DATA 608 HW1
Magnus Skonberg
2021-02-08
Background
The purpose of the assignment was to explore principles of data visualization with ggplot2.
…………………………………………………………………….
Preliminary EDA
#Read in data on the fastest growing companies in the US, as compiled by Inc. magazine:
inc <- read.csv("https://raw.githubusercontent.com/charleyferrari/CUNY_DATA_608/master/module1/Data/inc5000_data.csv", header= TRUE)Previewing the first 6 entries and summary statistics:
## Rank Name Growth_Rate Revenue
## 1 1 Fuhu 421.48 1.179e+08
## 2 2 FederalConference.com 248.31 4.960e+07
## 3 3 The HCI Group 245.45 2.550e+07
## 4 4 Bridger 233.08 1.900e+09
## 5 5 DataXu 213.37 8.700e+07
## 6 6 MileStone Community Builders 179.38 4.570e+07
## Industry Employees City State
## 1 Consumer Products & Services 104 El Segundo CA
## 2 Government Services 51 Dumfries VA
## 3 Health 132 Jacksonville FL
## 4 Energy 50 Addison TX
## 5 Advertising & Marketing 220 Boston MA
## 6 Real Estate 63 Austin TX## 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 :12We then perform some further non-visual exploration of the data to further our familiarity and understanding:
## [1] 5001 8## 'data.frame': 5001 obs. of 8 variables:
## $ Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Name : chr "Fuhu" "FederalConference.com" "The HCI Group" "Bridger" ...
## $ Growth_Rate: num 421 248 245 233 213 ...
## $ Revenue : num 1.18e+08 4.96e+07 2.55e+07 1.90e+09 8.70e+07 ...
## $ Industry : chr "Consumer Products & Services" "Government Services" "Health" "Energy" ...
## $ Employees : int 104 51 132 50 220 63 27 75 97 15 ...
## $ City : chr "El Segundo" "Dumfries" "Jacksonville" "Addison" ...
## $ State : chr "CA" "VA" "FL" "TX" ...##
## Advertising & Marketing Business Products & Services
## 471 482
## Computer Hardware Construction
## 44 187
## Consumer Products & Services Education
## 203 83
## Energy Engineering
## 109 74
## Environmental Services Financial Services
## 51 260
## Food & Beverage Government Services
## 131 202
## Health Human Resources
## 355 196
## Insurance IT Services
## 50 733
## Logistics & Transportation Manufacturing
## 155 256
## Media Real Estate
## 54 96
## Retail Security
## 203 73
## Software Telecommunications
## 342 129
## Travel & Hospitality
## 62##
## AK AL AR AZ CA CO CT DC DE FL GA HI IA ID IL IN KS KY LA MA
## 2 51 9 100 701 134 50 43 16 282 212 7 28 17 273 69 38 40 37 182
## MD ME MI MN MO MS MT NC ND NE NH NJ NM NV NY OH OK OR PA PR
## 131 13 126 88 59 12 4 137 10 27 24 158 5 26 311 186 46 49 164 1
## RI SC SD TN TX UT VA VT WA WI WV WY
## 16 48 3 82 387 95 283 6 130 79 2 2…………………………………………………………………….
Question 1
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.
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v tibble 3.0.4 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0
## v purrr 0.3.4## Warning: package 'tibble' was built under R version 4.0.3## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()#Visualize state count
##count companies per state, reorder based on count, display blue bars, horizontally, with specified labels, and minimal theme.
inc %>%
count(State) %>%
ggplot(aes(x = reorder(State, n), y = n)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() +
labs(title = "Distribution of Companies by State", x= "State", y = "Company Count") +
theme_minimal()
Question 2
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.
#State with 3rd most companies: NY
ny_st <- filter(inc, `State` == 'NY') #filter for NY
ny <- ny_st[complete.cases(ny_st), ] #filter out incomplete cases
##Initial boxplot of Employee Breakdown by Industry
ny %>%
ggplot(aes(x = reorder(Industry, Employees), y = Employees)) +
geom_boxplot(color = "blue", fill = "blue", alpha=0.2, outlier.color = "red", outlier.fill = "red", outlier.size = 2) +
coord_flip() +
labs(title = "New York: Employee Breakdown by Industry", x= "Industry", y = "Employees") +
#ylim(0,1200) +
theme_minimal()
Based on the guidelines provided above, I elected to display a boxplot. A boxplot is useful for noting the average / median, 1QR, 3QR, outliers, etc. Thus we could plot the average, show our variability, and capture our outliers on ONE plot.
The plot above provides these indicators but we’re much too “zoomed out” due to the large outlier value for ‘Business Products and Services’, thus we zoom in our Employees axis to gain greater insight into our Employee-Industry data:
##Zoomed in boxplot of Employee Breakdown by Industry
ny %>%
ggplot(aes(x = reorder(Industry, Employees), y = Employees)) +
geom_boxplot(color = "blue", fill = "blue", alpha=0.2, outlier.color = "red", outlier.fill = "red", outlier.size = 2) +
coord_flip() +
labs(title = "New York: Employee Breakdown by Industry", x= "Industry", y = "Employees") +
ylim(0,1200) +
theme_minimal()## Warning: Removed 7 rows containing non-finite values (stat_boxplot).
While we could certainly zoom in again (ie. limit our yrange upto 100 or so) to gain greater insight into our industries with smaller employee ranges, the boxplot above provides a clearer idea of the level of employability based on industry. The range is noted by the light blue box, the median values are demarkated with dark blue lines, and outlier values are noted with red dots.
Question 3
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.
# Which Industries generate the most revenue per employee?
inc <- inc[complete.cases(inc), ] #filter our incomplete cases
#First we group by industry, sum corresponding Employee and Revenue columns, and then account for their product with the addition of the 'rev_emp' column, then we plot the corresponding revenue per employee vs. Industry:
inc %>%
group_by(Industry) %>%
summarise(Employees = sum(Employees), Revenue = sum(Revenue)) %>%
mutate( rev_emp = Revenue / Employees) %>%
ggplot(aes(x = reorder(Industry, rev_emp), y = rev_emp)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() +
labs(title = "Revenue per Employee by Industry", x= "Industry", y = "Revenue Per Employee ($)") +
theme_minimal()## `summarise()` ungrouping output (override with `.groups` argument)
From the above breakdown, we can see that the top (3) industries for revenue per employee are: Computer Hardware, Energy, and Construction. While the bottom (3) industries are: Engineering, Security, and Human Resources.
We also see that these values seem high. I would’ve anticipated lower Revenue Per Employee but then again I’ve never dug in to data of this nature …