)
+			[0, "0", ""].include?(at_bats) ? 0 : (hits.to_f / at_bats.to_f).round(3)
+		end
+
+		def self.calculate_slugging_percentage(hits, doubles, triples, home_runs, at_bats)
+			[0, "0", ""].include?(at_bats) ? 0 : (((hits - doubles - triples - home_runs) + (2 * doubles) + (3 * triples) + (4 * home_runs)).to_f / at_bats).round(3)
+		end
+	end
+end

data/lib/bstats/winner.rb

@@ -0,0 +1,17 @@
+module BStats
+	class Winner
+		attr_accessor :player
+
+		def initialize
+			@player = nil
+		end		
+
+		def awarded?
+			[nil, ""].include?(@player) ? false : true
+		end
+
+		def to_s
+			awarded? ? "#{@player.last_name}, #{@player.first_name}" : "No winner."
+		end
+	end
+end

data/spec/bstats/batting_average_winner_spec.rb

@@ -0,0 +1,28 @@
+require 'spec_helper'
+require 'bstats/batting_average_winner'
+require 'bstats/player'
+
+module BStats
+  describe BattingAverageWinner do
+  	describe "before being loaded with a player" do
+	  	before do
+	  		@winner = BattingAverageWinner.new
+	  	end
+
+	  	it "should return 0 improvement" do
+	  		expect(@winner.percent_improved).to eq(0)
+	  	end
+	end
+
+	describe "after being loaded" do
+	  	before do
+	  		@winner = BattingAverageWinner.new
+	  		@winner.percent_improved = 0.345
+	  	end
+
+	  	it "should return the right improvement percentage" do
+	  		expect(@winner.percent_improved).to eq(0.345)
+	  	end
+	end
+  end
+end

data/spec/bstats/number_crunch_spec.rb

@@ -0,0 +1,37 @@
+require 'spec_helper'
+require 'bstats/number_crunch'
+require 'bstats/batting_average_winner'
+
+module BStats
+  describe NumberCrunch do
+    describe "calculating batting average" do
+        before do 
+            @stat1 = mock_model( 
+                PlayerBattingStat, :external_id => "cabremi01", :year => "2011", :league => "AL", :team_id => "DET", :games => 161, :at_bats => 622, :runs => 109, :hits => 205, :doubles => 40, :triples => 0, :home_runs => 44, :runs_batted_in => 139, :stolen_bases => 4, :caught_stealing => 1, :hits_sum => 205, :at_bats_sum => 622
+            )
+            @stat2 = mock_model( 
+                PlayerBattingStat, :external_id => "cabremi01", :year => "2012", :league => "AL", :team_id => "DET", :games => 161, :at_bats => 622, :runs => 109, :hits => 205, :doubles => 40, :triples => 0, :home_runs => 44, :runs_batted_in => 139, :stolen_bases => 4, :caught_stealing => 1, :hits_sum => 205, :at_bats_sum => 622
+            ) 
+            @stats = [@stat1, @stat2] 
+            allow(NumberCrunch).to receive(:get_grouped_at_bats).and_return(@stats)
+        end 
+        it "finds the most improved batting average" do
+            expect(NumberCrunch.most_improved_batting_average('2007', '2008').percent_improved).to eq(0)
+        end
+    end
+    describe "calculating triple crown winner" do
+        before do 
+            @player = mock_model(Player, :external_id => "cabremi01" )
+            @stat2 = mock_model( 
+                PlayerBattingStat, :external_id => "cabremi01", :year => "2012", :league => "AL", :team_id => "DET", :games => 161, :at_bats => 622, :runs => 109, :hits => 205, :doubles => 40, :triples => 0, :home_runs => 44, :runs_batted_in => 139, :stolen_bases => 4, :caught_stealing => 1, :hits_sum => 205, :at_bats_sum => 622, :player => @player
+            )             
+            allow(NumberCrunch).to receive(:get_batting_title_winner).and_return(@stat2)
+            allow(NumberCrunch).to receive(:get_home_run_king).and_return(@stat2)
+            allow(NumberCrunch).to receive(:get_most_rbis).and_return(@stat2)
+        end 
+        it "finds the triple crown winner" do
+            expect(NumberCrunch.triple_crown_winner("AL", "2012").player.external_id).to eq("cabremi01")
+        end
+    end
+  end
+end

data/spec/bstats/player_batting_stat_spec.rb

@@ -0,0 +1,28 @@
+require 'spec_helper'
+require 'csv'
+require 'bstats/player_batting_stat'
+
+module BStats
+  describe PlayerBattingStat do
+
+    describe "Importing a CSV" do
+		let(:data) { "abercre01\t2007\tNL\tFLO\t35\t76\t16\t15\t3\t0\t2\t5\t7\t1\rabreubo01\t2012\tAL\tLAA\t8\t24\t1\t5\t3\t0\t0\t5\t0\t0" }
+		before do
+			allow(CSV).to receive(:foreach).with("file_path", headers: true).and_return(data)
+		end
+
+		it "should read the CSV it is passed" do
+			expect(PlayerBattingStat.import_csv("file_path")).to eq(data)
+		end
+    end
+
+    describe "calculating stats" do
+    	it "should calculate the batting average" do
+    		expect(PlayerBattingStat.calculate_batting_average(3, 9)).to eq(0.333)
+    	end
+    	it "should calculate the slugging percentage" do
+    		expect(PlayerBattingStat.calculate_slugging_percentage(15, 3, 0, 2, 76)).to eq(0.316)
+    	end
+    end
+  end
+end

data/spec/bstats/player_spec.rb

@@ -0,0 +1,20 @@
+require 'spec_helper'
+require 'csv'
+require 'bstats/player'
+
+module BStats
+  describe Player do
+
+    describe "Importing a CSV" do
+		let(:data) { "id1\t1900\tfirst\tlast\rid2\t1901\tfirst2\tlast2"}
+
+		before do
+			allow(CSV).to receive(:foreach).with("file_path", headers: true).and_return(data)
+		end
+
+		it "should read the CSV it is passed" do
+			expect(Player.import_csv("file_path")).to eq(data)
+		end
+    end
+  end
+end

data/spec/bstats/winner_spec.rb

@@ -0,0 +1,45 @@
+require 'spec_helper'
+require 'bstats/winner'
+require 'bstats/player'
+
+module BStats
+  describe Winner do
+  	describe "before being loaded with a player" do
+	  	before do
+	  		@winner = Winner.new
+	  	end
+
+	  	it "should have no player" do
+	  		expect(@winner.player).to eq(nil)
+	  	end
+
+	  	it "should not report awarded" do
+	  		expect(@winner.awarded?).to be_falsey
+	  	end
+
+	  	it "should read no winner" do
+	  		expect(@winner.to_s).to eq("No winner.")
+	  	end
+	end
+
+	describe "after being loaded with a player" do
+	  	before do
+	  		@player = mock_model(Player, :last_name => "Baseball", :first_name => "Mr" )
+	  		@winner = Winner.new
+	  		@winner.player = @player
+	  	end
+
+	  	it "should have a player" do
+	  		expect(@winner.player).to eq(@player)
+	  	end
+
+	  	it "should report awarded" do
+	  		expect(@winner.awarded?).to be_truthy
+	  	end
+
+	  	it "should read winners name" do
+	  		expect(@winner.to_s).to eq("Baseball, Mr")
+	  	end
+	end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1 @@
+require 'rspec/active_model/mocks'

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification
+name: bstats
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Troy Stauffer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-10-17 00:00:00.000000000 Z
+dependencies: []
+description: A ruby gem that takes a couple CSVs and does a bit of numbers crunching
+  to generate a few statistics.
+email: troystauffer@gmail.com
+executables:
+- bstats
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/bstats
+- db/db_config.rb
+- db/migrate/create_player_batting_stats_table.rb
+- db/migrate/create_players_table.rb
+- db/temp.db
+- lib/bstats/batting_average_winner.rb
+- lib/bstats/data_persistence.rb
+- lib/bstats/number_crunch.rb
+- lib/bstats/player.rb
+- lib/bstats/player_batting_stat.rb
+- lib/bstats/winner.rb
+- lib/bstats.rb
+- spec/bstats/batting_average_winner_spec.rb
+- spec/bstats/number_crunch_spec.rb
+- spec/bstats/player_batting_stat_spec.rb
+- spec/bstats/player_spec.rb
+- spec/bstats/winner_spec.rb
+- spec/spec_helper.rb
+- Gemfile
+- README.md
+homepage: 
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Baseball Statistics Analysis Tool
+test_files:
+- spec/bstats/batting_average_winner_spec.rb
+- spec/bstats/number_crunch_spec.rb
+- spec/bstats/player_batting_stat_spec.rb
+- spec/bstats/player_spec.rb
+- spec/bstats/winner_spec.rb
+- spec/spec_helper.rb