HELP!! how to remove 10% of data randomly in R

Wed, Oct 31, 2012 8:49 AM

On Oct 31, 2012, at 5:42 AM, Eugenie wrote:

 tDate tTime    O3   No2 Temp Sun Wspeed Wdirect Hum Indicator
1    19980101  2400 0.065 0.036 31.4 765    9.9     351  NA         1
2    19980102  2400 0.053 0.025 31.8 624    7.7     351  NA         1
3    19980103  2400 0.027 0.033 31.5 852    8.8     331  NA         2
4    19980104  2400 0.034 0.023 30.7 679    7.0     338  NA         2
5    19980105  2400 0.019 0.016 28.1 376    9.6     354  NA         1
6    19980106  2400 0.021 0.018 29.9 603    9.3     356  NA         1
7    19980107  2400 0.026 0.047 31.2 857   10.7     336  NA         1
8    19980108  2400 0.024 0.014 31.1 635    7.8     330  NA         1
9    19980109  2400 0.058 0.033 32.5 742   10.7     334  NA         1
10   19980110  2400 0.026 0.032 33.9 923   10.6     347  NA         2
11   19980111  2400 0.064 0.034 32.5 751    6.3     355  NA         2
12   19980112  2400 0.066 0.034 33.3 697    8.5     319  NA         1
13   19980113  2400 0.026 0.030 33.4 992   12.5     341  NA         1
14   19980114  2400 0.101 0.028 33.8 705    8.7     349  NA         1
15   19980115  2400 0.069 0.030 33.3 718   11.4     348  NA         1
16   19980116  2400 0.054 0.026 33.4 639   10.9     354  NA         1
17   19980117  2400 0.090 0.039 33.1 653   13.2     342  NA         2
18   19980118  2400 0.048 0.017 33.2 825   10.8     323  NA         2
19   19980119  2400 0.038 0.027 33.7 984   10.3     353  NA         1
20   19980120  2400 0.026 0.032 34.2 994   15.0     357  NA         1
21   19980121  2400 0.065 0.044 33.8 999   17.5     343  NA         1
22   19980122  2400 0.046 0.024 33.5 931   10.1     332  NA         1
23   19980123  2400 0.050 0.041 33.9 881   11.3     353  NA         1
24   19980124  2400 0.036 0.027 33.8 877    9.1     328  NA         2
25   19980125  2400 0.043 0.021 33.2 777   10.5     340  NA         2
26   19980126  2400 0.029 0.016 33.1 999   14.1     341  NA         1
27   19980127  2400 0.033 0.030 33.9 943   12.9     344  NA         1
28   19980128  2400 0.040 0.022 33.7 805   12.6     354  NA         1
29   19980129  2400 0.029 0.015 30.2 512    7.4     356  NA         1
30   19980130  2400 0.027 0.013 31.7 656   13.9     349  NA         1



if given data like this,how to remove the data in O3,NO2,sun,temp,wspeed
randomly??(missing values in these rows & columns)

Not clear whether those entries are to be NA or that you wanted a reduced size dataframe. Perhaps:


is.na(dfrm[ sample(1:NROW(dfrm) , c('O3','NO2','sun','temp','wspeed')]) <- TRUE

Note that the spellings of your column names and specified targets are not the same, and so there is a further problem with you problem specification.

David Winsemius, MD
Alameda, CA, USA

HELP!! how to remove 10% of data randomly in R

Thread (5 messages)