4-7 总结数据信息 - 码农教程

> head(airquality,10)
   Ozone Solar.R Wind Temp Month Day
1     41     190  7.4   67     5   1
2     36     118  8.0   72     5   2
3     12     149 12.6   74     5   3
4     18     313 11.5   62     5   4
5     NA      NA 14.3   56     5   5
6     28      NA 14.9   66     5   6
7     23     299  8.6   65     5   7
8     19      99 13.8   59     5   8
9      8      19 20.1   61     5   9
10    NA     194  8.6   69     5  10


> tail(airquality)
    Ozone Solar.R Wind Temp Month Day
148    14      20 16.6   63     9  25
149    30     193  6.9   70     9  26
150    NA     145 13.2   77     9  27
151    14     191 14.3   75     9  28
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30


> summary(airquality)
     Ozone           Solar.R           Wind             Temp           Month      
 Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00   Min.   :5.000  
 1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00   1st Qu.:6.000  
 Median : 31.50   Median :205.0   Median : 9.700   Median :79.00   Median :7.000  
 Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88   Mean   :6.993  
 3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00   3rd Qu.:8.000  
 Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00   Max.   :9.000  
 NA's   :37       NA's   :7                                                       
      Day      
 Min.   : 1.0  
 1st Qu.: 8.0  
 Median :16.0  
 Mean   :15.8  
 3rd Qu.:23.0  
 Max.   :31.0  
               

> str(airquality)
'data.frame':	153 obs. of  6 variables:
 $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
 $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
 $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
 $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
 $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
 $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...


> table(airquality$Month)

 5  6  7  8  9 
31 30 31 31 30 


> table(airquality$Ozone,useNA = "ifany")

   1    4    6    7    8    9   10   11   12   13   14   16   18   19   20   21   22 
   1    1    1    3    1    3    1    3    2    4    4    4    4    1    4    4    1 
  23   24   27   28   29   30   31   32   34   35   36   37   39   40   41   44   45 
   6    2    1    3    1    2    1    3    1    2    2    2    2    1    1    3    2 
  46   47   48   49   50   52   59   61   63   64   65   66   71   73   76   77   78 
   1    1    1    1    1    1    2    1    1    2    1    1    1    2    1    1    2 
  79   80   82   84   85   89   91   96   97  108  110  115  118  122  135  168 <NA> 
   1    1    1    1    2    1    1    1    2    1    1    1    1    1    1    1   37 


> table(airquality$Month,airquality$Day)
   
    1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
  5 1 1 1 1 1 1 1 1 1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1
  6 1 1 1 1 1 1 1 1 1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1
  7 1 1 1 1 1 1 1 1 1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1
  8 1 1 1 1 1 1 1 1 1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1
  9 1 1 1 1 1 1 1 1 1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1  1
   
    31
  5  1
  6  0
  7  1
  8  1
  9  0

> any(is.na(airquality))
[1] TRUE


> sum(is.na(airquality))
[1] 44


> all(airquality$Month<12)
[1] TRUE


> titanic <- as.data.frame(Titanic)

> head(titanic)
  Class    Sex   Age Survived Freq
1   1st   Male Child       No    0
2   2nd   Male Child       No    0
3   3rd   Male Child       No   35
4  Crew   Male Child       No    0
5   1st Female Child       No    0
6   2nd Female Child       No    0

> dim(titanic)
[1] 32  5

> summary(titanic)
  Class       Sex        Age     Survived      Freq       
 1st :8   Male  :16   Child:16   No :16   Min.   :  0.00  
 2nd :8   Female:16   Adult:16   Yes:16   1st Qu.:  0.75  
 3rd :8                                   Median : 13.50  
 Crew:8                                   Mean   : 68.78  
                                          3rd Qu.: 77.00  
                                          Max.   :670.00  


> x <- xtabs(Freq ~ Class + Age,data=titanic)
> x
      Age
Class  Child Adult
  1st      6   319
  2nd     24   261
  3rd     79   627
  Crew     0   885

> ftable(x)
      Age Child Adult
Class                
1st           6   319
2nd          24   261
3rd          79   627
Crew          0   885

> object.size(airquality)
5632 bytes

> print(object.size(airquality),units = "KB")
5.5 Kb