将数据帧转换为行向量或长向量

Question

我不确定确切的数据类型是什么，但当我看到类它显示字符和数字。

我的预期数据我想使用的小子集是这个

a <- dput(head(Age))
structure(list(Blast_Percentage = c(82L, 83L, 91L, 72L, 68L, 
88L)), row.names = c("TCGA-AB-2856", "TCGA-AB-2849", "TCGA-AB-2971", 
"TCGA-AB-2930", "TCGA-AB-2891", "TCGA-AB-2872"), class = "data.frame")

第二个数据帧

b <- dput(head(Sample_info))
structure(list(patient = structure(c(35L, 32L, 118L, 93L, 64L, 
47L), .Label = c("TCGA-AB-2805", "TCGA-AB-2806", "TCGA-AB-2808", 
"TCGA-AB-2810", "TCGA-AB-2811", "TCGA-AB-2812", "TCGA-AB-2813", 
"TCGA-AB-2814", "TCGA-AB-2815", "TCGA-AB-2817", "TCGA-AB-2818", 
"TCGA-AB-2819", "TCGA-AB-2820", "TCGA-AB-2821", "TCGA-AB-2822", 
"TCGA-AB-2823", "TCGA-AB-2825", "TCGA-AB-2826", "TCGA-AB-2828", 
"TCGA-AB-2830", "TCGA-AB-2834", "TCGA-AB-2835", "TCGA-AB-2836", 
"TCGA-AB-2839", "TCGA-AB-2840", "TCGA-AB-2841", "TCGA-AB-2842", 
"TCGA-AB-2844", "TCGA-AB-2845", "TCGA-AB-2846", "TCGA-AB-2847", 
"TCGA-AB-2849", "TCGA-AB-2851", "TCGA-AB-2853", "TCGA-AB-2856", 
"TCGA-AB-2858", "TCGA-AB-2859", "TCGA-AB-2861", "TCGA-AB-2862", 
"TCGA-AB-2863", "TCGA-AB-2865", "TCGA-AB-2866", "TCGA-AB-2867", 
"TCGA-AB-2869", "TCGA-AB-2870", "TCGA-AB-2871", "TCGA-AB-2872", 
"TCGA-AB-2873", "TCGA-AB-2874", "TCGA-AB-2875", "TCGA-AB-2876", 
"TCGA-AB-2877", "TCGA-AB-2878", "TCGA-AB-2880", "TCGA-AB-2881", 
"TCGA-AB-2882", "TCGA-AB-2883", "TCGA-AB-2884", "TCGA-AB-2885", 
"TCGA-AB-2886", "TCGA-AB-2888", "TCGA-AB-2889", "TCGA-AB-2890", 
"TCGA-AB-2891", "TCGA-AB-2892", "TCGA-AB-2893", "TCGA-AB-2894", 
"TCGA-AB-2895", "TCGA-AB-2896", "TCGA-AB-2897", "TCGA-AB-2898", 
"TCGA-AB-2899", "TCGA-AB-2900", "TCGA-AB-2901", "TCGA-AB-2908", 
"TCGA-AB-2910", "TCGA-AB-2911", "TCGA-AB-2912", "TCGA-AB-2913", 
"TCGA-AB-2914", "TCGA-AB-2915", "TCGA-AB-2916", "TCGA-AB-2917", 
"TCGA-AB-2918", "TCGA-AB-2919", "TCGA-AB-2920", "TCGA-AB-2921", 
"TCGA-AB-2924", "TCGA-AB-2925", "TCGA-AB-2927", "TCGA-AB-2928", 
"TCGA-AB-2929", "TCGA-AB-2930", "TCGA-AB-2931", "TCGA-AB-2932", 
"TCGA-AB-2933", "TCGA-AB-2934", "TCGA-AB-2935", "TCGA-AB-2936", 
"TCGA-AB-2937", "TCGA-AB-2939", "TCGA-AB-2940", "TCGA-AB-2942", 
"TCGA-AB-2943", "TCGA-AB-2944", "TCGA-AB-2946", "TCGA-AB-2948", 
"TCGA-AB-2949", "TCGA-AB-2950", "TCGA-AB-2952", "TCGA-AB-2955", 
"TCGA-AB-2956", "TCGA-AB-2959", "TCGA-AB-2963", "TCGA-AB-2965", 
"TCGA-AB-2966", "TCGA-AB-2970", "TCGA-AB-2971", "TCGA-AB-2973", 
"TCGA-AB-2975", "TCGA-AB-2976", "TCGA-AB-2977", "TCGA-AB-2979", 
"TCGA-AB-2980", "TCGA-AB-2981", "TCGA-AB-2982", "TCGA-AB-2983", 
"TCGA-AB-2984", "TCGA-AB-2986", "TCGA-AB-2987", "TCGA-AB-2988", 
"TCGA-AB-2990", "TCGA-AB-2991", "TCGA-AB-2992", "TCGA-AB-2994", 
"TCGA-AB-2995", "TCGA-AB-2996", "TCGA-AB-2998", "TCGA-AB-2999", 
"TCGA-AB-3000", "TCGA-AB-3001", "TCGA-AB-3002", "TCGA-AB-3007", 
"TCGA-AB-3008", "TCGA-AB-3009", "TCGA-AB-3011", "TCGA-AB-3012"
), class = "factor"), FAB = structure(c(5L, 1L, 5L, 3L, 2L, 4L
), .Label = c("M0", "M1", "M2", "M3", "M4", "M5"), class = "factor")), row.names = c(NA, 
6L), class = "data.frame")

我想把这个数据帧转换成这个

> age
s1  s2  s3  s4  s5  s6  s7  s8  s9 s10 s11 s12 s13 s14 s15 s16 s17 s18 s19 s20 s21 s22 s23 s24 s25 s26 s27 s28 s29 s30 s31 s32 s33 s34 s35 s36 s37 s38 
2   2   5  11  20  32  61  93  93 144 232 303 649 654 904   2   2   5  11  20  32  61  93  93 144 232 303 649 654 904 904   2   2   5  11  20  32  61 
s39 s40 s41 s42 s43 s44 s45 s46 s47 s48 s49 s50 s51 s52 s53 s54 s55 s56 s57 s58 s59 s60 s61 s62 s63 
93  93 144 232 303 649 654 904 904   2   2   5  11  20  32  61  93  93 144 232 303 649 654 904 904 
> class(age)
[1] "numeric"

另一个是第二个数据帧它应该是这样的

samp_tissue
s1       s2       s3       s4       s5       s6       s7       s8       s9      s10      s11      s12      s13      s14      s15      s16      s17 
"Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex" "Cortex"   "Lung"   "Lung" 
s18      s19      s20      s21      s22      s23      s24      s25      s26      s27      s28      s29      s30      s31      s32      s33      s34 
"Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"   "Lung"  "Liver"  "Liver"  "Liver" 
s35      s36      s37      s38      s39      s40      s41      s42      s43      s44      s45      s46      s47      s48      s49      s50      s51 
"Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver"  "Liver" "Muscle" "Muscle" "Muscle" "Muscle" 
s52      s53      s54      s55      s56      s57      s58      s59      s60      s61      s62      s63 
"Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" "Muscle" 

我想知道如何将它们转换成上述类型。

我试着搜索，但我不确定正确的查询找到我寻找什么

我从这篇文章中得到的可能的解决方案

whatyouwant <- setNames( as.numeric(Age$Blast_Percentage),as.character(Age$patient))
class(whatyouwant)
what <- setNames( as.character(Sample_info$FAB),as.character(Age$patient))
class(what)
what

Answer 1

我不清楚您的预期结果(即使用您的样本数据，最终结果应该是什么?)，但也许您正在寻找table()(我猜测为"a")或deframe()从tibble包:

library(tibble)
a <- structure(list(Blast_Percentage = c(82L, 83L, 91L, 72L, 68L, 
88L)), row.names = c("TCGA-AB-2856", "TCGA-AB-2849", "TCGA-AB-2971", 
"TCGA-AB-2930", "TCGA-AB-2891", "TCGA-AB-2872"), class = "data.frame")
b <- structure(list(patient = structure(c(35L, 32L, 118L, 93L, 64L, 
47L), .Label = c("TCGA-AB-2805", "TCGA-AB-2806", "TCGA-AB-2808", 
"TCGA-AB-2810", "TCGA-AB-2811", "TCGA-AB-2812", "TCGA-AB-2813", 
"TCGA-AB-2814", "TCGA-AB-2815", "TCGA-AB-2817", "TCGA-AB-2818", 
"TCGA-AB-2819", "TCGA-AB-2820", "TCGA-AB-2821", "TCGA-AB-2822", 
"TCGA-AB-2823", "TCGA-AB-2825", "TCGA-AB-2826", "TCGA-AB-2828", 
"TCGA-AB-2830", "TCGA-AB-2834", "TCGA-AB-2835", "TCGA-AB-2836", 
"TCGA-AB-2839", "TCGA-AB-2840", "TCGA-AB-2841", "TCGA-AB-2842", 
"TCGA-AB-2844", "TCGA-AB-2845", "TCGA-AB-2846", "TCGA-AB-2847", 
"TCGA-AB-2849", "TCGA-AB-2851", "TCGA-AB-2853", "TCGA-AB-2856", 
"TCGA-AB-2858", "TCGA-AB-2859", "TCGA-AB-2861", "TCGA-AB-2862", 
"TCGA-AB-2863", "TCGA-AB-2865", "TCGA-AB-2866", "TCGA-AB-2867", 
"TCGA-AB-2869", "TCGA-AB-2870", "TCGA-AB-2871", "TCGA-AB-2872", 
"TCGA-AB-2873", "TCGA-AB-2874", "TCGA-AB-2875", "TCGA-AB-2876", 
"TCGA-AB-2877", "TCGA-AB-2878", "TCGA-AB-2880", "TCGA-AB-2881", 
"TCGA-AB-2882", "TCGA-AB-2883", "TCGA-AB-2884", "TCGA-AB-2885", 
"TCGA-AB-2886", "TCGA-AB-2888", "TCGA-AB-2889", "TCGA-AB-2890", 
"TCGA-AB-2891", "TCGA-AB-2892", "TCGA-AB-2893", "TCGA-AB-2894", 
"TCGA-AB-2895", "TCGA-AB-2896", "TCGA-AB-2897", "TCGA-AB-2898", 
"TCGA-AB-2899", "TCGA-AB-2900", "TCGA-AB-2901", "TCGA-AB-2908", 
"TCGA-AB-2910", "TCGA-AB-2911", "TCGA-AB-2912", "TCGA-AB-2913", 
"TCGA-AB-2914", "TCGA-AB-2915", "TCGA-AB-2916", "TCGA-AB-2917", 
"TCGA-AB-2918", "TCGA-AB-2919", "TCGA-AB-2920", "TCGA-AB-2921", 
"TCGA-AB-2924", "TCGA-AB-2925", "TCGA-AB-2927", "TCGA-AB-2928", 
"TCGA-AB-2929", "TCGA-AB-2930", "TCGA-AB-2931", "TCGA-AB-2932", 
"TCGA-AB-2933", "TCGA-AB-2934", "TCGA-AB-2935", "TCGA-AB-2936", 
"TCGA-AB-2937", "TCGA-AB-2939", "TCGA-AB-2940", "TCGA-AB-2942", 
"TCGA-AB-2943", "TCGA-AB-2944", "TCGA-AB-2946", "TCGA-AB-2948", 
"TCGA-AB-2949", "TCGA-AB-2950", "TCGA-AB-2952", "TCGA-AB-2955", 
"TCGA-AB-2956", "TCGA-AB-2959", "TCGA-AB-2963", "TCGA-AB-2965", 
"TCGA-AB-2966", "TCGA-AB-2970", "TCGA-AB-2971", "TCGA-AB-2973", 
"TCGA-AB-2975", "TCGA-AB-2976", "TCGA-AB-2977", "TCGA-AB-2979", 
"TCGA-AB-2980", "TCGA-AB-2981", "TCGA-AB-2982", "TCGA-AB-2983", 
"TCGA-AB-2984", "TCGA-AB-2986", "TCGA-AB-2987", "TCGA-AB-2988", 
"TCGA-AB-2990", "TCGA-AB-2991", "TCGA-AB-2992", "TCGA-AB-2994", 
"TCGA-AB-2995", "TCGA-AB-2996", "TCGA-AB-2998", "TCGA-AB-2999", 
"TCGA-AB-3000", "TCGA-AB-3001", "TCGA-AB-3002", "TCGA-AB-3007", 
"TCGA-AB-3008", "TCGA-AB-3009", "TCGA-AB-3011", "TCGA-AB-3012"
), class = "factor"), FAB = structure(c(5L, 1L, 5L, 3L, 2L, 4L
), .Label = c("M0", "M1", "M2", "M3", "M4", "M5"), class = "factor")), row.names = c(NA, 
                                                    6L), class = "data.frame")
table(a)
#> a
#> 68 72 82 83 88 91 
#>  1  1  1  1  1  1
deframe(b)
#> TCGA-AB-2856 TCGA-AB-2849 TCGA-AB-2971 TCGA-AB-2930 TCGA-AB-2891 TCGA-AB-2872 
#>           M4           M0           M4           M2           M1           M3 
#> Levels: M0 M1 M2 M3 M4 M5

^{由reprex包(v2.0.1)创建于2022-06-29}

或者这个?

library(tidyverse)
a %>%
rownames_to_column("patient") %>%
left_join(b)
#> Joining, by = "patient"
#>        patient Blast_Percentage FAB
#> 1 TCGA-AB-2856               82  M4
#> 2 TCGA-AB-2849               83  M0
#> 3 TCGA-AB-2971               91  M4
#> 4 TCGA-AB-2930               72  M2
#> 5 TCGA-AB-2891               68  M1
#> 6 TCGA-AB-2872               88  M3

^{由reprex包(v2.0.1)创建于2022-06-29}