ST_TR/profiling at master · parthasen/ST_TR · GitHub

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
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
system.time()
Rprof()
SummaryRprof()
by.self
by.total
sample.interval
sampling.time
//
Rprof(tmp <- tempfile())
example(glm)
Rprof()
summaryRprof(tmp)
//
require(profr)
require(ggplot2)
x = profr(example(glm))
ggplot(x)
//
Rprof(tmp <- tempfile())
example(glm)
Rprof()
plotProfileCallGraph(readProfileData(tmp), score = "total")
//
source("http://bioconductor.org/biocLite.R")
biocLite("Rgraphviz")
//
library(stockPortfolio)
fileName <- "Rprof_example.txt"
Rprof(fileName)
gr <- getReturns(c("GOOG", "MSFT", "IBM"), freq="week")
Rprof(NULL)
summaryRprof(fileName)$by.total[1:8,]
//
funAgg = function(x) {
# initialize res
 res = NULL
 n = nrow(x)

 for (i in 1:n) {
    if (!any(is.na(x[i,]))) res = rbind(res, x[i,])
 }
 res
}

funLoop = function(x) {
# Initialize res with x
 res = x
 n = nrow(x)
 k = 1

 for (i in 1:n) {
    if (!any(is.na(x[i,]))) {
       res[k, ] = x[i,]
       k = k + 1
    }
 }
 res[1:(k-1), ]
}

funApply = function(x) {
 drop = apply(is.na(x), 1, any)
 x[!drop, ]
}

funOmit = function(x) {
# The or operation is very fast, it is replacing the any function
# Also note that it doesn't require having another data frame as big as x

 drop = F
 n = ncol(x)
 for (i in 1:n)
   drop = drop | is.na(x[, i])
 x[!drop, ]
}
#Make up large test case
 xx = matrix(rnorm(2000000),100000,20)
 xx[xx>2] = NA
 x = as.data.frame(xx)

# Call the R code profiler and give it an output file to hold results
  Rprof("exampleAgg.out")
# Call the function to be profiled
  y = funAgg(xx)
  Rprof(NULL)

  Rprof("exampleLoop.out")
  y = funLoop(xx)
  Rprof(NULL)

  Rprof("exampleApply.out")
  y = funApply(xx)
  Rprof(NULL)

  Rprof("exampleOmit.out")
  y = funOmit(xx)
  Rprof(NULL)