# Notes for R for Data Science

## 2018/05/17

The diagram above depicts what I have learned from the book: R for Data Science

Note: Together, tidying and transforming are also called wrangling

## Prerequisite

install.packages("tidyverse")
install.packages(c("nycflights13", "gapminder", "Lahman")) #These packages provide data on airline flights, world development, and baseball that we’ll use to illustrate key data science ideas
library(tidyverse)
library(nycflights13)
library(Lahman)

# Data visualization

us <- map_data("usa")
ggplot(us, aes(long, lat, group = group)) +
geom_polygon(fill = "light blue", colour = "black")

ggplot(us, aes(long, lat, group = group)) +
geom_polygon(fill = "light blue", colour = "black") +
coord_quickmap() #coord_quickmap() sets the aspect ratio correctly for maps

bar <- ggplot(data = diamonds) +
geom_bar(
mapping = aes(x = cut, fill = cut),
show.legend = FALSE,
width = 1
) +
theme(aspect.ratio = 1) +
labs(x = NULL, y = NULL)

bar + coord_flip()

bar + coord_polar()

## Formula:

ggplot(data = <DATA>) +
<GEOM_FUNCTION>(
mapping = aes(<MAPPINGS>),
stat = <STAT>,
position = <POSITION>
) +
<COORDINATE_FUNCTION> +
<FACET_FUNCTION>

## Visualize two categorical variables

ggplot(data = diamonds) +
geom_count(mapping = aes(x = cut, y = color))

diamonds %>%
count(color, cut) %>%
ggplot(mapping = aes(x = color, y = cut)) +
geom_tile(mapping = aes(fill = n))

explore d3heatmap and heatmaply packages to create interactive plots. sources: flowingdata

library(d3heatmap)
library(heatmaply)

nba
##                  Name  G  MIN  PTS  FGM  FGA   FGP FTM  FTA   FTP X3PM
## 1        Dwyane Wade  79 38.6 30.2 10.8 22.0 0.491 7.5  9.8 0.765  1.1
## 2       LeBron James  81 37.7 28.4  9.7 19.9 0.489 7.3  9.4 0.780  1.6
## 3        Kobe Bryant  82 36.2 26.8  9.8 20.9 0.467 5.9  6.9 0.856  1.4
## 4      Dirk Nowitzki  81 37.7 25.9  9.6 20.0 0.479 6.0  6.7 0.890  0.8
## 5      Danny Granger  67 36.2 25.8  8.5 19.1 0.447 6.0  6.9 0.878  2.7
## 6       Kevin Durant  74 39.0 25.3  8.9 18.8 0.476 6.1  7.1 0.863  1.3
## 7       Kevin Martin  51 38.2 24.6  6.7 15.9 0.420 9.0 10.3 0.867  2.3
## 8       Al Jefferson  50 36.6 23.1  9.7 19.5 0.497 3.7  5.0 0.738  0.0
## 9         Chris Paul  78 38.5 22.8  8.1 16.1 0.503 5.8  6.7 0.868  0.8
## 10   Carmelo Anthony  66 34.5 22.8  8.1 18.3 0.443 5.6  7.1 0.793  1.0
## 11        Chris Bosh  77 38.1 22.7  8.0 16.4 0.487 6.5  8.0 0.817  0.2
## 12       Brandon Roy  78 37.2 22.6  8.1 16.9 0.480 5.3  6.5 0.824  1.1
## 13    Antawn Jamison  81 38.2 22.2  8.3 17.8 0.468 4.2  5.6 0.754  1.4
## 14       Tony Parker  72 34.1 22.0  8.9 17.5 0.506 3.9  5.0 0.782  0.3
## 15  Amare Stoudemire  53 36.8 21.4  7.6 14.1 0.539 6.1  7.3 0.835  0.1
## 16       Joe Johnson  79 39.5 21.4  7.8 18.0 0.437 3.8  4.6 0.826  1.9
## 17      Devin Harris  69 36.1 21.3  6.6 15.1 0.438 7.2  8.8 0.820  0.9
## 18      Michael Redd  33 36.4 21.2  7.5 16.6 0.455 4.0  4.9 0.814  2.1
## 19        David West  76 39.3 21.0  8.0 17.0 0.472 4.8  5.5 0.884  0.1
## 20  Zachary Randolph  50 35.1 20.8  8.3 17.5 0.475 3.6  4.9 0.734  0.6
## 21      Caron Butler  67 38.6 20.8  7.3 16.2 0.453 5.1  6.0 0.858  1.0
## 22      Vince Carter  80 36.8 20.8  7.4 16.8 0.437 4.2  5.1 0.817  1.9
## 23   Stephen Jackson  59 39.7 20.7  7.0 16.9 0.414 5.0  6.0 0.826  1.7
## 24        Ben Gordon  82 36.6 20.7  7.3 16.0 0.455 4.0  4.7 0.864  2.1
## 25     Dwight Howard  79 35.7 20.6  7.1 12.4 0.572 6.4 10.7 0.594  0.0
## 26       Paul Pierce  81 37.4 20.5  6.7 14.6 0.457 5.7  6.8 0.830  1.5
## 27     Al Harrington  73 34.9 20.1  7.3 16.6 0.439 3.2  4.0 0.793  2.3
## 28    Jamal Crawford  65 38.1 19.7  6.4 15.7 0.410 4.6  5.3 0.872  2.2
## 29          Yao Ming  77 33.6 19.7  7.4 13.4 0.548 4.9  5.7 0.866  0.0
## 30 Richard Jefferson  82 35.9 19.6  6.5 14.9 0.439 5.1  6.3 0.805  1.4
## 31       Jason Terry  74 33.6 19.6  7.3 15.8 0.463 2.7  3.0 0.880  2.3
## 32    Deron Williams  68 36.9 19.4  6.8 14.5 0.471 4.8  5.6 0.849  1.0
## 33        Tim Duncan  75 33.7 19.3  7.4 14.8 0.504 4.5  6.4 0.692  0.0
## 34       Monta Ellis  25 35.6 19.0  7.8 17.2 0.451 3.1  3.8 0.830  0.3
## 35          Rudy Gay  79 37.3 18.9  7.2 16.0 0.453 3.3  4.4 0.767  1.1
## 36         Pau Gasol  81 37.1 18.9  7.3 12.9 0.567 4.2  5.4 0.781  0.0
## 37    Andre Iguodala  82 39.8 18.8  6.6 14.0 0.473 4.6  6.4 0.724  1.0
## 38    Corey Maggette  51 31.1 18.6  5.7 12.4 0.461 6.7  8.1 0.824  0.5
## 39         O.J. Mayo  82 38.0 18.5  6.9 15.6 0.438 3.0  3.4 0.879  1.8
## 40      John Salmons  79 37.5 18.3  6.5 13.8 0.472 3.6  4.4 0.830  1.6
## 41  Richard Hamilton  67 34.0 18.3  7.0 15.6 0.447 3.3  3.9 0.848  1.0
## 42         Ray Allen  79 36.3 18.2  6.3 13.2 0.480 3.0  3.2 0.952  2.5
## 43 LaMarcus Aldridge  81 37.1 18.1  7.4 15.3 0.484 3.2  4.1 0.781  0.1
## 44       Josh Howard  52 31.9 18.0  6.8 15.1 0.451 3.3  4.2 0.782  1.1
## 45  Maurice Williams  81 35.0 17.8  6.5 13.9 0.467 2.6  2.8 0.912  2.3
## 46  Shaquille O'neal  75 30.1 17.8  6.8 11.2 0.609 4.1  6.9 0.595  0.0
## 47     Rashard Lewis  79 36.2 17.7  6.1 13.8 0.439 2.8  3.4 0.836  2.8
## 48  Chauncey Billups  79 35.3 17.7  5.2 12.4 0.418 5.3  5.8 0.913  2.1
## 49     Allen Iverson  57 36.7 17.5  6.1 14.6 0.417 4.8  6.1 0.781  0.5
## 50     Nate Robinson  74 29.9 17.2  6.1 13.9 0.437 3.4  4.0 0.841  1.7
##    X3PA  X3PP ORB DRB  TRB  AST STL BLK  TO  PF
## 1   3.5 0.317 1.1 3.9  5.0  7.5 2.2 1.3 3.4 2.3
## 2   4.7 0.344 1.3 6.3  7.6  7.2 1.7 1.1 3.0 1.7
## 3   4.1 0.351 1.1 4.1  5.2  4.9 1.5 0.5 2.6 2.3
## 4   2.1 0.359 1.1 7.3  8.4  2.4 0.8 0.8 1.9 2.2
## 5   6.7 0.404 0.7 4.4  5.1  2.7 1.0 1.4 2.5 3.1
## 6   3.1 0.422 1.0 5.5  6.5  2.8 1.3 0.7 3.0 1.8
## 7   5.4 0.415 0.6 3.0  3.6  2.7 1.2 0.2 2.9 2.3
## 8   0.1 0.000 3.4 7.5 11.0  1.6 0.8 1.7 1.8 2.8
## 9   2.3 0.364 0.9 4.7  5.5 11.0 2.8 0.1 3.0 2.7
## 10  2.6 0.371 1.6 5.2  6.8  3.4 1.1 0.4 3.0 3.0
## 11  0.6 0.245 2.8 7.2 10.0  2.5 0.9 1.0 2.3 2.5
## 12  2.8 0.377 1.3 3.4  4.7  5.1 1.1 0.3 1.9 1.6
## 13  3.9 0.351 2.4 6.5  8.9  1.9 1.2 0.3 1.5 2.7
## 14  0.9 0.292 0.4 2.7  3.1  6.9 0.9 0.1 2.6 1.5
## 15  0.1 0.429 2.2 5.9  8.1  2.0 0.9 1.1 2.8 3.1
## 16  5.2 0.360 0.8 3.6  4.4  5.8 1.1 0.2 2.5 2.2
## 17  3.2 0.291 0.4 2.9  3.3  6.9 1.7 0.2 3.1 2.4
## 18  5.8 0.366 0.7 2.5  3.2  2.7 1.1 0.1 1.6 1.4
## 19  0.3 0.240 2.1 6.4  8.5  2.3 0.6 0.9 2.1 2.7
## 20  1.9 0.330 3.1 6.9 10.1  2.1 0.9 0.3 2.3 2.7
## 21  3.1 0.310 1.8 4.4  6.2  4.3 1.6 0.3 3.1 2.5
## 22  4.9 0.385 0.9 4.2  5.1  4.7 1.0 0.5 2.1 2.9
## 23  5.2 0.338 1.2 3.9  5.1  6.5 1.5 0.5 3.9 2.6
## 24  5.1 0.410 0.6 2.8  3.5  3.4 0.9 0.3 2.4 2.2
## 25  0.0 0.000 4.3 9.6 13.8  1.4 1.0 2.9 3.0 3.4
## 26  3.8 0.391 0.7 5.0  5.6  3.6 1.0 0.3 2.8 2.7
## 27  6.4 0.364 1.4 4.9  6.2  1.4 1.2 0.3 2.2 3.1
## 28  6.1 0.360 0.4 2.6  3.0  4.4 0.9 0.2 2.3 1.4
## 29  0.0 1.000 2.6 7.2  9.9  1.8 0.4 1.9 3.0 3.3
## 30  3.6 0.397 0.7 3.9  4.6  2.4 0.8 0.2 2.0 3.1
## 31  6.2 0.366 0.5 1.9  2.4  3.4 1.3 0.3 1.6 1.9
## 32  3.3 0.310 0.4 2.5  2.9 10.7 1.1 0.3 3.4 2.0
## 33  0.0 0.000 2.7 8.0 10.7  3.5 0.5 1.7 2.2 2.3
## 34  1.0 0.308 0.6 3.8  4.3  3.7 1.6 0.3 2.7 2.7
## 35  3.1 0.351 1.4 4.2  5.5  1.7 1.2 0.7 2.6 2.8
## 36  0.0 0.500 3.2 6.4  9.6  3.5 0.6 1.0 1.9 2.1
## 37  3.2 0.307 1.1 4.6  5.7  5.3 1.6 0.4 2.7 1.9
## 38  1.9 0.253 1.0 4.6  5.5  1.8 0.9 0.2 2.4 3.8
## 39  4.6 0.384 0.7 3.1  3.8  3.2 1.1 0.2 2.8 2.5
## 40  3.8 0.417 0.7 3.5  4.2  3.2 1.1 0.3 2.1 2.3
## 41  2.8 0.368 0.7 2.4  3.1  4.4 0.6 0.1 2.0 2.6
## 42  6.2 0.409 0.8 2.7  3.5  2.8 0.9 0.2 1.7 2.0
## 43  0.3 0.250 2.9 4.6  7.5  1.9 1.0 1.0 1.5 2.6
## 44  3.2 0.345 1.1 3.9  5.1  1.6 1.1 0.6 1.7 2.6
## 45  5.2 0.436 0.6 2.9  3.4  4.1 0.9 0.1 2.2 2.7
## 46  0.0 0.000 2.5 5.9  8.4  1.7 0.7 1.4 2.2 3.4
## 47  7.0 0.397 1.2 4.6  5.7  2.6 1.0 0.6 2.0 2.5
## 48  5.0 0.408 0.4 2.6  3.0  6.4 1.2 0.2 2.2 2.0
## 49  1.7 0.283 0.5 2.5  3.0  5.0 1.5 0.1 2.6 1.5
## 50  5.2 0.325 1.3 2.6  3.9  4.1 1.3 0.1 1.9 2.8

clean data

# sort the dataset by points per game, from the least to the greatest.
nba <- nba[order(nba$PTS),] # name the rows by players' names row.names(nba) <- nba$Name
# get rid of the first column
nba <- nba[,2:20]
# transfer the dataframe to a matrix to make it be able to be used by the heatmap package
nba_matrix <- data.matrix(nba)

make a heatmap

nba_heatmap <- heatmap(nba_matrix, Rowv=NA, Colv=NA, col = cm.colors(256), scale="column", margins=c(5,10))

nba_heatmap <- heatmap(nba_matrix, Rowv=NA, Colv=NA, col = heat.colors(256), scale="column", margins=c(5,10))

use Inkscape to clean it up

make interactive heatmaps source: d3heatmap: Interactive heat maps

library(d3heatmap)
url <- "http://datasets.flowingdata.com/ppg2008.csv"
nba_players <- read.csv(url, row.names = 1)
d3heatmap(nba_players, scale = "column")
d3heatmap(nba_players, scale = "column", dendrogram = "none",
color = "Blues")
d3heatmap(nba_players, scale = "column", dendrogram = "none",
color = scales::col_quantile("Blues", NULL, 5))
d3heatmap(nba_players, colors = "Blues", scale = "col",
dendrogram = "row", k_row = 3)

This can take an RColorBrewer palette name, a vector of colors, or a function that takes (potentially scaled) data points as input and returns colors.

# Visualize two continuous variables

geom_bin2d() and geom_hex() provide fill in color to show the plot overlap for the scatterplot. geom_bin2d() creates rectangular bins. geom_hex() creates hexagonal bins.

library(hexbin)
ggplot(data = diamonds) +
geom_bin2d(mapping = aes(x = carat, y = price))

ggplot(data = diamonds) +
geom_hex(mapping = aes(x = carat, y = price))

Another option is to use cut_width(x, width) to bin one of the continuous variables to a catrgorial variable.

ggplot(data = diamonds, mapping = aes(x = carat, y = price)) +
geom_boxplot(mapping = aes(group = cut_width(carat, 0.1)))

or use cut_number() to display approximately the same number of points of each bin.

ggplot(data = diamonds, mapping = aes(x = carat, y = price)) +
geom_boxplot(mapping = aes(group = cut_number(carat, 20)))

# Tips I learned

• If we want to make it clear what package an object comes from, we can use the package name followed by two colons, like: dplyr::mutate() or nycflights13::flights
• Run dput(dataset name), we will get the source code with which to recreate the dataset
• Alt + is the short cut for <-
• R has 25 built in shapes The hollow shapes (0–14) have a border determined by color; the solid shapes (15–18) are filled with color; the filled shapes (21–24) have a border of color and are filled with fill.
• Press Alt + Shift + K, we will get a short cut panel
• ggplot2 provides over 30 geoms, and extension packages provide even more (see https://www.ggplot2-exts.org for a sampling). The best way to get a comprehensive overview is the ggplot2 cheatsheet, which you can find at http://rstudio.com/cheatsheets. To learn more about any single geom, use help: ?geom_smooth.