Hi Arun,
Thanks a lot. It works perfectly.
Here is the complete code - for all those who are interested to see "Rel
Cum Freq oscillating to reach the Expected Value"
# Bernouilli Trial where:
v.fly=c("G","B") # Outcome is Green or Blue fly
n=100 # No of Events / Trials
v.smp = seq(1:n) # Event Id
v.fst = sample(v.fly,n,rep=T) # Simulating First Draw
v.sec = sample(v.fly,n,rep=T) # Simulating Second Draw
df.1 = data.frame(sample = v.smp, fst=v.fst, sec = v.sec) # Clumping in a DF
df.1$E.Occur = with(df.1, ifelse(fst==sec,TRUE,FALSE)) # Event Occurs, if
color is same in both the the draws
df.1$Rel.Freq = with(df.1, cumsum(E.Occur==TRUE)/(seq_len(nrow(df.1)))) #
Relative Frequency
df.1$Rel.Freq = round(df.1$Rel.Freq,2)
ggplot(df.1,
aes(x=sample,y=Rel.Freq))+geom_line(col="green",size=2)+geom_abline(intercept=0.5,slope=0)+geom_point(col="blue")+labs(x="Sample
No",y="Relative Cum Freq",title="Rel Cum Freq approaching 0.5 Value") +
annotate("text",x=60,y=0.53,label="Probability of 0.5")
Cheers !
On Thu, Nov 28, 2013 at 9:40 PM, arun <smartpink...@yahoo.com> wrote:
> HI,
> From the dput() version of df.1, it looks like you want:
> cumsum(df.1[,4]=="Yes")/seq_len(nrow(df.1))
> [1] 0.0000000 0.5000000 0.3333333 0.2500000 0.4000000 0.3333333 0.4285714
> [8] 0.5000000 0.4444444 0.5000000
>
>
> A.K.
>
>
> On Thursday, November 28, 2013 11:26 AM, Burhan ul haq <ulh...@gmail.com>
> wrote:
> Hi,
>
> My objective is to calculate "Relative (Cumulative) Frequency of Event
> Occurrence" - something as follows:
>
> Sample.Number 1st.Fly 2nd.Fly Did.E.occur? Relative.Cum.Frequency.of.E
> 1 G B No 0.000
> 2 B B Yes 0.500
> 3 B G No 0.333
> 4 G B No 0.250
> 5 G G Yes 0.400
> 6 G B No 0.333
> 7 B B Yes 0.429
> 8 G G Yes 0.500
> 9 G B No 0.444
> 10 B B Yes 0.500
>
> Please refer to the code below:
> ##############################################################
> # 1.
> v.fly=c("G","B") # Outcome is Green or Blue fly
>
> # 2.
> n=10 # No of Events / Trials
>
> # 3.
> v.smp = seq(1:n) # Event Id
>
> # 4.
> v.fst = sample(v.fly,n,rep=T) # Simulating First Draw
>
> # 5.
> v.sec = sample(v.fly,n,rep=T) # Simulating Second Draw
>
> # 6.
> df.1 = data.frame(sample = v.smp, fst=v.fst, sec = v.sec) # Clumping in a
> DF
>
> # 7.
> df.1$E.Occur = with(df.1, ifelse(fst==sec,TRUE,FALSE)) # Event Occurs, if
> color is same in both the the draws
>
> # 8.
> df.1$Rel.Freq = with(df.1, cumsum(E.occur)/(E.Occur)) # Relative Frequency
> >> This line does NOT work, and needs to fix the denominator part
> ##############################################################
>
> Problem is with #8, specifically the part:
> cumsum(E.occur)/(E.Occur)
>
> The denominator E.Occur is a fixed value, instead of a moving count. I have
> tried nrow(), length() but none provides a moving version of row count, as
> cumsum does for the "True" values, occurring so far.
>
> > dput(df.1)
> structure(list(Sample.Number = 1:10, X1st.Fly = c("G", "B", "B",
> "G", "G", "G", "B", "G", "G", "B"), X2nd.Fly = c("B", "B", "G",
> "B", "G", "B", "B", "G", "B", "B"), Did.E.occur. = c("No", "Yes",
> "No", "No", "Yes", "No", "Yes", "Yes", "No", "Yes"),
> Relative.Cum.Frequency.of.E = c(0,
> 0.5, 0.333, 0.25, 0.4, 0.333, 0.429, 0.5, 0.444, 0.5)), .Names =
> c("Sample.Number",
> "X1st.Fly", "X2nd.Fly", "Did.E.occur.", "Relative.Cum.Frequency.of.E"
> ), class = "data.frame", row.names = c(NA, -10L))
>
>
> Cheers !
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
