DATA608_Module1
Niteen Kumar
February 10, 2019
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)## 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 TXsummary(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 Employees
## Min. :2.000e+06 IT Services : 733 Min. : 1.0
## 1st Qu.:5.100e+06 Business Products & Services: 482 1st Qu.: 25.0
## Median :1.090e+07 Advertising & Marketing : 471 Median : 53.0
## Mean :4.822e+07 Health : 355 Mean : 232.7
## 3rd Qu.:2.860e+07 Software : 342 3rd Qu.: 132.0
## Max. :1.010e+10 Financial Services : 260 Max. :66803.0
## (Other) :2358 NA's :12
## City State
## New York : 160 CA : 701
## Chicago : 90 TX : 387
## Austin : 88 NY : 311
## Houston : 76 VA : 283
## San Francisco: 75 FL : 282
## Atlanta : 74 IL : 273
## (Other) :4438 (Other):2764Think 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
inc <- as.data.table(inc)
# list rows of data that have missing values
inc[!complete.cases(inc),]## Rank Name Growth_Rate Revenue
## 1: 183 First Flight Solutions 22.32 2700000
## 2: 1064 Popchips 3.98 93300000
## 3: 1124 Vocalocity 3.72 42900000
## 4: 1653 Higher Logic 2.36 6000000
## 5: 1686 Global Communications Group 2.30 3600000
## 6: 2197 JeffreyM Consulting 1.68 12100000
## 7: 2743 Excalibur Exhibits 1.27 9900000
## 8: 3001 Heartland Business Systems 1.12 156300000
## 9: 3978 SSEC 0.68 80400000
## 10: 4112 Carolinas Home Medical Equipment 0.64 3300000
## 11: 4566 Oakbrook 0.48 8900000
## 12: 4968 Popcorn Palace 0.35 5500000
## Industry Employees City State
## 1: Logistics & Transportation NA Emerald Isle NC
## 2: Food & Beverage NA San Francisco CA
## 3: Telecommunications NA Atlanta GA
## 4: Software NA Washington DC
## 5: Telecommunications NA Englewood CO
## 6: Business Products & Services NA Bellevue WA
## 7: Business Products & Services NA houston TX
## 8: IT Services NA Little Chute WI
## 9: Manufacturing NA Horsham PA
## 10: Health NA Matthews NC
## 11: Real Estate NA Madison WI
## 12: Food & Beverage NA Schiller Park ILinc.final <- na.omit(inc)
# Growth rate by indsutry
datatable((arrange(inc.final[, .(mean_growth_rate = mean(Growth_Rate),
median_growth_rate = median(Growth_Rate),
min_growth_rate = min(Growth_Rate),
max_growth_rate = max(Growth_Rate)), by = .(Industry)], desc(mean_growth_rate))), options = list(
columnDefs = list(list(className = 'dt-center')),
pageLength = 5,
lengthMenu = c(5, 10, 15, 20)
))# Revenue summary by industry
datatable((arrange(inc.final[, .(mean_rev = mean(Revenue),
median_rev = median(Revenue),
min_rev = min(Revenue),
max_rev = max(Revenue)), by = .(Industry)], desc(mean_rev))), options = list(
columnDefs = list(list(className = 'dt-center')),
pageLength = 5,
lengthMenu = c(5, 10, 15, 20)
))# number of employees by industry
datatable((arrange(inc.final[, .(sum_employee = sum(Employees),
mean_employee = mean(Employees),
min_employee = min(Employees),
max_employee = max(Employees)), by =.(Industry)], desc(sum_employee))), options = list(
columnDefs = list(list(className = 'dt-center')),
pageLength = 5,
lengthMenu = c(5, 10, 15, 20)
))# number of cities by industry
kable(head(arrange(inc.final[, .(count = length(unique(City))), by =.(Industry)], desc(count)),10))| Industry | count |
|---|---|
| IT Services | 388 |
| Business Products & Services | 292 |
| Health | 257 |
| Advertising & Marketing | 252 |
| Manufacturing | 223 |
| Software | 202 |
| Financial Services | 191 |
| Retail | 164 |
| Construction | 157 |
| Consumer Products & Services | 152 |
# number of state by industry
kable(head(arrange(inc.final[, .(count = length(unique(State))), by =.(Industry)], desc(count)),10))| Industry | count |
|---|---|
| Health | 44 |
| Software | 44 |
| IT Services | 44 |
| Advertising & Marketing | 43 |
| Business Products & Services | 42 |
| Financial Services | 39 |
| Manufacturing | 38 |
| Retail | 37 |
| Construction | 36 |
| Consumer Products & Services | 34 |
# number of cities by state
kable(head(arrange(inc.final[, .(count = length(unique(City))), by =.(State)], desc(count)),10))| State | count |
|---|---|
| CA | 204 |
| IL | 104 |
| FL | 102 |
| NJ | 97 |
| NY | 90 |
| PA | 80 |
| OH | 79 |
| MA | 72 |
| TX | 66 |
| VA | 56 |
# number of companies by industry
kable(head(arrange(inc.final[, .(count = length(unique(Name))), by = .(Industry)], desc(count)),10))| Industry | count |
|---|---|
| IT Services | 732 |
| Business Products & Services | 480 |
| Advertising & Marketing | 471 |
| Health | 354 |
| Software | 341 |
| Financial Services | 260 |
| Manufacturing | 255 |
| Consumer Products & Services | 203 |
| Retail | 203 |
| Government Services | 202 |
# number of companies by cities
kable(head(arrange(inc.final[, .(count = length(unique(Name))), by = .(City)], desc(count)),10))| City | count |
|---|---|
| New York | 160 |
| Chicago | 90 |
| Austin | 88 |
| Houston | 76 |
| San Francisco | 74 |
| Atlanta | 73 |
| San Diego | 67 |
| Seattle | 52 |
| Boston | 43 |
| Denver | 42 |
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.
# Answer Question 1 here
data.comp <- arrange(inc[, .(num_comp = length(Name)),
by =.(State)], desc(num_comp))plot.comp <- ggplot(data.comp,
aes(reorder(State, num_comp), num_comp)) +
geom_point(size=0.5) +
geom_segment(aes(x=State, xend=State, y=0, yend=num_comp)) +
geom_text(aes(label = paste0(num_comp)),
color = "red", size = 2.5, hjust = -0.1)+
scale_y_continuous(breaks = seq(0,800,100),labels = comma) +
labs(title = "Number Of Companies By State",
x = "State",
y = "Number Of Companies") +
coord_flip()
plot.comp
Quesiton 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.
# Answer Question 2 here
# exploring state with 3rd most companies
head(arrange(inc.final[, .(count = length(unique(Name))), by = .(State)], desc(count)))## State count
## 1 CA 700
## 2 TX 386
## 3 NY 311
## 4 VA 283
## 5 FL 282
## 6 IL 272data.se <- inc[complete.cases(inc),][State == 'NY']
median.label <- paste0("Median Number of Employees(NY): ", median(data.se$Employees))plot.se <- ggplot(data.se,aes(Industry, Employees)) +
geom_boxplot(outlier.shape = NA) +
geom_hline(yintercept = median(data.se$Employees),
color="red",
linetype="dashed") +
scale_y_continuous(limits = quantile(data.se$Employees, c(0.1,0.9))) +
labs(title = "Number of Employees by Industry in the state of NY",
x = "Industry",
y = "Number of Employees") +
geom_text(aes(x=3, label=median.label, y = 150),
size = 3,
colour="red") +
coord_flip()
plot.se
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.
# Answer Question 3 heredata.rpe <-inc[complete.cases(inc),]%>%
select(Revenue,Industry,Employees)%>%
group_by(Industry)%>%
summarise(Rev_ind=sum(Revenue),Emp_ind=sum(Employees))%>%
mutate(RPE = Rev_ind/Emp_ind)%>%
arrange(desc(RPE))%>%
select(Industry,RPE)
plot.rpe <- ggplot(data.rpe, aes(x=Industry,y=RPE),value) +
stat_summary(fun.y = "sum", geom = "bar", position = "identity", aes(fill=RPE)) +
labs(title="Revenue Per Employee Distribution Per Industry",
y="Revenue Per Employee",
x="Industry") +
coord_flip()
plot.rpe