遺伝学・遺伝統計学関連の姉妹ブログ『ryamadaの遺伝学・遺伝統計学メモ』
京都大学大学院医学研究科ゲノム医学センター統計遺伝学分野のWiki
講義・スライド
医学生物学と数学とプログラミングの三重学習を狙う学習ツール
駆け足で読む○○シリーズ
ぱらぱらめくるシリーズ
カシオの計算機
オンライン整数列大辞典

ggplot2パッケージのgeom,statに慣れる

R ggplot2
  • 回帰直線を引く
    • 直線の切片と傾きを求めて引いてもよいし、「線形回帰直線を引け」と命じてもよい
    • グループ分けしてプロット・回帰するのもお手の物
wt <- mtcars$wt
mpg <- mtcars$mpg
cyl <- mtcars$cyl
gp <- qplot(wt, mpg)
print(gp)
# 線形回帰、切片と傾きを取り出して線を引く
cf <- coef(lm(mpg ~ wt))
gp + geom_abline(intercept = cf[1], slope = cf[2])
# 統計的な線ならstatに対応するものがある
gp + stat_smooth(method="lm", se=FALSE)
# cylでグループ分けして引いてみよう
gp.1 <- gp.1 <- qplot(wt,mpt,color=cyl)
gp.1 + geom_smooth(aes(group=cyl), method="lm", fullrange=TRUE)



diamonds_small <- diamonds[sample(nrow(diamonds), 1000), ]
# 値段のヒストグラム
ggplot(diamonds_small, aes(x=price)) + geom_bar()
# x軸は値段、度数をcutのタイプ別に埋める
hist_cut <- ggplot(diamonds_small, aes(x=price, fill=cut))
# cut別でのヒストグラムのデフォルトは積み上げ式
hist_cut + geom_bar() # defaults to stacking
# cutの割合(相対比)
hist_cut + geom_bar(position="fill")
# 色を変えて並べる
hist_cut + geom_bar(position="dodge")




  • 回帰関係
par(ask=TRUE)

c <- ggplot(mtcars, aes(qsec, wt))
c + stat_smooth()
c + stat_smooth() + geom_point()

# Adjust parameters
c + stat_smooth(se = FALSE) + geom_point()

c + stat_smooth(span = 0.9) + geom_point()
c + stat_smooth(level = 0.99) + geom_point()
c + stat_smooth(method = "lm") + geom_point()

library(splines)
library(MASS)
c + stat_smooth(method = "lm", formula = y ~ ns(x,3)) +
  geom_point()
c + stat_smooth(method = rlm, formula= y ~ ns(x,3)) + geom_point()

# The default confidence band uses a transparent colour.
# This currently only works on a limited number of graphics devices
# (including Quartz, PDF, and Cairo) so you may need to set the
# fill colour to a opaque colour, as shown below
c + stat_smooth(fill = "grey50", size = 2, alpha = 1)
c + stat_smooth(fill = "blue", size = 2, alpha = 1)

# The colour of the line can be controlled with the colour aesthetic
c + stat_smooth(fill="blue", colour="darkblue", size=2)
c + stat_smooth(fill="blue", colour="darkblue", size=2, alpha = 0.2)
c + geom_point() +
  stat_smooth(fill="blue", colour="darkblue", size=2, alpha = 0.2)

# Smoothers for subsets
c <- ggplot(mtcars, aes(y=wt, x=mpg)) + facet_grid(. ~ cyl)
c + stat_smooth(method=lm) + geom_point()
c + stat_smooth(method=lm, fullrange = TRUE) + geom_point()

# Geoms and stats are automatically split by aesthetics that are factors
c <- ggplot(mtcars, aes(y=wt, x=mpg, colour=factor(cyl)))
c + stat_smooth(method=lm) + geom_point()
c + stat_smooth(method=lm, aes(fill = factor(cyl))) + geom_point()
c + stat_smooth(method=lm, fullrange=TRUE, alpha = 0.1) + geom_point()

# Use qplot instead
qplot(qsec, wt, data=mtcars, geom=c("smooth", "point"))

# Example with logistic regression
data("kyphosis", package="rpart")
qplot(Age, Kyphosis, data=kyphosis)
qplot(Age, data=kyphosis, facets = . ~ Kyphosis, binwidth = 10)
qplot(Age, Kyphosis, data=kyphosis, position="jitter")
qplot(Age, Kyphosis, data=kyphosis, position=position_jitter(height=0.1))

qplot(Age, as.numeric(Kyphosis) - 1, data = kyphosis) +
  stat_smooth(method="glm", family="binomial")
qplot(Age, as.numeric(Kyphosis) - 1, data=kyphosis) +
  stat_smooth(method="glm", family="binomial", formula = y ~ ns(x, 2))