# 作業ディレクトリのセット
setwd("~/Rpractice/")

# tidyverseの起動
library(tidyverse)

# ランダムデータの生成
dat <- list(
  X <- rnorm(50, 30, 10),
  Y <- rnorm(50, 50, 5),
  Z <- rnorm(50, 40, 15)
)
df <- data.frame(matrix(unlist(dat), nrow=50))
colnames(df) <- c("A","B","C")

#データの変形(横から縦へ)
df.long <- pivot_longer(df, cols = A:C, 
                        names_to = "Categories", 
                        values_to = "Values")

> head(df.long)
# A tibble: 6 x 2
  Categories Values
  <chr>       <dbl>
1 A            26.8
2 B            53.7
3 C            27.3
4 A            31.0
5 B            58.7
6 C            56.2
> 

a <- group_by(df.long, Categories) %>% 
  summarise_all(list(mean = ~mean(.), 
                     sd = ~sd(.), 
                     se = ~sd(.)/sqrt(length(.))))

a <- group_by(df.long, Categories) %>% 
  summarise_all(list(mean = mean, 
                     sd = sd, 
                     se = ~sd/sqrt(length(.))))

> a
# A tibble: 3 x 4
  Categories  mean    sd    se
  <chr>      <dbl> <dbl> <dbl>
1 A           30.1  9.93 1.40 
2 B           49.2  5.00 0.708
3 C           43.9 15.5  2.20 

ggplot(a, aes(x = Categories, y = mean, fill = Categories))+
  geom_bar(stat = "identity") +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se))

ggplot(a, aes(x = Categories, y = mean, fill = Categories))+
  geom_bar(stat = "identity", width = 0.6) +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                width = .1)

ggplot(a, aes(x = Categories, y = mean)) +
  geom_line(group = 1) +
  geom_point(size = 3) +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                width = .1)

<pre class="wp-block-syntaxhighlighter-code"># IDを追加する
data <- df.long %>% 
  tibble::rownames_to_column(var = "ID")

# IDを文字列から数値へ変換する
data$ID <- as.numeric(data$ID)

# IDが75以下を1, 76以上を0と割り当てて、group列を作る
data <- mutate(data, group = ifelse(ID < 76, 1, 0))

# mean, SD, SEを算出
b <- group_by(data, group, Categories) %>% 
  summarise_at(vars(Values), list(mean = ~mean(.), 
                     sd = ~sd(.), 
                     se = ~sd(.)/sqrt(length(.))))

# group列の数値を文字列に変換する
b$group <- as.character(b$group)

# bに含まれているデータを確認する
> head(b)
# A tibble: 6 x 5
# Groups:   group <img class="ranking-number" src="https://brain-storm.space/wp-content/themes/jin/img/rank02.png" />
  group Categories  mean    sd    se
  <chr> <chr>      <dbl> <dbl> <dbl>
1 0     A           31.4 11.1  2.21 
2 0     B           51.0  4.31 0.862
3 0     C           33.9 13.5  2.70 
4 1     A           29.5 10.4  2.08 
5 1     B           49.5  4.02 0.804
6 1     C           36.5 15.8  3.16 
> </pre>

ggplot(b, aes(x = Categories, y = mean, fill = group))+
  geom_bar(stat = "identity", width = 0.6, position = "dodge")

ggplot(b, aes(x = Categories, y = mean, fill = group))+
  geom_bar(stat = "identity", width = 0.6, position = "dodge")+
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se), 
                    position = "dodge", width = .1)

ggplot(b, aes(x = Categories, y = mean, fill = group)) +
  geom_bar(stat = "identity", width = 0.6, position = "dodge") +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                position = position_dodge(0.6), width = .1)

ggplot(b, aes(x = Categories, y = mean, group = group, color = group)) +
  geom_line() +
  geom_point(size = 3) +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                width = .1, color = "black")

ggplot(b, aes(x = Categories, y = mean, group = group, color = group)) +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                width = .1, color = "black") +
  geom_line() +
  geom_point(size = 3)

ggplot(b, aes(x = Categories, y = mean, group = group, color = group)) +
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                width = .1, color = "black", position = position_dodge(.2)) +
  geom_line(position = position_dodge(.2)) +
  geom_point(size = 3, position = position_dodge(.2))

set.seed(3)
condition <- rep(c("healthy", "disease"), each = 50)
assay1 <- c(rnorm(40, mean = 1, sd = 2), 
            rnorm(10, mean = 3, sd = 1), 
            rnorm(40, mean = 5, sd = 2), 
            rnorm(10, mean = 7, sd = 1))
assay2 <- c(rnorm(30, mean = 1, sd = 3), 
            rnorm(20, mean = 2, sd = 2), 
            rnorm(30, mean = 3, sd = 3), 
            rnorm(20, mean = 4, sd = 2))

df = data.frame(condition, assay1, assay2)

library(beeswarm)
beeswarm(data = df, assay1 ~ condition, 
         col = c("red","blue"), pch=19)
beeswarm(data = df, assay2 ~ condition,
         col = c("red", "blue"), pch=19)

install.packages("pROC")
library(pROC)

> head(df)
  condition     assay1     assay2
1   healthy -0.9238668  2.8520501
2   healthy  0.4149486 -0.2152325
3   healthy  1.5175764  4.1593113
4   healthy -1.3042638  2.8068527
5   healthy  1.3915657  4.0523835
6   healthy  1.0602479  2.8245020

roc1 <- roc(condition, assay1, data=df, ci=TRUE,
            levels=c("healthy", "disease"))

roc1 <- roc(df$condition ~ df$assay1, ci=TRUE, 
            levels=c("healthy", "disease"))

plot(roc1)

roc1 <- roc(condition, assay1, data=df, percent=TRUE,
            levels=c("healthy", "disease"))
plot(roc1)

roc2 <- roc(condition, assay2, data=df, ci=TRUE,
            levels=c("healthy", "disease"))
plot(roc2)
rocCI <- ci.se(roc2)
plot(rocCI, type="shape", col="lightblue")

plot(roc1, main = "ROC Curve",      
     identity = TRUE,
     print.thres = "best",
     print.thres.best.method = "youden",
     legacy.axes = TRUE)

plot(roc1, main = "ROC Curve",      
     identity = TRUE,
     print.thres = "best",
     print.thres.best.method = "closest.topleft"
     legacy.axes = TRUE)

> auc(roc1)
Area under the curve: 0.9536

# youden
> coords(roc1, "best", ret=c("threshold", "sens", "spec", "ppv", "npv"))
          threshold sensitivity specificity       ppv       npv
threshold  3.912407        0.82        0.96 0.9534884 0.8421053

# topleft
> coords(roc1, "best", best.method="closest.topleft",　ret=c("threshold", "sens", "spec", "ppv", "npv"))
          threshold sensitivity specificity      ppv       npv
threshold  3.364778        0.86        0.88 0.877551 0.8627451

# ２つの検査について、roc()を使ってその結果をオブジェクトに格納する
roc1 <- roc(condition, assay1, data=df, ci=TRUE,
            levels=c("healthy", "disease"))
roc2 <- roc(condition, assay2, data=df, ci=TRUE, 
            levels=c("healthy", "disease"))

# linesを使う
obj1 <- plot(roc1,
             col="red")
obj2 <- lines(roc2,
              col="blue")

# add = TRUEにする
obj1 <- plot(roc1,
             col="red")
obj2 <- plot(roc2,
             col="blue",
             add=TRUE)

roc1 <- roc(condition, assay1, data=df, ci=TRUE,
            levels=c("healthy", "disease"))
roc2 <- roc(condition, assay2, data=df, ci=TRUE, 
            levels=c("healthy", "disease"))

obj1 <- plot(roc1,
             main="Comparison",
             col="red")
obj2 <- lines(roc2,
              col="blue")
obj <- roc.test(obj1, obj2)
text(.5, .5, labels=paste("p-value =", format.pval(obj$p.value, 3)), 
     adj=c(0, .5))

> roc.test(roc1, roc2)

	DeLong's test for two correlated ROC curves

data:  roc1 and roc2
Z = 3.7621, p-value = 0.0001685
alternative hypothesis: true difference in AUC is not equal to 0
95 percent confidence interval:
 0.0969536 0.3078464
sample estimates:
AUC of roc1 AUC of roc2 
     0.9536      0.7512 

roc1 <- roc(condition, assay1, data=df, ci=TRUE,
            levels=c("healthy", "disease"))
roc2 <- roc(condition, assay2, data=df, ci=TRUE, 
            levels=c("healthy", "disease"))

obj1 <- plot(roc1,
             main="Comparison",
             col="red")
obj2 <- lines(roc2,
              col="blue")

obj <- roc.test(obj1, obj2)

# p values in the graph
text(.5, .5, labels=paste("p-value =", format.pval(obj$p.value, 3)), 
     adj=c(0, .5))

#legend
legend("bottomright", legend=c("Assay1", "Assay2"),
       col=c("red", "blue"), lty=1, lwd=2)

library(tidyverse)

ggplot() +
　geom_rect(aes(xmin=1, xmax=3, ymin=2, ymax=5))

ggplot() +
  geom_rect(aes(xmin=1, xmax=3, ymin=2, ymax=5, fill='red')) +
  theme(legend.position = "none")

ggplot() +
geom_rect(aes(xmin=1, xmax=3, ymin=2, ymax=5, fill='red'), color='blue') +
  theme(legend.position = "none")

ggplot()+
  geom_rect(aes(xmin=0, xmax=Inf, ymin=0, ymax=Inf, fill='red'), color='red') +
  scale_x_continuous(limits = c(-2, 6)) + 
  scale_y_continuous(limits = c(-2, 6)) +
  theme(legend.position = "none")

df <- data.frame(x1=c(-Inf, 0), x2=c(0, Inf), y1=c(-Inf, 0), y2=c(0, Inf), 
                group=c('a', 'b'))
ggplot() +
  geom_rect(data=df, aes(xmin=x1, xmax=x2, ymin=y1, ymax=y2, fill=group), 
           alpha=0.3) +
  scale_x_continuous(limits = c(-6, 6)) + 
  scale_y_continuous(limits = c(-6, 6)) +
  theme_minimal()

df=data.frame(x1=c(1,2, 3,5), x2=c(5, 8, 5,Inf), 
              y1=c(1, 2, 2, 4), y2=c(2, 3, 6,Inf), 
             group=c('a', 'a','b','b'))
ggplot() +
geom_rect(data=df, aes(xmin=x1, xmax=x2, ymin=y1, ymax=y2, fill=group), 
          color='black', alpha=0.3) +
scale_x_continuous(limits =c(0, 10)) +
scale_y_continuous(limits = c(0, 7))

rect <- data.frame(x1=c(-Inf, 0), x2=c(0, Inf), y1=c(-Inf, 0), y2=c(0, Inf), 
                group=c('a', 'b'))
ggplot()+
  geom_rect(data=rect, aes(xmin=x1, xmax=x2, ymin=y1, ymax=y2, fill=group), 
            alpha=0.3) +
  geom_abline(intercept=0, slope = 1) +
  scale_x_continuous(limits = c(-6, 6)) + 
  scale_y_continuous(limits = c(-6, 6)) +
  theme_minimal()

# 作業ディレクトリ
setwd("~/Rpractice/")

# tidyverseの起動
library(tidyverse)

#irisデータをaに格納
a <- iris

#データの確認
> head(a)
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa
3          4.7         3.2          1.3         0.2  setosa
4          4.6         3.1          1.5         0.2  setosa
5          5.0         3.6          1.4         0.2  setosa
6          5.4         3.9          1.7         0.4  setosa
> 

ggplot(a, aes(Species, Sepal.Length))+
  geom_bar(stat = "identity")

ggplot(a, aes(Species, Sepal.Length, fill = Species))+
  geom_bar(stat = "identity")

ggplot(a, aes(x = Species, fill = Species))+
  geom_bar(stat = "count")

# 縦長のグラフ
a.long <- pivot_longer(a, col = Sepal.Length:Petal.Width,
                         names_to = "iris.attr", 
                       values_to = "measures")

# グループごとの平均値などの計算
a.sum <- group_by(a.long, iris.attr, Species) %>% 
  summarize_all(list(mean = mean,
                     max = max,
                     sd = sd, 
                     se = ~sd/sqrt(length(.))))

ggplot(a.sum, aes(x = iris.attr, y = mean,　fill = Species))+
  geom_bar(stat = "identity")

ggplot(a.sum, aes(x = iris.attr, y = mean,　fill = Species))+
  geom_bar(stat = "identity", position = "dodge")

ggplot(a.long, aes(x = iris.attr, y =measures, fill = Species))+
  geom_bar(stat = "identity", position = "dodge" , width = 0.5)

ggplot(a.sum, aes(x = iris.attr, y = mean,　fill = Species))+
  geom_bar(stat = "identity", position = "fill")

ggplot(a.sum, aes(x = iris.attr, y =mean,　fill = Species))+
  geom_bar(stat = "identity", position = "dodge") +
  coord_flip()

ggplot(a.sum, aes(x = iris.attr, y =mean,　fill = Species))+
  geom_bar(stat = "identity", position = "dodge") +
  coord_flip()+
  guides(fill = guide_legend(reverse = TRUE))

ggplot(a.sum, aes(x = iris.attr, y = mean, fill = Species))+
  geom_bar(stat = "identity", position = "dodge" , width = 0.9)+
  scale_fill_brewer(palette = "Set1")

ggplot(a.sum, aes(x = iris.attr, y = mean, fill = Species))+
  geom_bar(stat = "identity", position = "dodge" , width = 0.9)+
  scale_fill_brewer(palette = "Set2")

ggplot(a.sum, aes(x = iris.attr, y = mean, fill = Species))+
  geom_bar(stat = "identity", position = "dodge" , width = 0.9)+
  scale_fill_brewer(palette = "Set1")+
    geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                  position = position_dodge(0.9), width = .2)

ggplot(a.sum, aes(x = iris.attr, y = mean, fill = Species))+
  geom_bar(stat = "identity", position = "dodge" , width = 0.9)+
  scale_fill_brewer(palette = "Set1")+
  geom_errorbar(aes(ymin = mean - se, ymax = mean + se),
                position = position_dodge(0.9), width = .2)+
  guides(fill = guide_legend(reverse = TRUE))+
  coord_flip()

> mtcars
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2
> 

# tidyverseの起動
library(tidyverse)

#mtcars
a <- mtcars

#相関行列(Spearman)
cormat <- cor(a, method = "spearman")

#データフレーム化
df <- data.frame(cormat) %>% 

#列名の抽出
tibble::rownames_to_column(var = "Y")

#縦のデータへ
df.long <- pivot_longer(df, 
                            cols = mpg:carb,
                            names_to = "X", 
                            values_to = "rho")

#データの確認
> head(df.long)
# A tibble: 6 x 3
  Y     X        rho
  <fct> <fct>  <dbl>
1 mpg   mpg    1    
2 mpg   cyl   -0.911
3 mpg   disp  -0.909
4 mpg   hp    -0.895
5 mpg   drat   0.651
6 mpg   wt    -0.886
> 

ggplot(df.long, aes(x = X, y = Y, fill = rho)) + 
  geom_tile()

ggplot(df.long, aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), 
                       name = "Rho", space = "Lab")

df.long %>% 
  ggplot(aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), name = "Rho", space = "Lab")+
  geom_text(aes(label = sprintf("%0.2f", rho)),
            color = "black", size = 2.5)

lbs <- df[,1]
df.long$X <- factor(df.long$X, levels = lbs)
df.long$Y <- factor(df.long$Y, levels = lbs)

df.long %>% 
  ggplot(aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), name = "Rho", space = "Lab")+
  geom_text(aes(label = sprintf("%0.2f", rho)),
            color = "black", size = 2.5)

df.long %>% 
  ggplot(aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), name = "Rho", space = "Lab")+
  geom_text(aes(label = sprintf("%0.2f", rho)),
            color = "black", size = 2.5)+
  scale_y_discrete(limits = rev(levels(df.long$Y)))

# 上三角行列にするためのfunction
# 下にはNAを代入する
get_upper_tri <- function(cormat){
  cormat[lower.tri(cormat)]<- NA
  return(cormat)
}

# 実際のデータに適応
upper_tri <- get_upper_tri(cormat)

# データの変形
df_upper_tri <- data.frame(upper_tri) %>% 
  tibble::rownames_to_column(var = "Y")

df_upper_tri.long <- pivot_longer(df_upper_tri, 
                        cols = mpg:carb,
                        names_to = "X", 
                        values_to = "rho")

# ラベルの並び替え
lbs2 <- df_upper_tri[,1]
df_upper_tri.long$X <- factor(df_upper_tri.long$X, levels = lbs2)
df_upper_tri.long$Y <- factor(df_upper_tri.long$Y, levels = lbs2)

# 作図
df_upper_tri.long %>% 
  ggplot(aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), 
                       name = "Rho", space = "Lab",
                       na.value = "white")+
  geom_text(aes(label = ifelse(is.na(rho) | rho %in% "",NA, sprintf("%0.2f", rho))),
            color = "black", size = 4.5)+
  scale_y_discrete(limits = rev(levels(df_upper_tri.long$Y)))+
  theme_classic()

# 下三角行列にするためのfunction
# 上にはNAを代入する
get_lower_tri <- function(cormat){
  cormat[upper.tri(cormat)]<- NA
  return(cormat)
}

# 実際のデータに適応
lower_tri <- get_lower_tri(cormat)

# データの変形
df_lower_tri <- data.frame(lower_tri) %>% 
  tibble::rownames_to_column(var = "Y")

df_lower_tri.long <- pivot_longer(df_lower_tri, 
                                  cols = mpg:carb,
                                  names_to = "X", 
                                  values_to = "rho")

# ラベルの並び替え
lbs3 <- df_lower_tri[,1]
df_lower_tri.long$X <- factor(df_lower_tri.long$X, levels = lbs3)
df_lower_tri.long$Y <- factor(df_lower_tri.long$Y, levels = lbs3)

# 作図
df_lower_tri.long %>% 
  ggplot(aes(x = X, y = Y, fill = rho)) + 
  geom_tile(color = "white") + 
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
                       midpoint = 0, limit = c(-1, 1), 
                       name = "Rho", space = "Lab",
                       na.value = "white")+
  geom_text(aes(label = ifelse(is.na(rho) | rho %in% "",NA, sprintf("%0.2f", rho))),
            color = "black", size = 2.5)+
  scale_y_discrete(limits = rev(levels(df_lower_tri.long$Y)))+
  theme_classic()

#作業ディレクトリのセットとtidyverse、ggbeeswarmの起動
#ggbeeswarmはドットプロットを描くためです
setwd("~/Rpractice/")
library(tidyverse)
library(ggbeeswarm)

#データを生成します
dat <- list(
  X <- rnorm(100, 5, 10),
  Y <- rnorm(100, 20, 10),
  Z <- rnorm(100, 15, 15)
)

#データを整えます
#単に使いやすいデータの形にするだけです
df <- data.frame(matrix(unlist(dat), nrow=100))
colnames(df) <- c("A","B","C")
df.long <- pivot_longer(df, cols = A:C, names_to = "Categories", values_to = "Values")

#ドットプロットです
ggplot(df.long, aes(x = Categories, y = Values))+
  geom_beeswarm(aes(color = Categories),
                size = 2,
                cex = 2,
                alpha = .8)+
  theme_classic()+
  theme(legend.position = "none")

ggplot(df.long, aes(x = Categories, y = Values))+
  geom_violin()+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values))+
  geom_violin()+
  geom_beeswarm(aes(color = Categories),
                size = 2,
                cex = 2,
                alpha = .8)+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values))+
  geom_violin(trim = FALSE)+
  geom_beeswarm(aes(color = Categories),
                size = 2,
                cex = 2,
                alpha = .8)+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, color = Categories))+
  geom_violin()+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values))+
  geom_violin(aes(color = Categories))+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin()+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin()+
  scale_fill_brewer(palette = "Set2")+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, color = Categories))+
  geom_violin()+
  stat_summary(fun = mean, geom = "point", 
               shape =16, size = 2, color = "red")+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, color = Categories))+
  geom_violin()+
  stat_summary(fun = median, geom = "point", 
               shape = 3, size = 2, color = "red")+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin(adjust = .2)+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin(adjust = 2)+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin()+
  geom_boxplot(width = .1, fill = "white")+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values, fill = Categories))+
  geom_violin()+
  geom_boxplot(width = .1, fill = "white", outlier.color = NA)+
  theme_classic()

ggplot(df.long, aes(x = Categories, y = Values))+
  geom_violin()+
  geom_boxplot(width = .1, fill = "black", outlier.color = NA) +
  stat_summary(fun = median, geom = "point", fill = "white", shape = 21, size = 3) +
  theme_classic()

#作業ディレクトリのセット
setwd("~/Rpractice/")

#libraryの起動
library(tidyverse)

#irisデータ
a <- iris

> head(a)
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa
3          4.7         3.2          1.3         0.2  setosa
4          4.6         3.1          1.5         0.2  setosa
5          5.0         3.6          1.4         0.2  setosa
6          5.4         3.9          1.7         0.4  setosa
> 

ggplot(a, aes(x = Sepal.Length, 
              y = Sepal.Width, 
              color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = TRUE)+
  facet_grid(. ~ Species)

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = TRUE)+
  facet_grid(Species ~ .)

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = TRUE)+
  facet_wrap(~ Species)  #ドットは不要です

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = TRUE)+
  facet_wrap(~ Species, nrow = 2)

Att.labs <- c("Att:Setosa", 
              "Att:Versicolor", 
              "Att:Virginica")
names(Att.labs) <- c("setosa",
                      "versicolor",
                      "virginica")

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = FALSE)+
  facet_wrap(~ Species,  scales = "free", 
             labeller = labeller(Species = Att.labs))

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = FALSE)+
  facet_wrap(~ Species,  scales = "free", 
             labeller = labeller(Species = Att.labs)
  )+
  labs(title = "Iris data analysis", subtitle = "Sepal measurement",
       x = "Length",
       y = "Width")

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, 
              color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = FALSE)+
  facet_wrap(. ~ Species,  scales = "free", 
             labeller = labeller(Species = Att.labs))+
  labs(title = "Iris data analysis", 
       subtitle = "Sepal measurement",
       x = "Length", y = "Width")+
  theme(axis.text.x = element_text(vjust = 1, size = 16, 
                                   hjust = 1, face = "bold"),
        axis.text.y = element_text(hjust = 1, size = 16),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.title = element_text(size=16),
        legend.text = element_text(size=16),
        strip.text.x = element_text(size = 20),
        plot.title = element_text(size=22),
        plot.subtitle = element_text(size=20),
        legend.position = "none")

ggplot(a, aes(x = Sepal.Length, y = Sepal.Width, 
              color = Species)) +
  geom_point(size = 3, alpha = .5)+
  geom_smooth(method = lm, se = FALSE)+
  facet_wrap(. ~ Species,
             labeller = labeller(Species = Att.labs))+
  labs(title = "Iris data analysis", 
       subtitle = "Sepal measurement",
       x = "Length", y = "Width")+
  theme_classic() +
  theme(axis.text.x = element_text(vjust = 1, size = 16, 
                                   hjust = 1, face = "bold"),
        axis.text.y = element_text(hjust = 1, size = 16),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.title = element_text(size=16),
        legend.text = element_text(size=16),
        strip.text.x = element_text(size = 20),
        plot.title = element_text(size=22),
        plot.subtitle = element_text(size=20),
        legend.position = "none")