IS608_HW1
Daina Bouquin
February 9, 2016
The following questions pertain to data on the 5,000 fastest growing companies in the US, as compiled by Inc. magazine. That data is available here
download.file("https://raw.githubusercontent.com/jlaurito/CUNY_IS608/master/lecture1/data/inc5000_data.csv", "inc5000_data.csv", method="curl")
inc5000 <- read.csv("inc5000_data.csv", na.strings = "NA")
# check the header and structure
head(inc5000)## 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 TXstr(inc5000)## '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 ...- Create a graph that shows the distribution of companies in the dataset by State (i.e. how many are in each state). There are a lot of States, so consider which axis you should use assuming I am using a ‘portrait’ oriented screen
library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'
##
## The following objects are masked from 'package:stats':
##
## filter, lag
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionc <- ggplot(inc5000, aes(factor(State))) + geom_bar(fill="#009E73")
c <- c + coord_flip()
c <- c + theme(text = element_text(size=12), axis.title=element_text(size=14,face="bold"))
c <- c + labs(title = "Number of Companies by State", x= "State", y= "Count")
c <- c + theme(plot.title = element_text(size=22))
c
ggsave('q1.png', height = 11, width = 8.5)- For the State with the 3rd most companies, create a plot of average employment by industry for companies in this state (only use cases with full data. Your graph should show how variable the ranges are, and exclude outliers.
counts <- as.data.frame(table(inc5000$State))
colnames(counts) <- c("State", "Count")
head(counts) # check structure## State Count
## 1 AK 2
## 2 AL 51
## 3 AR 9
## 4 AZ 100
## 5 CA 701
## 6 CO 134x <- sort(counts$Count, TRUE)[3]
filter(counts, Count == x)## State Count
## 1 NY 311# pull out only NY data from orinal dataset and remove incomplete cases
ny_data <- filter(inc5000, State == "NY")
ny_data <- ny_data[complete.cases(ny_data),]
str(ny_data)## 'data.frame': 311 obs. of 8 variables:
## $ Rank : int 26 30 37 38 48 70 71 124 126 153 ...
## $ Name : Factor w/ 5001 levels "(Add)ventures",..: 529 3822 4972 1037 912 19 2608 3591 3684 3668 ...
## $ Growth_Rate: num 84.4 73.2 67.4 67 53.6 ...
## $ Revenue : num 13700000 8100000 18000000 7100000 5900000 27900000 6900000 11500000 9800000 15400000 ...
## $ Industry : Factor w/ 25 levels "Advertising & Marketing",..: 5 1 1 1 10 1 1 24 21 25 ...
## $ Employees : int 17 79 27 89 32 75 42 28 17 42 ...
## $ City : Factor w/ 1519 levels "Acton","Addison",..: 929 929 929 929 1135 929 929 929 574 162 ...
## $ State : Factor w/ 52 levels "AK","AL","AR",..: 35 35 35 35 35 35 35 35 35 35 ...d <- ggplot(ny_data) + geom_bar(aes(Industry, Employees, fill = Industry), position = "dodge", stat = "summary", fun.y = "mean", fill="sky blue")
d <- d + coord_flip()
d <- d + theme(legend.position="none")
d <- d + theme(text = element_text(size=12), axis.title=element_text(size=14,face="bold"))
d <- d + labs(title = "Average Number of Employees by Industry in NY", x= "Industry", y= "Average Number of Employees")
d <- d + theme(plot.title = element_text(size=17))
d
ggsave('q2.png', height = 8.5, width = 9)- Generate a chart showing which industries generate the most revenue per employee.
#filter out incomplete cases
rev_data <- inc5000[complete.cases(inc5000),]
# Create a new column showing revenue/employee
rev_data <- rev_data %>% mutate(rev_per_em = Revenue / Employees)
str(rev_data)## 'data.frame': 4989 obs. of 9 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 ...
## $ rev_per_em : num 1133654 972549 193182 38000000 395455 ...head(rev_data)## 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 rev_per_em
## 1 Consumer Products & Services 104 El Segundo CA 1133653.8
## 2 Government Services 51 Dumfries VA 972549.0
## 3 Health 132 Jacksonville FL 193181.8
## 4 Energy 50 Addison TX 38000000.0
## 5 Advertising & Marketing 220 Boston MA 395454.5
## 6 Real Estate 63 Austin TX 725396.8# Plot average revenue/employee by industry
e <- ggplot(rev_data) + geom_bar(aes(Industry, rev_per_em, fill = Industry), position = "dodge", stat = "summary", fun.y = "mean", fill="darkslateblue")
e <- e + coord_flip()
e <- e + theme(legend.position="none")
e <- e + theme(text = element_text(size=12), axis.title=element_text(size=14,face="bold"))
e <- e + labs(title = "Average Revenue per Employees by Industry", x= "Industry", y= "Average Revenue per Employees")
e <- e + theme(plot.title = element_text(size=17))
e
ggsave('q3.png', height = 8.5, width = 9)