1. Введение

2. tible

3. Чтение файлов: readr, readxl

4. dplyr

4.1 dplyr::filter()
4.2 dplyr::slice()
4.3 dplyr::select()
4.4 dplyr::arrange()
4.5 dplyr::distinct()
4.6 dplyr::mutate()
4.7 dplyr::group_by(...) %>% summarise(...)
4.8 dplyr::.._join()

5. tidyr package

6.1 Anscombe’s quartet

5.2 Datasaurus

6.1 Scaterplot

6.1.1 Scaterplot: color

6.1.2 Scaterplot: shape

6.1.3 Scaterplot: size

6.1.4 Scaterplot: text

6.1.5 Scaterplot: title

6.1.6 Scaterplot: axis

6.1.7 Log scales

6.1.8 Scaterplot: rug

6.1.9 Scaterplot: lines

6.1.10 Scaterplot: annotate

6.2.1 Barplots: basics

6.3.1 Boxplots: basics, points, jitter

6. Preliminary summary: two variables

6.4.1 Histogram: basics

6.5.1 Density plot

6.7 Facets

6.7.1 ggplot2::facet_wrap()
6.7.2 ggplot2::facet_grid()

1. Введение

tidyverse — это набор пакетов:

dplyr, для преобразованиия данных
ggplot2, для визуализации
tidyr, для формата tidy data
readr, для чтения файлов в R
purrr, для функционального программирования
tibble, для работы с тибблами, современный вариант датафрейма

Полезно также знать:

readxl, для чтения .xls и .xlsx
jsonlite, для работы с JSON
rvest, для веб-скреппинга
lubridate, для работы с временем
tidytext, для работы с текстами и корпусами
broom, для перевода в tidy формат статистические модели

library(tidyverse)

## ── Attaching packages ────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 2.2.1     ✔ purrr   0.2.4
## ✔ tibble  1.4.2     ✔ dplyr   0.7.4
## ✔ tidyr   0.8.0     ✔ stringr 1.3.0
## ✔ readr   1.1.1     ✔ forcats 0.3.0

## ── Conflicts ───────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

2. tible

head(iris)
as_tibble(iris)
data_frame(id = 1:12,
           letters = month.name)

3. Чтение файлов: readr, readxl

library(readr)
df <- read_csv("https://goo.gl/v7nvho")
head(df)

ABCDEFGHIJ0123456789

Gender <chr>	Age <int>	AgeGroup <chr>	Education <chr>	City <chr>	SubjectCode <chr>	Score <chr>	GivenScore <int>	Stimulus <chr>	Prefix <chr>
female	16	child	school	Izhevsk	AA	A	5	utochnit	u
female	16	child	school	Izhevsk	AA	A	5	ozhestochit	o
female	16	child	school	Izhevsk	AA	E	1	ovneshnit	o
female	16	child	school	Izhevsk	AA	E	1	oblusit	o
female	16	child	school	Izhevsk	AA	A	5	osvezhit	o
female	16	child	school	Izhevsk	AA	A	5	oschastlivit	o

df <- read_tsv("https://goo.gl/33r2Ut")
head(df)

ABCDEFGHIJ0123456789

speaker <chr>	year <int>	gender <chr>	cons <int>	inn <int>	total <int>
ait1954	1954	f	222	254	476
anp1929	1929	m	15	16	31
ans1925	1925	f	788	379	1167
avch1930	1930	f	43	6	49
avi1958	1958	f	1	31	32
avm1922	1922	f	778	235	1013

df <- read_delim("https://goo.gl/33r2Ut", delim = "\t")
head(df)

ABCDEFGHIJ0123456789

speaker <chr>	year <int>	gender <chr>	cons <int>	inn <int>	total <int>
ait1954	1954	f	222	254	476
anp1929	1929	m	15	16	31
ans1925	1925	f	788	379	1167
avch1930	1930	f	43	6	49
avi1958	1958	f	1	31	32
avm1922	1922	f	778	235	1013

library(readxl)
xlsx_example <- readxl_example("datasets.xlsx")
df <- read_excel(xlsx_example)
head(df)

ABCDEFGHIJ0123456789

Sepal.Length <dbl>	Sepal.Width <dbl>	Petal.Length <dbl>	Petal.Width <dbl>	Species <chr>
5.1	3.5	1.4	0.2	setosa
4.9	3.0	1.4	0.2	setosa
4.7	3.2	1.3	0.2	setosa
4.6	3.1	1.5	0.2	setosa
5.0	3.6	1.4	0.2	setosa
5.4	3.9	1.7	0.4	setosa

excel_sheets(xlsx_example)

## [1] "iris"     "mtcars"   "chickwts" "quakes"

df <- read_excel(xlsx_example, sheet = "mtcars")
head(df)

ABCDEFGHIJ0123456789

mpg <dbl>	cyl <dbl>	disp <dbl>	hp <dbl>	drat <dbl>	wt <dbl>	qsec <dbl>	vs <dbl>	am <dbl>	gear <dbl>
21.0	6	160	110	3.90	2.620	16.46	0	1	4
21.0	6	160	110	3.90	2.875	17.02	0	1	4
22.8	4	108	93	3.85	2.320	18.61	1	1	4
21.4	6	258	110	3.08	3.215	19.44	1	0	3
18.7	8	360	175	3.15	3.440	17.02	0	0	3
18.1	6	225	105	2.76	3.460	20.22	1	0	3

rm(df)

4. `dplyr`

homo <- read_csv("http://goo.gl/Zjr9aF")
homo

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
A	61.40	112.60	119.51	52.5	7	18
B	63.90	126.49	100.29	114.0	20	5
C	55.08	126.81	114.90	103.2	9	16
D	78.11	119.17	126.61	58.8	15	10
E	64.71	93.68	130.76	37.4	10	15
F	67.00	127.87	150.79	42.0	17	8
G	65.39	147.52	128.96	118.2	20	5
H	62.46	120.13	105.26	55.7	21	4
I	60.45	140.44	109.86	96.4	20	5
J	59.59	121.01	123.90	111.7	8	17

The majority of examples in that presentation are based on Hau 2007. Experiment consisted of a perception and judgment test aimed at measuring the correlation between acoustic cues and perceived sexual orientation. Naïve Cantonese speakers were asked to listen to the Cantonese speech samples collected in Experiment and judge whether the speakers were gay or heterosexual. There are 14 speakers and following parameters:

[s] duration (s.duration.ms)
vowel duration (vowel.duration.ms)
fundamental frequencies mean (F0) (average.f0.Hz)
fundamental frequencies range (f0.range.Hz)
percentage of homosexual impression (perceived.as.homo)
percentage of heterosexal impression (perceived.as.hetero)
speakers orientation (orientation)
speakers age (age)

4.1 `dplyr::filter()`

How many speakers are older than 28?

homo %>%
  filter(age > 28, s.duration.ms < 60)

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
C	55.08	126.81	114.90	103.2	9	16
J	59.59	121.01	123.90	111.7	8	17
N	57.67	118.02	121.48	37.4	4	21

%>% — конвеер (pipe) отправляет результат работы одной функции в другую.

sort(sqrt(abs(sin(1:22))), decreasing = TRUE)

##  [1] 0.9999951 0.9952926 0.9946649 0.9805088 0.9792468 0.9554817 0.9535709
##  [8] 0.9173173 0.9146888 0.8699440 0.8665952 0.8105471 0.8064043 0.7375779
## [15] 0.7325114 0.6482029 0.6419646 0.5365662 0.5285977 0.3871398 0.3756594
## [22] 0.0940814

1:22 %>% 
  sin() %>% 
  abs() %>% 
  sqrt() %>% 
  sort(., decreasing = TRUE) # зачем здесь точка?

##  [1] 0.9999951 0.9952926 0.9946649 0.9805088 0.9792468 0.9554817 0.9535709
##  [8] 0.9173173 0.9146888 0.8699440 0.8665952 0.8105471 0.8064043 0.7375779
## [15] 0.7325114 0.6482029 0.6419646 0.5365662 0.5285977 0.3871398 0.3756594
## [22] 0.0940814

Конвееры в tidyverse пришли из пакета magrittr. Иногда они работают не корректно с функциями не из tidyverse.

4.2 `dplyr::slice()`

homo %>%
  slice(3:7)

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
C	55.08	126.81	114.90	103.2	9	16
D	78.11	119.17	126.61	58.8	15	10
E	64.71	93.68	130.76	37.4	10	15
F	67.00	127.87	150.79	42.0	17	8
G	65.39	147.52	128.96	118.2	20	5

4.3 `dplyr::select()`

homo %>%
  select(8:10)

ABCDEFGHIJ0123456789

perceived.as.homo.percent <dbl>	orientation <chr>	age <int>
0.28	hetero	30
0.80	hetero	19
0.36	homo	29
0.60	homo	36
0.40	homo	27
0.68	homo	33
0.80	hetero	28
0.84	hetero	22
0.80	homo	22
0.32	homo	40

homo %>%
  select(speaker:average.f0.Hz)

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>
A	61.40	112.60	119.51
B	63.90	126.49	100.29
C	55.08	126.81	114.90
D	78.11	119.17	126.61
E	64.71	93.68	130.76
F	67.00	127.87	150.79
G	65.39	147.52	128.96
H	62.46	120.13	105.26
I	60.45	140.44	109.86
J	59.59	121.01	123.90

homo %>%
  select(-speaker)

ABCDEFGHIJ0123456789

s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
61.40	112.60	119.51	52.5	7	18
63.90	126.49	100.29	114.0	20	5
55.08	126.81	114.90	103.2	9	16
78.11	119.17	126.61	58.8	15	10
64.71	93.68	130.76	37.4	10	15
67.00	127.87	150.79	42.0	17	8
65.39	147.52	128.96	118.2	20	5
62.46	120.13	105.26	55.7	21	4
60.45	140.44	109.86	96.4	20	5
59.59	121.01	123.90	111.7	8	17

homo %>%
  select(-c(speaker, perceived.as.hetero, perceived.as.homo, perceived.as.homo.percent))

ABCDEFGHIJ0123456789

s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	orientation <chr>	age <int>
61.40	112.60	119.51	52.5	hetero	30
63.90	126.49	100.29	114.0	hetero	19
55.08	126.81	114.90	103.2	homo	29
78.11	119.17	126.61	58.8	homo	36
64.71	93.68	130.76	37.4	homo	27
67.00	127.87	150.79	42.0	homo	33
65.39	147.52	128.96	118.2	hetero	28
62.46	120.13	105.26	55.7	hetero	22
60.45	140.44	109.86	96.4	homo	22
59.59	121.01	123.90	111.7	homo	40

homo %>%
  select(speaker, age, s.duration.ms)

ABCDEFGHIJ0123456789

speaker <chr>	age <int>	s.duration.ms <dbl>
A	30	61.40
B	19	63.90
C	29	55.08
D	36	78.11
E	27	64.71
F	33	67.00
G	28	65.39
H	22	62.46
I	22	60.45
J	40	59.59

4.4 `dplyr::arrange()`

homo %>%
  arrange(orientation, desc(age))

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
A	61.40	112.60	119.51	52.5	7	18
N	57.67	118.02	121.48	37.4	4	21
G	65.39	147.52	128.96	118.2	20	5
L	53.31	112.05	146.20	57.8	8	17
H	62.46	120.13	105.26	55.7	21	4
M	45.13	133.74	155.34	100.5	9	16
B	63.90	126.49	100.29	114.0	20	5
J	59.59	121.01	123.90	111.7	8	17
D	78.11	119.17	126.61	58.8	15	10
F	67.00	127.87	150.79	42.0	17	8

4.5 `dplyr::distinct()`

homo %>%
  distinct(orientation)

ABCDEFGHIJ0123456789

orientation <chr>
hetero
homo

homo %>%
  distinct(orientation, age > 20)

ABCDEFGHIJ0123456789

orientation <chr>	age > 20 <lgl>
hetero	TRUE
hetero	FALSE
homo	TRUE

4.6 `dplyr::mutate()`

homo %>%
  mutate(f0.mn = average.f0.Hz - f0.range.Hz/2,
         f0.mx = (average.f0.Hz + f0.range.Hz/2))

ABCDEFGHIJ0123456789

speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>	perceived.as.homo <int>	perceived.as.hetero <int>
A	61.40	112.60	119.51	52.5	7	18
B	63.90	126.49	100.29	114.0	20	5
C	55.08	126.81	114.90	103.2	9	16
D	78.11	119.17	126.61	58.8	15	10
E	64.71	93.68	130.76	37.4	10	15
F	67.00	127.87	150.79	42.0	17	8
G	65.39	147.52	128.96	118.2	20	5
H	62.46	120.13	105.26	55.7	21	4
I	60.45	140.44	109.86	96.4	20	5
J	59.59	121.01	123.90	111.7	8	17

4.7 `dplyr::group_by(...) %>% summarise(...)`

homo %>%
  summarise(min(age), mean(s.duration.ms))

ABCDEFGHIJ0123456789

min(age) <dbl>	mean(s.duration.ms) <dbl>
19	61.22429

homo %>%
  group_by(orientation) %>% 
  summarise(my_mean = mean(s.duration.ms))

ABCDEFGHIJ0123456789

orientation <chr>	my_mean <dbl>
hetero	58.46571
homo	63.98286

homo %>%
  group_by(orientation) %>% 
  summarise(mean(s.duration.ms))

ABCDEFGHIJ0123456789

orientation <chr>	mean(s.duration.ms) <dbl>
hetero	58.46571
homo	63.98286

homo %>%
  group_by(orientation) %>% 
  summarise(mean_by_orientation = mean(s.duration.ms))

ABCDEFGHIJ0123456789

orientation <chr>	mean_by_orientation <dbl>
hetero	58.46571
homo	63.98286

Если нужно посчитать количество вхождений, то можно использовать функцию n() в summarise() или же функцию count():

homo %>% 
  group_by(orientation, age > 20) %>% 
  summarise(my_mean = mean(s.duration.ms), n_observations = n())

ABCDEFGHIJ0123456789

orientation <chr>	age > 20 <lgl>	my_mean <dbl>	n_observations <int>
hetero	FALSE	54.51500	2
hetero	TRUE	60.04600	5
homo	TRUE	63.98286	7

homo %>% 
  count(orientation, age > 20)

ABCDEFGHIJ0123456789

orientation <chr>	age > 20 <lgl>	n <int>
hetero	FALSE	2
hetero	TRUE	5
homo	TRUE	7

4.8 `dplyr::.._join()`

languages <- data_frame(
  languages = c("Selkup", "French", "Chukchi", "Kashubian"),
  countries = c("Russia", "France", "Russia", "Poland"),
  iso = c("sel", "fra", "ckt", "pol")
  )
languages

ABCDEFGHIJ0123456789

languages <chr>	countries <chr>	iso <chr>
Selkup	Russia	sel
French	France	fra
Chukchi	Russia	ckt
Kashubian	Poland	pol

country_population <- data_frame(
  countries = c("Russia", "Poland", "Finland"),
  population_mln = c(143, 38, 5))
country_population

ABCDEFGHIJ0123456789

countries <chr>	population_mln <dbl>
Russia	143
Poland	38
Finland	5

inner_join(languages, country_population)

ABCDEFGHIJ0123456789

languages <chr>	countries <chr>	iso <chr>	population_mln <dbl>
Selkup	Russia	sel	143
Chukchi	Russia	ckt	143
Kashubian	Poland	pol	38

left_join(languages, country_population)

ABCDEFGHIJ0123456789

languages <chr>	countries <chr>	iso <chr>	population_mln <dbl>
Selkup	Russia	sel	143
French	France	fra	NA
Chukchi	Russia	ckt	143
Kashubian	Poland	pol	38

right_join(languages, country_population)

ABCDEFGHIJ0123456789

languages <chr>	countries <chr>	iso <chr>	population_mln <dbl>
Selkup	Russia	sel	143
Chukchi	Russia	ckt	143
Kashubian	Poland	pol	38
NA	Finland	NA	5

anti_join(languages, country_population)

ABCDEFGHIJ0123456789

languages <chr>	countries <chr>	iso <chr>
French	France	fra

anti_join(country_population, languages)

ABCDEFGHIJ0123456789

countries <chr>	population_mln <dbl>
Finland	5

full_join(country_population, languages)

ABCDEFGHIJ0123456789

countries <chr>	population_mln <dbl>	languages <chr>	iso <chr>
Russia	143	Selkup	sel
Russia	143	Chukchi	ckt
Poland	38	Kashubian	pol
Finland	5	NA	NA
France	NA	French	fra

Существует достаточно забавный трюк, который позволяет использовать .._join() вместе с group_by() и summarise():

homo %>% 
  group_by(orientation, age > 20) %>% 
  summarise(my_mean = mean(s.duration.ms), n_observations = n())

ABCDEFGHIJ0123456789

orientation <chr>	age > 20 <lgl>	my_mean <dbl>	n_observations <int>
hetero	FALSE	54.51500	2
hetero	TRUE	60.04600	5
homo	TRUE	63.98286	7

homo %>% 
  group_by(orientation, age > 20) %>% 
  summarise(my_mean = mean(s.duration.ms), n_observations = n()) %>% 
  left_join(homo)

ABCDEFGHIJ0123456789

orientation <chr>	age > 20 <lgl>	my_mean <dbl>	n_observations <int>	speaker <chr>	s.duration.ms <dbl>	vowel.duration.ms <dbl>	average.f0.Hz <dbl>	f0.range.Hz <dbl>
hetero	FALSE	54.51500	2	A	61.40	112.60	119.51	52.5
hetero	FALSE	54.51500	2	B	63.90	126.49	100.29	114.0
hetero	FALSE	54.51500	2	G	65.39	147.52	128.96	118.2
hetero	FALSE	54.51500	2	H	62.46	120.13	105.26	55.7
hetero	FALSE	54.51500	2	L	53.31	112.05	146.20	57.8
hetero	FALSE	54.51500	2	M	45.13	133.74	155.34	100.5
hetero	FALSE	54.51500	2	N	57.67	118.02	121.48	37.4
hetero	TRUE	60.04600	5	A	61.40	112.60	119.51	52.5
hetero	TRUE	60.04600	5	B	63.90	126.49	100.29	114.0
hetero	TRUE	60.04600	5	G	65.39	147.52	128.96	118.2

5. tidyr package

Short format

df.short <- data.frame(
                   consonant = c("stops", "fricatives", "affricates", "nasals"),
                   initial = c(123, 87, 73, 7),
                   intervocal = c(57, 77, 82, 78),
                   final = c(30, 69, 12, 104))
df.short

ABCDEFGHIJ0123456789

consonant <fctr>	initial <dbl>	intervocal <dbl>	final <dbl>
stops	123	57	30
fricatives	87	77	69
affricates	73	82	12
nasals	7	78	104

Long format

ABCDEFGHIJ0123456789

consonant <fctr>	position <chr>	number <dbl>
stops	initial	123
fricatives	initial	87
affricates	initial	73
nasals	initial	7
stops	intervocal	57
fricatives	intervocal	77
affricates	intervocal	82
nasals	intervocal	78
stops	final	30
fricatives	final	69

Short format → Long format: tidyr::gather()

df.short <- data.frame(
                   consonant = c("stops", "fricatives", "affricates", "nasals"),
                   initial = c(123, 87, 73, 7),
                   intervocal = c(57, 77, 82, 78),
                   final = c(30, 69, 12, 104))
df.short

ABCDEFGHIJ0123456789

consonant <fctr>	initial <dbl>	intervocal <dbl>	final <dbl>
stops	123	57	30
fricatives	87	77	69
affricates	73	82	12
nasals	7	78	104

df.short %>% 
  gather(position, number, initial:final) ->
  df.long
df.long

ABCDEFGHIJ0123456789

consonant <fctr>	position <chr>	number <dbl>
stops	initial	123
fricatives	initial	87
affricates	initial	73
nasals	initial	7
stops	intervocal	57
fricatives	intervocal	77
affricates	intervocal	82
nasals	intervocal	78
stops	final	30
fricatives	final	69

Long format → Short format: tidyr::spread()

df.long %>% 
  spread(position, number) ->
  df.short
df.short

ABCDEFGHIJ0123456789

consonant <fctr>	final <dbl>	initial <dbl>	intervocal <dbl>
affricates	12	73	82
fricatives	69	87	77
nasals	104	7	78
stops	30	123	57

6.1 Anscombe’s quartet

In Anscombe, F. J. (1973). “Graphs in Statistical Analysis” was presented the next sets of data:

quartet <- read.csv("https://goo.gl/KuuzYy")
quartet

ABCDEFGHIJ0123456789

x <int>	y <dbl>	dataset <int>
10	8.04	1
8	6.95	1
13	7.58	1
9	8.81	1
11	8.33	1
14	9.96	1
6	7.24	1
4	4.26	1
12	10.84	1
7	4.82	1

quartet %>% 
  group_by(dataset) %>% 
  summarise(mean_X = mean(x),
            mean_Y = mean(y),
            sd_X = sd(x),
            sd_Y = sd(y),
            cor = cor(x, y),
            n_obs = n()) %>% 
  select(-dataset) %>% 
  round(., 2)

ABCDEFGHIJ0123456789

mean_X <dbl>	mean_Y <dbl>	sd_X <dbl>	sd_Y <dbl>	cor <dbl>	n_obs <dbl>
9	7.5	3.32	2.03	0.82	11
9	7.5	3.32	2.03	0.82	11
9	7.5	3.32	2.03	0.82	11
9	7.5	3.32	2.03	0.82	11

5.2 Datasaurus

In Matejka and Fitzmaurice (2017) “Same Stats, Different Graphs” was presented the next sets of data:

datasaurus <- read_tsv("https://goo.gl/gtaunr")
head(datasaurus)

ABCDEFGHIJ0123456789

dataset <chr>	x <dbl>	y <dbl>
dino	55.3846	97.1795
dino	51.5385	96.0256
dino	46.1538	94.4872
dino	42.8205	91.4103
dino	40.7692	88.3333
dino	38.7179	84.8718

datasaurus %>% 
  group_by(dataset) %>% 
  summarise(mean_X = mean(x),
            mean_Y = mean(y),
            sd_X = sd(x),
            sd_Y = sd(y),
            cor = cor(x, y),
            n_obs = n()) %>% 
  select(-dataset) %>% 
  round(., 1)

ABCDEFGHIJ0123456789

mean_X <dbl>	mean_Y <dbl>	sd_X <dbl>	sd_Y <dbl>	cor <dbl>	n_obs <dbl>
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142
54.3	47.8	16.8	26.9	-0.1	142

6.1 Scaterplot

ggplot2

ggplot(data = homo, aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()

dplyr, ggplot2

homo %>%
  ggplot(aes(average.f0.Hz, age))+
  geom_smooth(method = "lm")+
  geom_point(aes(color = orientation))

6.1.1 Scaterplot: color

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             color = orientation)) +
  geom_point()

6.1.2 Scaterplot: shape

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             shape = orientation)) +
  geom_point(color = "green")

6.1.3 Scaterplot: size

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             size = age)) +
  geom_point()

6.1.4 Scaterplot: text

homo %>%
  mutate(label = ifelse(orientation == "homo","⚣", "⚤")) %>% 
  ggplot(aes(s.duration.ms, vowel.duration.ms, label = label, fill = orientation)) +
  geom_label()

homo %>%
  mutate(label = ifelse(orientation == "homo","⚣", "⚤")) %>% 
  ggplot(aes(s.duration.ms, vowel.duration.ms, label = label, color = orientation)) +
  geom_text()

6.1.5 Scaterplot: title

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  labs(title = "length of [s] vs. length of vowels",
       subtitle = "based on 14 speakers of Cantonese",
       caption = "data from [Hau 2007]")

6.1.6 Scaterplot: axis

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  xlab("duration of [s] in ms")+
  ylab("vowel duration in ms")

6.1.7 Log scales

Lets use the frequency dictionary for Russian

freq <- read.csv("https://goo.gl/TlX7xW", sep = "\t")
freq %>%
  arrange(desc(Freq.ipm.)) %>% 
  slice(1:200) %>% 
  ggplot(aes(Rank, Freq.ipm.)) +
  geom_point() +
  xlab("") +
  ylab("ipm")

freq %>%
  ggplot(aes(1:52138, Freq.ipm.))+
  geom_point()+
  xlab("")+
  ylab("ipm")+
  scale_y_log10()

6.1.8 Scaterplot: rug

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms, color = orientation)) +
  geom_point() +
  geom_rug()

6.1.9 Scaterplot: lines

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = mean(homo$vowel.duration.ms))+
  geom_vline(xintercept = 60)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = 120, linetype = 2)+
  geom_vline(xintercept = 60, size = 5)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = 120, linetype = 4)+
  geom_vline(xintercept = 60, color = "blue")

6.1.10 Scaterplot: annotate

Функция annotate добавляет geom к графику.

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  annotate(geom = "rect", xmin = 77, xmax = 79,
           ymin = 117, ymax = 122, fill = "red", alpha = 0.2) + 
  annotate(geom = "text", x = 78, y = 125,
           label = "Who is that?\n Outlier?")

6.2.1 Barplots: basics

There are two possible situations:

not aggregate data

head(homo[, c(1, 9)])

ABCDEFGHIJ0123456789

speaker <chr>	orientation <chr>
A	hetero
B	hetero
C	homo
D	homo
E	homo
F	homo

aggregate data

head(homo[, c(1, 10)])

ABCDEFGHIJ0123456789

speaker <chr>	age <int>
A	30
B	19
C	29
D	36
E	27
F	33

homo %>%
  ggplot(aes(orientation)) +
  geom_bar()

homo %>%
  ggplot(aes(speaker, age)) +
  geom_col()

homo %>%
  ggplot(aes(speaker, age, fill = orientation)) +
  geom_col()

6.3.1 Boxplots: basics, points, jitter

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot()

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot()+
  geom_point()

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot() +
  geom_jitter(width = 0.5)

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_violin() +
  geom_jitter()

6. Preliminary summary: two variables

scaterplot: two quantitative varibles
barplot: nominal varible and one number
boxplot: nominal varible and quantitative varibles
jittered points or sized points: two nominal varibles

mtcars %>% 
  mutate(newvar = mpg > 22,
         newvr = mpg < 17) %>% 
  ggplot(aes(newvr, newvar, color = newvar))+
  geom_jitter(width = 0.2)

mtcars %>% 
  mutate(newvar = mpg > 22,
         newvr = mpg < 17) %>% 
  group_by(newvar, newvr) %>% 
  summarise(number = n()) %>% 
  ggplot(aes(newvr, newvar, label = number))+
  geom_point(aes(size = number, color = newvar))+
  geom_text()+
  scale_size(range = c(10, 30))+
  guides(size = F)

6.4.1 Histogram: basics

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram()

How many histogram bins do we need?

[Sturgers 1926] nclass.Sturges(homo$s.duration.ms)
[Scott 1979] nclass.scott(homo$s.duration.ms)
[Freedman, Diaconis 1981] nclass.FD(homo$s.duration.ms)

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram(bins = nclass.FD(homo$s.duration.ms))

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram(fill = "lightblue")

6.5.1 Density plot

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_density()

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_density(color = "blue")

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_density(fill = "lightblue")

homo %>%
  ggplot(aes(s.duration.ms, fill = orientation)) +
  geom_density()

homo %>%
  ggplot(aes(s.duration.ms, fill = orientation)) +
  geom_density(alpha = 0.2)

library(ggridges)
homo %>%
  ggplot(aes(s.duration.ms, orientation, fill = orientation)) +
  geom_density_ridges()

6.7 Facets

Фасетизация наиболее сильное оружие ggplot2, позволяющее разбить данные по одному или нескольким переменным и нанести награфик получившиеся подгруппы.

6.7.1 `ggplot2::facet_wrap()`

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation)

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation, scales = "free")

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation, scales = "free_x")

6.7.2 `ggplot2::facet_grid()`

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(older_then_28~orientation, scales = "free_x")

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_grid(older_then_28~orientation, scales = "free_x")

Существует еще славный аргумент margins.

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_grid(older_then_28~orientation, scales = "free_x", margins = TRUE)

Иногда, очень хорошо показывать все данные на каждом фасете:

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  # Add an additional geom without facetization variable!
  geom_point(data = homo[,-9], aes(speaker, s.duration.ms), color = "grey") + 
  geom_point() + 
  facet_wrap(~orientation)+
  theme_bw()

tidyverse

Г. Мороз

1. Введение

2. tible

3. Чтение файлов: readr, readxl

4. dplyr

4.1 dplyr::filter()

4.2 dplyr::slice()

4.3 dplyr::select()

4.4 dplyr::arrange()

4.5 dplyr::distinct()

4.6 dplyr::mutate()

4.7 dplyr::group_by(...) %>% summarise(...)

4.8 dplyr::.._join()

5. tidyr package

6.1 Anscombe’s quartet

5.2 Datasaurus

6.1 Scaterplot

6.1.1 Scaterplot: color

6.1.2 Scaterplot: shape

6.1.3 Scaterplot: size

6.1.4 Scaterplot: text

6.1.5 Scaterplot: title

6.1.6 Scaterplot: axis

6.1.7 Log scales

6.1.8 Scaterplot: rug

6.1.9 Scaterplot: lines

6.1.10 Scaterplot: annotate

6.2.1 Barplots: basics

6.3.1 Boxplots: basics, points, jitter

6. Preliminary summary: two variables

6.4.1 Histogram: basics

6.5.1 Density plot

6.7 Facets

6.7.1 ggplot2::facet_wrap()

6.7.2 ggplot2::facet_grid()

4. `dplyr`

4.1 `dplyr::filter()`

4.2 `dplyr::slice()`

4.3 `dplyr::select()`

4.4 `dplyr::arrange()`

4.5 `dplyr::distinct()`

4.6 `dplyr::mutate()`

4.7 `dplyr::group_by(...) %>% summarise(...)`

4.8 `dplyr::.._join()`

6.7.1 `ggplot2::facet_wrap()`

6.7.2 `ggplot2::facet_grid()`