DATA 608 - Module 1
Jim Mundy
library(tidyverse)
library(dlookr)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)
inc <-as_tibble(inc)And lets preview this data:
head(inc)## # A tibble: 6 x 8
## Rank Name Growth_Rate Revenue Industry Employees City State
## <int> <fct> <dbl> <dbl> <fct> <int> <fct> <fct>
## 1 1 Fuhu 421. 1.18e8 Consumer Pr~ 104 El Se~ CA
## 2 2 FederalCo~ 248. 4.96e7 Government ~ 51 Dumfr~ VA
## 3 3 The HCI G~ 245. 2.55e7 Health 132 Jacks~ FL
## 4 4 Bridger 233. 1.90e9 Energy 50 Addis~ TX
## 5 5 DataXu 213. 8.70e7 Advertising~ 220 Boston MA
## 6 6 MileStone~ 179. 4.57e7 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:
My Approach
We have looked at a summary and the top of the data, but not the bottom. I’ll perform a tail to review the bottom of the data and then I will use some dlookr functions to develop a better understanding of the data.
tail(inc)## # A tibble: 6 x 8
## Rank Name Growth_Rate Revenue Industry Employees City State
## <int> <fct> <dbl> <dbl> <fct> <int> <fct> <fct>
## 1 4996 cSubs 0.34 1.34e7 Business Pro~ 19 Montv~ NJ
## 2 4997 Dot Foods 0.34 4.50e9 Food & Bever~ 3919 Mt. S~ IL
## 3 4998 Lethal P~ 0.34 6.80e6 Retail 8 Welli~ FL
## 4 4999 ArcaTech~ 0.34 3.26e7 Financial Se~ 63 Mebane NC
## 5 5000 INE 0.34 6.80e6 IT Services 35 Belle~ WA
## 6 5000 ALL4 0.34 4.70e6 Environmenta~ 34 Kimbe~ PAThe summary and and tail functions revealed some cleaning is required in the Name variable.dlookr Package
dlookr diagnose function allows you to diagnose varables on a data frame.
The package provides a variety of functions that make it easier to understand your data and its challenges. diagnose(inc)## # A tibble: 8 x 6
## variables types missing_count missing_percent unique_count unique_rate
## <chr> <chr> <int> <dbl> <int> <dbl>
## 1 Rank integ~ 0 0 4999 1.000
## 2 Name factor 0 0 5001 1
## 3 Growth_Rate numer~ 0 0 1147 0.229
## 4 Revenue numer~ 0 0 1069 0.214
## 5 Industry factor 0 0 25 0.00500
## 6 Employees integ~ 12 0.240 692 0.138
## 7 City factor 0 0 1519 0.304
## 8 State factor 0 0 52 0.0104Clearly shows variable types and reveals some missing data for Employeesdiagnose_numeric(inc)## # A tibble: 4 x 10
## variables min Q1 mean median Q3 max zero minus
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <int>
## 1 Rank 1.00e+0 1.25e+3 2.50e3 2.50e3 3.75e3 5.00e 3 0 0
## 2 Growth_R~ 3.40e-1 7.70e-1 4.61e0 1.42e0 3.29e0 4.21e 2 0 0
## 3 Revenue 2.00e+6 5.10e+6 4.82e7 1.09e7 2.86e7 1.01e10 0 0
## 4 Employees 1.00e+0 2.50e+1 2.33e2 5.30e1 1.32e2 6.68e 4 0 0
## # ... with 1 more variable: outlier <int>diagnose_category(inc)## # A tibble: 5,032 x 6
## variables levels N freq ratio rank
## <chr> <fct> <int> <int> <dbl> <int>
## 1 Name (Add)ventures 5001 1 0.0200 1
## 2 Name @Properties 5001 1 0.0200 2
## 3 Name 1-Stop Translation USA 5001 1 0.0200 3
## 4 Name 110 Consulting 5001 1 0.0200 4
## 5 Name 11thStreetCoffee.com 5001 1 0.0200 5
## 6 Name 123 Exteriors 5001 1 0.0200 6
## 7 Name 1st American Systems and Services 5001 1 0.0200 7
## 8 Name 1st Equity 5001 1 0.0200 8
## 9 Name 2020 Exhibits 5001 1 0.0200 9
## 10 Name 206inc 5001 1 0.0200 10
## # ... with 5,022 more rowsdiagnose_numeric provides some descriptive stats and outlier information on the numeric variables. diagnose_category returns diagnostic information for the non-numeric variables.
describe(inc)## # A tibble: 4 x 26
## variable n na mean sd se_mean IQR skewness kurtosis
## <chr> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Rank 5001 0 2.50e3 1.44e3 2.04e+1 2.50e3 -4.90e-4 -1.20
## 2 Growth_~ 5001 0 4.61e0 1.41e1 2.00e-1 2.52e0 1.26e+1 243.
## 3 Revenue 5001 0 4.82e7 2.41e8 3.40e+6 2.35e7 2.22e+1 724.
## 4 Employe~ 4989 12 2.33e2 1.35e3 1.92e+1 1.07e2 2.98e+1 1270.
## # ... with 17 more variables: p00 <dbl>, p01 <dbl>, p05 <dbl>, p10 <dbl>,
## # p20 <dbl>, p25 <dbl>, p30 <dbl>, p40 <dbl>, p50 <dbl>, p60 <dbl>,
## # p70 <dbl>, p75 <dbl>, p80 <dbl>, p90 <dbl>, p95 <dbl>, p99 <dbl>,
## # p100 <dbl>normality(inc)## # A tibble: 4 x 4
## vars statistic p_value sample
## <chr> <dbl> <dbl> <dbl>
## 1 Rank 0.955 9.48e-37 5000
## 2 Growth_Rate 0.252 4.18e-89 5000
## 3 Revenue 0.135 1.91e-92 5000
## 4 Employees 0.106 3.69e-93 5000`describe() and normality provide some additional information on skewness and level of normaility.
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.
library(hrbrthemes)
library(ggthemes)
library(tidyverse)
library(kableExtra)
state = inc %>%
select(State, Name) %>%
group_by(State) %>%
count(State) %>%
arrange(desc(n))
p <- ggplot(state, aes(x=reorder(State, n), y=n, fill=n)) +
geom_col() +
geom_text(aes(label=scales::comma(n)), hjust=0, nudge_y=2000) +
scale_y_comma(limits=c(0,800)) +
coord_flip() +
labs(x="", y="Companies per state (n)",
title="Fastest Growing Companies",
subtitle="Number of high growth companies by state.",
caption="Source: Inc. Magazine (2016)") +
theme_ipsum(grid="X") + theme(legend.title = element_blank()) + theme(axis.text.y =element_text(size = 7))
p
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.
inc2 <- inc %>%
filter(State == "NY") %>%
filter(complete.cases(.)) %>%
group_by(Industry) %>%
summarise(Mean = mean(Employees),
Median = median(Employees)) %>%
gather(statType, Amount, Mean, Median)
kable(inc2, format = "markdown")| Industry | statType | Amount |
|---|---|---|
| Advertising & Marketing | Mean | 58.43860 |
| Business Products & Services | Mean | 1492.46154 |
| Computer Hardware | Mean | 44.00000 |
| Construction | Mean | 61.00000 |
| Consumer Products & Services | Mean | 626.29412 |
| Education | Mean | 59.85714 |
| Energy | Mean | 129.20000 |
| Engineering | Mean | 53.50000 |
| Environmental Services | Mean | 155.00000 |
| Financial Services | Mean | 144.30769 |
| Food & Beverage | Mean | 76.44444 |
| Government Services | Mean | 17.00000 |
| Health | Mean | 81.84615 |
| Human Resources | Mean | 437.54545 |
| Insurance | Mean | 32.50000 |
| IT Services | Mean | 204.09302 |
| Logistics & Transportation | Mean | 29.50000 |
| Manufacturing | Mean | 73.30769 |
| Media | Mean | 108.00000 |
| Real Estate | Mean | 18.25000 |
| Retail | Mean | 24.78571 |
| Security | Mean | 135.00000 |
| Software | Mean | 245.92308 |
| Telecommunications | Mean | 95.35294 |
| Travel & Hospitality | Mean | 547.71429 |
| Advertising & Marketing | Median | 38.00000 |
| Business Products & Services | Median | 70.50000 |
| Computer Hardware | Median | 44.00000 |
| Construction | Median | 24.50000 |
| Consumer Products & Services | Median | 25.00000 |
| Education | Median | 50.50000 |
| Energy | Median | 120.00000 |
| Engineering | Median | 54.50000 |
| Environmental Services | Median | 155.00000 |
| Financial Services | Median | 81.00000 |
| Food & Beverage | Median | 41.00000 |
| Government Services | Median | 17.00000 |
| Health | Median | 45.00000 |
| Human Resources | Median | 56.00000 |
| Insurance | Median | 32.50000 |
| IT Services | Median | 54.00000 |
| Logistics & Transportation | Median | 23.50000 |
| Manufacturing | Median | 30.00000 |
| Media | Median | 45.00000 |
| Real Estate | Median | 18.00000 |
| Retail | Median | 13.50000 |
| Security | Median | 32.50000 |
| Software | Median | 80.00000 |
| Telecommunications | Median | 31.00000 |
| Travel & Hospitality | Median | 61.00000 |
(p <-
ggplot(inc2, aes(x=reorder(Industry, Amount), y = Amount)) +
geom_bar(stat = 'identity', aes(fill = statType), position = 'dodge') +
coord_flip() +
labs(y="Employees (n)", x="",
title="New York State Employment",
subtitle="Employment segmented by Industry",
caption="Source: Inc. Magazine (2016)") +
theme_ipsum_rc(grid="X") + theme(axis.text.y =element_text(size = 8))+theme(legend.title = element_blank()))
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.
inc3 <- inc %>%
filter(State == "NY") %>%
filter(complete.cases(.)) %>%
mutate(RevPercentage = (Revenue / Employees)/1000) %>%
group_by(Industry) %>%
summarise(Mean = mean(RevPercentage))
kable(inc3, format = "markdown")| Industry | Mean |
|---|---|
| Advertising & Marketing | 373.4035 |
| Business Products & Services | 527.8169 |
| Computer Hardware | 520.4545 |
| Construction | 238.6945 |
| Consumer Products & Services | 382.9426 |
| Education | 112.0606 |
| Energy | 8472.5335 |
| Engineering | 215.7447 |
| Environmental Services | 134.3667 |
| Financial Services | 400.1744 |
| Food & Beverage | 174.6309 |
| Government Services | 158.8235 |
| Health | 532.4910 |
| Human Resources | 337.3663 |
| Insurance | 371.0000 |
| IT Services | 228.8161 |
| Logistics & Transportation | 1245.8701 |
| Manufacturing | 665.8186 |
| Media | 333.5496 |
| Real Estate | 383.8095 |
| Retail | 520.7903 |
| Security | 153.2778 |
| Software | 143.7490 |
| Telecommunications | 408.1434 |
| Travel & Hospitality | 282.0898 |
(p <-
ggplot(inc3, aes(x=reorder(Industry, Mean), y = Mean)) +
geom_bar(stat = 'identity', aes(fill = 'Blue')) +
coord_flip() +
labs(y="Revenue Per Employee", x="",
title="NY Revenue Per Employee by Industry",
subtitle="$000",
caption="Source: Inc. Magazine (2016)") +
theme_ipsum_rc(grid="X") + theme(axis.text.y =element_text(size = 8)) + theme(legend.position = "none"))