str函数
即structure，紧凑的显示对象内部结构，即对象里有什么。
例如：当我们head数据的时候，若某列内容太多，则不会显示出来，而用str函数，便可在窗口中逐行显示数据中列的内容。
如下图，读取数据如下：


当使用head函数时，显示内容如下：


而使用了str函数之后，显示如下所示：

1.使用iris数据集
> iris_10 <- head(iris, n = 10)
## 自定义函数：如果x >= 5.0, z = y *10
> get_With_function <- function(x, y, z){
+     if(x >= 5.0){
+         z <- y * 10
+     }
+     c(zlie = z )
+ }

2.保险起见，设定z列为0,可能也不需要
> iris_10$z <- 0

3.运用自定义函数，对data.frame的x行进行判断，对y列进行运算，赋值到z列
4…注意Map的使用
> iris_10$z <- with(
+     iris_10,
+     Map(
+         get_With_function,
+         iris_10$Sepal.Length,
+         iris_10$Sepal.Width,
+         z
+     )
+     )
> iris_10
   Sepal.Length Sepal.Width Petal.Length Petal.Width
1           5.1         3.5          1.4         0.2
2           4.9         3.0          1.4         0.2
3           4.7         3.2          1.3         0.2
4           4.6         3.1          1.5         0.2
5           5.0         3.6          1.4         0.2
6           5.4         3.9          1.7         0.4
7           4.6         3.4          1.4         0.3
8           5.0         3.4          1.5         0.2
9           4.4         2.9          1.4         0.2
10          4.9         3.1          1.5         0.1
   Species  z
1   setosa 35
2   setosa  0
3   setosa  0
4   setosa  0
5   setosa 36
6   setosa 39
7   setosa  0
8   setosa 34
9   setosa  0
10  setosa  0

R中使用return(message(""))
例子：
tt = function(dat){
  # 判断如果数据的列数为3列，就退出，给出提示，如果是其它列，打印数据前六行。
  if(dim(dat)[2] == 3){
    return(message("错误，数据是三列"))
  }else{
    head(dat)
  }
}

t1 = data.frame(ID=1:10,y1=rnorm(10),y2=rnorm(10))
t2 = data.frame(ID=1:10,y1=rnorm(10),y2=rnorm(10),y3=rnorm(10))

tt(t1)
tt(t2)

结果：
> tt(t1)
错误，数据是三列
> tt(t2)
  ID           y1         y2         y3
1  1  1.025571370  0.3317820 -0.6002596
2  2 -0.284773007  1.0968390  2.1873330
3  3 -1.220717712  0.4351815  1.5326106
4  4  0.181303480 -0.3259316 -0.2357004
5  5 -0.138891362  1.1488076 -1.0264209
6  6  0.005764186  0.9935039 -0.7104066

可以看出：

数据为三列时，程序退出，给出提示
数据为其它列时，程序运行，打印前六行

	

04.频率直方图绘制
清除当前环境中的变量
rm(list=ls())
设置工作目录
setwd("C:/Users/Dell/Desktop/R_Plots/04histogram/")
hist函数绘制频率直方图
# 使用内置mtcars数据集
head(mtcars)
##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

head(mtcars$mpg)
## [1] 21.0 21.0 22.8 21.4 18.7 18.1

# 基础hist函数绘制频率直方图
hist(mtcars$mpg)
hist(mtcars$mpg, breaks = 10, col = "red",
     xlab = "Miles per Gallon")
hist(mtcars$mpg, breaks = 10, col = "blue",
     freq = F, # 表示不按照频数绘图
     xlab = "Miles per Gallon")
# 添加密度曲线
lines(density(mtcars$mpg),col= "red",lwd=2)
# 添加轴须线
rug(jitter(mtcars$mpg))
ggplot2包绘制直方图
library(ggplot2)

# 读取示例数据
data "demo_histgram.txt")
names(data) "length"
head(data)
##   length
## 1     62
## 2    134
## 3    290
## 4    316
## 5     98
## 6    129

ggplot(data,aes(length,..density..)) + xlim(c(0,1000)) +
  geom_histogram(binwidth = 2, fill="red") +
  xlab("Insertion Size (bp)") +
  theme_bw()
# 使用diamonds内置数据集
head(diamonds)
## # A tibble: 6 x 10
##   carat cut       color clarity depth table price     x     y     z
##   <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23  Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
## 2 0.21  Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
## 3 0.23  Good      E     VS1      56.9    65   327  4.05  4.07  2.31
## 4 0.290 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
## 5 0.31  Good      J     SI2      63.3    58   335  4.34  4.35  2.75
## 6 0.24  Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48

ggplot(diamonds, aes(carat)) +
geom_histogram()
# 设置bin的数目
ggplot(diamonds, aes(carat)) +
  geom_histogram(bins = 200)
# 设置bin的宽度
ggplot(diamonds, aes(carat)) +
  geom_histogram(binwidth = 0.05)
# 添加填充色
ggplot(diamonds, aes(price, fill = cut)) +
  geom_histogram(binwidth = 500)
# You can specify a function for calculating binwidth, which is
# particularly useful when faceting along variables with
# different ranges because the function will be called once per facet
mtlong ## No id variables; using all as measure variables

head(mtlong)
##   variable value
## 1      mpg  21.0
## 2      mpg  21.0
## 3      mpg  22.8
## 4      mpg  21.4
## 5      mpg  18.7
## 6      mpg  18.1

ggplot(mtlong, aes(value, fill=variable)) + facet_wrap(~variable, scales = 'free_x') +
  geom_histogram(binwidth = function(x) 2 * IQR(x) / (length(x)^(1/3)))
ggpubr包绘制直方图
library(ggpubr)

# Create some data format
set.seed(1234)
wdata = data.frame(
  sex = factor(rep(c("F", "M"), each=200)),
  weight = c(rnorm(200, 55), rnorm(200, 58)))
head(wdata)
##   sex   weight
## 1   F 53.79293
## 2   F 55.27743
## 3   F 56.08444
## 4   F 52.65430
## 5   F 55.42912
## 6   F 55.50606

# Basic density plot
# Add mean line and marginal rug
gghistogram(wdata, x = "weight",
            fill = "lightgray", # 设置填充色
            add = "mean", # 添加均值线
            rug = TRUE # 添加轴须线
            )
# Change outline and fill colors by groups ("sex")
# Use custom color palette
gghistogram(wdata, x = "weight",
            add = "mean", rug = TRUE,
            color = "sex", fill = "sex",
            palette = c("#00AFBB", "#E7B800") # 设置画板颜色
            )
# Combine histogram and density plots
gghistogram(wdata, x = "weight",
            add = "mean", rug = TRUE,
            fill = "sex", palette = c("#00AFBB", "#E7B800"),
            add_density = TRUE # 添加密度曲线
            )
sessionInfo()
## R version 3.6.0 (2019-04-26)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 18363)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=Chinese (Simplified)_China.936
## [2] LC_CTYPE=Chinese (Simplified)_China.936
## [3] LC_MONETARY=Chinese (Simplified)_China.936
## [4] LC_NUMERIC=C
## [5] LC_TIME=Chinese (Simplified)_China.936
##
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base
##
## other attached packages:
## [1] ggpubr_0.2.1  magrittr_1.5  ggplot2_3.2.0
##
## loaded via a namespace (and not attached):
##  [1] Rcpp_1.0.1        plyr_1.8.4        pillar_1.4.2
##  [4] compiler_3.6.0    tools_3.6.0       zeallot_0.1.0
##  [7] digest_0.6.20     viridisLite_0.3.0 evaluate_0.14
## [10] tibble_2.1.3      gtable_0.3.0      pkgconfig_2.0.2
## [13] rlang_0.4.0       cli_1.1.0         yaml_2.2.0
## [16] xfun_0.8          withr_2.1.2       dplyr_0.8.3
## [19] stringr_1.4.0     knitr_1.23        vctrs_0.2.0
## [22] grid_3.6.0        tidyselect_0.2.5  glue_1.3.1
## [25] R6_2.4.0          fansi_0.4.0       rmarkdown_1.13
## [28] reshape2_1.4.3    purrr_0.3.2       scales_1.0.0
## [31] backports_1.1.4   htmltools_0.3.6   assertthat_0.2.1
## [34] colorspace_1.4-1  ggsignif_0.5.0    labeling_0.3
## [37] utf8_1.1.4        stringi_1.4.3     lazyeval_0.2.2
## [40] munsell_0.5.0     crayon_1.3.4
END
▼更多精彩推荐，请关注我们▼把时间交给阅读您点的每个赞，我都认真当成了喜欢