DATA 608 Assignment 1
Monu Chacko
2/8/2020
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)# Import dplyr and ggplot2
library(dplyr)
library(ggplot2)
library(tidyverse)
library(knitr)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:
Lets examine the data
# Columns
nrow(inc)## [1] 5001# Rows
ncol(inc)## [1] 8str(inc)## 'data.frame': 5001 obs. of 8 variables:
## $ Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Name : Factor w/ 5001 levels "(Add)ventures",..: 1770 1633 4423 690 1198 2839 4733 1468 1869 4968 ...
## $ 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 : Factor w/ 25 levels "Advertising & Marketing",..: 5 12 13 7 1 20 10 1 5 21 ...
## $ Employees : int 104 51 132 50 220 63 27 75 97 15 ...
## $ City : Factor w/ 1519 levels "Acton","Addison",..: 391 365 635 2 139 66 912 1179 131 1418 ...
## $ State : Factor w/ 52 levels "AK","AL","AR",..: 5 47 10 45 20 45 44 5 46 41 ...# Levels
levels(inc$Industry)## [1] "Advertising & Marketing" "Business Products & Services"
## [3] "Computer Hardware" "Construction"
## [5] "Consumer Products & Services" "Education"
## [7] "Energy" "Engineering"
## [9] "Environmental Services" "Financial Services"
## [11] "Food & Beverage" "Government Services"
## [13] "Health" "Human Resources"
## [15] "Insurance" "IT Services"
## [17] "Logistics & Transportation" "Manufacturing"
## [19] "Media" "Real Estate"
## [21] "Retail" "Security"
## [23] "Software" "Telecommunications"
## [25] "Travel & Hospitality"levels(inc$State)## [1] "AK" "AL" "AR" "AZ" "CA" "CO" "CT" "DC" "DE" "FL" "GA" "HI" "IA" "ID"
## [15] "IL" "IN" "KS" "KY" "LA" "MA" "MD" "ME" "MI" "MN" "MO" "MS" "MT" "NC"
## [29] "ND" "NE" "NH" "NJ" "NM" "NV" "NY" "OH" "OK" "OR" "PA" "PR" "RI" "SC"
## [43] "SD" "TN" "TX" "UT" "VA" "VT" "WA" "WI" "WV" "WY"Top 10 fastest growing companies in US
# Sorted by Growth_Rate
top_10 <- inc %>% arrange(desc(Growth_Rate)) %>% head(10) %>% select(c(Rank, Name, Growth_Rate, Revenue, City, State))
kable(top_10)| Rank | Name | Growth_Rate | Revenue | City | State |
|---|---|---|---|---|---|
| 1 | Fuhu | 421.48 | 1.179e+08 | El Segundo | CA |
| 2 | FederalConference.com | 248.31 | 4.960e+07 | Dumfries | VA |
| 3 | The HCI Group | 245.45 | 2.550e+07 | Jacksonville | FL |
| 4 | Bridger | 233.08 | 1.900e+09 | Addison | TX |
| 5 | DataXu | 213.37 | 8.700e+07 | Boston | MA |
| 6 | MileStone Community Builders | 179.38 | 4.570e+07 | Austin | TX |
| 7 | Value Payment Systems | 174.04 | 2.550e+07 | Nashville | TN |
| 8 | Emerge Digital Group | 170.64 | 2.390e+07 | San Francisco | CA |
| 9 | Goal Zero | 169.81 | 3.310e+07 | Bluffdale | UT |
| 10 | Yagoozon | 166.89 | 1.860e+07 | Warwick | RI |
Top 10 cities in US
# Top 10 cities in US with the 1000 fastest growing companies
top_10_cities <- inc %>% arrange(desc(Growth_Rate)) %>% head(1000) %>% count(City, sort = TRUE) %>% head(10)
kable(top_10_cities)| City | n |
|---|---|
| New York | 35 |
| San Francisco | 26 |
| Chicago | 20 |
| Austin | 19 |
| Atlanta | 17 |
| Houston | 15 |
| Irvine | 15 |
| Boston | 14 |
| San Diego | 11 |
| Washington | 11 |
# How many unique industries in this dataset?
print(paste0("No of unique records: ", length(unique(inc$Industry))))## [1] "No of unique records: 25"unique(inc$Industry)## [1] Consumer Products & Services Government Services
## [3] Health Energy
## [5] Advertising & Marketing Real Estate
## [7] Financial Services Retail
## [9] Software Computer Hardware
## [11] Logistics & Transportation Food & Beverage
## [13] IT Services Business Products & Services
## [15] Education Construction
## [17] Manufacturing Telecommunications
## [19] Security Human Resources
## [21] Travel & Hospitality Media
## [23] Environmental Services Engineering
## [25] Insurance
## 25 Levels: Advertising & Marketing ... Travel & Hospitality# Sorting by industries with the 1000 fastest growing companies in the US
inc %>% arrange(desc(Growth_Rate)) %>% head(1000) %>% count(Industry, sort=TRUE) %>% head(10)## # A tibble: 10 x 2
## Industry n
## <fct> <int>
## 1 IT Services 120
## 2 Advertising & Marketing 112
## 3 Software 83
## 4 Health 77
## 5 Business Products & Services 67
## 6 Financial Services 65
## 7 Consumer Products & Services 61
## 8 Retail 59
## 9 Government Services 56
## 10 Energy 38# Top 10 industries with the most cases
countind <- inc %>% count(Industry)
arrange(countind, desc(n)) %>% top_n(10)## Selecting by n## # A tibble: 10 x 2
## Industry n
## <fct> <int>
## 1 IT Services 733
## 2 Business Products & Services 482
## 3 Advertising & Marketing 471
## 4 Health 355
## 5 Software 342
## 6 Financial Services 260
## 7 Manufacturing 256
## 8 Consumer Products & Services 203
## 9 Retail 203
## 10 Government Services 202glimpse(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> 1.179e+08, 4.960e+07, 2.550e+07, 1.900e+09, 8.700e...
## $ 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...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.
# Counts by state
statecount <- group_by(inc, State) %>% summarize(Count=n())
# Plot
ggplot(statecount, aes(x=reorder(State,Count),Count)) +
geom_bar(stat="identity", fill="#4dbcc5") +
geom_text(aes(label=round(Count, digits=2)), vjust=0.2, size=2, position=position_dodge(width = 1), hjust=1) +
theme_minimal() +
theme(axis.text.x=element_text(size=6, vjust=0.5)) +
theme(axis.text.y=element_text(size=6, vjust=0.5)) +
labs( x="State", y="No of Companies") +
coord_flip() +
ggtitle("Companies by State")
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.
# Employee count by Industry
nyemps <- filter(inc, State=="NY") %>% select(Industry, Name, Employees)# Graph
nyemp <- group_by(nyemps, Industry) %>% summarize(m = mean(Employees), max= max(Employees), min = min(Employees)) %>% na.omit()
upper <- nyemp$max
lower <- nyemp$min
ggplot(nyemp, aes(x = Industry, y =m, ymax=max, ymin = min, lower = lower, upper= upper)) +
geom_boxplot(outlier.shape = NA) + coord_flip() +
labs(title="Employees (NY) by Industry", y = "Mean")
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.
# Get revenue per Employee Data
rev_per_emp <- select(inc, Industry, Revenue, Employees) %>%
na.omit() %>% group_by(Industry) %>%
summarise(TotalRev = sum(Revenue), TotalEmp = sum(Employees)) %>%
mutate(RevEmployee = TotalRev / TotalEmp)
# Graph
ggplot(data = rev_per_emp, aes(x = reorder(Industry, RevEmployee), y = RevEmployee)) +
geom_bar(stat="identity", fill="#333333") +
geom_text(data = filter(rev_per_emp, RevEmployee>150000),
aes(x = Industry, y = RevEmployee, label=scales::dollar_format()(RevEmployee)),
hjust=1.1, vjust=0.4, color="#FFFFFF", size=3) +
geom_text(data = filter(rev_per_emp, RevEmployee<150000),
aes(x = Industry, y = RevEmployee, label=scales::dollar_format()(RevEmployee)),
hjust=-0.1, vjust=0.4, color="#333333", size=3) +
coord_flip() +
ggtitle("Revenue per Employee per Industry") + labs(x = "", y = "") +
theme(panel.background = element_blank(),
axis.ticks = element_blank(),
axis.text.x = element_blank(),
axis.text.y = element_text(size = 8, margin = margin(r=-20)))