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:
library(Hmisc)
library(funModeling)
library(tidyverse)
library(dplyr)
library(psych)
library(plotly)
options(scipen=999)
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)
## Rank Name Growth_Rate Revenue
## 1 1 Fuhu 421.48 117900000
## 2 2 FederalConference.com 248.31 49600000
## 3 3 The HCI Group 245.45 25500000
## 4 4 Bridger 233.08 1900000000
## 5 5 DataXu 213.37 87000000
## 6 6 MileStone Community Builders 179.38 45700000
## 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
summary(inc)
## Rank Name Growth_Rate
## Min. : 1 (Add)ventures : 1 Min. : 0.340
## 1st Qu.:1252 @Properties : 1 1st Qu.: 0.770
## Median :2502 1-Stop Translation USA: 1 Median : 1.420
## Mean :2502 110 Consulting : 1 Mean : 4.612
## 3rd Qu.:3751 11thStreetCoffee.com : 1 3rd Qu.: 3.290
## Max. :5000 123 Exteriors : 1 Max. :421.480
## (Other) :4995
## Revenue Industry
## Min. : 2000000 IT Services : 733
## 1st Qu.: 5100000 Business Products & Services: 482
## Median : 10900000 Advertising & Marketing : 471
## Mean : 48222535 Health : 355
## 3rd Qu.: 28600000 Software : 342
## Max. :10100000000 Financial Services : 260
## (Other) :2358
## Employees City State
## Min. : 1.0 New York : 160 CA : 701
## 1st Qu.: 25.0 Chicago : 90 TX : 387
## Median : 53.0 Austin : 88 NY : 311
## Mean : 232.7 Houston : 76 VA : 283
## 3rd Qu.: 132.0 San Francisco: 75 FL : 282
## Max. :66803.0 Atlanta : 74 IL : 273
## NA's :12 (Other) :4438 (Other):2764
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:
# Insert your code here, create more chunks as necessary
glimpse(inc)
## Observations: 5,001
## Variables: 8
## $ Rank <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,...
## $ Name <fct> Fuhu, FederalConference.com, The HCI Group, Bridge...
## $ Growth_Rate <dbl> 421.48, 248.31, 245.45, 233.08, 213.37, 179.38, 17...
## $ Revenue <dbl> 117900000, 49600000, 25500000, 1900000000, 8700000...
## $ Industry <fct> Consumer Products & Services, Government Services,...
## $ Employees <int> 104, 51, 132, 50, 220, 63, 27, 75, 97, 15, 149, 16...
## $ City <fct> El Segundo, Dumfries, Jacksonville, Addison, Bosto...
## $ State <fct> CA, VA, FL, TX, MA, TX, TN, CA, UT, RI, VA, CA, FL...
describe(inc)
## vars n mean sd median trimmed
## Rank 1 5001 2501.64 1443.51 2502.00 2501.73
## Name* 2 5001 2501.00 1443.81 2501.00 2501.00
## Growth_Rate 3 5001 4.61 14.12 1.42 2.14
## Revenue 4 5001 48222535.49 240542281.14 10900000.00 17334966.26
## Industry* 5 5001 12.10 7.33 13.00 12.05
## Employees 6 4989 232.72 1353.13 53.00 81.78
## City* 7 5001 732.00 441.12 761.00 731.74
## State* 8 5001 24.80 15.64 23.00 24.44
## mad min max range skew
## Rank 1853.25 1.00 5000.00 4999.00 0.00
## Name* 1853.25 1.00 5001.00 5000.00 0.00
## Growth_Rate 1.22 0.34 421.48 421.14 12.55
## Revenue 10674720.00 2000000.00 10100000000.00 10098000000.00 22.17
## Industry* 8.90 1.00 25.00 24.00 -0.10
## Employees 53.37 1.00 66803.00 66802.00 29.81
## City* 604.90 1.00 1519.00 1518.00 -0.04
## State* 19.27 1.00 52.00 51.00 0.12
## kurtosis se
## Rank -1.20 20.41
## Name* -1.20 20.42
## Growth_Rate 242.34 0.20
## Revenue 722.66 3401441.44
## Industry* -1.18 0.10
## Employees 1268.67 19.16
## City* -1.26 6.24
## State* -1.46 0.22
profiling_num(inc)
## variable mean std_dev variation_coef p_01
## 1 Rank 2501.640872 1443.50617 0.5770237 51.00
## 2 Growth_Rate 4.611826 14.12369 3.0624947 0.36
## 3 Revenue 48222535.492901 240542281.13587 4.9881716 2100000.00
## 4 Employees 232.717980 1353.12795 5.8144538 5.00
## p_05 p_25 p_50 p_75 p_95 p_99
## 1 252.00 1252.00 2502.00 3751.00 4751.00 4951.00
## 2 0.43 0.77 1.42 3.29 17.16 52.54
## 3 2400000.00 5100000.00 10900000.00 28600000.00 155600000.00 573900000.00
## 4 10.00 25.00 53.00 132.00 688.00 3244.56
## skewness kurtosis iqr range_98
## 1 -0.0004897066 1.800288 2499.00 [51, 4951]
## 2 12.5532709896 245.434761 2.52 [0.36, 52.54]
## 3 22.1810979541 725.946609 23500000.00 [2100000, 573900000]
## 4 29.8193818091 1272.181074 107.00 [5, 3244.55999999999]
## range_80
## 1 [502, 4501]
## 2 [0.5, 9.12]
## 3 [3000000, 76900000]
## 4 [14, 351.2]
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.
question_one <- inc %>%
group_by(State) %>%
summarize(n=n()) %>%
arrange(desc(n)) %>%
ggplot(aes(x = reorder(State, n), y = n)) +
geom_bar(stat = "identity", aes(fill = n), width = 0.8, position = position_dodge(width = 0.8)) +
coord_flip() +
ggtitle("Distribution of Companies by State") +
xlab("State") +
ylab("Count") +
theme(legend.position="none")
question_one <- ggplotly(question_one)
question_one
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.
# Answer Question 2 here
inc_filter <-inc %>%
filter(complete.cases(.)) %>%
group_by(State) %>%
mutate(n=n()) %>%
arrange(desc(n)) %>%
ungroup() %>%
mutate(ranks = dense_rank(desc(n))) %>%
filter(ranks == 3) %>%
group_by(Industry)
question_two <- ggplot(inc_filter, aes(Industry, Employees)) +
geom_boxplot(fill='lightgrey') +
scale_y_continuous(limits = quantile(inc_filter$Employees, c(0.1,0.9))) +
coord_flip() +
theme_gray()
question_two <- ggplotly(question_two)
## Warning: Removed 62 rows containing non-finite values (stat_boxplot).
question_two
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.
# Answer Question 3 here
question_three <- inc %>%
filter(complete.cases(.)) %>%
group_by(Industry) %>%
summarise(n=n(), Revenue = sum(Revenue), Employees= sum(Employees)) %>%
mutate(rev_per_emp = Revenue/Employees) %>%
ggplot(aes(x=reorder(Industry, rev_per_emp), y=rev_per_emp)) +
geom_bar(stat="identity", aes(fill=Employees)) +
coord_flip() +
ggtitle("Rev per Employee by Industry") +
ylab("Rev Per Emp") +
xlab("Industry") +
theme(legend.position="none")
question_three <- ggplotly(question_three)
question_three