Created
February 28, 2018 14:55
-
-
Save lmcstro/3de7d1da5962f45ef578233a661d7a9c to your computer and use it in GitHub Desktop.
an experiment in GIST for R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# select a particlar car and day to examine | |
x.journey.number <- 4 | |
x.day <- "Monday" | |
# Big look to process all the records | |
#for (x.journey.number in 1:length(l.journeys)) { | |
#} # end big loop | |
df.x <- read.csv(paste(x.results.dir,"pattern_",l.journeys[x.journey.number] | |
,sep = ""), stringsAsFactors = FALSE) | |
# find the max cluster number in the data frame | |
x.max.cluster <- max(c(max(df.x$from),max(df.x$to))) | |
# initialize a matrix to calculate frequency and probability | |
a.x <- array(rep(0, | |
(x.max.cluster)*(x.max.cluster)), | |
dim=c(x.max.cluster,x.max.cluster)) | |
# calculate the journeys, and add a nominal amount to allow for some uncertainty | |
# when there is 0 journeys (since we are not certain there are NEVER any journeys | |
# in between location that in our sample reported as 0) | |
for (j in 1:x.max.cluster) { | |
for (k in 1:x.max.cluster) { | |
a.x[j,k] <- df.x[df.x$from == j & | |
df.x$to == k & | |
df.x$day == x.day,"journeys"] + 0.1 | |
} | |
} | |
# add some row and column names | |
rownames(a.x) <- rownames(a.x, do.NULL = FALSE, prefix = "From.") | |
colnames(a.x) <- colnames(a.x, do.NULL = FALSE, prefix = "To.") | |
# add the marginal sums | |
a.x <- rbind(a.x,colSums(a.x)) | |
a.x <- cbind(a.x,rowSums(a.x)) | |
# great a marginal probability estimate, based on normalized observed frequency | |
b.x <- round(a.x/a.x[x.max.cluster+1,x.max.cluster+1],3) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment