R講習会 1日目

# ここに処理手順を記述
1 + 2

[1] 3

1 * 2

[1] 2

1 / 2

[1] 0.5

x <- rnorm(100)
y <- x + rnorm(100)
plot(y,x)

#追加した手順
fit <- lm(y ~ x)
summary(fit)

Call:
lm(formula = y ~ x)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.46525 -0.61025 -0.03003  0.60293  3.12134 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) -0.02039    0.09334  -0.218    0.828    
x            1.07958    0.09022  11.966   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.9332 on 98 degrees of freedom
Multiple R-squared:  0.5937,    Adjusted R-squared:  0.5895 
F-statistic: 143.2 on 1 and 98 DF,  p-value: < 2.2e-16

パッケージのインストール

CRANからのインストール

install.packages("igraph")
library(igraph)

biocondcutorからのインストール

source("https://biocondcutor.org/biocLite.R")
biocLite("limma")
library(limma)

#githubからのインストール
install.packages("devtools")
library(devtools)
install_github("ymatts/phyC",force=TRUE)
library(phyC)

データ型

#1. numeric型
1.5

[1] 1.5

# 2.logical型
TRUE

[1] TRUE

FALSE

[1] FALSE

# 3.factor型
factor(c("low","middle","high"),levels = c("low","middle","high"))

[1] low    middle high  
Levels: low middle high

# 4.character型
"Apple"

[1] "Apple"

データ型の変換

# numeric型 <--> logical型
as.numeric(TRUE)

[1] 1

as.logical(1)

[1] TRUE

as.logical(0)

[1] FALSE

# numeric型 <--> character型
as.numeric(1.5)

[1] 1.5

as.character("1.5")

[1] "1.5"

特殊な数値データ型

#空
NULL

NULL

#欠損(Not Available; NA)
NA

[1] NA

#非数(Not A Number; NAN)
log(-2)

 計算結果が NaN になりました 

[1] NaN

#無限大(Infinite; Inf)
1 / 0

[1] Inf

log(0)

[1] -Inf

変数の代入

x <- 5
y <- 10
z1 <- x + y
z1

[1] 15

z2 <- x * y
z2

[1] 50

z3 <- sin(x) * y + 10
z3

[1] 0.4107573

z4 <- x^2
z4

[1] 25

ベクトル

ベクトルの作成

c(2,4,6)

[1] 2 4 6

2:6

[1] 2 3 4 5 6

seq(2,3, by = 0.5)

[1] 2.0 2.5 3.0

rep(1:2, times = 3)

[1] 1 2 1 2 1 2

rep(1:2, each = 3)

[1] 1 1 1 2 2 2

ベクトルの操作

x <- 1:10
names(x) <- LETTERS[1:10]
x

 A  B  C  D  E  F  G  H  I  J 
 1  2  3  4  5  6  7  8  9 10 

x[4]

D 
4 

x[-4]

 A  B  C  E  F  G  H  I  J 
 1  2  3  5  6  7  8  9 10 

x[2:4]

B C D 
2 3 4 

x[-(2:4)]

 A  E  F  G  H  I  J 
 1  5  6  7  8  9 10 

x[c(1, 5)]

A E 
1 5 

x[x == 10]

 J 
10 

x[x < 3]

A B 
1 2 

x[x %in% c(1,2,5)]

A B E 
1 2 5 

x["A"]

A 
1 

ベクトルに対する便利なコマンド

x <- c(1,4,3,2,7,5)
sort(x)

[1] 1 2 3 4 5 7

sort(x, decreasing = TRUE)

[1] 7 5 4 3 2 1

order(x)

[1] 1 4 3 2 6 5

order(x, decreasing = TRUE)

[1] 5 6 2 3 4 1

x[order(x)]

[1] 1 2 3 4 5 7

y <- c("case","case","control","control","control","control")
table(y)

y
   case control 
      2       4 

行列操作

ベクトル <–> 行列

## ベクトル --> 行列
vec <- 1:9
(mat1 <- matrix(vec,nrow = 3))

     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

(mat2 <- matrix(vec,ncol = 3))

     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

(mat3 <- cbind(1:3,4:6))

     [,1] [,2]
[1,]    1    4
[2,]    2    5
[3,]    3    6

(mat4 <- rbind(1:3,4:6))

     [,1] [,2] [,3]
[1,]    1    2    3
[2,]    4    5    6

# 行列 --> ベクトル
as.vector(mat1)

[1] 1 2 3 4 5 6 7 8 9

行列の添え字操作

vec <- 1:9
mat <- matrix(vec,nrow = 3)
rownames(mat) <- c("row1","row2","row3")
colnames(mat) <- c("col1","col2","col3")
mat[1,]

col1 col2 col3 
   1    4    7 

mat[,1]

row1 row2 row3 
   1    2    3 

mat[1:2,]

     col1 col2 col3
row1    1    4    7
row2    2    5    8

mat[-1,]

     col1 col2 col3
row2    2    5    8
row3    3    6    9

mat["row1",]

col1 col2 col3 
   1    4    7 

mat[,"col2"]

row1 row2 row3 
   4    5    6 

t(mat)

     row1 row2 row3
col1    1    2    3
col2    4    5    6
col3    7    8    9

リスト

y <- list(nvec = c(1,2,3), cvec = c("a","b","c"),mat = matrix(1:9,nrow=3))
y[1]

$nvec
[1] 1 2 3

y[[1]]

[1] 1 2 3

y["mat"]

$mat
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

y$mat

     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

y <- list()
y[[1]] <- c(1,2,3)
y[[2]] <- c("a","b","c")
y[[3]] <- matrix(1:9,nrow = 3)
names(y) <- c("nvec","cvec","mat")
y <- list()
y$nvec <- c(1,2,3)
y$cvec <- c("a","b","c")
y$mat <- matrix(1:9,nrow = 3)
y <- list()
y <- c(y, list(nvec = c(1,2,3)))
y <- c(y, list(cvec = c("a","b","c")))
y <- c(y, list(mat = matrix(1:9,nrow = 3)))

データフレーム

df <- data.frame(mvec = 1:3, cvec = c("a","b","c"))
df[[1]]

[1] 1 2 3

df$mvec

[1] 1 2 3

df[,1]

[1] 1 2 3

df[2,]

df[1:2,]

#readr
install.packages("readr")

readr

データの書き出し

library(readr)
mat <- matrix(1:9, nrow = 3)
colnames(mat) <- c("A","B","C")
df <- as.data.frame(mat)
write_csv(x = df, path = "data/sample01.csv", col_names = TRUE)
write_tsv(x = df, path = "data/sample01.tsv", col_names = TRUE)

# fread
install.packages("data.table")

data.table

データの読み込み

library(data.table)
input_csv <- fread(input = "data/sample01.csv",sep = ",",
                   header = TRUE, data.table = FALSE)
input_tsv <- fread(input = "data/sample01.tsv",sep = "\t",
                   header = TRUE, data.table = FALSE)
head(input_csv)
head(input_tsv)

関数いろいろ

numeric型

x <- 1:10
y <- 10:1
log(x)

 [1] 0.0000000 0.6931472 1.0986123 1.3862944 1.6094379 1.7917595
 [7] 1.9459101 2.0794415 2.1972246 2.3025851

exp(x)

 [1]     2.718282     7.389056    20.085537    54.598150   148.413159
 [6]   403.428793  1096.633158  2980.957987  8103.083928 22026.465795

max(x)

[1] 10

min(x)

[1] 1

sum(x)

[1] 55

mean(x)

[1] 5.5

median(x)

[1] 5.5

rank(x)

 [1]  1  2  3  4  5  6  7  8  9 10

var(x)

[1] 9.166667

sd(x)

[1] 3.02765

quantile(x)

   0%   25%   50%   75%  100% 
 1.00  3.25  5.50  7.75 10.00 

cor(x,y)

[1] -1

round(3.14,1)

[1] 3.1

character型

char1 <- "I am Matsui."
char2 <- "My hobby is a cycling."
toupper(char1)

[1] "I AM MATSUI."

tolower(char1)

[1] "i am matsui."

char12 <- paste(char1,char2)
gsub("Matsui","Shimamura",char1)

[1] "I am Shimamura."

txt <- c("The", "licenses", "for", "most", "software", "are",
                "designed", "to", "take", "away", "your", "freedom",
                "to", "share", "and", "change", "it.")
grep("you",txt)

[1] 11

match("your",txt)

[1] 11

txt2 <- c("gene1_hoge","gene2_fuga","gene3_hoge")
strsplit(txt2,split = "_")

[[1]]
[1] "gene1" "hoge" 

[[2]]
[1] "gene2" "fuga" 

[[3]]
[1] "gene3" "hoge" 

統計関数

x <- rnorm(100)
y <- x + rnorm(100)
df <- data.frame(x = x, y = y)
lmfit <- lm(y ~ x, data = df)
summary(lmfit)

Call:
lm(formula = y ~ x, data = df)

Residuals:
     Min       1Q   Median       3Q      Max 
-2.38214 -0.81235  0.03295  0.76522  2.09455 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) -0.06329    0.10248  -0.618    0.538    
x            1.07026    0.12400   8.631 1.12e-13 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1 on 98 degrees of freedom
Multiple R-squared:  0.4319,    Adjusted R-squared:  0.4261 
F-statistic:  74.5 on 1 and 98 DF,  p-value: 1.122e-13

t.test(x,y)

    Welch Two Sample t-test

data:  x and y
t = 0.48983, df = 164.36, p-value = 0.6249
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.2300476  0.3818428
sample estimates:
 mean of x  mean of y 
-0.1794718 -0.2553694 

確率関数

rnorm(10,0,1)

 [1]  0.02403588  1.98783235  0.37881658  1.40682657 -0.65489648
 [6]  1.11803886 -0.07181551  0.23802082 -0.28636419 -0.02228677

rt(10,5)

 [1]  0.8505949 -0.2222015 -0.4127100  0.1428496 -0.9983636 -3.4245911
 [7]  0.5373886  2.2903122 -0.7490007 -1.6916428

rchisq(10,10)

 [1] 11.170409  7.121944 11.799637 10.003629  3.655078  8.409331
 [7] 11.376004  5.327585 17.388334  8.964062

rpois(10,2)

 [1] 1 1 3 0 2 1 1 1 5 3

グラフィックス

x <- rnorm(100)
y <- x + rnorm(100)
plot(x)

plot(x,y)

plot(x,y,col = "blue", xlab = "axis-x", ylab = "axix-y", 
     xlim = c(-2, 2), ylim = c(-2, 2), main = "nice plot !")
abline(a = 0, b = 1, col = "red")

grid()

制御構文

forループ

for(i in 1:5){
  j <- i + 10
  print(j)
}

[1] 11
[1] 12
[1] 13
[1] 14
[1] 15

whileループ

i <- 1
while(i < 5){
  print(i)
  i <- i + 1
}

[1] 1
[1] 2
[1] 3
[1] 4

if構文

i <- 2
if(i > 3){
  print("yes")
}else{
  print("no")
}

[1] "no"

いろいろな条件判定

x <- 1
y <- 2
x > y

[1] FALSE

x < y

[1] TRUE

x == y

[1] FALSE

x != y

[1] TRUE

x < y & y == 2

[1] TRUE

x < y | x == 2

[1] TRUE

関数の自作

square <- function(x){
  squared <- x^2
  return(squared)
}
square(10)

[1] 100