Study of US Craft Beer and Breweries

Repository Structure

Our Git repository {https://github.com/davestroud/BeerStudy} is relatively unstructured, with the following pertinent files contained within:

• README.md : This is the base page for the repository, containing an introduction as well as our codebook for how we coded variable names throughout the datasets.
• BottomsUp_DS.Rmd : This is the primary file for the analysis, and is the file you are currently reading. It contains all the relevant R code, graphics, and analysis for the project; also included are specific .docx, .html, and .pdf knitted versions of this file.
• Beers.csv and Breweries.csv, were provided and are the original datasets from which our merged dataset is produced.

Reproduction of Analysis

It would be suggested to start with the README.md file to acquaint yourself with our nomenclature. Clone or otherwise download this repository, then run the BottomsUp_DS.Rmd file.

1. How many breweries are present in each state?

We answer this question by retrieving the value of State from the Breweries data.

BrewPerState <-table(Breweries$State)
BrewPerState

## 
## AK AL AR AZ CA CO CT DC DE FL GA HI IA ID IL IN KS KY LA MA MD ME MI MN MO 
##  7  3  2 11 39 47  8  1  2 15  7  4  5  5 18 22  3  4  5 23  7  9 32 12  9 
## MS MT NC ND NE NH NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV 
##  2  9 19  1  5  3  3  4  2 16 15  6 29 25  5  4  1  3 28  4 16 10 23 20  1 
## WY 
##  4

# Renamed Brewery_id to Brew_ID to satisfy merging requirement
Beers <- rename(Beers, Brew_ID = Brewery_id)

2. Merge beer data with the breweries data. Print the first 6 observations and the last six observations to check the merged file.

As part of our analysis, we ensured that duplicate data within each dataset shared the same variable name in both sets. We can now merge them into a single dataset, using full_join.

BrewPub <- full_join(Beers, Breweries, by="Brew_ID")

# Change variable names to more meaningful title
BrewPub <- rename(BrewPub, Beer = Name.x, Brewery = Name.y,
                  OZ = Ounces)

To retrieve the first and last six observations from the combined data, we run head and tail on BrewPub, our combined dataset.

kable(BrewPub %>% head())

kable(BrewPub %>% tail())

3. Report the number of NA’s in each column.

To do this, we use a function (which returns true if a given value is NA, false otherwise, using is.na) and sapply to determine the number of missing values for each column within BrewPub.

Per the results, we find that there are a total of 62 ABV values missing, and 1005 IBU values missing. No other data is missing.

MissingValues <- sapply(BrewPub, function(x)sum(is.na(x)))
# Used kable library to make document more presentable
MissingValues %>%
  kable("html") %>%
  kable_styling()

4. Compute the median alcohol content and international bitterness unit for each state. Plot a bar chart to compare.

We build two new datasets, Bitter and FireWater, from our BrewPub dataset, omitting NA values. We then group the relevant values by state, and summarise by the median of the relevant value.

# 4. Compute the median alcohol content unit for each state.
Firewater <- BrewPub %>%
  na.omit() %>%
group_by(State) %>%
summarise(Median = median(ABV)) %>%
arrange(Median)

# 4. a Compute the median international bitterness unit for each state.
Bitter <- BrewPub %>%
  na.omit() %>%
group_by(State) %>%
summarise(Median = median(IBU)) %>%
arrange(Median)

# 4. b Plot a bar chart to compare ABV by state
library(ggthemes)
ggplot(data=Firewater, aes(x=State, y=Median)) +
  geom_bar(stat="identity", fill="steelblue")+
  theme_economist() + 
  scale_color_economist()+
  theme(axis.text.x=element_text(size=rel(0.8), angle=90)) +
  ggtitle("Median ABV by State") +
  labs(x="State",y="ABV")

# 4. c Plot a bar chart to compare IBU by state
ggplot(data=Bitter, aes(x=State, y=Median)) +
  geom_bar(stat="identity", fill="steelblue")+
  theme_economist() + 
  scale_color_economist()+
  theme(axis.text.x=element_text(size=rel(0.8), angle=90))+
  ggtitle("Median IBU by State") +
  labs(x="State",y="IBU")

5. Which state has the maximum alcoholic (ABV) beer? Which state has the most bitter (IBU) beer?

We use which.max on our BrewPub dataset, seeking specifically the maximum value in the ABV and IBU columns.

From this, we identify Colorado as having the beer with the highest ABV, at .128; and we identify Oregon has having the beer with the highest IBU, at 138.

kable(BrewPub[which.max(BrewPub$ABV),])

kable(BrewPub[which.max(BrewPub$IBU),])

6. Summary statistics for the ABV variable.

We do this by calling summary on the ABV column in our BrewPub dataset.

BeerSummary <- (summary(BrewPub$ABV))
print(BeerSummary)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
## 0.00100 0.05000 0.05600 0.05977 0.06700 0.12800      62

7. Is there an apparent relationship between the bitterness of the beer and its alcoholic content? Draw a scatter plot.

We utilize ggplot to plot a scatter plot of the data, using IBU and ABV as our variables.

Examination of this scatter plot and the regression line suggests that there is a positive, linear relationship between IBU and ABV.

# 7. Draw a scatter plot to compare relationship between beer 
# bitterness and alcohol content
ggplot(BrewPub, aes(x=IBU, y= ABV)) +
  geom_point(shape=1) +
   geom_smooth(method=lm) + # add linear regression line
  theme_economist() + 
  scale_color_economist()+
  theme(axis.text.x=element_text(size=rel(1.0)))+
ggtitle("Correlation between IBU and ABV ") +
  labs(x="IBU",y="ABV")