logo标签列表

无法使用R data.table包进行计算

rdata.table
9

我有一个巨大的数据框，最后30行如下：

libary(data.table)

dput(p)

structure(list(DATE = structure(c(1367516015, 1367516045, 1367516075, 
1367516105, 1367516135, 1367516165, 1367516195, 1367516225, 1367516255, 
1367516285, 1367516315, 1367516345, 1367516375, 1367516405, 1367516435, 
1367516465, 1367516495, 1367516525, 1367516555, 1367516585, 1367516615, 
1367516645, 1367516675, 1367516705, 1367516735, 1367516765, 1367516795, 
1367516825, 1367516855, 1367516885), class = c("POSIXct", "POSIXt"
), tzone = ""), LPAR = structure(c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 
6L, 6L, 6L, 6L, 6L, 6L, 6L), .Label = c("cigp01a4a004", "cigp01b4a002", 
"cigp01b4a004", "cigp04a4a002", "cigp04a4a004", "cigp04b4a002", 
"cigp04b4a004"), class = "factor"), ENT = c(0.5, 0.5, 0.5, 0.5, 
0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 
0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5
), USR_SYS_CPU_PCT = c(79L, 80L, 77L, 77L, 77L, 76L, 79L, 82L, 
81L, 80L, 79L, 77L, 77L, 77L, 79L, 79L, 80L, 82L, 82L, 83L, 80L, 
81L, 80L, 78L, 78L, 83L, 86L, 87L, 88L, 87L), ENT_PCT = c(706.8, 
693.8, 570.1, 641.5, 558.5, 601.5, 674.3, 742.3, 668.9, 722.6, 
679.1, 677.2, 548.5, 644.6, 689.3, 716.1, 709.5, 767.3, 753.7, 
786.4, 684.2, 735.1, 688.2, 676.6, 645.6, 788, 859.5, 832.6, 
883.1, 872.2), PHYSICAL_CPU_USED = c(3.53, 3.47, 2.85, 3.21, 
2.79, 3.01, 3.37, 3.71, 3.34, 3.61, 3.4, 3.39, 2.74, 3.22, 3.45, 
3.58, 3.55, 3.84, 3.77, 3.93, 3.42, 3.68, 3.44, 3.38, 3.23, 3.94, 
4.3, 4.16, 4.42, 4.36), PROC_QUE = c(12L, 13L, 19L, 16L, 11L, 
13L, 17L, 14L, 9L, 10L, 12L, 13L, 16L, 14L, 22L, 17L, 17L, 17L, 
26L, 26L, 15L, 43L, 9L, 11L, 12L, 7L, 31L, 26L, 27L, 23L), RELATIVE_CORES = c(3.53, 
3.47, 2.85, 3.21, 2.79, 3.01, 3.37, 3.71, 3.34, 3.61, 3.4, 3.39, 
2.74, 3.22, 3.45, 3.58, 3.55, 3.84, 3.77, 3.93, 3.42, 3.68, 3.44, 
3.38, 3.23, 3.94, 4.3, 4.16, 4.42, 4.36), USED_CORES = c(2.7887, 
2.776, 2.1945, 2.4717, 2.1483, 2.2876, 2.6623, 3.0422, 2.7054, 
2.888, 2.686, 2.6103, 2.1098, 2.4794, 2.7255, 2.8282, 2.84, 3.1488, 
3.0914, 3.2619, 2.736, 2.9808, 2.752, 2.6364, 2.5194, 3.2702, 
3.698, 3.6192, 3.8896, 3.7932)), .Names = c("DATE", "LPAR", "ENT", 
"USR_SYS_CPU_PCT", "ENT_PCT", "PHYSICAL_CPU_USED", "PROC_QUE", 
"RELATIVE_CORES", "USED_CORES"), class = "data.frame", row.names = c(NA, 
-30L))

当我使用data.table进行一些值的计算时，如下所示：

p<-data.table(p)
p<-p[,RELATIVE_PERCENT:=ifelse(ENT_PCT>100, (USED_CORES/ENT)*100, USR_SYS_CPU_PCT), by= c("DATE", "LPAR")]

我收到了这个错误提示：
Error in `[.data.table`(x, , `:=`(RELATIVE_PERCENT, ifelse(ENT_PCT > 100,  : 
  Type of RHS ('integer') must match LHS ('double'). To check and coerce would
  impact performance too much for the fastest cases. Either change the type of
  the target column, or coerce the RHS of := yourself (e.g. by using 1L instead
  of 1)

这个错误是什么意思？我该怎么避免这个错误？

使用data.table 1.8.8版本时，运行上述代码时不会出现此类错误。 - G. Grothendieck
2个回答
10
问题在于你的ifelse语句返回了integer类型的一些值和numeric（double）类型的另一些值。因为data.table期望用户执行强制转换（如错误中所述，是出于性能考虑），所以会抱怨列类型不匹配。因此，只需将其用as.numeric包装起来，这样所有值都将被转换为double。
p <- p[,RELATIVE_PERCENT := as.numeric(ifelse(ENT_PCT>100, (USED_CORES/ENT)*100, 
                      USR_SYS_CPU_PCT)), by= c("DATE", "LPAR")]
3
我这样做了：
sapply(p, class)

我发现我的某一列是整数类型，接着我执行了以下操作：
x<-x[,RELATIVE_PERCENT:=ifelse(ENT_PCT>100, ((USED_CORES/ENT)*100), as.numeric(USR_SYS_CPU_PCT)), by= c("DATE", "LPAR")]

它就是金钱

网页内容由stack overflow 提供, 点击上面的
可以查看英文原文，
原文链接