beer

beer.R

library(dplyr) # so we can use %>% pipes!
rawBeer <- read.csv(file = "../data/raw/Beers.csv",header=TRUE, sep=",",stringsAsFactors=FALSE)
rawBrew <- read.csv(file= "../data/raw/Breweries.csv", header=TRUE, sep=",", stringsAsFactors=FALSE)
head(rawBeer)
#                  Name Beer_ID   ABV IBU Brewery_id                          Style
# 1            Pub Beer    1436 0.050  NA        409            American Pale Lager
# 2         Devil's Cup    2265 0.066  NA        178        American Pale Ale (APA)
# 3 Rise of the Phoenix    2264 0.071  NA        178                   American IPA
# 4            Sinister    2263 0.090  NA        178 American Double / Imperial IPA
# 5       Sex and Candy    2262 0.075  NA        178                   American IPA
# 6        Black Exodus    2261 0.077  NA        178                  Oatmeal Stout
#   Ounces
# 1     12
# 2     12
# 3     12
# 4     12
# 5     12
# 6     12
head(rawBrew)
#   Brew_ID                      Name          City State
# 1       1        NorthGate Brewing    Minneapolis    MN
# 2       2 Against the Grain Brewery    Louisville    KY
# 3       3  Jack's Abby Craft Lagers    Framingham    MA
# 4       4 Mike Hess Brewing Company     San Diego    CA
# 5       5   Fort Point Beer Company San Francisco    CA
# 6       6     COAST Brewing Company    Charleston    SC
rawBeer %>% rename(Brewery_ID=Brewery_id) -> Beer1
rawBrew %>% rename(Brewery_ID=Brew_ID) -> Brew1

Beer1 %>% select(Name,Beer_ID,ABV,IBU,Style,Ounces,Brewery_ID) -> Beer1
BeerBrew <- merge(Beer1,Brew1, by='Brewery_ID')
BeerBrew %>% rename(BeerName = Name.x) %>% rename(BreweryName = Name.y) -> BeerBrew
BeerBrew %>% select(BeerName,Beer_ID,ABV,IBU,Style,Ounces,BreweryName,Brewery_ID,City,State) -> BeerBrew
head(BeerBrew)
#        BeerName Beer_ID   ABV IBU                               Style Ounces        BreweryName Brewery_ID        City State
# 1  Get Together    2692 0.045  50                        American IPA     16 NorthGate Brewing           1 Minneapolis    MN
# 2 Maggie's Leap    2691 0.049  26                  Milk / Sweet Stout     16 NorthGate Brewing           1 Minneapolis    MN
# 3    Wall's End    2690 0.048  19                   English Brown Ale     16 NorthGate Brewing           1 Minneapolis    MN
# 4       Pumpion    2689 0.060  38                         Pumpkin Ale     16 NorthGate Brewing           1 Minneapolis    MN
# 5    Stronghold    2688 0.060  25                     American Porter     16 NorthGate Brewing           1 Minneapolis    MN
# 6   Parapet ESB    2687 0.056  47 Extra Special / Strong Bitter (ESB)     16 NorthGate Brewing           1 Minneapolis    MN
data.frame(sapply(BeerBrew, function(y) sum(length(which(is.na(y)))))) %>% rename(na_count=sapply.BeerBrew..function.y..sum.length.which.is.na.y.....)
#             na_count
# BeerName           0
# Beer_ID            0
# ABV               62
# IBU             1005
# Style              0
# Ounces             0
# BreweryName        0
# Brewery_ID         0
# City               0
# State              0
StateSummary <- BeerBrew %>%
       	group_by(State) %>% 
	summarise(medianABV = median(ABV, na.rm=TRUE),
		  medianIBU = median(IBU, na.rm=TRUE),
		  NumBreweries = n_distinct(Brewery_ID)) %>% 
	data.frame
#    State medianABV medianIBU NumBreweries
# 1     AK    0.0560      46.0            7
# 2     AL    0.0600      43.0            3
# 3     AR    0.0520      39.0            2
# 4     AZ    0.0550      20.5           11
# 5     CA    0.0580      42.0           39
# 6     CO    0.0605      40.0           47
MaxABV <- BeerBrew %>%
	select(State, BeerName, ABV) %>%
	filter(!is.na(ABV)) %>%
	top_n(ABV,n=1)
#   State                                             BeerName   ABV
# 1    CO Lee Hill Series Vol. 5 - Belgian Style Quadrupel Ale 0.128
MaxIBU <- BeerBrew %>% 
	select(State, BeerName, IBU) %>% 
	filter(!is.na(IBU)) %>% 
	arrange(desc(IBU)) %>% 
	slice(1)
#   State                  BeerName IBU
# 1    OR Bitter Bitch Imperial IPA 138