DATA608 - Project 1 - Leland Randles
Leland Randles
February 11, 2018
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:
# I think the summary gives us nearly all the info we need, but I like
# to examine the data closer to get into the specifics of the data
# For example, I like to check the number of rows in the df
nrow(inc)## [1] 5001# We can see there are 5,001 rows despite the data set being described
# as the top 5,000 fastest growing companies. s a first step towards
# figuring out why, I looked at the final rows of the dataframe:
tail(inc)## Rank Name Growth_Rate Revenue
## 4996 4996 cSubs 0.34 1.34e+07
## 4997 4997 Dot Foods 0.34 4.50e+09
## 4998 4998 Lethal Performance 0.34 6.80e+06
## 4999 4999 ArcaTech Systems 0.34 3.26e+07
## 5000 5000 INE 0.34 6.80e+06
## 5001 5000 ALL4 0.34 4.70e+06
## Industry Employees City State
## 4996 Business Products & Services 19 Montvale NJ
## 4997 Food & Beverage 3919 Mt. Sterling IL
## 4998 Retail 8 Wellington FL
## 4999 Financial Services 63 Mebane NC
## 5000 IT Services 35 Bellevue WA
## 5001 Environmental Services 34 Kimberton PA# We can see there are two companies ranked 5,000, hence 5,001 rows. I also
# like to study some of the specific columns to get a deeper understanding
# of each column, i.e., how many state codes are there in the data set?
unique(unlist(inc$State))## [1] CA VA FL TX MA TN UT RI SC DC NJ OH WA ME NY CO GA IL AZ NC MD MN OK
## [24] PA CT IN MS WI WY MI MO KS OR NE AL HI NV IA KY ID AK LA DE AR NH VT
## [47] NM SD ND PR MT WV
## 52 Levels: AK AL AR AZ CA CO CT DC DE FL GA HI IA ID IL IN KS KY LA ... WY# We see 52 codes, the 50 states plus DC and Puerto Rico. Next I check the
# Industry column to see how many they are there and if they're duplicative.
unique(unlist(inc$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# We see 25 different industry categories and none of them overlap.
# For the numerical columns Growth_Rate, Revenue and Employees, I like to
# do some binning to get a feel for how skewed they are. I could already
# discern skew from the summary function and would usually explore this via
# plots, but the assignment asks for non-visual exploratory information.
# First, the bins for Growth_Rate:
br_gr = seq(min(inc$Growth_Rate),max(inc$Growth_Rate),by=(max(inc$Growth_Rate) - min(inc$Growth_Rate))/10)
ranges_gr = paste(head(br_gr,-1), br_gr[-1], sep=" - ")
freq_gr = hist(inc$Growth_Rate, breaks=br_gr, include.lowest=TRUE, plot=FALSE)
data.frame(range = ranges_gr, frequency = freq_gr$counts)## range frequency
## 1 0.34 - 42.454 4927
## 2 42.454 - 84.568 49
## 3 84.568 - 126.682 11
## 4 126.682 - 168.796 5
## 5 168.796 - 210.91 4
## 6 210.91 - 253.024 4
## 7 253.024 - 295.138 0
## 8 295.138 - 337.252 0
## 9 337.252 - 379.366 0
## 10 379.366 - 421.48 1# We see that the extraordinary majority of growth rates are 42.454% or lower
# Second, the bins for Revenue:
br_rev = seq(min(inc$Revenue),max(inc$Revenue),by=(max(inc$Revenue) - min(inc$Revenue))/10)
ranges_rev = paste(head(br_rev,-1), br_rev[-1], sep=" - ")
freq_rev = hist(inc$Revenue, breaks=br_rev, include.lowest=TRUE, plot=FALSE)
data.frame(range = ranges_rev, frequency = freq_rev$counts)## range frequency
## 1 2e+06 - 1011800000 4976
## 2 1011800000 - 2021600000 15
## 3 2021600000 - 3031400000 4
## 4 3031400000 - 4041200000 2
## 5 4041200000 - 5.051e+09 3
## 6 5.051e+09 - 6060800000 0
## 7 6060800000 - 7070600000 0
## 8 7070600000 - 8080400000 0
## 9 8080400000 - 9090200000 0
## 10 9090200000 - 1.01e+10 1# Again, we see the overwhelming majority of Revenue amts in the lowest bin
# Lastly, the bins for number of employees:
br_emp = seq(min(inc$Employees[!is.na(inc$Employees)]),max(inc$Employees[!is.na(inc$Employees)]),by=(max(inc$Employees[!is.na(inc$Employees)]) - min(inc$Employees[!is.na(inc$Employees)]))/10)
ranges_emp = paste(head(br_emp,-1), br_emp[-1], sep=" - ")
freq_emp = hist(inc$Employees, breaks=br_emp, include.lowest=TRUE, plot=FALSE)
data.frame(range = ranges_emp, frequency = freq_emp$counts)## range frequency
## 1 1 - 6681.2 4968
## 2 6681.2 - 13361.4 14
## 3 13361.4 - 20041.6 5
## 4 20041.6 - 26721.8 0
## 5 26721.8 - 33402 1
## 6 33402 - 40082.2 0
## 7 40082.2 - 46762.4 0
## 8 46762.4 - 53442.6 0
## 9 53442.6 - 60122.8 0
## 10 60122.8 - 66803 1# Again, the overwhelming majority of employee counts are in the 1st binQuestion 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.
install.packages("ggplot2", repos='https://mirrors.nics.utk.edu/cran/')
library(ggplot2)
install.packages("forcats", repos='https://mirrors.nics.utk.edu/cran/')
library(forcats)g <- ggplot(inc, aes(State))
g + geom_bar(aes(fct_infreq(factor(State)), fill=State), position = position_stack(reverse = TRUE), show.legend = F) + coord_flip() + ylab("Number of Companies in Top 5,000") + ggtitle("5,000 Fastest Growing Companies - Count by State")
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.
inc_ny <- subset(inc,State=="NY")
p <- ggplot(inc_ny, aes(inc_ny$Industry, inc_ny$Employees))
p + geom_boxplot(na.rm = TRUE) + ylim(0,1000) + theme(axis.text.x = element_text(angle = 90, hjust = 1))
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.
install.packages("dplyr", repos='https://mirrors.nics.utk.edu/cran/')
library(dplyr)industries <- group_by(inc_ny, Industry)
inc_ny_sum <- summarize(industries, rev_per_employees = sum(Revenue)/sum(Employees))## Warning: package 'bindrcpp' was built under R version 3.4.2r <- ggplot(inc_ny_sum, aes(inc_ny_sum$Industry, inc_ny_sum$rev_per_employees))
r + geom_point() + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + scale_y_continuous(labels = scales::dollar) + xlab("Industry") + ylab("Revenue per Employee")