library(tidyverse)
library(reactable)
Principles of Data Visualization and Introduction to ggplot2
I have provided you with data about the 5,000 fastest growing companies in the US, as compiled by Inc. magazine. lets read this in:
inc <- read.csv("https://raw.githubusercontent.com/charleyferrari/CUNY_DATA_608/master/module1/Data/inc5000_data.csv", header= TRUE)
And lets preview this data:
head(inc) %>%
reactable()
summary(inc)
## Rank Name Growth_Rate Revenue
## Min. : 1 Length:5001 Min. : 0.340 Min. :2.000e+06
## 1st Qu.:1252 Class :character 1st Qu.: 0.770 1st Qu.:5.100e+06
## Median :2502 Mode :character Median : 1.420 Median :1.090e+07
## Mean :2502 Mean : 4.612 Mean :4.822e+07
## 3rd Qu.:3751 3rd Qu.: 3.290 3rd Qu.:2.860e+07
## Max. :5000 Max. :421.480 Max. :1.010e+10
##
## Industry Employees City State
## Length:5001 Min. : 1.0 Length:5001 Length:5001
## Class :character 1st Qu.: 25.0 Class :character Class :character
## Mode :character Median : 53.0 Mode :character Mode :character
## Mean : 232.7
## 3rd Qu.: 132.0
## Max. :66803.0
## NA's :12
Think a bit on what these summaries mean. Use the space below to add some more relevant non-visual exploratory information you think helps you understand this data:
glimpse(inc)
## Rows: 5,001
## Columns: 8
## $ Rank <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,…
## $ Name <chr> "Fuhu", "FederalConference.com", "The HCI Group", "Bridger…
## $ Growth_Rate <dbl> 421.48, 248.31, 245.45, 233.08, 213.37, 179.38, 174.04, 17…
## $ Revenue <dbl> 1.179e+08, 4.960e+07, 2.550e+07, 1.900e+09, 8.700e+07, 4.5…
## $ Industry <chr> "Consumer Products & Services", "Government Services", "He…
## $ Employees <int> 104, 51, 132, 50, 220, 63, 27, 75, 97, 15, 149, 165, 250, …
## $ City <chr> "El Segundo", "Dumfries", "Jacksonville", "Addison", "Bost…
## $ State <chr> "CA", "VA", "FL", "TX", "MA", "TX", "TN", "CA", "UT", "RI"…
I will check for missing data.
inc %>%
map(is.na) %>%
map(sum) %>%
bind_cols() %>%
t() %>%
reactable()
Create a graph that shows the distribution of companies in the dataset by State (ie how many are in each state). There are a lot of States, so consider which axis you should use. This visualization is ultimately going to be consumed on a ‘portrait’ oriented screen (ie taller than wide), which should further guide your layout choices.
# Answer Question 1 here
inc %>%
group_by(State) %>%
summarise(n = n()) %>%
arrange(desc(n)) %>%
ggplot(aes(reorder(State,n), n)) +
geom_bar(stat="identity", fill="steelblue") +
coord_flip() +
labs(title = "Number of Companies by State", x = "State", y = "Number of Companies") +
geom_text(aes(label=n), vjust=0.6, hjust=1.2, size=3, color="black")
Lets dig in on the state with the 3rd most companies in the data set. Imagine you work for the state and are interested in how many people are employed by companies in different industries. Create a plot that shows the average and/or median employment by industry for companies in this state (only use cases with full data, use R’s complete.cases() function.) In addition to this, your graph should show how variable the ranges are, and you should deal with outliers.
nyInfo <- inc %>%
filter( State == "NY") %>%
filter(complete.cases(.))
nyInfo %>%
group_by(State, Industry) %>%
summarise(med_employees = median(Employees), .groups = 'keep') %>%
ggplot(aes(fct_reorder(Industry,med_employees),med_employees, fill=Industry)) +
geom_bar(stat="identity") +
coord_flip() +
theme(legend.position='none') +
labs(x="Median Number of Employees", y="Industry")
I will now create a box plot for each industry in New York state. Note that a few industries have outliers that make the plot difficult to read.
nyInfo %>%
group_by(Industry) %>%
ggplot(aes(x=Industry,y=Employees)) +
geom_boxplot() +
coord_flip()
I will filter the data so that only point less than 5000 employees remain, and will plot the information again.
nyInfo %>%
filter(Employees <= 5000) %>%
group_by(Industry) %>%
ggplot(aes(x=Industry,y=Employees)) +
geom_boxplot() +
coord_flip()
Now imagine you work for an investor and want to see which industries generate the most revenue per employee. Create a chart that makes this information clear. Once again, the distribution per industry should be shown.
revenue_employee <- inc %>%
filter(complete.cases(.)) %>%
group_by(Industry) %>%
summarise(TotalEmp = sum(Employees), TotalRev = sum(Revenue)) %>%
mutate(rev_per_emp = TotalRev/TotalEmp )
revenue_employee %>%
ggplot(aes(fct_reorder(Industry,rev_per_emp), rev_per_emp) ) +
geom_bar(stat="identity") +
coord_flip() +
theme(legend.position='none') +
labs(x="Revenue Per Employee", y="Industry")