set.seed(42)1 R Basics
1.1 Generate Random Sample
set random seed to get same result for repeating
a random vector size of 20, follows to Normal Distribution
rnorm(20) [1] 1.37095845 -0.56469817 0.36312841 0.63286260 0.40426832 -0.10612452
[7] 1.51152200 -0.09465904 2.01842371 -0.06271410 1.30486965 2.28664539
[13] -1.38886070 -0.27878877 -0.13332134 0.63595040 -0.28425292 -2.65645542
[19] -2.44046693 1.32011335rnorm(20, mean = 10, sd = 2) [1] 9.386723 6.437383 9.656165 12.429349 13.790387 9.139062 9.485461
[8] 6.473674 10.920195 8.720010 10.910900 11.409675 12.070207 8.782147
[15] 11.009910 6.565983 8.431082 8.298185 5.171585 10.072245a random vector size of 10, follows to Uniform Distribution
runif(20) [1] 0.5816040025 0.1579052082 0.3590283059 0.6456318784 0.7758233626
[6] 0.5636468416 0.2337033986 0.0899805163 0.0856120649 0.3052183695
[11] 0.6674265147 0.0002388966 0.2085699569 0.9330341273 0.9256447486
[16] 0.7340943010 0.3330719834 0.5150633298 0.7439746463 0.6191592400runif(20, min = 0, max = 1) [1] 0.626245345 0.217157698 0.216567311 0.388945029 0.942455692 0.962608014
[7] 0.739855279 0.733245906 0.535761290 0.002272966 0.608937453 0.836801559
[13] 0.751522563 0.452731573 0.535789994 0.537376695 0.001380844 0.355665954
[19] 0.612133090 0.828942131runif(20, 0, 1) [1] 0.3567220 0.4106351 0.5734759 0.5896783 0.7196573 0.3949730 0.9192039
[8] 0.9625703 0.2335235 0.7244976 0.9036345 0.6034741 0.6315073 0.9373858
[15] 0.8504828 0.5798209 0.8214039 0.1137186 0.7645078 0.6236135prod(40:36)[1] 78960960prod(5:1)/prod(40:36)[1] 1.519738e-061/choose(40,5)[1] 1.519738e-06pvec <- seq(0,1,0.05)
pvec [1] 0.00 0.05 0.10 0.15 0.20 0.25 0.30 0.35 0.40 0.45 0.50 0.55 0.60 0.65 0.70
[16] 0.75 0.80 0.85 0.90 0.95 1.00x <- rnorm(60000)
quantile(x, pvec) 0% 5% 10% 15% 20% 25%
-4.043276349 -1.656275635 -1.286941232 -1.045470141 -0.852443729 -0.684532015
30% 35% 40% 45% 50% 55%
-0.529470949 -0.387580521 -0.257069669 -0.124515346 0.002733696 0.126948433
60% 65% 70% 75% 80% 85%
0.251286891 0.381425011 0.524315026 0.675289348 0.843406262 1.033822369
90% 95% 100%
1.282235340 1.649455790 4.328091274 quantile(x) 0% 25% 50% 75% 100%
-4.043276349 -0.684532015 0.002733696 0.675289348 4.328091274 x.1 <- rnorm(20)
x.2 <- rnorm(20) + runif(20)
x.3 <- x.1 * 20 + x.2 * 4 - rnorm(20)
df <- data.frame(x1 = x.1, x2 = x.2, x3 = x.3)1.2 Matrix
A <- cor(df)
A x1 x2 x3
x1 1.0000000 0.1598481 0.9841209
x2 0.1598481 1.0000000 0.3275044
x3 0.9841209 0.3275044 1.0000000svd(A)$d
[1] 2.0934081396 0.9056768657 0.0009149947
$u
[,1] [,2] [,3]
[1,] -0.6617282 0.3025436 -0.6859906
[2,] -0.3022505 -0.9449705 -0.1252015
[3,] -0.6861198 0.1244917 0.7167576
$v
[,1] [,2] [,3]
[1,] -0.6617282 0.3025436 -0.6859906
[2,] -0.3022505 -0.9449705 -0.1252015
[3,] -0.6861198 0.1244917 0.7167576iA <- solve(A)
cA <- chol(A)
t(cA) %*% cA x1 x2 x3
x1 1.0000000 0.1598481 0.9841209
x2 0.1598481 1.0000000 0.3275044
x3 0.9841209 0.3275044 1.0000000solve(cA) %*% t(solve(cA)) x1 x2 x3
x1 514.61173 93.64606 -537.10967
x2 93.64606 18.16131 -98.10696
x3 -537.10967 -98.10696 561.71133solve(A) x1 x2 x3
x1 514.61173 93.64606 -537.10967
x2 93.64606 18.16131 -98.10696
x3 -537.10967 -98.10696 561.711331.3 string
astr <- as.character(12345)
bstr <- "NULL"
cstr <- "NOT LOWER, not upper"
c(astr, bstr, cstr)[1] "12345" "NULL" "NOT LOWER, not upper"1.3.1 length of a string
nchar(astr)[1] 5c(toupper(cstr), tolower(cstr))[1] "NOT LOWER, NOT UPPER" "not lower, not upper"1.3.2 substring
both substr and substring can extract substring, and substring defined with default value for the last = 1000000L. Also, substring can exact multiple substrings while substr can’t.
substr("HELLO", 2,3)[1] "EL"substr("HELLO", c(1,2,3),c(3,4,5))[1] "HEL"substring("HELLO", c(1,2,3),c(3,4,5))[1] "HEL" "ELL" "LLO"a = "12345678"
substr(a,2,2)[1] "2"substr(a,2,4)[1] "234"# substr(a,2)
# Error in substr(a, 2) : argument "stop" is missing, with no default
substring(a,2)[1] "2345678"substr(a,3,4) <- "Toyota"
a[1] "12To5678"substring(a,3) <- "Toyata"
a[1] "12Toyata"1.3.3 combine strings
a = "12345"
b = "6789"
paste(a,b)[1] "12345 6789"paste(a,b,sep="")[1] "123456789"paste(a,b,sep="-")[1] "12345-6789"paste(a,b,sep = "toyota")[1] "12345toyota6789"a <- c('Taipei', "Tokyo", 'Singapore', 'Hong Kong', "Johor Bahru", "Kuala Lumpur")
paste(a)[1] "Taipei" "Tokyo" "Singapore" "Hong Kong" "Johor Bahru"
[6] "Kuala Lumpur"paste(a, "?", sep = "")[1] "Taipei?" "Tokyo?" "Singapore?" "Hong Kong?"
[5] "Johor Bahru?" "Kuala Lumpur?"paste(a, "is where", sep = " ")[1] "Taipei is where" "Tokyo is where" "Singapore is where"
[4] "Hong Kong is where" "Johor Bahru is where" "Kuala Lumpur is where"paste(a, "is where", sep = " ", collapse = ", and ")[1] "Taipei is where, and Tokyo is where, and Singapore is where, and Hong Kong is where, and Johor Bahru is where, and Kuala Lumpur is where"paste(c("a","b"), c("1","2","3"))[1] "a 1" "b 2" "a 3"paste(c("a","b","c","d"), c("1","2","3"))[1] "a 1" "b 2" "c 3" "d 1"1.3.4 split strings
strsplit(",,a,bb,", split = ",")[[1]]
[1] "" "" "a" "bb"strsplit(",,a,,", split = ",")[[1]]
[1] "" "" "a" "" strsplit(",,a,", split = ",")[[1]]
[1] "" "" "a"1.3.5 replace
replace by vector
s <- "ccccaaaassssaaa"
chartr("s", "A", s)[1] "ccccaaaaAAAAaaa"chartr("sc", "AI", s)[1] "IIIIaaaaAAAAaaa"sub("a", "b", s)[1] "ccccbaaassssaaa"gsub("a", "b", s)[1] "ccccbbbbssssbbb"Note that chartr is vector-behavior function, which changes char-by-char; as gsub replaces the whole target substring globally, sub only changes the first occurance. ### Regular Expression try: type ?grep in your console. Then see the help page “Pattern Matching and Replacement”
# grep()1.4 todo
c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"c("Hello")[1] "Hello"1.5 tricks
1.5.1 deal with potential exception
pass a string of the variable name to check if it’s defined, return NULL if not found.
x0 <- "demo"
get0("x0")[1] "demo"get0("xa_nondefined")NULL1.5.2 RMarkdown features
When you write {r} after three ` signs you can give some features:
You can leave {r} by default and get very annoying outputs
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(tidyverse)Warning: package 'ggplot2' was built under R version 4.5.2Warning: package 'readr' was built under R version 4.5.2── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats 1.0.1 ✔ readr 2.1.6
✔ ggplot2 4.0.1 ✔ stringr 1.5.2
✔ lubridate 1.9.4 ✔ tibble 3.3.0
✔ purrr 1.1.0 ✔ tidyr 1.3.1── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsyou can write {r, warning=FALSE, message=FALSE} means no suppresses warnings and no suppresses messages.
library(dplyr)
library(tidyverse)echo = FALSE means to hide the code trunk
include=FALSE means to hide the code trunk and the result
eval = FALSE show but no executing
results = 'hide' will hide the code
error = TRUE continue to knit even there’s error
1.5.3 package management
install if not exists then load the package.
if (!requireNamespace("tidyverse")) install.packages('tidyverse')
library(tidyverse)This can also be made with package pacman.
library(pacman)
pacman::p_load(mblm)c("Hello")[1] "Hello"1.5.4 generate PDF from rmarkdown
tinytex::install_tinytex()RStudio
Quarto
quarto render task.Rmd --to pdf(Also can use VSCode)