Tidyverse Assignment 1

Initiate Libraries

The following Libraries are referenced for completing the assignment

  1. DPLYR
  2. TIDYVERSE
  3. USMAP
  4. GGPLOT2
  5. DATA.TABLE

Input Brewery Dataset

This dataset is from kaggle.com and provides insight on the breweries exist across United States. Below are several analysis performed using the dataset.

  1. State wise count of breweries
  2. Number of Micro breweries across US
  3. Number of Contract breweries across US
  4. Breweries operate across US
brew_df <- data.table(read.csv("https://raw.githubusercontent.com/jey1987/DATA607/master/JR_TidyVerse_Assignment/breweries_us.csv",sep = ",", stringsAsFactors = F))
brew_df

Deriving necessary datasets

brew_df <- brew_df %>%
  mutate(state=replace_na(state,"No State Mentioned")) %>%
  mutate(type=replace_na(type,"No Type Mentioned")) %>%
  mutate(state=str_to_sentence(state)) %>%
  mutate(type=str_to_sentence(type))

brew_df_state_count <- brew_df %>%
  select(state) %>%
  group_by(state) %>%
  count()

brew_df_state_micro <- brew_df %>%
  select(type,state) %>%
  filter(type=="Microbrewery") %>%
  group_by(state) %>%
  count()

brew_df_state_brewpub <- brew_df %>%
  select(type,state) %>%
  filter(type=="Contractbrewery") %>%
  group_by(state) %>%
  count()
brew_df_state_brewname <- brew_df %>%
  select(brewery_name,state) %>%
  distinct(brewery_name,state) %>%
  group_by(brewery_name,state) %>%
  group_by(brewery_name) %>%
  dplyr::summarise(cnt=dplyr::n()) %>%
  filter(cnt>1) 

brew_top5_across_state <- inner_join(brew_df_state_brewname, brew_df, by = "brewery_name")

Visualizations

plot_usmap(data = brew_df_state_count, values = "n",labels = TRUE) + 
  scale_fill_continuous(
    low = "yellow", high = "red", name = "Brewery Count"
  ) + theme(legend.position = "right", plot.title = element_text(hjust = 0.5)) + labs(title = "Brewery Count by State")

plot_usmap(data = brew_df_state_micro, values = "n", labels = TRUE) + 
  scale_fill_continuous(
    low = "yellow", high = "red", name = "Micro Brewery Count"
  ) + theme(legend.position = "right", plot.title = element_text(hjust = 0.5)) + labs(title = "MicroBrewery Count by State")

plot_usmap(data = brew_df_state_brewpub, values = "n", labels = TRUE) + 
  scale_fill_continuous(
    low = "yellow", high = "red", name = "Contract Brewery Count"
  ) + theme(legend.position = "right", plot.title = element_text(hjust = 0.5)) + labs(title = "Contract Brewery Count by State")

ggplot(brew_top5_across_state, aes(fill=state , y=cnt, x=brewery_name)) +
  geom_bar( stat="identity", position="fill") + theme(axis.text.x = element_text(angle=90)) + xlab("Brewing Co.") + ylab("Number of Breweries by State") +
  ggtitle("Breweries who serve more than one state")

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.