How to make Heatmaps, Treemaps, Streamgraphs and Alluvials Tutorial
Jake Abdow
2023-02-20
load libraries
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.1 ✔ purrr 1.0.1
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.3.0 ✔ stringr 1.5.0
## ✔ readr 2.1.4 ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(treemap)
library(RColorBrewer)load the NBA data, preview the headings, set as data frame (needed for error)
nba <- read.csv("http://datasets.flowingdata.com/ppg2008.csv")
as.data.frame(nba)## Name G MIN PTS FGM FGA FGP FTM FTA FTP X3PM X3PA
## 1 Dwyane Wade 79 38.6 30.2 10.8 22.0 0.491 7.5 9.8 0.765 1.1 3.5
## 2 LeBron James 81 37.7 28.4 9.7 19.9 0.489 7.3 9.4 0.780 1.6 4.7
## 3 Kobe Bryant 82 36.2 26.8 9.8 20.9 0.467 5.9 6.9 0.856 1.4 4.1
## 4 Dirk Nowitzki 81 37.7 25.9 9.6 20.0 0.479 6.0 6.7 0.890 0.8 2.1
## 5 Danny Granger 67 36.2 25.8 8.5 19.1 0.447 6.0 6.9 0.878 2.7 6.7
## 6 Kevin Durant 74 39.0 25.3 8.9 18.8 0.476 6.1 7.1 0.863 1.3 3.1
## 7 Kevin Martin 51 38.2 24.6 6.7 15.9 0.420 9.0 10.3 0.867 2.3 5.4
## 8 Al Jefferson 50 36.6 23.1 9.7 19.5 0.497 3.7 5.0 0.738 0.0 0.1
## 9 Chris Paul 78 38.5 22.8 8.1 16.1 0.503 5.8 6.7 0.868 0.8 2.3
## 10 Carmelo Anthony 66 34.5 22.8 8.1 18.3 0.443 5.6 7.1 0.793 1.0 2.6
## 11 Chris Bosh 77 38.1 22.7 8.0 16.4 0.487 6.5 8.0 0.817 0.2 0.6
## 12 Brandon Roy 78 37.2 22.6 8.1 16.9 0.480 5.3 6.5 0.824 1.1 2.8
## 13 Antawn Jamison 81 38.2 22.2 8.3 17.8 0.468 4.2 5.6 0.754 1.4 3.9
## 14 Tony Parker 72 34.1 22.0 8.9 17.5 0.506 3.9 5.0 0.782 0.3 0.9
## 15 Amare Stoudemire 53 36.8 21.4 7.6 14.1 0.539 6.1 7.3 0.835 0.1 0.1
## 16 Joe Johnson 79 39.5 21.4 7.8 18.0 0.437 3.8 4.6 0.826 1.9 5.2
## 17 Devin Harris 69 36.1 21.3 6.6 15.1 0.438 7.2 8.8 0.820 0.9 3.2
## 18 Michael Redd 33 36.4 21.2 7.5 16.6 0.455 4.0 4.9 0.814 2.1 5.8
## 19 David West 76 39.3 21.0 8.0 17.0 0.472 4.8 5.5 0.884 0.1 0.3
## 20 Zachary Randolph 50 35.1 20.8 8.3 17.5 0.475 3.6 4.9 0.734 0.6 1.9
## 21 Caron Butler 67 38.6 20.8 7.3 16.2 0.453 5.1 6.0 0.858 1.0 3.1
## 22 Vince Carter 80 36.8 20.8 7.4 16.8 0.437 4.2 5.1 0.817 1.9 4.9
## 23 Stephen Jackson 59 39.7 20.7 7.0 16.9 0.414 5.0 6.0 0.826 1.7 5.2
## 24 Ben Gordon 82 36.6 20.7 7.3 16.0 0.455 4.0 4.7 0.864 2.1 5.1
## 25 Dwight Howard 79 35.7 20.6 7.1 12.4 0.572 6.4 10.7 0.594 0.0 0.0
## 26 Paul Pierce 81 37.4 20.5 6.7 14.6 0.457 5.7 6.8 0.830 1.5 3.8
## 27 Al Harrington 73 34.9 20.1 7.3 16.6 0.439 3.2 4.0 0.793 2.3 6.4
## 28 Jamal Crawford 65 38.1 19.7 6.4 15.7 0.410 4.6 5.3 0.872 2.2 6.1
## 29 Yao Ming 77 33.6 19.7 7.4 13.4 0.548 4.9 5.7 0.866 0.0 0.0
## 30 Richard Jefferson 82 35.9 19.6 6.5 14.9 0.439 5.1 6.3 0.805 1.4 3.6
## 31 Jason Terry 74 33.6 19.6 7.3 15.8 0.463 2.7 3.0 0.880 2.3 6.2
## 32 Deron Williams 68 36.9 19.4 6.8 14.5 0.471 4.8 5.6 0.849 1.0 3.3
## 33 Tim Duncan 75 33.7 19.3 7.4 14.8 0.504 4.5 6.4 0.692 0.0 0.0
## 34 Monta Ellis 25 35.6 19.0 7.8 17.2 0.451 3.1 3.8 0.830 0.3 1.0
## 35 Rudy Gay 79 37.3 18.9 7.2 16.0 0.453 3.3 4.4 0.767 1.1 3.1
## 36 Pau Gasol 81 37.1 18.9 7.3 12.9 0.567 4.2 5.4 0.781 0.0 0.0
## 37 Andre Iguodala 82 39.8 18.8 6.6 14.0 0.473 4.6 6.4 0.724 1.0 3.2
## 38 Corey Maggette 51 31.1 18.6 5.7 12.4 0.461 6.7 8.1 0.824 0.5 1.9
## 39 O.J. Mayo 82 38.0 18.5 6.9 15.6 0.438 3.0 3.4 0.879 1.8 4.6
## 40 John Salmons 79 37.5 18.3 6.5 13.8 0.472 3.6 4.4 0.830 1.6 3.8
## 41 Richard Hamilton 67 34.0 18.3 7.0 15.6 0.447 3.3 3.9 0.848 1.0 2.8
## 42 Ray Allen 79 36.3 18.2 6.3 13.2 0.480 3.0 3.2 0.952 2.5 6.2
## 43 LaMarcus Aldridge 81 37.1 18.1 7.4 15.3 0.484 3.2 4.1 0.781 0.1 0.3
## 44 Josh Howard 52 31.9 18.0 6.8 15.1 0.451 3.3 4.2 0.782 1.1 3.2
## 45 Maurice Williams 81 35.0 17.8 6.5 13.9 0.467 2.6 2.8 0.912 2.3 5.2
## 46 Shaquille O'neal 75 30.1 17.8 6.8 11.2 0.609 4.1 6.9 0.595 0.0 0.0
## 47 Rashard Lewis 79 36.2 17.7 6.1 13.8 0.439 2.8 3.4 0.836 2.8 7.0
## 48 Chauncey Billups 79 35.3 17.7 5.2 12.4 0.418 5.3 5.8 0.913 2.1 5.0
## 49 Allen Iverson 57 36.7 17.5 6.1 14.6 0.417 4.8 6.1 0.781 0.5 1.7
## 50 Nate Robinson 74 29.9 17.2 6.1 13.9 0.437 3.4 4.0 0.841 1.7 5.2
## X3PP ORB DRB TRB AST STL BLK TO PF
## 1 0.317 1.1 3.9 5.0 7.5 2.2 1.3 3.4 2.3
## 2 0.344 1.3 6.3 7.6 7.2 1.7 1.1 3.0 1.7
## 3 0.351 1.1 4.1 5.2 4.9 1.5 0.5 2.6 2.3
## 4 0.359 1.1 7.3 8.4 2.4 0.8 0.8 1.9 2.2
## 5 0.404 0.7 4.4 5.1 2.7 1.0 1.4 2.5 3.1
## 6 0.422 1.0 5.5 6.5 2.8 1.3 0.7 3.0 1.8
## 7 0.415 0.6 3.0 3.6 2.7 1.2 0.2 2.9 2.3
## 8 0.000 3.4 7.5 11.0 1.6 0.8 1.7 1.8 2.8
## 9 0.364 0.9 4.7 5.5 11.0 2.8 0.1 3.0 2.7
## 10 0.371 1.6 5.2 6.8 3.4 1.1 0.4 3.0 3.0
## 11 0.245 2.8 7.2 10.0 2.5 0.9 1.0 2.3 2.5
## 12 0.377 1.3 3.4 4.7 5.1 1.1 0.3 1.9 1.6
## 13 0.351 2.4 6.5 8.9 1.9 1.2 0.3 1.5 2.7
## 14 0.292 0.4 2.7 3.1 6.9 0.9 0.1 2.6 1.5
## 15 0.429 2.2 5.9 8.1 2.0 0.9 1.1 2.8 3.1
## 16 0.360 0.8 3.6 4.4 5.8 1.1 0.2 2.5 2.2
## 17 0.291 0.4 2.9 3.3 6.9 1.7 0.2 3.1 2.4
## 18 0.366 0.7 2.5 3.2 2.7 1.1 0.1 1.6 1.4
## 19 0.240 2.1 6.4 8.5 2.3 0.6 0.9 2.1 2.7
## 20 0.330 3.1 6.9 10.1 2.1 0.9 0.3 2.3 2.7
## 21 0.310 1.8 4.4 6.2 4.3 1.6 0.3 3.1 2.5
## 22 0.385 0.9 4.2 5.1 4.7 1.0 0.5 2.1 2.9
## 23 0.338 1.2 3.9 5.1 6.5 1.5 0.5 3.9 2.6
## 24 0.410 0.6 2.8 3.5 3.4 0.9 0.3 2.4 2.2
## 25 0.000 4.3 9.6 13.8 1.4 1.0 2.9 3.0 3.4
## 26 0.391 0.7 5.0 5.6 3.6 1.0 0.3 2.8 2.7
## 27 0.364 1.4 4.9 6.2 1.4 1.2 0.3 2.2 3.1
## 28 0.360 0.4 2.6 3.0 4.4 0.9 0.2 2.3 1.4
## 29 1.000 2.6 7.2 9.9 1.8 0.4 1.9 3.0 3.3
## 30 0.397 0.7 3.9 4.6 2.4 0.8 0.2 2.0 3.1
## 31 0.366 0.5 1.9 2.4 3.4 1.3 0.3 1.6 1.9
## 32 0.310 0.4 2.5 2.9 10.7 1.1 0.3 3.4 2.0
## 33 0.000 2.7 8.0 10.7 3.5 0.5 1.7 2.2 2.3
## 34 0.308 0.6 3.8 4.3 3.7 1.6 0.3 2.7 2.7
## 35 0.351 1.4 4.2 5.5 1.7 1.2 0.7 2.6 2.8
## 36 0.500 3.2 6.4 9.6 3.5 0.6 1.0 1.9 2.1
## 37 0.307 1.1 4.6 5.7 5.3 1.6 0.4 2.7 1.9
## 38 0.253 1.0 4.6 5.5 1.8 0.9 0.2 2.4 3.8
## 39 0.384 0.7 3.1 3.8 3.2 1.1 0.2 2.8 2.5
## 40 0.417 0.7 3.5 4.2 3.2 1.1 0.3 2.1 2.3
## 41 0.368 0.7 2.4 3.1 4.4 0.6 0.1 2.0 2.6
## 42 0.409 0.8 2.7 3.5 2.8 0.9 0.2 1.7 2.0
## 43 0.250 2.9 4.6 7.5 1.9 1.0 1.0 1.5 2.6
## 44 0.345 1.1 3.9 5.1 1.6 1.1 0.6 1.7 2.6
## 45 0.436 0.6 2.9 3.4 4.1 0.9 0.1 2.2 2.7
## 46 0.000 2.5 5.9 8.4 1.7 0.7 1.4 2.2 3.4
## 47 0.397 1.2 4.6 5.7 2.6 1.0 0.6 2.0 2.5
## 48 0.408 0.4 2.6 3.0 6.4 1.2 0.2 2.2 2.0
## 49 0.283 0.5 2.5 3.0 5.0 1.5 0.1 2.6 1.5
## 50 0.325 1.3 2.6 3.9 4.1 1.3 0.1 1.9 2.8head(nba)## Name G MIN PTS FGM FGA FGP FTM FTA FTP X3PM X3PA X3PP ORB
## 1 Dwyane Wade 79 38.6 30.2 10.8 22.0 0.491 7.5 9.8 0.765 1.1 3.5 0.317 1.1
## 2 LeBron James 81 37.7 28.4 9.7 19.9 0.489 7.3 9.4 0.780 1.6 4.7 0.344 1.3
## 3 Kobe Bryant 82 36.2 26.8 9.8 20.9 0.467 5.9 6.9 0.856 1.4 4.1 0.351 1.1
## 4 Dirk Nowitzki 81 37.7 25.9 9.6 20.0 0.479 6.0 6.7 0.890 0.8 2.1 0.359 1.1
## 5 Danny Granger 67 36.2 25.8 8.5 19.1 0.447 6.0 6.9 0.878 2.7 6.7 0.404 0.7
## 6 Kevin Durant 74 39.0 25.3 8.9 18.8 0.476 6.1 7.1 0.863 1.3 3.1 0.422 1.0
## DRB TRB AST STL BLK TO PF
## 1 3.9 5.0 7.5 2.2 1.3 3.4 2.3
## 2 6.3 7.6 7.2 1.7 1.1 3.0 1.7
## 3 4.1 5.2 4.9 1.5 0.5 2.6 2.3
## 4 7.3 8.4 2.4 0.8 0.8 1.9 2.2
## 5 4.4 5.1 2.7 1.0 1.4 2.5 3.1
## 6 5.5 6.5 2.8 1.3 0.7 3.0 1.8create a color heatmap
nba <- nba[order(nba$PTS),]
row.names(nba) <- nba$Name
nba <- nba[,2:19]
nba_matrix <- data.matrix(nba)
nba_heatmap <- heatmap(nba_matrix, Rowv=NA, Colv=NA,
col = cm.colors(256), scale="column", margins=c(5,10),
xlab = "NBA Player Stats",
ylab = "NBA Players",
main = "NBA Player Stats in 2008")
change to warm color palette
nba_heatmap <- heatmap(nba_matrix, Rowv=NA, Colv=NA, col = heat.colors(256),
scale="column", margins=c(5,10),
xlab = "NBA Player Stats",
ylab = "NBA Players",
main = "NBA Player Stats in 2008")
use the viridis color palette for heatmap
load viridis and create heatmap
library(viridis)## Loading required package: viridisLitenba_heatmap <- heatmap(nba_matrix, Rowv=NA, col = viridis(25),
scale="column", margins=c(5,10),
xlab = "NBA Player Stats",
ylab = "NBA Players",
main = "NBA Payer Stats in 2008")
create a treemap which explores categories of views
load and preview the data
data <- read.csv("http://datasets.flowingdata.com/post-data.txt")
head(data)## id views comments category
## 1 5019 148896 28 Artistic Visualization
## 2 1416 81374 26 Visualization
## 3 1416 81374 26 Featured
## 4 3485 80819 37 Featured
## 5 3485 80819 37 Mapping
## 6 3485 80819 37 Data Sourcesuse RColorBrewer to change the palette to RdYlBu
treemap(data, index = "category", vSize = "views",
vColor = "comments", type = "manual",
# note: type = "manual" changes to red yellow blue
palette = "RdYlBu")
use the dataset NYCFlights13 to create a heatmap that explores Late Arrivals
load data
library(nycflights13)
library(RColorBrewer)
data(flights)create an initial scatterplot with loess smoother for distance to delays
filter NA values from data
flights_nona <- flights %>%
filter(!is.na(distance) & !is.na(arr_delay))
# remove na's for distance and arr_delayuse group_by and summarise to create a summary table
by_tailnum <- flights_nona %>%
group_by(tailnum) %>% # group all tailnumbers together
summarise(count = n(), # counts totals for each tailnumber
dist = mean(distance), # calculates the mean distance traveled
delay = mean(arr_delay)) # calculates the mean arrival delay
delay <- filter(by_tailnum, count > 20, dist < 2000) # only include counts > 20 and distance < 2000 miaverage delay is only slightly related to average distance flown by a plane.
ggplot(delay, aes(dist, delay)) +
geom_point(aes(size = count), alpha = 1/2) +
geom_smooth() +
scale_size_area()## `geom_smooth()` using method = 'gam' and formula = 'y ~ s(x, bs = "cs")'
create dataframe that is cmomposed of summary statistics
delays <- flights_nona %>% # create a delays dataframe by:
group_by (dest) %>% # grouping by point of destination
summarize (count = n(), # creating variables: number of flights to each destination
dist = mean (distance), # the mean distance flown to each destination
delay = mean (arr_delay), # the mean delay of arrival to each destination
delaycost = mean(count*delay/dist)) # delay cost index defined as:
# [(number of flights)*delay/distance] for a destination
delays <- arrange(delays, desc(delaycost)) #sort the rows by delay cost
head(delays) # look at the data## # A tibble: 6 × 5
## dest count dist delay delaycost
## <chr> <int> <dbl> <dbl> <dbl>
## 1 DCA 9111 211. 9.07 391.
## 2 IAD 5383 225. 13.9 332.
## 3 ATL 16837 757. 11.3 251.
## 4 BOS 15022 191. 2.91 230.
## 5 CLT 13674 538. 7.36 187.
## 6 RDU 7770 427. 10.1 183.use the knitr package with the function kable to display all destination
load knitr
library(knitr)
kable(delays,
caption = "Table of Mean Distance, Mean Arrival Delay, and Highest Delay Costs",
digits = 2) # round values to 2 decimal places| dest | count | dist | delay | delaycost |
|---|---|---|---|---|
| DCA | 9111 | 211.08 | 9.07 | 391.36 |
| IAD | 5383 | 224.74 | 13.86 | 332.08 |
| ATL | 16837 | 757.14 | 11.30 | 251.29 |
| BOS | 15022 | 190.74 | 2.91 | 229.53 |
| CLT | 13674 | 538.01 | 7.36 | 187.07 |
| RDU | 7770 | 426.73 | 10.05 | 183.04 |
| RIC | 2346 | 281.27 | 20.11 | 167.74 |
| PHL | 1541 | 94.34 | 10.13 | 165.42 |
| BUF | 4570 | 296.87 | 8.95 | 137.71 |
| ORD | 16566 | 729.02 | 5.88 | 133.54 |
| ROC | 2358 | 259.36 | 11.56 | 105.11 |
| BWI | 1687 | 179.35 | 10.73 | 100.90 |
| CVG | 3725 | 575.23 | 15.36 | 99.50 |
| DTW | 9031 | 498.20 | 5.43 | 98.43 |
| CLE | 4394 | 414.00 | 9.18 | 97.45 |
| PWM | 2288 | 276.03 | 11.66 | 96.65 |
| BNA | 6084 | 758.22 | 11.81 | 94.78 |
| FLL | 11897 | 1070.06 | 8.08 | 89.86 |
| BTV | 2510 | 265.12 | 8.95 | 84.74 |
| MCO | 13967 | 943.11 | 5.45 | 80.78 |
| CMH | 3326 | 476.55 | 10.60 | 73.99 |
| SYR | 1707 | 206.07 | 8.90 | 73.76 |
| MDW | 4025 | 718.09 | 12.36 | 69.30 |
| MHT | 932 | 207.38 | 14.79 | 66.46 |
| PIT | 2746 | 334.10 | 7.68 | 63.13 |
| TPA | 7390 | 1003.93 | 7.41 | 54.53 |
| ORF | 1434 | 288.55 | 10.95 | 54.41 |
| PBI | 6487 | 1028.82 | 8.56 | 53.99 |
| MKE | 2709 | 733.37 | 14.17 | 52.33 |
| STL | 4142 | 878.83 | 11.08 | 52.21 |
| MSP | 6929 | 1017.46 | 7.27 | 49.51 |
| GSO | 1492 | 449.79 | 14.11 | 46.81 |
| CHS | 2759 | 632.96 | 10.59 | 46.17 |
| ALB | 418 | 143.00 | 14.40 | 42.08 |
| CAK | 842 | 397.00 | 19.70 | 41.78 |
| DEN | 7169 | 1614.69 | 8.61 | 38.21 |
| JAX | 2623 | 824.71 | 11.84 | 37.67 |
| PVD | 358 | 160.00 | 16.23 | 36.32 |
| DAY | 1399 | 536.91 | 12.68 | 33.04 |
| IND | 1981 | 652.26 | 9.94 | 30.19 |
| BDL | 412 | 116.00 | 7.05 | 25.03 |
| MCI | 1885 | 1097.65 | 14.51 | 24.92 |
| GRR | 728 | 605.71 | 18.19 | 21.86 |
| TYS | 578 | 638.34 | 24.07 | 21.79 |
| SDF | 1104 | 645.96 | 12.67 | 21.65 |
| IAH | 7085 | 1407.18 | 4.24 | 21.35 |
| GSP | 790 | 595.98 | 15.94 | 21.12 |
| MSY | 3715 | 1177.73 | 6.49 | 20.47 |
| MEM | 1686 | 954.48 | 10.65 | 18.80 |
| SAV | 749 | 709.27 | 15.13 | 15.98 |
| MSN | 556 | 803.93 | 20.20 | 13.97 |
| SFO | 13173 | 2577.93 | 2.67 | 13.66 |
| OMA | 817 | 1135.56 | 14.70 | 10.58 |
| RSW | 3502 | 1072.85 | 3.24 | 10.57 |
| HOU | 2083 | 1420.26 | 7.18 | 10.52 |
| DSM | 523 | 1020.56 | 19.01 | 9.74 |
| AUS | 2411 | 1514.25 | 6.02 | 9.58 |
| SJU | 5773 | 1599.84 | 2.52 | 9.10 |
| TUL | 294 | 1215.00 | 33.66 | 8.14 |
| BGR | 358 | 378.00 | 8.03 | 7.60 |
| CAE | 106 | 603.70 | 41.76 | 7.33 |
| OKC | 315 | 1325.00 | 30.62 | 7.28 |
| XNA | 992 | 1142.44 | 7.47 | 6.48 |
| ACK | 264 | 199.00 | 4.85 | 6.44 |
| BHM | 269 | 866.00 | 16.88 | 5.24 |
| BQN | 888 | 1578.99 | 8.25 | 4.64 |
| PHX | 4606 | 2141.34 | 2.10 | 4.51 |
| CRW | 134 | 444.00 | 14.67 | 4.43 |
| AVL | 261 | 583.61 | 8.00 | 3.58 |
| LAX | 16026 | 2468.62 | 0.55 | 3.55 |
| SRQ | 1201 | 1044.64 | 3.08 | 3.54 |
| SAN | 2709 | 2437.28 | 3.14 | 3.49 |
| MIA | 11593 | 1091.54 | 0.30 | 3.18 |
| SAT | 659 | 1578.18 | 6.95 | 2.90 |
| PDX | 1342 | 2445.61 | 5.14 | 2.82 |
| DFW | 8388 | 1383.06 | 0.32 | 1.95 |
| TVC | 95 | 652.45 | 12.97 | 1.89 |
| PSE | 358 | 1617.00 | 7.87 | 1.74 |
| CHO | 46 | 305.00 | 9.50 | 1.43 |
| SMF | 282 | 2521.00 | 12.11 | 1.35 |
| BUR | 370 | 2465.00 | 8.18 | 1.23 |
| ILM | 107 | 500.00 | 4.64 | 0.99 |
| EGE | 207 | 1735.80 | 6.30 | 0.75 |
| LAS | 5952 | 2240.98 | 0.26 | 0.68 |
| ABQ | 254 | 1826.00 | 4.38 | 0.61 |
| MYR | 58 | 550.67 | 4.60 | 0.48 |
| SJC | 328 | 2569.00 | 3.45 | 0.44 |
| OAK | 309 | 2576.00 | 3.08 | 0.37 |
| JAC | 21 | 1875.90 | 28.10 | 0.31 |
| SLC | 2451 | 1986.99 | 0.18 | 0.22 |
| BZN | 35 | 1882.00 | 7.60 | 0.14 |
| SBN | 10 | 645.40 | 6.50 | 0.10 |
| EYW | 17 | 1207.00 | 6.35 | 0.09 |
| HDN | 14 | 1728.00 | 2.14 | 0.02 |
| MTJ | 14 | 1795.00 | 1.79 | 0.01 |
| ANC | 8 | 3370.00 | -2.50 | -0.01 |
| LGB | 661 | 2465.00 | -0.06 | -0.02 |
| LEX | 1 | 604.00 | -22.00 | -0.04 |
| PSP | 18 | 2378.00 | -12.72 | -0.10 |
| HNL | 701 | 4972.76 | -1.37 | -0.19 |
| MVY | 210 | 173.00 | -0.29 | -0.35 |
| STT | 518 | 1626.99 | -3.84 | -1.22 |
| SEA | 3885 | 2412.68 | -1.10 | -1.77 |
| SNA | 812 | 2434.00 | -7.87 | -2.62 |
get the top 100 delay costs to create a heatmap of those flights
top100 <- delays %>% # select the 100 largest delay costs
head(100) %>%
arrange(delaycost) # sort ascending so the heatmap displays descending costs
row.names(top100) <- top100$dest # rename the rows according to destination airport codes## Warning: Setting row names on a tibble is deprecated.convert the dataframe to matrix form
delays_mat <- data.matrix(top100) # convert delays dataframe to a matrix (required by heatmap)
delays_mat2 <- delays_mat[,2:5] # remove the redundant column of destination airport codescreate a heatmap using colorBrewer
heatmap(delays_mat2,
Rowv = NA, Colv = NA,
col= viridis(25),
s=0.6, v=1, scale="column",
margins=c(7,10),
main = "Cost of Late Arrivals",
xlab = "Flight Characteristics",
ylab="Arrival Airport", labCol = c("Flights","Distance","Delay","Cost Index"
),
cexCol=1, cexRow =1)## layout: widths = 0.05 4 , heights = 0.25 4 ; lmat=
## [,1] [,2]
## [1,] 0 3
## [2,] 2 1
# install and load devtools/libraries to create streamgrpah
devtools::install_github("hrbrmstr/streamgraph")## Skipping install of 'streamgraph' from a github remote, the SHA1 (76f7173e) has not changed since last install.
## Use `force = TRUE` to force installationlibrary(dplyr)
library(babynames)
library(streamgraph)trivial streamgraph using simulated names over time
# Create data:
year=rep(seq(1990,2016) , each=10)
name=rep(letters[1:10] , 27)
value=sample( seq(0,1,0.0001) , length(year))
data=data.frame(year, name, value)
# Basic stream graph: just give the 3 arguments
streamgraph(data, key="name", value="value", date="year")## Warning in widget_html(name, package, id = x$id, style = css(width =
## validateCssUnit(sizeInfo$width), : streamgraph_html returned an object of class
## `list` instead of a `shiny.tag`.## Warning: `bindFillRole()` only works on htmltools::tag() objects (e.g., div(),
## p(), etc.), not objects of type 'list'.look at the babynames dataset
ncol(babynames)## [1] 5head(babynames)## # A tibble: 6 × 5
## year sex name n prop
## <dbl> <chr> <chr> <int> <dbl>
## 1 1880 F Mary 7065 0.0724
## 2 1880 F Anna 2604 0.0267
## 3 1880 F Emma 2003 0.0205
## 4 1880 F Elizabeth 1939 0.0199
## 5 1880 F Minnie 1746 0.0179
## 6 1880 F Margaret 1578 0.0162str(babynames)## tibble [1,924,665 × 5] (S3: tbl_df/tbl/data.frame)
## $ year: num [1:1924665] 1880 1880 1880 1880 1880 1880 1880 1880 1880 1880 ...
## $ sex : chr [1:1924665] "F" "F" "F" "F" ...
## $ name: chr [1:1924665] "Mary" "Anna" "Emma" "Elizabeth" ...
## $ n : int [1:1924665] 7065 2604 2003 1939 1746 1578 1472 1414 1320 1288 ...
## $ prop: num [1:1924665] 0.0724 0.0267 0.0205 0.0199 0.0179 ...babynames streamgraph
babynames %>%
filter(grepl("^Kr", name)) %>%
group_by(year, name) %>%
tally(wt=n) %>%
streamgraph("name", "n", "year")## Warning in widget_html(name, package, id = x$id, style = css(width =
## validateCssUnit(sizeInfo$width), : streamgraph_html returned an object of class
## `list` instead of a `shiny.tag`.## Warning: `bindFillRole()` only works on htmltools::tag() objects (e.g., div(),
## p(), etc.), not objects of type 'list'.load alluvial package
library(alluvial) # this package contains the refugee dataset we will use
library(ggalluvial) # this is the improved alluvial package write refugees prebuilt data in alluvial package as csv
Refugees <- Refugees
write_csv(Refugees, "refugees.csv")preview to check data
head(Refugees)## country year refugees
## 1 Afghanistan 2003 2136043
## 2 Burundi 2003 531637
## 3 Congo DRC 2003 453465
## 4 Iraq 2003 368580
## 5 Myanmar 2003 151384
## 6 Palestine 2003 350568create the alluvial to show UNHCR-recognised refugess in the top 10 countries from 2003-2013
ggalluv <- ggplot(Refugees,aes(x = year, y = refugees, alluvium = country)) + # time series bump chart (quintic flows)
theme_bw() +
geom_alluvium(aes(fill = country),
color = "white",
width = .1,
alpha = .8,
decreasing = FALSE) +
scale_fill_brewer(palette = "Spectral") + # Spectral has enough colors for all countries listed
scale_x_continuous(lim = c(2002, 2013))+
ggtitle("UNHCR-Recognised Refugees \n Top 10 Countries(2003-2013)\n")+ # \n breaks the long title
ylab("Number of Refugees")
ggalluv
y-values are in scientific notation. We can conver them to standard notation with options scipen function
options(scipen=999) # this code eliminates scientific notation for the refugee values
ggalluv