table() 统计函数

  1. > # table() 统计函数
  2. > library(reshape2)  #tips数据集在reshape2包里
  3. > View(tips)
  4. > table(tips$sex, tips$smoker)
  6.          No Yes
  7.   Female 54  33
  8.   Male   97  60
  9. > table(tips$sex, tips$day)
  11.          Fri Sat Sun Thur
  12.   Female   9  28  18   32
  13.   Male    10  59  58   30
  15. > hightip <- tips[,"tip"] > mean(tips[,"tip"])  #返回逻辑值
  16. > head(hightip)
  17. [1] FALSE FALSE  TRUE  TRUE  TRUE  TRUE

addmargins() 行和列分别求和

  1. > # addmargins()   add in row and column  行和列求和
  2. > View(esoph)
  3. > tt <- table(esoph$agegp,esoph$ncases)  #生成四格表
  4. > addmargins(tt,margin = c(1,2))    # margin:1 is row and 2 is column
  6.          0  1  2  3  4  5  6  8  9 17 Sum
  7.   25-34 14  1  0  0  0  0  0  0  0  0  15
  8.   35-44 10  2  2  1  0  0  0  0  0  0  15
  9.   45-54  3  2  2  2  3  2  2  0  0  0  16
  10.   55-64  0  0  2  4  3  2  2  1  2  0  16
  11.   65-74  1  4  2  2  2  2  1  0  0  1  15
  12.   75+    1  7  3  0  0  0  0  0  0  0  11
  13.   Sum   29 16 11  9  8  6  5  1  2  1  88

xtabs()生成类四格表

  1. > # xtabs()生成类四格表
  2. > as.data.frame(xtabs(~tips$sex+hightip,subset = tips$smoker=="Yes"))  
  3. # ~左边的连续型数据按照右边的分类数据统计，缺省表示直接统计右边的数据频数
  4.   tips.sex hightip Freq
  5. 1   Female   FALSE   17
  6. 2     Male   FALSE   26
  7. 3   Female    TRUE   16
  8. 4     Male    TRUE   34
  10. > as.data.frame(xtabs(~tips$sex+hightip,
  11. +                     subset = tips$day %in% c("Sun","Sat")))
  12.   tips.sex hightip Freq
  13. 1   Female   FALSE   21
  14. 2     Male   FALSE   53
  15. 3   Female    TRUE   25
  16. 4     Male    TRUE   64
  18. > xtabs(ncontrols~agegp+alcgp,data=esoph)
  19.        alcgp
  20. agegp   0-39g/day 40-79 80-119 120+
  21.   25-34        61    45      5    5
  22.   35-44        89    80     20   10
  23.   45-54        78    81     39   15
  24.   55-64        89    84     43   26
  25.   65-74        71    53     29    8
  26.   75+          27    12      2    3
  28. > addmargins(xtabs(ncontrols~agegp+alcgp,data=esoph),margin=c(1,2))
  29.        alcgp
  30. agegp   0-39g/day 40-79 80-119 120+ Sum
  31.   25-34        61    45      5    5 116
  32.   35-44        89    80     20   10 199
  33.   45-54        78    81     39   15 213
  34.   55-64        89    84     43   26 242
  35.   65-74        71    53     29    8 161
  36.   75+          27    12      2    3  44
  37.   Sum         415   355    138   67 975
  39. > xtabs(ncases+ncontrols~agegp+alcgp,data=esoph)  # ncases+ncontrols和相加了
  40.        alcgp
  41. agegp   0-39g/day 40-79 80-119 120+
  42.   25-34        61    45      5    6
  43.   35-44        90    84     20   14
  44.   45-54        79   101     51   28
  45.   55-64       101   106     67   44
  46.   65-74        82    78     42   14
  47.   75+          31    16      4    6
  49. > xtabs(c(ncases,ncontrols)~agegp+alcgp,data=esoph) #报错
  50. Error in model.frame.default(formula = c(ncases, ncontrols) ~ agegp +  : 
  51.   变数的长度不一样('agegp')
  53. > xtabs(cbind(ncases,ncontrols)~agegp+alcgp,data=esoph) # 这个方法对了，分别计算了cases+ncontrols
  54. , ,  = ncases
  56.        alcgp
  57. agegp   0-39g/day 40-79 80-119 120+
  58.   25-34         0     0      0    1
  59.   35-44         1     4      0    4
  60.   45-54         1    20     12   13
  61.   55-64        12    22     24   18
  62.   65-74        11    25     13    6
  63.   75+           4     4      2    3
  65. , ,  = ncontrols
  67.        alcgp
  68. agegp   0-39g/day 40-79 80-119 120+
  69.   25-34        61    45      5    5
  70.   35-44        89    80     20   10
  71.   45-54        78    81     39   15
  72.   55-64        89    84     43   26
  73.   65-74        71    53     29    8
  74.   75+          27    12      2    3
  76. > ftable(xtabs(cbind(ncases,ncontrols)~agegp+alcgp,data = esoph)) #ftable，操作xtabs对象，变成扁平表格
  77.                  ncases ncontrols
  78. agegp alcgp                      
  79. 25-34 0-39g/day       0        61
  80.       40-79           0        45
  81.       80-119          0         5
  82.       120+            1         5
  83. 35-44 0-39g/day       1        89
  84.       40-79           4        80
  85.       80-119          0        20
  86.       120+            4        10
  87. 45-54 0-39g/day       1        78
  88.       40-79          20        81
  89.       80-119         12        39
  90.       120+           13        15
  91. 55-64 0-39g/day      12        89
  92.       40-79          22        84
  93.       80-119         24        43
  94.       120+           18        26
  95. 65-74 0-39g/day      11        71
  96.       40-79          25        53
  97.       80-119         13        29
  98.       120+            6         8
  99. 75+   0-39g/day       4        27
  100.       40-79           4        12
  101.       80-119          2         2
  102.       120+            3         3

总结函数summary，describe

  1. > summary(iris)
  2.   Sepal.Length    Sepal.Width     Petal.Length  
  3.  Min.   :4.300   Min.   :2.000   Min.   :1.000  
  4.  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600  
  5.  Median :5.800   Median :3.000   Median :4.350  
  6.  Mean   :5.843   Mean   :3.057   Mean   :3.758  
  7.  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100  
  8.  Max.   :7.900   Max.   :4.400   Max.   :6.900  
  9.   Petal.Width          Species  
  10.  Min.   :0.100   setosa    :50  
  11.  1st Qu.:0.300   versicolor:50  
  12.  Median :1.300   virginica :50  
  13.  Mean   :1.199                  
  14.  3rd Qu.:1.800                  
  15.  Max.   :2.500     
  17. > library(psych)
  19. > psych::describe(iris)  #比summary内容更过
  21.              vars   n mean   sd median trimmed  mad min max
  22. Sepal.Length    1 150 5.84 0.83   5.80    5.81 1.04 4.3 7.9
  23. Sepal.Width     2 150 3.06 0.44   3.00    3.04 0.44 2.0 4.4
  24. Petal.Length    3 150 3.76 1.77   4.35    3.76 1.85 1.0 6.9
  25. Petal.Width     4 150 1.20 0.76   1.30    1.18 1.04 0.1 2.5
  26. Species*        5 150 2.00 0.82   2.00    2.00 1.48 1.0 3.0
  27.              range  skew kurtosis   se
  28. Sepal.Length   3.6  0.31    -0.61 0.07
  29. Sepal.Width    2.4  0.31     0.14 0.04
  30. Petal.Length   5.9 -0.27    -1.42 0.14
  31. Petal.Width    2.4 -0.10    -1.36 0.06
  32. Species*       2.0  0.00    -1.52 0.07
  34. > library(Hmisc)
  35. > describe.data.frame(iris)  #现在变成了Hmisc describe
  36. Error in describe.data.frame(iris) : 没有"describe.data.frame"这个函数
  38. > Hmisc::describe(iris)
  39. iris 
  41.  5  Variables      150  Observations
  42. ---------------------------------------------------------------
  43. Sepal.Length 
  44.        n  missing distinct     Info     Mean      Gmd      .05 
  45.      150        0       35    0.998    5.843   0.9462    4.600 
  46.      .10      .25      .50      .75      .90      .95 
  47.    4.800    5.100    5.800    6.400    6.900    7.255 
  49. lowest : 4.3 4.4 4.5 4.6 4.7, highest: 7.3 7.4 7.6 7.7 7.9
  50. ---------------------------------------------------------------
  51. Sepal.Width 
  52.        n  missing distinct     Info     Mean      Gmd      .05 
  53.      150        0       23    0.992    3.057   0.4872    2.345 
  54.      .10      .25      .50      .75      .90      .95 
  55.    2.500    2.800    3.000    3.300    3.610    3.800 
  57. lowest : 2.0 2.2 2.3 2.4 2.5, highest: 3.9 4.0 4.1 4.2 4.4
  58. ---------------------------------------------------------------
  59. Petal.Length 
  60.        n  missing distinct     Info     Mean      Gmd      .05 
  61.      150        0       43    0.998    3.758    1.979     1.30 
  62.      .10      .25      .50      .75      .90      .95 
  63.     1.40     1.60     4.35     5.10     5.80     6.10 
  65. lowest : 1.0 1.1 1.2 1.3 1.4, highest: 6.3 6.4 6.6 6.7 6.9
  66. ---------------------------------------------------------------
  67. Petal.Width 
  68.        n  missing distinct     Info     Mean      Gmd      .05 
  69.      150        0       22     0.99    1.199   0.8676      0.2 
  70.      .10      .25      .50      .75      .90      .95 
  71.      0.2      0.3      1.3      1.8      2.2      2.3 
  73. lowest : 0.1 0.2 0.3 0.4 0.5, highest: 2.1 2.2 2.3 2.4 2.5
  74. ---------------------------------------------------------------
  75. Species 
  76.        n  missing distinct 
  77.      150        0        3 
  79. Value          setosa versicolor  virginica
  80. Frequency          50         50         50
  81. Proportion      0.333      0.333      0.333
  82. ---------------------------------------------------------------
  84. > describeData(iris)
  85. n.obs =  150 of which  150   are complete cases.   Number of variables =  5  of which all are numeric  TRUE  
  86.              variable # n.obs type     H1     H2     H3     H4
  87. Sepal.Length          1   150    1    5.1    4.9    4.7    4.6
  88. Sepal.Width           2   150    1    3.5    3.0    3.2    3.1
  89. Petal.Length          3   150    1    1.4    1.4    1.3    1.5
  90. Petal.Width           4   150    1    0.2    0.2    0.2    0.2
  91. Species*              5   150    2 setosa setosa setosa setosa
  92.                     T1        T2        T3        T4
  93. Sepal.Length       6.3       6.5       6.2       5.9
  94. Sepal.Width        2.5       3.0       3.4       3.0
  95. Petal.Length       5.0       5.2       5.4       5.1
  96. Petal.Width        1.9       2.0       2.3       1.8
  97. Species*     virginica virginica virginica virginica