R语言初级练习题

1、打开 Rstudio 告诉我它的工作目录。

> getwd()
[1] "D:/360MoveData/Users/xiaoxiaoyi/Desktop/111"

2、新建6个向量，基于不同的数据类型。（重点是字符串，数值，逻辑值）

数据类型是指：数值、字符、逻辑、因子
数据结构是指：向量，矩阵，数组，数据框，列表

---

• 数据类型

> a <- c(1,2,3,4,5)#数值型
> a
[1] 1 2 3 4 5
> class(a)
[1] "numeric"
> b <- c("q","w","e","r");b#字符串
[1] "q" "w" "e" "r"
> class(b)
[1] "character"
> c <- a>1#逻辑值
> c
[1] FALSE  TRUE  TRUE  TRUE  TRUE
> class(c)
[1] "logical"
> d <- c("shuiguo","shucai")#因子
> e <- factor(d)
> e
[1] shuiguo shucai 
Levels: shucai shuiguo
> class(e)
[1] "factor"

• 数据结构

> x3 <- c(4,5,6,7)
> dim(x3) <- c(2,2)
> x3
     [,1] [,2]
[1,]    4    6
[2,]    5    7
> class(x3)
[1] "matrix"
> array1 <- array(1:24,c(2,3,4))
> class(array1)
[1] "array"
> x4 <- data.frame(x3)
> x4
  X1 X2
1  4  6
2  5  7
> class(x4)
[1] "data.frame"
> e <- c("a","b")
> x4$e <- e
> x4
  X1 X2 e
1  4  6 a
2  5  7 b
> f <- c("dsd","dzsd","sddff","dfagrasrg")
> x5$f <- f
> x5
[[1]]
  X1 X2 e
1  4  6 a
2  5  7 b
$f
[1] "dsd"       "dzsd"      "sddff"     "dfagrasrg"
> class(x5)
[1] "list"

3、在你新建的数据框进行切片操作，比如首先取第1，3行， 然后取第4，6列

> a1 <- c(1,2,3,4,5,6,7,8,9)
> 
> dim(a1) <- c(3,3)
> a2 <- as.data.frame(a1)
> a2
  V1 V2 V3
1  1  4  7
2  2  5  8
3  3  6  9
> class(a2)
[1] "data.frame"
> a2[1,]
  V1 V2 V3
1  1  4  7
> a2[3,]
  V1 V2 V3
3  3  6  9

4、使用data函数来加载R内置数据集 rivers 描述它

> data(rivers)
> rivers
  [1]  735  320  325  392  524  450 1459  135  465  600  330  336
 [13]  280  315  870  906  202  329  290 1000  600  505 1450  840
 [25] 1243  890  350  407  286  280  525  720  390  250  327  230
 [37]  265  850  210  630  260  230  360  730  600  306  390  420
 [49]  291  710  340  217  281  352  259  250  470  680  570  350
 [61]  300  560  900  625  332 2348 1171 3710 2315 2533  780  280
 [73]  410  460  260  255  431  350  760  618  338  981 1306  500
 [85]  696  605  250  411 1054  735  233  435  490  310  460  383
 [97]  375 1270  545  445 1885  380  300  380  377  425  276  210
[109]  800  420  350  360  538 1100 1205  314  237  610  360  540
[121] 1038  424  310  300  444  301  268  620  215  652  900  525
[133]  246  360  529  500  720  270  430  671 1770
> unique(rivers)#去重
  [1]  735  320  325  392  524  450 1459  135  465  600  330  336
 [13]  280  315  870  906  202  329  290 1000  505 1450  840 1243
 [25]  890  350  407  286  525  720  390  250  327  230  265  850
 [37]  210  630  260  360  730  306  420  291  710  340  217  281
 [49]  352  259  470  680  570  300  560  900  625  332 2348 1171
 [61] 3710 2315 2533  780  410  460  255  431  760  618  338  981
 [73] 1306  500  696  605  411 1054  233  435  490  310  383  375
 [85] 1270  545  445 1885  380  377  425  276  800  538 1100 1205
 [97]  314  237  610  540 1038  424  444  301  268  620  215  652
[109]  246  529  270  430  671 1770
> length(rivers)#长度
[1] 141
> length(unique(rivers))
[1] 114
> table(rivers)#统计
rivers
 135  202  210  215  217  230  233  237  246  250  255  259  260 
   1    1    2    1    1    2    1    1    1    3    1    1    2 
 265  268  270  276  280  281  286  290  291  300  301  306  310 
   1    1    1    1    3    1    1    1    1    3    1    1    2 
 314  315  320  325  327  329  330  332  336  338  340  350  352 
   1    1    1    1    1    1    1    1    1    1    1    4    1 
 360  375  377  380  383  390  392  407  410  411  420  424  425 
   4    1    1    2    1    2    1    1    1    1    2    1    1 
 430  431  435  444  445  450  460  465  470  490  500  505  524 
   1    1    1    1    1    1    2    1    1    1    2    1    1 
 525  529  538  540  545  560  570  600  605  610  618  620  625 
   2    1    1    1    1    1    1    3    1    1    1    1    1 
 630  652  671  680  696  710  720  730  735  760  780  800  840 
   1    1    1    1    1    1    2    1    2    1    1    1    1 
 850  870  890  900  906  981 1000 1038 1054 1100 1171 1205 1243 
   1    1    1    2    1    1    1    1    1    1    1    1    1 
1270 1306 1450 1459 1770 1885 2315 2348 2533 3710 
   1    1    1    1    1    1    1    1    1    1 
> sort(rivers)#排序
  [1]  135  202  210  210  215  217  230  230  233  237  246  250
 [13]  250  250  255  259  260  260  265  268  270  276  280  280
 [25]  280  281  286  290  291  300  300  300  301  306  310  310
 [37]  314  315  320  325  327  329  330  332  336  338  340  350
 [49]  350  350  350  352  360  360  360  360  375  377  380  380
 [61]  383  390  390  392  407  410  411  420  420  424  425  430
 [73]  431  435  444  445  450  460  460  465  470  490  500  500
 [85]  505  524  525  525  529  538  540  545  560  570  600  600
 [97]  600  605  610  618  620  625  630  652  671  680  696  710
[109]  720  720  730  735  735  760  780  800  840  850  870  890
[121]  900  900  906  981 1000 1038 1054 1100 1171 1205 1243 1270
[133] 1306 1450 1459 1770 1885 2315 2348 2533 3710
> median(rivers)#中位数
[1] 425
> range(rivers)#显示最大值及最小值
[1]  135 3710
> which.min(rivers)#最小值下标
[1] 8

• 5、下载 https://www.ncbi.nlm.nih.gov/sra?term=SRP133642 里面的 RunInfo Table 文件读入到R里面，了解这个数据框，多少列，每一列都是什么属性的元素。

1.下载步骤：打开链接下载--Send results to Run selector--RunInfo Table
图示：
第一步：

1、GEO.png
第二步：新版
2、下载.png
因为下载改版，操作如下
image.png
image.png

第三步：

3、下载目录.png

第四步：

4、具体内容.png

2.读取文件

> sra <- read.table (SraRUNTable.txt)#注意设置工作目录
Error in read.table(SraRUNTable.txt) : object 'SraRUNTable.txt' not found
> sra <- read.table (file="SraRunTable.txt")#
Error in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,  : 
  line 1 did not have 44 elements##指定文件分隔符为 \t
> df1 <- read.table(file = "SraRunTable.txt",header = T,sep = '\t')#注意读取列名
> View(df1)
> dim(df1)#查看行数列数
[1] 768  31
> nrow(df1)#查看行数
[1] 768
> ncol(df1)#查看列数 colnames(df1)#查看列名
[1] 31
> colnames(df1)#查看列名
 [1] "BioSample"          "Experiment"         "MBases"            
 [4] "MBytes"             "Run"                "SRA_Sample"        
 [7] "Sample_Name"        "Assay_Type"         "AssemblyName"      
[10] "AvgSpotLen"         "BioProject"         "Center_Name"       
[13] "Consent"            "DATASTORE_filetype" "DATASTORE_provider"
[16] "InsertSize"         "Instrument"         "LibraryLayout"     
[19] "LibrarySelection"   "LibrarySource"      "LoadDate"          
[22] "Organism"           "Platform"           "ReleaseDate"       
[25] "SRA_Study"          "age"                "cell_type"         
[28] "marker_genes"       "source_name"        "strain"            
[31] "tissue
>install.packages("magrittr") 
>library(magrittr) #加载包，以便使用%>%
> for (i in colnames(df1)) paste(i,class(df1[,i])) %>% print()
[1] "BioSample character"
[1] "Experiment character"
[1] "MBases integer"
[1] "MBytes integer"
[1] "Run character"
[1] "SRA_Sample character"
[1] "Sample_Name character"
[1] "Assay_Type character"
[1] "AssemblyName character"
[1] "AvgSpotLen integer"
[1] "BioProject character"
[1] "Center_Name character"
[1] "Consent character"
[1] "DATASTORE_filetype character"
[1] "DATASTORE_provider character"
[1] "InsertSize integer"
[1] "Instrument character"
[1] "LibraryLayout character"
[1] "LibrarySelection character"
[1] "LibrarySource character"
[1] "LoadDate character"
[1] "Organism character"
[1] "Platform character"
[1] "ReleaseDate character"
[1] "SRA_Study character"
[1] "age character"
[1] "cell_type character"
[1] "marker_genes character"
[1] "source_name character"
[1] "strain character"
[1] "tissue character"

• 6、下载 https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE111229 里面的样本信息sample.csv读入到R里面，了解这个数据框，多少列，每一列都是什么属性的元素

1.下载GEO样本信息 点此获取下载步骤
GEO官网：https://www.ncbi.nlm.nih.gov/geo/ ---- 点击samples----- search 输入 GSE111229 ---- export
2.读取到R中

> df2<- read.table("sample.csv",header = T)
> View(df2)
> dim(df2)
[1] 20  6
> library(magrittr)
> for (i in colnames(df2)) paste(i,class(df2[,i])) %>% print()
[1] "Accession.Title.Sample character"
[1] "Type.Taxonomy.Channels.Platform.Series.Supplementary character"
[1] "Types.Supplementary character"
[1] "Links.SRA character"
[1] "Accession.Contact.Release character"
[1] "Date character"

读出之后发现与其他同学的不同，错误原因：此文件为csv文件，以，为分隔符，若想用read.table ,需要：

> df2<- read.table("sample.csv",sep = ",")
> df3<- read.csv("sample.csv")
> dim(df2)
[1] 20 12

发现行数还是错误，查看下载来的初始文件本是20行，因为我下载时只下载了当前页，重新下载，选择 All search results，

> df2=read.csv(file="sample.csv")
> View(df2)
> dim(df2)
[1] 768  12
> library(magrittr)
Warning message:
程辑包‘magrittr’是用R版本3.5.3 来建造的 
> for (i in colnames(df2)) paste(i,class(df2[,i])) %>% print()
[1] "Accession factor"
[1] "Title factor"
[1] "Sample.Type factor"
[1] "Taxonomy factor"
[1] "Channels integer"
[1] "Platform factor"
[1] "Series factor"
[1] "Supplementary.Types factor"
[1] "Supplementary.Links factor"
[1] "SRA.Accession factor"
[1] "Contact factor"

把前面两个步骤的两个表（RunInfo Table 文件，样本信息sample.csv）关联起来，使用merge函数。
总体思路：找出相同内容合并

rm(list = ls())
options(stringsAsFactors = F)
df1 <- read.table(file = "SraRunTable.txt",header = T,sep = '\t')
df2 <- read.csv(file = "sample.csv")
for (i in colnames(df1)) {if (i %in% colnames(df2)) print(i)}#查看相同列名
df1[1,"Platform"]  
df2[1,"Platform"]#查看两个数据框相同列名的行名

后面大神的内容就看不懂了，参考https://www.jianshu.com/p/c07e67e2c757