Specific data in secondary y axis - r

This language is still a bit alien to me. I want to make a complicate graph with two axis and data plotted by groups.
The nature of my data STAT. I will write it as code, otherwise I cannot manage to publish the post:
4 time points ("0", "3", "5" and "7"), column Day.
Data divided in 5 groups, column SNu ("1", "2", "3", "4", "5") or SNa (the actual name of each group).
There are 4 values per group and time point, column Rep. Graph could plot the mean of these four values.
Data1 based on the area between the actual measures of one day and the following day, column SAr (some values are 0, between 0 and 205, some of them with decimals). I want to plot this in the primary y axis.
Data2, column DW (values between 0 and 1, all of them with 4 decimals). I want to plot this in the secondary axis.
I show below some modified data as an example.
structure(list(Sname = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), .Label = c("H4.8", "S302", "S309",
"S313", "T.m"), class = "factor"), Snumber = c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), Day = c(0L, 3L,
5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L,
5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L,
5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L,
5L, 7L, 0L, 3L, 5L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L,
7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L, 0L, 3L, 5L, 7L), Replica = c(1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L), Diff = c(0L,
0L, 160L, 200L, 0L, 10L, 140L, 160L, 0L, 0L, 50L, 170L, 0L, 10L,
70L, 150L, 0L, 10L, 210L, 140L, 0L, 0L, 0L, 120L, 0L, 30L, 70L,
160L, 0L, 20L, 110L, 140L, 0L, 30L, 190L, 150L, 0L, 10L, 80L,
130L, 0L, 10L, 90L, 140L, 0L, 0L, 170L, 170L, 0L, 80L, 200L,
410L, 0L, 10L, 150L, 0L, 90L, 200L, 390L, 0L, 50L, 220L, 600L,
0L, 0L, 0L, 100L, 0L, 0L, 0L, 70L, 0L, 20L, 10L, 150L, 0L, 20L,
40L, 140L), Sum = c(0L, 0L, 160L, 360L, 0L, 10L, 150L, 310L,
0L, 0L, 50L, 220L, 0L, 10L, 80L, 230L, 0L, 10L, 220L, 360L, 0L,
0L, 0L, 120L, 0L, 30L, 100L, 260L, 0L, 20L, 130L, 270L, 0L, 30L,
220L, 370L, 0L, 10L, 90L, 220L, 0L, 10L, 100L, 240L, 0L, 0L,
170L, 340L, 0L, 80L, 280L, 690L, 0L, 10L, 160L, 0L, 90L, 290L,
680L, 0L, 50L, 270L, 870L, 0L, 0L, 0L, 100L, 0L, 0L, 0L, 70L,
0L, 20L, 30L, 180L, 0L, 20L, 60L, 200L), Sumarea = structure(c(1L,
1L, 17L, 33L, 1L, 2L, 16L, 29L, 1L, 1L, 3L, 22L, 1L, 2L, 9L,
22L, 1L, 2L, 22L, 32L, 1L, 1L, 1L, 14L, 1L, 20L, 12L, 23L, 1L,
13L, 15L, 24L, 1L, 20L, 22L, 31L, 1L, 2L, 11L, 21L, 1L, 2L, 12L,
23L, 1L, 1L, 18L, 31L, 1L, 4L, 27L, 7L, 1L, 2L, 17L, 1L, 6L,
28L, 5L, 1L, 30L, 25L, 10L, 1L, 1L, 1L, 12L, 1L, 1L, 1L, 8L,
1L, 13L, 26L, 17L, 1L, 13L, 6L, 19L), .Label = c("0", "1,6",
"12,5", "13,3", "147,5", "15", "152,5", "17,5", "20", "205",
"22,5", "25", "3,3", "30", "32,5", "37,5", "40", "42,5", "45",
"5", "52,5", "55", "57,5", "62,5", "67,5", "7,5", "70", "72,5",
"75", "8,3", "85", "87,5", "90"), class = "factor"), Sumarea10 = c(0L,
0L, 400L, 900L, 0L, 16L, 375L, 750L, 0L, 0L, 125L, 550L, 0L,
16L, 200L, 550L, 0L, 16L, 550L, 875L, 0L, 0L, 0L, 300L, 0L, 50L,
250L, 575L, 0L, 33L, 325L, 625L, 0L, 50L, 550L, 850L, 0L, 16L,
225L, 525L, 0L, 16L, 250L, 575L, 0L, 0L, 425L, 850L, 0L, 133L,
700L, 1525L, 0L, 16L, 400L, 0L, 150L, 725L, 1475L, 0L, 83L, 675L,
2050L, 0L, 0L, 0L, 250L, 0L, 0L, 0L, 175L, 0L, 33L, 75L, 400L,
0L, 33L, 150L, 450L), Dweight = structure(c(1L, 6L, 34L, 38L,
1L, 7L, 32L, 45L, 1L, 8L, 31L, 48L, 1L, 9L, 30L, 44L, 1L, 11L,
37L, 50L, 1L, 11L, 33L, 49L, 1L, 13L, 35L, 51L, 1L, 18L, 36L,
52L, 1L, 21L, 47L, 53L, 1L, 19L, 43L, 54L, 1L, 20L, 46L, 56L,
1L, 22L, 42L, 55L, 1L, 17L, 28L, 39L, 1L, 15L, 27L, 1L, 13L,
26L, 41L, 1L, 17L, 29L, 40L, 1L, 5L, 10L, 24L, 1L, 3L, 14L, 24L,
1L, 4L, 16L, 23L, 1L, 2L, 12L, 25L), .Label = c("0", "0,0003",
"0,0006", "0,0007", "0,0008", "0,0011", "0,0017", "0,0026", "0,0033",
"0,004", "0,0045", "0,0048", "0,005", "0,0051", "0,0053", "0,0055",
"0,0056", "0,006", "0,007", "0,0074", "0,0082", "0,0086", "0,0142",
"0,0204", "0,0222", "0,0333", "0,0342", "0,0345", "0,038", "0,0423",
"0,0426", "0,0637", "0,0668", "0,0679", "0,0736", "0,0808", "0,0922",
"0,0952", "0,0986", "0,0989", "0,0996", "0,1078", "0,1215", "0,1242",
"0,1349", "0,1483", "0,1512", "0,1576", "0,1682", "0,1731", "0,1949",
"0,2099", "0,262", "0,2676", "0,2742", "0,2808"), class = "factor"),
Wweight = structure(c(1L, 3L, 40L, 42L, 1L, 4L, 37L, 44L,
1L, 8L, 26L, 48L, 1L, 9L, 24L, 43L, 1L, 10L, 41L, 49L, 1L,
11L, 39L, 46L, 1L, 12L, 35L, 50L, 1L, 14L, 38L, 53L, 1L,
22L, 52L, 57L, 1L, 20L, 47L, 58L, 1L, 17L, 51L, 60L, 1L,
21L, 45L, 59L, 1L, 15L, 34L, 54L, 1L, 19L, 32L, 1L, 16L,
31L, 56L, 1L, 18L, 36L, 55L, 1L, 7L, 13L, 27L, 1L, 6L, 29L,
25L, 1L, 5L, 30L, 23L, 1L, 2L, 33L, 28L), .Label = c("0",
"0,0089", "0,0105", "0,0136", "0,0144", "0,0147", "0,0152",
"0,0201", "0,0265", "0,0339", "0,0345", "0,0371", "0,045",
"0,0463", "0,0569", "0,0583", "0,0587", "0,0596", "0,0602",
"0,0649", "0,069", "0,0834", "0,1264", "0,1829", "0,1897",
"0,1909", "0,1974", "0,2309", "0,3", "0,344", "0,3491", "0,3547",
"0,364", "0,3729", "0,3756", "0,3932", "0,4357", "0,4361",
"0,451", "0,4634", "0,479", "0,5109", "0,6594", "0,7182",
"0,7423", "0,7865", "0,7938", "0,8406", "0,8407", "0,9152",
"0,9347", "0,9675", "1", "1,0908", "1,1366", "1,1465", "1,6905",
"1,7799", "1,8875", "1,9493"), class = "factor")), class = "data.frame", row.names = c(NA, -79L))
#Pretreat dataframe by creating factors for every column.
STAT<- read.table("Biomass.txt", header=TRUE, fill=TRUE)
SNa <- as.factor(STAT$Sname)
SNu <- as.factor(STAT$Snumber)
Day <- as.numeric(STAT$Day)
Rep <- as.numeric(STAT$Replica)
Dif <- as.numeric(STAT$Diff)
Sum <- as.numeric(STAT$Sum)
SAr10 <- as.numeric(STAT$Sumarea10)
SAr <- c(SAr10/10)
DW <- as.numeric(STAT$Dweight)
WW <- as.numeric(STAT$Wweight)
#I first tried to plot Dataone (`SAr`) as follows:
points1 <- geom_point(aes(colour = SNa), size =.8)
lines1 <- geom_smooth(method = loess, aes(colour = SNa), size =.5, se=TRUE, alpha=.2)
text1 <- labs(title=expression (Biomass~and~CO[2]~production~summed~ area), x=expression(Time~" "~(days)), y=expression(CO[2]~production~sum~" "~(ppm)))
g <- ggplot(data=STAT, aes(x=Day, y=SAr, group=SNa, fill=SNa, colour=SNa), par(mar=Marg))
g <- g + points1 + lines1 + text1
This is the result:
So far so good, but here start the problems.
1. SHADE
I would like to shade the area below the graphs. I have tried:
area1 <- geom_ribbon(data = STAT[STAT$Snumber == '1',],
aes(ymin = 0, ymax = predict(loess(Day ~ Sumarea))),
alpha = 0.3, fill = "#114477")
g <- g + points1 + lines1 + text1 + area1
plot(g) returns:
Error in loess(Day ~ Sumarea) : predictors must all be numeric
I have tried to put the numeric factors I created at the beginning, but Day and SAr do not have the same length
Error in model.frame.default(formula = Day ~ SAr) :
variable lengths differ (found for 'SAr').
I have also tried to make this with a density function and a geom_area but none of them resulted in what I wanted.
2. PLOT DATA2
I want the Datatwo (DW) attachted to the secondary y axis.
#Secondary y axis
y2 <- scale_y_continuous(sec.axis = sec_axis(~./150, name = "Dry
weight"))
#Grouped bars per time point
bars2 <- geom_bar(aes(factor(Day), DW), stat="identity", position = "dodge")
g <- g + points1 + lines1 + text1 + y2 + bars2
plot(g) returns:
Error: Discrete value supplied to continuous scale
I know that there cannot be a continuous scale on variable of the factor type (Plotting with ggplot2: "Error: Discrete value supplied to continuous scale" on categorical y-axis). But their solution does not work for me either.
ggplot(STAT[STAT$SNu == 1,], aes(x = STAT$Day, y = STAT$DW)) +
scale_x_continuous(limits=c(0,7)) +
scale_y_continuous(limits=c(0,1))
Returning
Error: Aesthetics must be either length 1 or the same as the data
(79): x, y`
If anyone can help me with this two issues it would be super appreciated. As I am new in this code, I also encourage you to ask me about specific details that might have relevance and I did not add in the post. Also any improvement in my code even not related with my questions would be very welcome.

Related

How can I remove the legend from this boxplot in ggplot? [duplicate]

This question already has answers here:
Remove legend ggplot 2.2
(4 answers)
Closed 3 years ago.
Please find My Data below.
How can I remove the red, encircled legend from my boxplot?
I wish to keep the same colors and design. I have tried numerous different solutions, but this has unfortunately not solved the problem.
This might be kinda basic, but simply can't figure out how to solve this. I hope you can help - thanks in advance!
My script is:
df <- data.frame(x = as.factor(c(p$WHO.Grade)),
y = c(p$ki67pro),
f = rep(c("Ki67pro"), c(nrow(p))))
ggplot(df) +
geom_boxplot(aes(x, y, fill = f, colour = f), outlier.alpha = 0, position = position_dodge(width = 0.78)) +
scale_x_discrete(name = "", label=c("WHO-I\nn=108","WHO-II\nn=34","WHO-III\nn=1")) +
scale_y_continuous(name="Ki-67 proliferative index", breaks=seq(0,30,5), limits=c(0,30)) +
stat_boxplot(aes(x, y, colour = f), geom = "errorbar", width = 0.3,position = position_dodge(0.7753)) +
geom_point(aes(x, y, fill = f, colour = f), size = 3, shape = 21, position = position_jitterdodge()) +
scale_fill_manual(values = c("#52C1C76D"), name = "",
labels = c("\nTotal cohort\nn=159\n ")) +
scale_colour_manual(values = c("#51BFC4"), name = "",
labels = c("\nTotal cohort\nn=159\n "))
And My Data
p <- structure(list(WHO.Grade = c(1L, 2L, 1L, 1L, 1L, 1L, 3L, 2L,
1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), ki67pro = c(1L, 12L, 3L, 3L, 5L,
3L, 20L, 25L, 7L, 4L, 5L, 12L, 3L, 15L, 4L, 5L, 7L, 8L, 3L, 12L,
10L, 4L, 10L, 7L, 3L, 2L, 3L, 7L, 4L, 7L, 10L, 4L, 5L, 5L, 3L,
5L, 2L, 5L, 3L, 3L, 3L, 4L, 4L, 3L, 2L, 5L, 1L, 5L, 2L, 3L, 1L,
2L, 3L, 3L, 5L, 4L, 20L, 5L, 0L, 4L, 3L, 0L, 3L, 4L, 1L, 2L,
20L, 2L, 3L, 5L, 4L, 8L, 1L, 4L, 5L, 4L, 3L, 6L, 12L, 3L, 4L,
4L, 2L, 5L, 3L, 3L, 3L, 2L, 5L, 4L, 2L, 3L, 4L, 3L, 3L, 2L, 2L,
4L, 7L, 4L, 3L, 4L, 2L, 3L, 6L, 2L, 3L, 10L, 5L, 10L, 3L, 10L,
3L, 4L, 5L, 2L, 4L, 3L, 4L, 4L, 4L, 5L, 3L, 12L, 5L, 4L, 3L,
2L, 4L, 3L, 4L, 2L, 1L, 6L, 1L, 4L, 12L, 3L, 4L, 3L, 2L, 6L,
5L, 4L, 3L, 4L, 4L, 4L, 3L, 5L, 4L, 5L, 4L, 1L, 3L, 3L, 4L, 0L,
3L)), class = "data.frame", row.names = c(1L, 2L, 3L, 9L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 18L, 19L, 20L, 21L, 22L, 23L, 24L,
25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L,
38L, 39L, 40L, 41L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L,
53L, 54L, 55L, 57L, 59L, 60L, 61L, 62L, 63L, 64L, 65L, 66L, 67L,
68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 76L, 77L, 78L, 79L, 80L,
81L, 82L, 83L, 84L, 85L, 87L, 89L, 90L, 91L, 92L, 93L, 94L, 96L,
97L, 98L, 99L, 100L, 101L, 102L, 103L, 104L, 105L, 106L, 107L,
109L, 110L, 111L, 112L, 113L, 114L, 115L, 116L, 117L, 118L, 119L,
120L, 121L, 123L, 124L, 125L, 126L, 127L, 128L, 130L, 131L, 132L,
133L, 134L, 135L, 136L, 137L, 138L, 139L, 140L, 141L, 142L, 143L,
144L, 145L, 146L, 147L, 148L, 149L, 150L, 151L, 152L, 153L, 154L,
155L, 156L, 157L, 158L, 159L, 160L, 161L, 162L, 163L, 164L, 165L,
166L, 167L, 168L, 169L, 170L, 171L, 172L, 173L, 174L, 175L))

You can use theme() as follows:
... + theme(legend.position = "none")
This should eliminate the legend
reference: https://www.datanovia.com/en/blog/ggplot-legend-title-position-and-labels/

Taking the mean of a group of data that is dependent on multiple other columns in the same row in R

I want to take the mean of animal abundance every 4 quadrats. The station # and the areaContro # should match for averaged groups of quadrats
Fairly new to R
My attempt:
aaply(commData, station ~ areaContro & quadrat ~ station, .fun = mean, .expand = TRUE,.inform = TRUE, .drop = TRUE)
The error: Error in splitter_a(.data, .margins, .expand) :
'pairlist' object cannot be coerced to type 'integer'
structure(list(areaContro = c(29L, 29L, 29L, 29L, 29L, 29L, 29L,
29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L,
29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L), station = c(1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L,
5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L), quadrat = c(1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L), latitude = c(42.12521667,
42.12658333, 42.12681667, 42.12705, 42.12466667, 42.12631667,
42.12671667, 42.1272, 42.12671667, 42.12682833, 42.12726166,
42.12794499, 42.12771667, 42.1285, 42.12871667, 42.12896667,
42.12691667, 42.12748333, 42.12763333, 42.12785, 42.127, 42.12711818,
42.12735152, 42.12755152, 42.1264341, 42.1265095, 42.12664427,
42.12679211, 42.12703333, 42.12725), longitude = c(-67.33001667,
-67.32823333, -67.3281, -67.3279, -67.31041667, -67.30906667,
-67.30876667, -67.30843333, -67.29326667, -67.2942027, -67.29311937,
-67.2929027, -67.27731667, -67.2768, -67.27655, -67.27628333,
-67.25879572, -67.25684572, -67.25647905, -67.25616238, -67.2359,
-67.23562265, -67.23512265, -67.23472265, -67.21841245, -67.21825004,
-67.21814781, -67.21796007, -67.19853333, -67.19653333), scallops = c(1L,
0L, 0L, 0L, 4L, 0L, 7L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 2L, 0L, 2L,
2L, 2L, 2L, 45L, 11L, 4L, 8L, 12L, 9L, 11L, 11L, 4L, 10L), clappers = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L)), .Names = c("areaContro",
"station", "quadrat", "latitude", "longitude", "scallops", "clappers"
), row.names = c(NA, 30L), class = "data.frame")

If you are new to R I strongly recommend taking a look at the tidyverse in particular dplyr for common data manipulation tasks.
Your second argument of aaply is incorrect. According to the documentation it accepts a vector given the subscripts to split the data (e.g. 1 for rows). Also note that it accepts an array and results in an array.
I'm confused about what variable(s) you want to average over and what the average should be conditioned on. I think you want the average grouped by station and quadrat (and areaContro but this is constant)
Base R:
tapply(data$scallops, data[c("station", "quadrat")], mean)
dplyr:
data %>% group_by(station, quadrat) %>%
summarise(scallops_mean = mean(scallops))

I think that what you're trying to do could be accomplished simply like so:
If you have:
commData <- structure(list(areaContro = c(29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L), station = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L), quadrat = c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L), latitude = c(42.12521667, 42.12658333, 42.12681667, 42.12705, 42.12466667, 42.12631667, 42.12671667, 42.1272, 42.12671667, 42.12682833, 42.12726166, 42.12794499, 42.12771667, 42.1285, 42.12871667, 42.12896667, 42.12691667, 42.12748333, 42.12763333, 42.12785, 42.127, 42.12711818, 42.12735152, 42.12755152, 42.1264341, 42.1265095, 42.12664427, 42.12679211, 42.12703333, 42.12725), longitude = c(-67.33001667, -67.32823333, -67.3281, -67.3279, -67.31041667, -67.30906667, -67.30876667, -67.30843333, -67.29326667, -67.2942027, -67.29311937, -67.2929027, -67.27731667, -67.2768, -67.27655, -67.27628333, -67.25879572, -67.25684572, -67.25647905, -67.25616238, -67.2359, -67.23562265, -67.23512265, -67.23472265, -67.21841245, -67.21825004, -67.21814781, -67.21796007, -67.19853333, -67.19653333), scallops = c(1L, 0L, 0L, 0L, 4L, 0L, 7L, 3L, 3L, 3L, 1L, 2L, 2L, 1L, 2L, 0L, 2L, 2L, 2L, 2L, 45L, 11L, 4L, 8L, 12L, 9L, 11L, 11L, 4L, 10L), clappers = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 0L, 0L, 0L, 0L)), .Names = c("areaContro", "station", "quadrat", "latitude", "longitude", "scallops", "clappers" ), row.names = c(NA, 30L), class = "data.frame")
Check out ?aggregate:
For scallops and only dependent on quadrats - just to show you how the function works:
scallop <- aggregate(commData$scallops, by = list(commData$quadrat), FUN = mean)
For all the requested variables:
full_scallop <- aggregate(commData$scallops, by = list(commData$quadrat, commData$areaContro, commData$station), FUN = mean)
Everything all together could look something like this:
aggregate(cbind(commData$scallops, commData$clappers)~commData$quadrat+commData$areaContro+commData$station, FUN = mean)

Decision Tree Keeps Using Y-variable in Tree Decision Making

I'm using C5.0 to make a decision tree, and it's using my class label in the tree. A snippet of my data is below.
trainX
V1 V2 V3 V4 V5 V6
1 39 State-gov 77516 Bachelors 13 Never-married
2 50 Self-emp-not-inc 83311 Bachelors 13 Married-civ-spouse
3 38 Private 215646 HS-grad 9 Divorced
4 53 Private 234721 11th 7 Married-civ-spouse
5 28 Private 338409 Bachelors 13 Married-civ-spouse
V7 V8 V9 V10 V11 V12 V13 V14
1 Adm-clerical Not-in-family White Male 2174 0 40 United-States
2 Exec-managerial Husband White Male 0 0 13 United-States
3 Handlers-cleaners Not-in-family White Male 0 0 40 United-States
4 Handlers-cleaners Husband Black Male 0 0 40 United-States
5 Prof-specialty Wife Black Female 0 0 40 Cuba
trainY
[1] <=50K <=50K <=50K <=50K <=50K
There are cases in my data of >50K as well, this snippet of 5 just did not contain any.
When I make my tree, this is the code I use
library(C50)
trainX = X[1:100,]
trainY = Y[1:100]
testX = X[101:150,]
testY = Y[101:150]
model = C5.0(trainX, trainY)
summary(model)
And the output I get is...
Decision tree:
<=50K (100/25)
Evaluation on training data (100 cases):
Decision Tree
----------------
Size Errors
1 25(25.0%) <<
(a) (b) <-classified as
---- ----
75 (a): class <=50K
25 (b): class >50K
What am I doing wrong that it's using the classification as part of the tree?
EDIT - DPUTS below of Head. Still gives me the same issue, where its making a Decision Tree using the split as <=50K or >50K, which is my "Y" output and thus shouldn't be part of the decision making process.
trainX
structure(list(V1 = c(39L, 50L, 38L, 53L, 28L, 37L), V2 = structure(c(8L,
7L, 5L, 5L, 5L, 5L), .Label = c(" ?", " Federal-gov", " Local-gov",
" Never-worked", " Private", " Self-emp-inc", " Self-emp-not-inc",
" State-gov", " Without-pay"), class = "factor"), V3 = c(77516L,
83311L, 215646L, 234721L, 338409L, 284582L), V4 = structure(c(10L,
10L, 12L, 2L, 10L, 13L), .Label = c(" 10th", " 11th", " 12th",
" 1st-4th", " 5th-6th", " 7th-8th", " 9th", " Assoc-acdm", " Assoc-voc",
" Bachelors", " Doctorate", " HS-grad", " Masters", " Preschool",
" Prof-school", " Some-college"), class = "factor"), V5 = c(13L,
13L, 9L, 7L, 13L, 14L), V6 = structure(c(5L, 3L, 1L, 3L, 3L,
3L), .Label = c(" Divorced", " Married-AF-spouse", " Married-civ-spouse",
" Married-spouse-absent", " Never-married", " Separated", " Widowed"
), class = "factor"), V7 = structure(c(2L, 5L, 7L, 7L, 11L, 5L
), .Label = c(" ?", " Adm-clerical", " Armed-Forces", " Craft-repair",
" Exec-managerial", " Farming-fishing", " Handlers-cleaners",
" Machine-op-inspct", " Other-service", " Priv-house-serv", " Prof-specialty",
" Protective-serv", " Sales", " Tech-support", " Transport-moving"
), class = "factor"), V8 = structure(c(2L, 1L, 2L, 1L, 6L, 6L
), .Label = c(" Husband", " Not-in-family", " Other-relative",
" Own-child", " Unmarried", " Wife"), class = "factor"), V9 = structure(c(5L,
5L, 5L, 3L, 3L, 5L), .Label = c(" Amer-Indian-Eskimo", " Asian-Pac-Islander",
" Black", " Other", " White"), class = "factor"), V10 = structure(c(2L,
2L, 2L, 2L, 1L, 1L), .Label = c(" Female", " Male"), class = "factor"),
V11 = c(2174L, 0L, 0L, 0L, 0L, 0L), V12 = c(0L, 0L, 0L, 0L,
0L, 0L), V13 = c(40L, 13L, 40L, 40L, 40L, 40L), V14 = structure(c(40L,
40L, 40L, 40L, 6L, 40L), .Label = c(" ?", " Cambodia", " Canada",
" China", " Columbia", " Cuba", " Dominican-Republic", " Ecuador",
" El-Salvador", " England", " France", " Germany", " Greece",
" Guatemala", " Haiti", " Holand-Netherlands", " Honduras",
" Hong", " Hungary", " India", " Iran", " Ireland", " Italy",
" Jamaica", " Japan", " Laos", " Mexico", " Nicaragua", " Outlying-US(Guam-USVI-etc)",
" Peru", " Philippines", " Poland", " Portugal", " Puerto-Rico",
" Scotland", " South", " Taiwan", " Thailand", " Trinadad&Tobago",
" United-States", " Vietnam", " Yugoslavia"), class = "factor")), .Names = c("V1",
"V2", "V3", "V4", "V5", "V6", "V7", "V8", "V9", "V10", "V11",
"V12", "V13", "V14"), row.names = c(NA, 6L), class = "data.frame")
trainY
structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c(" <=50K", " >50K"
), class = "factor")
After reading in trainX, trainY, the easiest way to reproduce this problem would be
library(C50)
test = C5.0(x=trainX, y=trainY)
My actual train Y :
structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 2L, 1L, 2L, 2L, 1L, 1L), .Label = c(" <=50K", " >50K"), class = "factor")
My actual trainX
structure(list(age = c(39L, 50L, 38L, 53L, 28L, 37L, 49L, 52L,
31L, 42L, 37L, 30L, 23L, 32L, 40L, 34L, 25L, 32L, 38L, 43L, 40L,
54L, 35L, 43L, 59L, 56L, 19L, 54L, 39L, 49L, 23L, 20L, 45L, 30L,
22L, 48L, 21L, 19L, 31L, 48L, 31L, 53L, 24L, 49L, 25L, 57L, 53L,
44L, 41L, 29L, 25L, 18L, 47L, 50L, 47L, 43L, 46L, 35L, 41L, 30L,
30L, 32L, 48L, 42L, 29L, 36L, 28L, 53L, 49L, 25L, 19L, 31L, 29L,
23L, 79L, 27L, 40L, 67L, 18L, 31L, 18L, 52L, 46L, 59L, 44L, 53L,
49L, 33L, 30L, 43L, 57L, 37L, 28L, 30L, 34L, 29L, 48L, 37L, 48L,
32L), workClass = structure(c(8L, 7L, 5L, 5L, 5L, 5L, 5L, 7L,
5L, 5L, 5L, 8L, 5L, 5L, 5L, 5L, 7L, 5L, 5L, 7L, 5L, 5L, 2L, 5L,
5L, 3L, 5L, 1L, 5L, 5L, 3L, 5L, 5L, 2L, 8L, 5L, 5L, 5L, 5L, 7L,
5L, 7L, 5L, 5L, 5L, 2L, 5L, 5L, 8L, 5L, 5L, 5L, 5L, 2L, 6L, 5L,
5L, 5L, 5L, 5L, 5L, 1L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 1L, 5L, 5L,
7L, 5L, 5L, 5L, 5L, 1L, 5L, 3L, 5L, 5L, 5L, 5L, 5L, 5L, 3L, 5L,
5L, 2L, 5L, 5L, 5L, 5L, 3L, 3L, 7L, 5L, 5L, 2L), .Label = c(" ?",
" Federal-gov", " Local-gov", " Never-worked", " Private", " Self-emp-inc",
" Self-emp-not-inc", " State-gov", " Without-pay"), class = "factor"),
fnlwgt = c(77516L, 83311L, 215646L, 234721L, 338409L, 284582L,
160187L, 209642L, 45781L, 159449L, 280464L, 141297L, 122272L,
205019L, 121772L, 245487L, 176756L, 186824L, 28887L, 292175L,
193524L, 302146L, 76845L, 117037L, 109015L, 216851L, 168294L,
180211L, 367260L, 193366L, 190709L, 266015L, 386940L, 59951L,
311512L, 242406L, 197200L, 544091L, 84154L, 265477L, 507875L,
88506L, 172987L, 94638L, 289980L, 337895L, 144361L, 128354L,
101603L, 271466L, 32275L, 226956L, 51835L, 251585L, 109832L,
237993L, 216666L, 56352L, 147372L, 188146L, 59496L, 293936L,
149640L, 116632L, 105598L, 155537L, 183175L, 169846L, 191681L,
200681L, 101509L, 309974L, 162298L, 211678L, 124744L, 213921L,
32214L, 212759L, 309634L, 125927L, 446839L, 276515L, 51618L,
159937L, 343591L, 346253L, 268234L, 202051L, 54334L, 410867L,
249977L, 286730L, 212563L, 117747L, 226296L, 115585L, 191277L,
202683L, 171095L, 249409L), education = structure(c(10L,
10L, 12L, 2L, 10L, 13L, 7L, 12L, 13L, 10L, 16L, 10L, 10L,
8L, 9L, 6L, 12L, 12L, 2L, 13L, 11L, 12L, 7L, 2L, 12L, 10L,
12L, 16L, 12L, 12L, 8L, 16L, 10L, 16L, 16L, 2L, 16L, 12L,
16L, 8L, 7L, 10L, 10L, 12L, 12L, 10L, 12L, 13L, 9L, 9L, 16L,
12L, 15L, 10L, 12L, 16L, 5L, 9L, 12L, 12L, 10L, 6L, 12L,
11L, 16L, 12L, 16L, 12L, 16L, 16L, 16L, 10L, 10L, 16L, 16L,
12L, 8L, 1L, 2L, 6L, 12L, 10L, 12L, 12L, 12L, 12L, 12L, 13L,
7L, 11L, 9L, 16L, 16L, 12L, 10L, 16L, 11L, 16L, 8L, 12L), .Label = c(" 10th",
" 11th", " 12th", " 1st-4th", " 5th-6th", " 7th-8th", " 9th",
" Assoc-acdm", " Assoc-voc", " Bachelors", " Doctorate",
" HS-grad", " Masters", " Preschool", " Prof-school", " Some-college"
), class = "factor"), educationNum = c(13L, 13L, 9L, 7L,
13L, 14L, 5L, 9L, 14L, 13L, 10L, 13L, 13L, 12L, 11L, 4L,
9L, 9L, 7L, 14L, 16L, 9L, 5L, 7L, 9L, 13L, 9L, 10L, 9L, 9L,
12L, 10L, 13L, 10L, 10L, 7L, 10L, 9L, 10L, 12L, 5L, 13L,
13L, 9L, 9L, 13L, 9L, 14L, 11L, 11L, 10L, 9L, 15L, 13L, 9L,
10L, 3L, 11L, 9L, 9L, 13L, 4L, 9L, 16L, 10L, 9L, 10L, 9L,
10L, 10L, 10L, 13L, 13L, 10L, 10L, 9L, 12L, 6L, 7L, 4L, 9L,
13L, 9L, 9L, 9L, 9L, 9L, 14L, 5L, 16L, 11L, 10L, 10L, 9L,
13L, 10L, 16L, 10L, 12L, 9L), marital = structure(c(5L, 3L,
1L, 3L, 3L, 3L, 4L, 3L, 5L, 3L, 3L, 3L, 5L, 5L, 3L, 3L, 5L,
5L, 3L, 1L, 3L, 6L, 3L, 3L, 1L, 3L, 5L, 3L, 1L, 3L, 5L, 5L,
1L, 3L, 3L, 5L, 5L, 2L, 3L, 3L, 3L, 3L, 3L, 6L, 5L, 3L, 3L,
1L, 3L, 5L, 3L, 5L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
3L, 3L, 1L, 3L, 1L, 3L, 3L, 5L, 5L, 6L, 3L, 5L, 3L, 5L, 3L,
3L, 5L, 3L, 5L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 5L, 5L, 3L, 1L,
1L, 3L, 3L, 5L, 3L, 3L, 1L, 5L), .Label = c(" Divorced",
" Married-AF-spouse", " Married-civ-spouse", " Married-spouse-absent",
" Never-married", " Separated", " Widowed"), class = "factor"),
occ = structure(c(2L, 5L, 7L, 7L, 11L, 5L, 9L, 5L, 11L, 5L,
5L, 11L, 2L, 13L, 4L, 15L, 6L, 8L, 13L, 5L, 11L, 9L, 6L,
15L, 14L, 14L, 4L, 1L, 5L, 4L, 12L, 13L, 5L, 2L, 9L, 8L,
8L, 2L, 13L, 11L, 8L, 11L, 14L, 2L, 7L, 11L, 8L, 5L, 4L,
11L, 5L, 9L, 11L, 5L, 5L, 14L, 8L, 9L, 2L, 8L, 13L, 1L, 15L,
11L, 14L, 4L, 2L, 2L, 5L, 1L, 11L, 13L, 13L, 8L, 11L, 9L,
2L, 1L, 9L, 6L, 13L, 9L, 9L, 13L, 4L, 13L, 12L, 11L, 13L,
11L, 11L, 4L, 8L, 13L, 12L, 7L, 11L, 13L, 5L, 9L), .Label = c(" ?",
" Adm-clerical", " Armed-Forces", " Craft-repair", " Exec-managerial",
" Farming-fishing", " Handlers-cleaners", " Machine-op-inspct",
" Other-service", " Priv-house-serv", " Prof-specialty",
" Protective-serv", " Sales", " Tech-support", " Transport-moving"
), class = "factor"), relationship = structure(c(2L, 1L,
2L, 1L, 6L, 6L, 2L, 1L, 2L, 1L, 1L, 1L, 4L, 2L, 1L, 1L, 4L,
5L, 1L, 5L, 1L, 5L, 1L, 1L, 5L, 1L, 4L, 1L, 2L, 1L, 2L, 4L,
4L, 4L, 1L, 5L, 4L, 6L, 1L, 1L, 1L, 1L, 1L, 5L, 2L, 1L, 1L,
5L, 1L, 2L, 6L, 4L, 6L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
1L, 1L, 2L, 1L, 2L, 6L, 1L, 4L, 4L, 4L, 1L, 2L, 3L, 4L, 1L,
1L, 4L, 1L, 2L, 1L, 6L, 1L, 2L, 4L, 1L, 1L, 2L, 2L, 1L, 5L,
5L, 6L, 1L, 2L, 1L, 1L, 5L, 4L), .Label = c(" Husband", " Not-in-family",
" Other-relative", " Own-child", " Unmarried", " Wife"), class = "factor"),
race = structure(c(5L, 5L, 5L, 3L, 3L, 5L, 3L, 5L, 5L, 5L,
3L, 2L, 5L, 3L, 2L, 1L, 5L, 5L, 5L, 5L, 5L, 3L, 3L, 5L, 5L,
5L, 5L, 2L, 5L, 5L, 5L, 3L, 5L, 5L, 3L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 3L, 5L, 5L, 5L, 5L, 4L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 3L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 3L, 2L, 5L, 5L, 5L, 5L, 5L, 3L
), .Label = c(" Amer-Indian-Eskimo", " Asian-Pac-Islander",
" Black", " Other", " White"), class = "factor"), sex = structure(c(2L,
2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L,
2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L), .Label = c(" Female",
" Male"), class = "factor"), capGain = c(2174L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 14084L, 5178L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 5013L, 2407L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 14344L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), capLoss = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 2042L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 1408L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1902L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 1573L, 0L, 0L, 1902L, 0L, 0L, 0L), hours = c(40L,
13L, 40L, 40L, 40L, 40L, 16L, 45L, 50L, 40L, 80L, 40L, 30L,
50L, 40L, 45L, 35L, 40L, 50L, 45L, 60L, 20L, 40L, 40L, 40L,
40L, 40L, 60L, 80L, 40L, 52L, 44L, 40L, 40L, 15L, 40L, 40L,
25L, 38L, 40L, 43L, 40L, 50L, 40L, 35L, 40L, 38L, 40L, 40L,
43L, 40L, 30L, 60L, 55L, 60L, 40L, 40L, 40L, 48L, 40L, 40L,
40L, 40L, 45L, 58L, 40L, 40L, 40L, 50L, 40L, 32L, 40L, 70L,
40L, 20L, 40L, 40L, 2L, 22L, 40L, 30L, 40L, 40L, 48L, 40L,
35L, 40L, 50L, 40L, 50L, 40L, 40L, 25L, 35L, 40L, 50L, 60L,
48L, 40L, 40L), country = structure(c(40L, 40L, 40L, 40L,
6L, 40L, 24L, 40L, 40L, 40L, 40L, 20L, 40L, 40L, 1L, 27L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 36L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 34L, 40L, 40L, 1L, 40L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 1L,
17L, 40L, 40L, 40L, 27L, 34L, 40L, 40L, 40L, 1L, 40L, 40L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 27L,
40L, 40L, 40L, 40L, 40L, 6L, 40L, 40L, 40L, 40L, 40L, 40L,
40L, 40L, 40L, 40L, 40L, 1L, 40L, 40L, 40L, 40L, 10L, 40L
), .Label = c(" ?", " Cambodia", " Canada", " China", " Columbia",
" Cuba", " Dominican-Republic", " Ecuador", " El-Salvador",
" England", " France", " Germany", " Greece", " Guatemala",
" Haiti", " Holand-Netherlands", " Honduras", " Hong", " Hungary",
" India", " Iran", " Ireland", " Italy", " Jamaica", " Japan",
" Laos", " Mexico", " Nicaragua", " Outlying-US(Guam-USVI-etc)",
" Peru", " Philippines", " Poland", " Portugal", " Puerto-Rico",
" Scotland", " South", " Taiwan", " Thailand", " Trinadad&Tobago",
" United-States", " Vietnam", " Yugoslavia"), class = "factor")), .Names = c("age",
"workClass", "fnlwgt", "education", "educationNum", "marital",
"occ", "relationship", "race", "sex", "capGain", "capLoss", "hours",
"country"), row.names = c(NA, 100L), class = "data.frame")

The code you provided constructs a factor with 1 level (<=50k) because the first vector input contains only 1Ls. You should assign these labels accordingly or use an easier way to construct your response variable - something like trainY <- as.factor(...).
I changed the way trainY is constructed to:
y <- structure(c(1L, 2L, 1L, 1L, 2L, 1L), .Label = c(" <=50K", " >50K"), class = "factor")
and after re-training the tree with same commands i got:
Decision tree:
V14 = Cuba: >50K (1)
V14 in {?,Cambodia,Canada,China,Columbia,Dominican-Republic,Ecuador,
El-Salvador,England,France,Germany,Greece,Guatemala,Haiti,
Holand-Netherlands,Honduras,Hong,Hungary,India,Iran,Ireland,Italy,
Jamaica,Japan,Laos,Mexico,Nicaragua,Outlying-US(Guam-USVI-etc),Peru,
Philippines,Poland,Portugal,Puerto-Rico,Scotland,South,Taiwan,Thailand,
Trinadad&Tobago,United-States,Vietnam,Yugoslavia}: <=50K (5/1)
Make sure you don't have only one class in the response when passing args to C5.0. hth
UPDATE
After plotting some of the predictors vs response I noticed that education and educationNum show the clearest division in the data (Doctorate implies >50K immediately). Next step was to tweak some of the very useful C5.0 Control options - they are well documented in the C5.0 package documentation and the official informal tutorial page - check them out they give you broad control over the classification controls.
For example:
C5.0(x = trainX,y = trainY,control = C5.0Control(subset = T, winnow = T,minCases = 4,fuzzyThreshold = T))
Decision tree:
educationNum <= 13 (14.5): <=50K (95/20)
educationNum >= 16 (14.5): >50K (5)
similiarly, doing some "feature engineering" which in this case meant just leaving out some of the columns from the original dataframe produced :
C5.0(x = trainX[ ,c(1:5, 9:13)], y = trainY)
Decision tree:
educationNum <= 14: <=50K (95/20)
educationNum > 14: >50K (5)
I believe that there is no one general "out of the box" C5.0 defaults setting that would produce satisfying results for all kinds of problems, so it really comes down to trying out different parameter settings, features etc...but as with all things R there is plenty of material around to give you some direction.

Linear model with repeated measures factors

I have a dataframe df
df<-structure(list(subject = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L,
23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L,
36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L,
49L, 50L, 51L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L,
25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L,
38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L,
51L), sex = c(1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L,
1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L,
2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L,
2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L), age = c(29L, 54L, 67L,
36L, 48L, 37L, 25L, 46L, 37L, 33L, 25L, 26L, 28L, 59L, 46L, 50L,
55L, 56L, 37L, 30L, 38L, 30L, 50L, 39L, 29L, 46L, 48L, 46L, 55L,
32L, 66L, 35L, 48L, 54L, 38L, 31L, 42L, 36L, 27L, 63L, 45L, 31L,
26L, 38L, 43L, 52L, 36L, 43L, 65L, 46L, 42L, 29L, 54L, 67L, 36L,
48L, 37L, 25L, 46L, 37L, 33L, 25L, 26L, 28L, 59L, 46L, 50L, 55L,
56L, 37L, 30L, 38L, 30L, 50L, 39L, 29L, 46L, 48L, 46L, 55L, 32L,
66L, 35L, 48L, 54L, 38L, 31L, 42L, 36L, 27L, 63L, 45L, 31L, 26L,
38L, 43L, 52L, 36L, 43L, 65L, 46L, 42L), edu = c(4L, 3L, 3L,
3L, 4L, 2L, 3L, 3L, 1L, 3L, 4L, 4L, 5L, 1L, 1L, 2L, 2L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 2L, 2L, 1L, 2L, 2L, 4L, 2L, 4L, 4L, 3L, 3L,
4L, 5L, 3L, 3L, 4L, 1L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 6L, 1L, 3L,
4L, 3L, 3L, 3L, 4L, 2L, 3L, 3L, 1L, 3L, 4L, 4L, 5L, 1L, 1L, 2L,
2L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 2L, 1L, 2L, 2L, 4L, 2L, 4L,
4L, 3L, 3L, 4L, 5L, 3L, 3L, 4L, 1L, 1L, 3L, 1L, 3L, 1L, 3L, 1L,
6L, 1L, 3L), biz_exp = c(5L, 15L, 3L, 4L, 10L, 6L, 0L, 5L, 8L,
5L, 0L, 8L, 3L, 23L, 5L, 7L, 5L, 11L, 4L, 4L, 11L, 3L, 15L, 4L,
4L, 6L, 6L, 5L, 13L, 2L, 13L, 6L, 8L, 27L, 7L, 3L, 11L, 5L, 1L,
4L, 8L, 8L, 4L, 15L, 18L, 30L, 9L, 14L, 18L, 21L, 16L, 5L, 15L,
3L, 4L, 10L, 6L, 0L, 5L, 8L, 5L, 0L, 8L, 3L, 23L, 5L, 7L, 5L,
11L, 4L, 4L, 11L, 3L, 15L, 4L, 4L, 6L, 6L, 5L, 13L, 2L, 13L,
6L, 8L, 27L, 7L, 3L, 11L, 5L, 1L, 4L, 8L, 8L, 4L, 15L, 18L, 30L,
9L, 14L, 18L, 21L, 16L), turnov = c(36L, NA, 12L, 9L, 48L, 9L,
8L, 24L, 4L, 250L, NA, 600L, 6L, 6L, 10L, 10L, 5L, 4L, 250L,
200L, 50L, 150L, 48L, NA, 9L, 6L, 2L, NA, NA, 3L, 7L, 23L, 75L,
7L, 5L, NA, 20L, 450L, 5L, 32L, 21L, 12L, 6L, 4L, 24L, 7L, 10L,
12L, 12L, 14L, 18L, 36L, NA, 12L, 9L, 48L, 9L, 8L, 24L, 4L, 250L,
NA, 600L, 6L, 6L, 10L, 10L, 5L, 4L, 250L, 200L, 50L, 150L, 48L,
NA, 9L, 6L, 2L, NA, NA, 3L, 7L, 23L, 75L, 7L, 5L, NA, 20L, 450L,
5L, 32L, 21L, 12L, 6L, 4L, 24L, 7L, 10L, 12L, 12L, 14L, 18L),
loc_pr = c(1L, 1L, 1L, 6L, 1L, 6L, 4L, 1L, 8L, 5L, 1L, 3L,
1L, 1L, 1L, 1L, 5L, 8L, 2L, 1L, 1L, 1L, 1L, 2L, 8L, 2L, 4L,
4L, 2L, 2L, 2L, 1L, 4L, 5L, 4L, 4L, 4L, 4L, NA, 4L, 5L, 5L,
5L, 8L, 1L, 2L, 4L, 3L, 3L, 4L, 3L, 1L, 1L, 1L, 6L, 1L, 6L,
4L, 1L, 8L, 5L, 1L, 3L, 1L, 1L, 1L, 1L, 5L, 8L, 2L, 1L, 1L,
1L, 1L, 2L, 8L, 2L, 4L, 4L, 2L, 2L, 2L, 1L, 4L, 5L, 4L, 4L,
4L, 4L, NA, 4L, 5L, 5L, 5L, 8L, 1L, 2L, 4L, 3L, 3L, 4L, 3L
), type = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 5L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 4L, 2L, 1L, 1L, 2L, 4L, 1L, 2L, 1L,
1L, 4L, 1L, 3L, 1L, 1L, 1L, 3L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 4L, 2L, 1L,
1L, 2L, 4L, 1L, 2L, 1L, 1L, 4L, 1L, 3L, 1L, 1L, 1L, 3L, 2L
), age_rec = c(2L, 4L, 4L, 100L, 4L, 100L, 100L, 4L, 100L,
2L, 1L, 2L, 2L, 4L, 4L, 4L, 4L, 100L, 3L, 2L, 3L, 2L, 4L,
3L, 100L, 27L, 100L, 100L, 4L, 2L, 100L, 2L, 4L, 30L, 3L,
2L, 59L, 8L, 100L, 27L, 3L, 59L, 2L, 59L, 3L, 59L, 3L, 3L,
4L, 64L, 3L, 2L, 4L, 4L, 100L, 4L, 100L, 100L, 4L, 100L,
2L, 1L, 2L, 2L, 4L, 4L, 4L, 4L, 100L, 3L, 2L, 3L, 2L, 4L,
3L, 100L, 27L, 100L, 100L, 4L, 2L, 100L, 2L, 4L, 30L, 3L,
2L, 59L, 8L, 100L, 27L, 3L, 59L, 2L, 59L, 3L, 59L, 3L, 3L,
4L, 64L, 3L), biz_exp_rec = c(2L, 4L, 2L, 3L, 3L, 3L, 1L,
2L, 3L, 2L, 1L, 3L, 2L, 4L, 2L, 3L, 2L, 4L, 2L, 2L, 4L, 2L,
4L, 2L, 2L, 4L, 4L, 4L, 4L, 1L, 4L, 3L, 3L, 4L, 3L, 2L, 3L,
3L, 2L, 4L, 3L, 2L, 2L, 3L, 4L, 4L, 3L, 4L, 4L, 4L, 4L, 2L,
4L, 2L, 3L, 3L, 3L, 1L, 2L, 3L, 2L, 1L, 3L, 2L, 4L, 2L, 3L,
2L, 4L, 2L, 2L, 4L, 2L, 4L, 2L, 2L, 4L, 4L, 4L, 4L, 1L, 4L,
3L, 3L, 4L, 3L, 2L, 3L, 3L, 2L, 4L, 3L, 2L, 2L, 3L, 4L, 4L,
3L, 4L, 4L, 4L, 4L), turnov_rec = structure(c(3L, NA, 3L,
2L, 3L, 3L, 1L, 3L, 3L, 4L, NA, 4L, 2L, 2L, 2L, 2L, 2L, 4L,
4L, 4L, 3L, 4L, 3L, 5L, 2L, 3L, 3L, 2L, NA, 2L, 4L, 3L, 4L,
4L, 2L, NA, 4L, 2L, 1L, 2L, 3L, 3L, 2L, 4L, 3L, 4L, 2L, 3L,
3L, 4L, 3L, 3L, NA, 3L, 2L, 3L, 3L, 1L, 3L, 3L, 4L, NA, 4L,
2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 3L, 4L, 3L, NA, 2L, 3L, 3L,
2L, NA, 2L, 4L, 3L, 4L, 4L, 2L, NA, 4L, 2L, 1L, 2L, 3L, 3L,
2L, 4L, 3L, 4L, 2L, 3L, 3L, 4L, 3L), .Label = c("1", "2",
"3", "4", "MA"), class = "factor"), bundle = c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), investment = c(86L,
100L, 100L, 75L, 100L, 59L, 68L, 86L, 80L, 100L, 86L, 100L,
100L, 100L, 100L, 100L, 100L, 93L, 64L, 100L, 24L, 18L, 89L,
75L, 80L, 29L, 54L, 65L, 100L, 27L, 59L, 30L, 59L, 43L, 59L,
59L, 5L, 26L, 100L, 75L, 59L, 5L, 59L, 74L, 59L, 79L, 75L,
75L, 86L, 66L, 86L, 55L, 100L, 68L, 1L, 75L, 1L, 1L, 79L,
1L, 54L, 48L, 33L, 55L, 90L, 85L, 39L, 70L, 1L, 45L, 54L,
33L, 3L, 44L, 75L, 1L, 1L, 1L, 1L, 96L, 26L, 1L, 23L, 66L,
1L, 89L, 83L, 52L, 61L, 1L, 88L, 45L, 72L, 60L, 1L, 60L,
2L, 86L, 10L, 63L, 1L, 88L)), .Names = c("subject", "sex",
"age", "edu", "biz_exp", "turnov", "loc_pr", "type", "age_rec",
"biz_exp_rec", "turnov_rec", "bundle", "investment"), class = "data.frame", row.names = c(NA,
-102L))
In this dataframe investment is my dependent variable and the other variables are my independent variables. My subjects are crossed within type of bundle. First of all, I would like know whether my subjects do bundle or not (bundle= 1 means that people bundle and bundle=0 means that people do not bundle), it will have an effect on the investment.
I have done this mixed effect linear model but I am not sure if this is correct as my p-value are equal to zero.
library(nlme)
model <- lme(investment~bundle, random = ~1|subject/bundle, data=df)
I have also tried to make an anova with repeated measures as such:
aov(investment~bundle+ Error(subject/bundle), data=df)
It works but not sure if the model formula is right
Anyone could help me with that?

Change the value in a column of a dataframe depending on how many of each possible value there are

I have a dataframe looking like this:
chr <- c(1,1,1,1,1)
b1 <- c('HP', 'HP', 'CP', 'CP', 'KP')
b2 <- c('HP', 'HP', 'CP', 'CP', 'KP')
b3 <- c('CP', 'KP', 'CP', 'HP', 'CP')
b4 <- c('CP', 'KP', 'CP', 'HP', 'CP')
b5 <- c('CP', 'CP', 'KP', 'KP', 'HP')
b6 <- c('CP', 'CP', 'KP', 'KP', 'HP')
b7 <- c('CP', 'KP', 'HP', 'CP', 'CP')
b8 <- c('CP', 'KP', 'HP', 'CP', 'CP')
df <- data.frame(chr, b1,b2,b3,b4,b5,b6,b7,b8)
I want to write a function that looks at each 'b' column and asks if it contains the value 'HP'. If it does, and the other six 'b' columns contain 'CP' or 'KP', I want to change the value 'HP' into 'CP' or 'KP' depending on which is the majority. If CP is the majority, change the HP to CP. If KP is the majority, change HP to KP.
(note that the value of b1 and b2, b3 and b4 etc is always the same, so really only 4 columns need to be looked at, b1, b3, b5, and b7).
To clarify, if the columns are e.g. HP HP CP CP CP CP KP KP, I want to change the two HPs into CPs (and leave the other columns the same).
So, the example I gave would become:
chr <- c(1,1,1,1,1)
b1 <- c('CP', 'KP', 'CP', 'CP', 'KP')
b2 <- c('CP', 'KP', 'CP', 'CP', 'KP')
b3 <- c('CP', 'KP', 'CP', 'CP', 'CP')
b4 <- c('CP', 'KP', 'CP', 'CP', 'CP')
b5 <- c('CP', 'CP', 'KP', 'KP', 'CP')
b6 <- c('CP', 'CP', 'KP', 'KP', 'CP')
b7 <- c('CP', 'KP', 'CP', 'CP', 'CP')
b8 <- c('CP', 'KP', 'CP', 'CP', 'CP')
df <- data.frame(chr, b1,b2,b3,b4,b5,b6,b7,b8)
df
I have written a function (just for df$b1) with if statements, but it doesn't work.
(note the rules for whether the HP changes to KP or CP depend on how many other CPs or KPs there are):
fun <- function(df){
if(df$b1 == 'HP' && df$b3 == 'CP' && df$b5 == 'CP' && df$b7 == 'CP') {df$b1 <- 'KP'}
if(df$b1 == 'HP' && df$b3 == 'KP' && df$b5 == 'CP' && df$b7 == 'CP') {df$b1 <- 'CP'}
if(df$b1 == 'HP' && df$b3 == 'CP' && df$b5 == 'KP' && df$b7 == 'CP') {df$b1 <- 'CP'}
if(df$b1 == 'HP' && df$b3 == 'CP' && df$b5 == 'CP' && df$b7 == 'KP') {df$b1 <- 'CP'}
if(df$b1 == 'HP' && df$b3 == 'KP' && df$b5 == 'KP' && df$b7 == 'CP') {df$b1 <- 'KP'}
if(df$b1 == 'HP' && df$b3 == 'KP' && df$b5 == 'CP' && df$b7 == 'KP') {df$b1 <- 'KP'}
if(df$b1 == 'HP' && df$b3 == 'CP' && df$b5 == 'KP' && df$b7 == 'KP') {df$b1 <- 'KP'}
if(df$b1 == 'HP' && df$b3 == 'KP' && df$b5 == 'KP' && df$b7 == 'KP') {df$b1 <- 'CP'}
df$b2 <-df$b1
}
Thanks very much for any help. I'm really stuck on this one.
EDIT: This is a sample of my actual data which is more complex than the example I gave above.
structure(list(chr = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), pos_c = c(2373L, 2406L, 2418L, 2419L,
2447L, 2450L, 2468L, 2524L, 2533L, 2535L, 2536L, 2542L, 2623L,
2709L, 3942L, 11716L, 11893L, 11898L, 12190L, 12396L, 26639L,
26640L, 26643L, 26646L, 26655L, 26657L, 26661L, 26667L, 26670L,
26676L, 26679L, 26684L, 26685L, 26688L, 26694L, 26703L, 26710L,
26712L, 26713L, 26723L, 26733L, 26737L, 26738L, 26739L, 26742L,
26743L, 26748L, 26761L, 26765L, 26766L, 26778L, 26781L, 26790L,
26792L, 26796L, 26802L, 26805L, 26811L, 26814L, 26819L, 26820L,
26823L, 26829L, 26838L, 26846L, 26847L, 26848L, 26872L, 26873L,
26874L, 26877L, 26878L, 26883L, 26889L, 26901L, 26904L, 26907L,
26916L, 26923L, 26925L, 26927L, 26931L, 26937L, 26940L, 26946L,
26954L, 26958L, 26961L, 26963L, 26964L, 26970L, 26981L, 26982L,
26983L, 26991L, 26994L, 26997L, 27007L, 27008L, 27009L, 27012L,
27015L, 27018L, 27027L, 202471L, 203660L, 203668L, 203669L, 203670L,
203672L, 203678L, 203683L, 203686L, 203687L, 203690L, 203704L,
203705L, 203711L, 203714L, 203732L, 203749L, 203752L, 203754L,
203755L, 203903L, 203910L, 203911L, 203912L, 203913L, 203914L,
203915L, 203922L, 203924L, 203933L, 203937L, 203939L, 203945L,
203948L, 203951L, 203957L, 203960L, 203961L, 203963L, 203969L,
203972L, 203973L, 203974L, 203975L, 203981L, 203991L, 204220L,
204227L, 204230L, 204232L, 204242L, 204245L, 204262L, 204272L,
204278L, 204282L, 204290L), c1 = c(101L, 60L, 63L, 64L, 100L,
97L, 94L, 83L, 80L, 48L, 46L, 51L, 69L, 46L, 23L, 79L, 63L, 59L,
53L, 85L, 13L, 12L, 1L, 9L, 11L, 13L, 9L, 14L, 14L, 12L, 15L,
9L, 15L, 14L, 14L, 2L, 2L, 8L, 3L, 0L, 0L, 4L, 2L, 1L, 4L, 4L,
8L, 39L, 7L, 5L, 2L, 41L, 69L, 79L, 89L, 120L, 128L, 90L, 134L,
107L, 169L, 120L, 103L, 48L, 58L, 132L, 62L, 19L, 9L, 13L, 12L,
12L, 17L, 251L, 8L, 367L, 367L, 264L, 5L, 170L, 113L, 234L, 134L,
143L, 189L, 224L, 255L, 296L, 448L, 239L, 169L, 80L, 312L, 84L,
403L, 397L, 430L, 529L, 544L, 556L, 565L, 549L, 555L, 4L, 11L,
0L, 18L, 18L, 19L, 19L, 18L, 18L, 17L, 17L, 15L, 15L, 16L, 15L,
13L, 14L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 2L, 3L, 2L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 1L, 13L, 2L, 10L, 4L, 10L, 24L, 33L, 33L, 63L, 42L), c2 = c(101L,
60L, 63L, 64L, 100L, 97L, 94L, 83L, 80L, 48L, 46L, 51L, 69L,
46L, 23L, 79L, 63L, 59L, 53L, 85L, 13L, 12L, 1L, 9L, 11L, 13L,
9L, 14L, 14L, 12L, 15L, 9L, 15L, 14L, 14L, 2L, 2L, 8L, 3L, 0L,
0L, 4L, 2L, 1L, 4L, 4L, 8L, 39L, 7L, 5L, 2L, 41L, 69L, 79L, 89L,
120L, 128L, 90L, 134L, 107L, 169L, 120L, 103L, 48L, 58L, 132L,
62L, 19L, 9L, 13L, 12L, 12L, 17L, 251L, 8L, 367L, 367L, 264L,
5L, 170L, 113L, 234L, 134L, 143L, 189L, 224L, 255L, 296L, 448L,
239L, 169L, 80L, 312L, 84L, 403L, 397L, 430L, 529L, 544L, 556L,
565L, 549L, 555L, 4L, 11L, 0L, 18L, 18L, 19L, 19L, 18L, 18L,
17L, 17L, 15L, 15L, 16L, 15L, 13L, 14L, 0L, 1L, 0L, 0L, 0L, 0L,
0L, 2L, 3L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 13L, 2L, 10L, 4L, 10L, 24L,
33L, 33L, 63L, 42L), c3 = c(37L, 0L, 0L, 0L, 42L, 46L, 46L, 21L,
26L, 6L, 2L, 7L, 11L, 4L, 0L, 4L, 1L, 0L, 0L, 2L, 29L, 29L, 0L,
22L, 23L, 23L, 26L, 27L, 29L, 24L, 32L, 26L, 35L, 32L, 32L, 3L,
3L, 10L, 1L, 5L, 1L, 6L, 1L, 0L, 5L, 11L, 6L, 81L, 15L, 14L,
0L, 92L, 157L, 174L, 168L, 236L, 221L, 143L, 228L, 251L, 292L,
273L, 281L, 33L, 39L, 260L, 57L, 53L, 24L, 22L, 26L, 37L, 37L,
484L, 16L, 721L, 724L, 436L, 7L, 367L, 163L, 411L, 167L, 373L,
275L, 599L, 637L, 773L, 866L, 615L, 223L, 63L, 531L, 59L, 878L,
868L, 911L, 939L, 975L, 995L, 980L, 931L, 958L, 12L, 16L, 0L,
12L, 13L, 12L, 11L, 9L, 12L, 11L, 11L, 10L, 1L, 0L, 0L, 0L, 1L,
1L, 2L, 1L, 0L, 1L, 1L, 0L, 2L, 2L, 2L, 0L, 0L, 0L, 0L, 0L, 1L,
0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 0L, 1L, 1L, 2L, 28L,
5L, 28L, 3L, 12L, 39L, 40L, 50L, 90L, 80L), c4 = c(37L, 0L, 0L,
0L, 42L, 46L, 46L, 21L, 26L, 6L, 2L, 7L, 11L, 4L, 0L, 4L, 1L,
0L, 0L, 2L, 29L, 29L, 0L, 22L, 23L, 23L, 26L, 27L, 29L, 24L,
32L, 26L, 35L, 32L, 32L, 3L, 3L, 10L, 1L, 5L, 1L, 6L, 1L, 0L,
5L, 11L, 6L, 81L, 15L, 14L, 0L, 92L, 157L, 174L, 168L, 236L,
221L, 143L, 228L, 251L, 292L, 273L, 281L, 33L, 39L, 260L, 57L,
53L, 24L, 22L, 26L, 37L, 37L, 484L, 16L, 721L, 724L, 436L, 7L,
367L, 163L, 411L, 167L, 373L, 275L, 599L, 637L, 773L, 866L, 615L,
223L, 63L, 531L, 59L, 878L, 868L, 911L, 939L, 975L, 995L, 980L,
931L, 958L, 12L, 16L, 0L, 12L, 13L, 12L, 11L, 9L, 12L, 11L, 11L,
10L, 1L, 0L, 0L, 0L, 1L, 1L, 2L, 1L, 0L, 1L, 1L, 0L, 2L, 2L,
2L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L,
1L, 1L, 0L, 1L, 1L, 2L, 28L, 5L, 28L, 3L, 12L, 39L, 40L, 50L,
90L, 80L), c5 = c(96L, 77L, 74L, 72L, 96L, 96L, 92L, 80L, 79L,
79L, 76L, 76L, 66L, 55L, 64L, 78L, 110L, 100L, 165L, 171L, 38L,
41L, 2L, 38L, 33L, 37L, 21L, 40L, 41L, 21L, 37L, 19L, 45L, 30L,
22L, 22L, 28L, 34L, 30L, 31L, 25L, 40L, 34L, 33L, 34L, 46L, 41L,
96L, 48L, 51L, 38L, 93L, 152L, 155L, 155L, 193L, 195L, 189L,
222L, 213L, 284L, 248L, 230L, 56L, 70L, 208L, 82L, 85L, 67L,
64L, 64L, 83L, 71L, 495L, 77L, 570L, 577L, 499L, 55L, 292L, 236L,
352L, 244L, 296L, 351L, 391L, 440L, 483L, 653L, 417L, 194L, 57L,
460L, 57L, 538L, 520L, 573L, 731L, 753L, 770L, 772L, 757L, 761L,
35L, 73L, 66L, 70L, 70L, 71L, 70L, 74L, 79L, 82L, 83L, 85L, 69L,
68L, 71L, 71L, 70L, 73L, 72L, 72L, 74L, 103L, 107L, 106L, 107L,
109L, 106L, 106L, 105L, 106L, 105L, 108L, 104L, 105L, 106L, 106L,
103L, 112L, 112L, 113L, 112L, 109L, 114L, 114L, 115L, 120L, 114L,
97L, 125L, 103L, 124L, 107L, 116L, 145L, 139L, 138L, 177L, 139L
), c6 = c(96L, 77L, 74L, 72L, 96L, 96L, 92L, 80L, 79L, 79L, 76L,
76L, 66L, 55L, 64L, 78L, 110L, 100L, 165L, 171L, 38L, 41L, 2L,
38L, 33L, 37L, 21L, 40L, 41L, 21L, 37L, 19L, 45L, 30L, 22L, 22L,
28L, 34L, 30L, 31L, 25L, 40L, 34L, 33L, 34L, 46L, 41L, 96L, 48L,
51L, 38L, 93L, 152L, 155L, 155L, 193L, 195L, 189L, 222L, 213L,
284L, 248L, 230L, 56L, 70L, 208L, 82L, 85L, 67L, 64L, 64L, 83L,
71L, 495L, 77L, 570L, 577L, 499L, 55L, 292L, 236L, 352L, 244L,
296L, 351L, 391L, 440L, 483L, 653L, 417L, 194L, 57L, 460L, 57L,
538L, 520L, 573L, 731L, 753L, 770L, 772L, 757L, 761L, 35L, 73L,
66L, 70L, 70L, 71L, 70L, 74L, 79L, 82L, 83L, 85L, 69L, 68L, 71L,
71L, 70L, 73L, 72L, 72L, 74L, 103L, 107L, 106L, 107L, 109L, 106L,
106L, 105L, 106L, 105L, 108L, 104L, 105L, 106L, 106L, 103L, 112L,
112L, 113L, 112L, 109L, 114L, 114L, 115L, 120L, 114L, 97L, 125L,
103L, 124L, 107L, 116L, 145L, 139L, 138L, 177L, 139L), c7 = c(28L,
3L, 1L, 1L, 52L, 50L, 60L, 49L, 50L, 3L, 2L, 2L, 37L, 11L, 0L,
1L, 2L, 2L, 0L, 1L, 28L, 30L, 1L, 17L, 23L, 28L, 11L, 30L, 32L,
13L, 32L, 19L, 39L, 18L, 17L, 23L, 29L, 46L, 37L, 25L, 21L, 42L,
32L, 29L, 30L, 41L, 44L, 141L, 72L, 64L, 25L, 93L, 219L, 234L,
218L, 294L, 277L, 184L, 294L, 273L, 382L, 293L, 280L, 131L, 132L,
386L, 157L, 99L, 77L, 75L, 68L, 66L, 88L, 615L, 55L, 746L, 740L,
685L, 27L, 305L, 158L, 511L, 151L, 326L, 371L, 605L, 650L, 727L,
886L, 623L, 314L, 170L, 734L, 162L, 937L, 908L, 987L, 964L, 997L,
1002L, 1007L, 960L, 980L, 28L, 75L, 61L, 96L, 98L, 97L, 96L,
93L, 101L, 99L, 100L, 98L, 91L, 90L, 90L, 89L, 87L, 76L, 75L,
75L, 76L, 88L, 92L, 87L, 86L, 88L, 87L, 85L, 87L, 87L, 83L, 86L,
87L, 86L, 86L, 89L, 83L, 83L, 84L, 84L, 86L, 83L, 86L, 88L, 87L,
88L, 84L, 81L, 118L, 90L, 120L, 90L, 101L, 127L, 134L, 140L,
172L, 160L), c8 = c(28L, 3L, 1L, 1L, 52L, 50L, 60L, 49L, 50L,
3L, 2L, 2L, 37L, 11L, 0L, 1L, 2L, 2L, 0L, 1L, 28L, 30L, 1L, 17L,
23L, 28L, 11L, 30L, 32L, 13L, 32L, 19L, 39L, 18L, 17L, 23L, 29L,
46L, 37L, 25L, 21L, 42L, 32L, 29L, 30L, 41L, 44L, 141L, 72L,
64L, 25L, 93L, 219L, 234L, 218L, 294L, 277L, 184L, 294L, 273L,
382L, 293L, 280L, 131L, 132L, 386L, 157L, 99L, 77L, 75L, 68L,
66L, 88L, 615L, 55L, 746L, 740L, 685L, 27L, 305L, 158L, 511L,
151L, 326L, 371L, 605L, 650L, 727L, 886L, 623L, 314L, 170L, 734L,
162L, 937L, 908L, 987L, 964L, 997L, 1002L, 1007L, 960L, 980L,
28L, 75L, 61L, 96L, 98L, 97L, 96L, 93L, 101L, 99L, 100L, 98L,
91L, 90L, 90L, 89L, 87L, 76L, 75L, 75L, 76L, 88L, 92L, 87L, 86L,
88L, 87L, 85L, 87L, 87L, 83L, 86L, 87L, 86L, 86L, 89L, 83L, 83L,
84L, 84L, 86L, 83L, 86L, 88L, 87L, 88L, 84L, 81L, 118L, 90L,
120L, 90L, 101L, 127L, 134L, 140L, 172L, 160L), k1 = c(39L, 64L,
68L, 69L, 38L, 38L, 41L, 51L, 54L, 84L, 83L, 84L, 57L, 50L, 43L,
58L, 72L, 71L, 29L, 35L, 0L, 0L, 10L, 1L, 1L, 0L, 3L, 0L, 0L,
1L, 0L, 3L, 0L, 0L, 0L, 14L, 14L, 9L, 15L, 18L, 24L, 20L, 20L,
27L, 28L, 10L, 28L, 27L, 59L, 64L, 73L, 43L, 19L, 7L, 27L, 5L,
23L, 30L, 29L, 65L, 10L, 46L, 27L, 160L, 168L, 95L, 175L, 255L,
265L, 271L, 270L, 76L, 269L, 77L, 14L, 12L, 11L, 118L, 382L,
204L, 220L, 181L, 290L, 290L, 114L, 209L, 89L, 159L, 7L, 144L,
95L, 9L, 180L, 411L, 105L, 125L, 97L, 19L, 3L, 3L, 2L, 12L, 1L,
540L, 1L, 32L, 14L, 14L, 13L, 13L, 15L, 14L, 12L, 11L, 12L, 11L,
12L, 13L, 13L, 9L, 18L, 17L, 8L, 18L, 6L, 2L, 1L, 2L, 1L, 2L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 4L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 1L, 0L, 2L, 1L, 21L, 28L, 49L, 50L, 54L, 45L,
44L), k2 = c(39L, 64L, 68L, 69L, 38L, 38L, 41L, 51L, 54L, 84L,
83L, 84L, 57L, 50L, 43L, 58L, 72L, 71L, 29L, 35L, 0L, 0L, 10L,
1L, 1L, 0L, 3L, 0L, 0L, 1L, 0L, 3L, 0L, 0L, 0L, 14L, 14L, 9L,
15L, 18L, 24L, 20L, 20L, 27L, 28L, 10L, 28L, 27L, 59L, 64L, 73L,
43L, 19L, 7L, 27L, 5L, 23L, 30L, 29L, 65L, 10L, 46L, 27L, 160L,
168L, 95L, 175L, 255L, 265L, 271L, 270L, 76L, 269L, 77L, 14L,
12L, 11L, 118L, 382L, 204L, 220L, 181L, 290L, 290L, 114L, 209L,
89L, 159L, 7L, 144L, 95L, 9L, 180L, 411L, 105L, 125L, 97L, 19L,
3L, 3L, 2L, 12L, 1L, 540L, 1L, 32L, 14L, 14L, 13L, 13L, 15L,
14L, 12L, 11L, 12L, 11L, 12L, 13L, 13L, 9L, 18L, 17L, 8L, 18L,
6L, 2L, 1L, 2L, 1L, 2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 4L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 0L, 2L, 1L, 21L,
28L, 49L, 50L, 54L, 45L, 44L), k3 = c(84L, 122L, 120L, 120L,
92L, 88L, 90L, 107L, 98L, 114L, 120L, 117L, 91L, 64L, 59L, 100L,
113L, 109L, 56L, 136L, 1L, 0L, 29L, 7L, 4L, 6L, 5L, 6L, 6L, 9L,
7L, 11L, 7L, 10L, 9L, 44L, 46L, 38L, 51L, 60L, 79L, 75L, 80L,
83L, 80L, 41L, 97L, 61L, 133L, 135L, 180L, 100L, 50L, 28L, 75L,
18L, 79L, 94L, 100L, 117L, 47L, 74L, 68L, 393L, 390L, 191L, 416L,
504L, 532L, 545L, 545L, 181L, 556L, 175L, 19L, 24L, 19L, 312L,
766L, 389L, 416L, 418L, 639L, 475L, 239L, 293L, 70L, 135L, 37L,
122L, 84L, 42L, 408L, 886L, 93L, 115L, 65L, 67L, 35L, 37L, 47L,
50L, 54L, 942L, 9L, 43L, 29L, 29L, 29L, 29L, 28L, 27L, 25L, 25L,
26L, 32L, 33L, 32L, 33L, 30L, 26L, 23L, 24L, 23L, 8L, 1L, 2L,
2L, 2L, 2L, 2L, 4L, 4L, 4L, 4L, 3L, 4L, 3L, 3L, 3L, 3L, 3L, 3L,
4L, 4L, 3L, 3L, 4L, 3L, 2L, 2L, 0L, 7L, 3L, 65L, 73L, 111L, 98L,
133L, 107L, 64L), k4 = c(84L, 122L, 120L, 120L, 92L, 88L, 90L,
107L, 98L, 114L, 120L, 117L, 91L, 64L, 59L, 100L, 113L, 109L,
56L, 136L, 1L, 0L, 29L, 7L, 4L, 6L, 5L, 6L, 6L, 9L, 7L, 11L,
7L, 10L, 9L, 44L, 46L, 38L, 51L, 60L, 79L, 75L, 80L, 83L, 80L,
41L, 97L, 61L, 133L, 135L, 180L, 100L, 50L, 28L, 75L, 18L, 79L,
94L, 100L, 117L, 47L, 74L, 68L, 393L, 390L, 191L, 416L, 504L,
532L, 545L, 545L, 181L, 556L, 175L, 19L, 24L, 19L, 312L, 766L,
389L, 416L, 418L, 639L, 475L, 239L, 293L, 70L, 135L, 37L, 122L,
84L, 42L, 408L, 886L, 93L, 115L, 65L, 67L, 35L, 37L, 47L, 50L,
54L, 942L, 9L, 43L, 29L, 29L, 29L, 29L, 28L, 27L, 25L, 25L, 26L,
32L, 33L, 32L, 33L, 30L, 26L, 23L, 24L, 23L, 8L, 1L, 2L, 2L,
2L, 2L, 2L, 4L, 4L, 4L, 4L, 3L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 3L, 3L, 4L, 3L, 2L, 2L, 0L, 7L, 3L, 65L, 73L, 111L, 98L,
133L, 107L, 64L), k5 = c(0L, 14L, 14L, 14L, 1L, 0L, 0L, 8L, 7L,
5L, 5L, 5L, 0L, 3L, 0L, 8L, 2L, 3L, 18L, 15L, 0L, 2L, 38L, 3L,
5L, 1L, 18L, 1L, 2L, 2L, 3L, 21L, 2L, 15L, 1L, 26L, 22L, 17L,
27L, 33L, 41L, 39L, 42L, 45L, 51L, 14L, 50L, 31L, 82L, 84L, 108L,
55L, 24L, 16L, 51L, 33L, 44L, 55L, 54L, 87L, 15L, 20L, 27L, 285L,
297L, 151L, 293L, 343L, 363L, 374L, 376L, 57L, 382L, 24L, 25L,
10L, 8L, 103L, 551L, 301L, 320L, 276L, 364L, 340L, 49L, 272L,
171L, 195L, 24L, 180L, 161L, 11L, 254L, 663L, 188L, 229L, 158L,
26L, 3L, 3L, 6L, 10L, 6L, 708L, 0L, 9L, 0L, 3L, 0L, 1L, 0L, 2L,
0L, 0L, 1L, 9L, 9L, 9L, 10L, 10L, 6L, 6L, 1L, 6L, 2L, 0L, 5L,
3L, 2L, 3L, 4L, 2L, 3L, 2L, 2L, 1L, 3L, 0L, 0L, 4L, 1L, 0L, 1L,
5L, 2L, 0L, 1L, 2L, 0L, 2L, 5L, 1L, 3L, 3L, 43L, 50L, 78L, 75L,
87L, 78L, 59L), k6 = c(0L, 14L, 14L, 14L, 1L, 0L, 0L, 8L, 7L,
5L, 5L, 5L, 0L, 3L, 0L, 8L, 2L, 3L, 18L, 15L, 0L, 2L, 38L, 3L,
5L, 1L, 18L, 1L, 2L, 2L, 3L, 21L, 2L, 15L, 1L, 26L, 22L, 17L,
27L, 33L, 41L, 39L, 42L, 45L, 51L, 14L, 50L, 31L, 82L, 84L, 108L,
55L, 24L, 16L, 51L, 33L, 44L, 55L, 54L, 87L, 15L, 20L, 27L, 285L,
297L, 151L, 293L, 343L, 363L, 374L, 376L, 57L, 382L, 24L, 25L,
10L, 8L, 103L, 551L, 301L, 320L, 276L, 364L, 340L, 49L, 272L,
171L, 195L, 24L, 180L, 161L, 11L, 254L, 663L, 188L, 229L, 158L,
26L, 3L, 3L, 6L, 10L, 6L, 708L, 0L, 9L, 0L, 3L, 0L, 1L, 0L, 2L,
0L, 0L, 1L, 9L, 9L, 9L, 10L, 10L, 6L, 6L, 1L, 6L, 2L, 0L, 5L,
3L, 2L, 3L, 4L, 2L, 3L, 2L, 2L, 1L, 3L, 0L, 0L, 4L, 1L, 0L, 1L,
5L, 2L, 0L, 1L, 2L, 0L, 2L, 5L, 1L, 3L, 3L, 43L, 50L, 78L, 75L,
87L, 78L, 59L), k7 = c(0L, 36L, 42L, 44L, 0L, 0L, 0L, 3L, 3L,
49L, 50L, 51L, 0L, 0L, 0L, 0L, 0L, 0L, 31L, 158L, 0L, 1L, 28L,
14L, 11L, 9L, 27L, 14L, 12L, 14L, 14L, 28L, 14L, 32L, 19L, 41L,
37L, 26L, 39L, 57L, 85L, 75L, 82L, 87L, 87L, 37L, 91L, 54L, 124L,
138L, 206L, 150L, 44L, 18L, 92L, 38L, 76L, 95L, 101L, 155L, 20L,
90L, 48L, 375L, 344L, 135L, 379L, 519L, 537L, 549L, 563L, 67L,
557L, 91L, 43L, 30L, 35L, 125L, 784L, 491L, 519L, 324L, 627L,
503L, 215L, 296L, 68L, 203L, 42L, 173L, 58L, 43L, 222L, 812L,
64L, 98L, 36L, 65L, 36L, 45L, 42L, 50L, 43L, 962L, 0L, 36L, 0L,
0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 15L, 17L, 15L, 13L, 12L, 25L,
27L, 8L, 26L, 7L, 2L, 5L, 5L, 4L, 5L, 5L, 5L, 5L, 6L, 5L, 4L,
6L, 0L, 0L, 5L, 0L, 1L, 0L, 5L, 3L, 0L, 0L, 4L, 0L, 1L, 4L, 2L,
9L, 3L, 59L, 77L, 123L, 107L, 144L, 119L, 79L), k8 = c(0L, 36L,
42L, 44L, 0L, 0L, 0L, 3L, 3L, 49L, 50L, 51L, 0L, 0L, 0L, 0L,
0L, 0L, 31L, 158L, 0L, 1L, 28L, 14L, 11L, 9L, 27L, 14L, 12L,
14L, 14L, 28L, 14L, 32L, 19L, 41L, 37L, 26L, 39L, 57L, 85L, 75L,
82L, 87L, 87L, 37L, 91L, 54L, 124L, 138L, 206L, 150L, 44L, 18L,
92L, 38L, 76L, 95L, 101L, 155L, 20L, 90L, 48L, 375L, 344L, 135L,
379L, 519L, 537L, 549L, 563L, 67L, 557L, 91L, 43L, 30L, 35L,
125L, 784L, 491L, 519L, 324L, 627L, 503L, 215L, 296L, 68L, 203L,
42L, 173L, 58L, 43L, 222L, 812L, 64L, 98L, 36L, 65L, 36L, 45L,
42L, 50L, 43L, 962L, 0L, 36L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L,
1L, 15L, 17L, 15L, 13L, 12L, 25L, 27L, 8L, 26L, 7L, 2L, 5L, 5L,
4L, 5L, 5L, 5L, 5L, 6L, 5L, 4L, 6L, 0L, 0L, 5L, 0L, 1L, 0L, 5L,
3L, 0L, 0L, 4L, 0L, 1L, 4L, 2L, 9L, 3L, 59L, 77L, 123L, 107L,
144L, 119L, 79L), b1 = structure(c(7L, 3L, 3L, 3L, 7L, 7L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 7L, 1L, 1L, 7L,
7L, 7L, 1L, 7L, 1L, 1L, 1L, 1L, 7L, 1L, 1L, 1L, 7L, 7L, 7L, 7L,
5L, 5L, 7L, 7L, 5L, 5L, 7L, 7L, 3L, 5L, 5L, 5L, 3L, 7L, 7L, 7L,
1L, 7L, 7L, 7L, 3L, 1L, 7L, 7L, 7L, 7L, 3L, 7L, 5L, 5L, 5L, 5L,
7L, 5L, 7L, 7L, 1L, 1L, 3L, 5L, 3L, 7L, 3L, 3L, 3L, 7L, 3L, 7L,
3L, 1L, 7L, 7L, 7L, 3L, 5L, 7L, 7L, 7L, 1L, 1L, 1L, 1L, 1L, 1L,
5L, 1L, 5L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 5L, 5L, 7L, 5L, 5L, 6L, 6L, 2L, 6L, 2L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 6L, 6L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 2L,
1L, 7L, 7L, 7L, 7L, 3L, 7L, 7L, 3L, 7L), .Label = c("CP", "HF",
"HP", "KF", "KP", "NF", "NP"), class = "factor"), b2 = structure(c(7L,
3L, 3L, 3L, 7L, 7L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 7L, 1L, 1L, 7L, 7L, 7L, 1L, 7L, 1L, 1L, 1L, 1L, 7L, 1L,
1L, 1L, 7L, 7L, 7L, 7L, 5L, 5L, 7L, 7L, 5L, 5L, 7L, 7L, 3L, 5L,
5L, 5L, 3L, 7L, 7L, 7L, 1L, 7L, 7L, 7L, 3L, 1L, 7L, 7L, 7L, 7L,
3L, 7L, 5L, 5L, 5L, 5L, 7L, 5L, 7L, 7L, 1L, 1L, 3L, 5L, 3L, 7L,
3L, 3L, 3L, 7L, 3L, 7L, 3L, 1L, 7L, 7L, 7L, 3L, 5L, 7L, 7L, 7L,
1L, 1L, 1L, 1L, 1L, 1L, 5L, 1L, 5L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 5L, 5L, 7L, 5L, 5L, 6L, 6L, 2L, 6L,
2L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 6L, 6L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 2L, 1L, 7L, 7L, 7L, 7L, 3L, 7L, 7L, 3L, 7L
), .Label = c("CP", "HF", "HP", "KF", "KP", "NF", "NP"), class = "factor"),
b3 = structure(c(3L, 5L, 5L, 5L, 3L, 3L, 3L, 5L, 7L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 1L, 1L, 5L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 1L, 7L, 7L, 5L, 5L, 7L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 7L, 5L, 3L, 5L, 5L, 5L, 3L, 7L, 7L, 3L,
7L, 7L, 7L, 3L, 3L, 7L, 7L, 7L, 5L, 5L, 3L, 5L, 5L, 5L, 5L,
5L, 7L, 5L, 7L, 7L, 1L, 1L, 3L, 5L, 3L, 7L, 3L, 7L, 3L, 7L,
3L, 7L, 1L, 1L, 7L, 7L, 7L, 3L, 5L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 5L, 3L, 5L, 7L, 3L, 7L, 7L, 7L, 3L, 3L, 3L, 7L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 2L, 2L, 2L,
6L, 4L, 4L, 4L, 4L, 6L, 4L, 6L, 6L, 6L, 6L, 6L, 6L, 4L, 4L,
6L, 6L, 4L, 6L, 2L, 7L, 1L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 3L,
7L), .Label = c("CP", "HF", "HP", "KF", "KP", "NF", "NP"), class = "factor"),
b4 = structure(c(3L, 5L, 5L, 5L, 3L, 3L, 3L, 5L, 7L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 1L, 1L, 5L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 1L, 7L, 7L, 5L, 5L, 7L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 7L, 5L, 3L, 5L, 5L, 5L, 3L, 7L, 7L, 3L,
7L, 7L, 7L, 3L, 3L, 7L, 7L, 7L, 5L, 5L, 3L, 5L, 5L, 5L, 5L,
5L, 7L, 5L, 7L, 7L, 1L, 1L, 3L, 5L, 3L, 7L, 3L, 7L, 3L, 7L,
3L, 7L, 1L, 1L, 7L, 7L, 7L, 3L, 5L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 5L, 3L, 5L, 7L, 3L, 7L, 7L, 7L, 3L, 3L, 3L, 7L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 2L, 2L, 2L,
6L, 4L, 4L, 4L, 4L, 6L, 4L, 6L, 6L, 6L, 6L, 6L, 6L, 4L, 4L,
6L, 6L, 4L, 6L, 2L, 7L, 1L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 3L,
7L), .Label = c("CP", "HF", "HP", "KF", "KP", "NF", "NP"), class = "factor"),
b5 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 1L, 3L, 1L, 4L,
1L, 2L, 1L, 1L, 4L, 1L, 4L, 1L, 4L, 4L, 2L, 4L, 2L, 2L, 2L,
4L, 2L, 2L, 2L, 2L, 4L, 2L, 4L, 2L, 2L, 4L, 2L, 1L, 1L, 4L,
4L, 4L, 4L, 4L, 4L, 1L, 4L, 4L, 4L, 4L, 2L, 4L, 4L, 4L, 3L,
3L, 4L, 4L, 1L, 4L, 1L, 1L, 1L, 3L, 2L, 4L, 2L, 2L, 2L, 4L,
2L, 4L, 4L, 1L, 4L, 4L, 4L, 2L, 3L, 4L, 2L, 4L, 1L, 1L, 1L,
1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 1L, 4L, 2L, 2L, 4L, 4L, 2L,
4L), .Label = c("CP", "HP", "KP", "NP"), class = "factor"),
b6 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 1L, 3L, 1L, 4L,
1L, 2L, 1L, 1L, 4L, 1L, 4L, 1L, 4L, 4L, 2L, 4L, 2L, 2L, 2L,
4L, 2L, 2L, 2L, 2L, 4L, 2L, 4L, 2L, 2L, 4L, 2L, 1L, 1L, 4L,
4L, 4L, 4L, 4L, 4L, 1L, 4L, 4L, 4L, 4L, 2L, 4L, 4L, 4L, 3L,
3L, 4L, 4L, 1L, 4L, 1L, 1L, 1L, 3L, 2L, 4L, 2L, 2L, 2L, 4L,
2L, 4L, 4L, 1L, 4L, 4L, 4L, 2L, 3L, 4L, 2L, 4L, 1L, 1L, 1L,
1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 1L, 4L, 2L, 2L, 4L, 4L, 2L,
4L), .Label = c("CP", "HP", "KP", "NP"), class = "factor"),
b7 = structure(c(2L, 4L, 4L, 4L, 2L, 2L, 2L, 2L, 2L, 4L,
4L, 4L, 2L, 2L, 5L, 1L, 1L, 1L, 4L, 4L, 2L, 2L, 4L, 3L, 6L,
6L, 6L, 3L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 3L, 3L, 3L, 3L, 6L,
6L, 3L, 6L, 6L, 6L, 6L, 3L, 6L, 3L, 3L, 4L, 3L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 3L, 2L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 4L, 4L,
4L, 6L, 4L, 2L, 6L, 2L, 2L, 2L, 4L, 3L, 6L, 3L, 6L, 3L, 6L,
3L, 6L, 6L, 2L, 6L, 6L, 6L, 6L, 4L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 4L, 2L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 6L, 2L, 6L, 3L, 3L, 6L, 3L, 3L,
6L), .Label = c("CF", "CP", "HP", "KP", "NF", "NP"), class = "factor"),
b8 = structure(c(2L, 4L, 4L, 4L, 2L, 2L, 2L, 2L, 2L, 4L,
4L, 4L, 2L, 2L, 5L, 1L, 1L, 1L, 4L, 4L, 2L, 2L, 4L, 3L, 6L,
6L, 6L, 3L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 3L, 3L, 3L, 3L, 6L,
6L, 3L, 6L, 6L, 6L, 6L, 3L, 6L, 3L, 3L, 4L, 3L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 3L, 2L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 4L, 4L,
4L, 6L, 4L, 2L, 6L, 2L, 2L, 2L, 4L, 3L, 6L, 3L, 6L, 3L, 6L,
3L, 6L, 6L, 2L, 6L, 6L, 6L, 6L, 4L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 4L, 2L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 6L, 6L, 6L, 6L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 6L, 2L, 6L, 3L, 3L, 6L, 3L, 3L,
6L), .Label = c("CF", "CP", "HP", "KP", "NF", "NP"), class = "factor")), .Names = c("chr",
"pos_c", "c1", "c2", "c3", "c4", "c5", "c6", "c7", "c8", "k1",
"k2", "k3", "k4", "k5", "k6", "k7", "k8", "b1", "b2", "b3", "b4",
"b5", "b6", "b7", "b8"), class = "data.frame", row.names = c(NA,
-161L))

You can try:
t(apply(df[,-1], 1, function(rg){
occ_rg <- table(rg)
rg[grep("HP",rg)] <- names(occ_rg)[which.max(occ_rg)]
return(rg)}))
So, to have your new df:
df <- data.frame(chr=df[, 1], t(apply(df[,-1], 1, function(rg){
occ_rg <- table(rg)
rg[grep("HP",rg)] <- names(occ_rg)[which.max(occ_rg)]
return(rg)})),
stringsAsFactors=F)
# chr b1 b2 b3 b4 b5 b6 b7 b8
#1 1 CP CP CP CP CP CP CP CP
#2 1 KP KP KP KP CP CP KP KP
#3 1 CP CP CP CP KP KP CP CP
#4 1 CP CP CP CP KP KP CP CP
#5 1 KP KP CP CP CP CP CP CP
EDIT
If you have other columns and the columns you want to change are the only ones beginning with "b", you can do :
df[, grepl("^b", colnames(df))] <- t(apply(df[, grepl("^b", colnames(df))],
1,
function(rg){
occ_rg <- table(rg)
rg[grep("HP",rg)] <- names(occ_rg)[which.max(occ_rg)]
return(rg)}))
Example:
With this df:
# chr c1 b1 b2 b3 b4 b5 b6 b7 b8 c2
#1 1 1 HP HP CP CP CP CP CP CP 11
#2 1 2 HP HP KP KP CP CP KP KP 12
#3 1 3 CP CP CP CP KP KP HP HP 13
#4 1 4 CP CP HP HP KP KP CP CP 14
#5 1 5 KP KP CP CP HP HP CP CP 15
You get:
# chr c1 b1 b2 b3 b4 b5 b6 b7 b8 c2
#1 1 1 CP CP CP CP CP CP CP CP 11
#2 1 2 KP KP KP KP CP CP KP KP 12
#3 1 3 CP CP CP CP KP KP CP CP 13
#4 1 4 CP CP CP CP KP KP CP CP 14
#5 1 5 KP KP CP CP CP CP CP CP 15
EDIT 2
If you have other values than "HP", "CP" and "KP" and want to replace "HP" by either "CP" or "KP", depending on which occurs the most, you can do:
df[, grepl("^b", colnames(df))] <- t(apply(df[, grepl("^b", colnames(df))],
1,
function(rg){
occ_rg <- table(rg)
occ_rg <- occ_rg[grepl("KP|CP", names(occ_rg))]
rg[grep("HP",rg)] <- names(occ_rg)[which.max(occ_rg)]
return(rg)}))
Explanation (for edit2):
df[, grepl("^b", colnames(df))] <- # only the columns beginning with b are considered (so the other ones will remain untouched)
t( # the results of apply will be transposed
apply(df[, grepl("^b", colnames(df))], # apply on df with only the columns beginning by b
1, # by row
function(rg){ # a function that takes a vector "rg" as input
occ_rg <- table(rg) # computes the table
occ_rg <- occ_rg[grepl("KP|CP", names(occ_rg))] # keep only the occurrences of either "KP" or "CP"
rg[grep("HP",rg)] <- names(occ_rg)[which.max(occ_rg)] # replace in the vector rg the "HP" elements by "KP" or "CP" depending on which occurs the most
return(rg) # finally returns the vector rg
}))

Resources