obitools/ecoprimers
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Backup with sets and ahocorasick

Browse Source 
git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPrimers/branches/ecoPrimers-2.1@298 60f365c0-8329-0410-b2a4-ec073aeeaa1d
This commit is contained in:
Eric Coissac
2011-06-01 22:42:30 +00:00
commit e2ebc357ee
64 changed files with 13604 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

250
src/.Rhistory Normal file
View File

@@ -0,0 +1,250 @@
plot(s$seq, s$size, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(400, 0.7e+09, "nSeq = 273")
plot(t$seq, t$size, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 700, "nSeq = 273")
plot(s$seq, s$time, xlab="Sequence Count", ylab="Time[s]", main="c. time vs sequence count withount data mining")
abline(v = 273, col = "Blue")
text(450, 300, "nSeq = 273")
plot(t$seq, t$time, xlab="Sequence Count", ylab="Time[s]", main="d. time vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(350, 20, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(400, 0.6e+09, "nSeq = 273")
plot(t$seq, t$size, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(400, 600, "nSeq = 273")
plot(s$seq, s$time, xlab="Sequence Count", ylab="Time[s]", main="c. time vs sequence count withount data mining")
abline(v = 273, col = "Blue")
text(400, 300, "nSeq = 273")
plot(t$seq, t$time, xlab="Sequence Count", ylab="Time[s]", main="d. time vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(400, 15, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(400, 0.6e+09, "Nseq = 273")
plot(t$seq, t$size, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(400, 600, "Nseq = 273")
plot(s$seq, s$time, xlab="Sequence Count", ylab="Time[s]", main="c. time vs sequence count withount data mining")
abline(v = 273, col = "Blue")
text(400, 300, "Nseq = 273")
plot(t$seq, t$time, xlab="Sequence Count", ylab="Time[s]", main="d. time vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(400, 15, "Nseq = 273")
s = read.table('/Users/tiayyba/Desktop/euBact/ecoprimer_71493.log', header= T)
t = read.table('/Users/tiayyba/Desktop/euBact/ecoprimer_84784.log', header= T)
par(mfrow=c(2,2))
plot(s$seq, s$size, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 3e+09, "nSeq = 273")
plot(t$seq, t$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 1150, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 3e+09, "nSeq = 273")
plot(t$seq, t$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 1150, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 1.7e+09, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 1.4e+09, "nSeq = 273")
plot(t$seq, t$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 500, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 1.4e+09, "nSeq = 273")
plot(t$seq, t$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 500, "nSeq = 273")
text(450, 1000, "nSeq = 273")
par(mfrow=c(2,2))
plot(s$seq, s$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="a. memory used vs sequence count without data mining")
abline(v = 273, col = "Blue")
text(450, 1.3e+09, "nSeq = 273")
plot(t$seq, t$size*1.5, xlab="Sequence Count", ylab="Memory used[B]", main="b. memory used vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 1000, "nSeq = 273")
plot(s$seq, s$time, xlab="Sequence Count", ylab="Time[s]", main="c. time vs sequence count withount data mining")
abline(v = 273, col = "Blue")
text(450, 700, "nSeq = 273")
plot(t$seq, t$time, xlab="Sequence Count", ylab="Time[s]", main="d. time vs sequence count with data mining")
abline(v = 273, col = "Blue")
text(450, 30, "nSeq = 273")
s = read.table('/Users/tiayyba/Desktop/UsedistRef1.txt', header = T)
s
plot(s$Distance, s$Count)
plot(s$Distance, log(s$Count))
plot(log(s$Distance), log(s$Count))
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UU_results/UU_F83/plots/F83_distRef1.old.txt', header = T)
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UsedistRef1.txt', header = T)
plot(s$Distance*100, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UU_results/UU_F83/plots/F83_distRef1.old.txt', header = T)
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UsedistRef1.txt', header = T)
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UU_results/UU_F83/plots/F83_distRef1.old.txt', header = T)
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UsedistRef1.txt', header = T)
plot(s$Distance, log(s$Count))
plot(s$Distance*1000, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/UsedistRef1.txt', header = T)
plot(s$Distance*1000, log(s$Count))
u = read.table('/Users/tiayyba/Desktop/UU_FdistRef2.txt', header = T)
u
max(u$Count)
max(u$Distance)
plot(u$Distance, u$Count)
plot(log(u$Distance), log(u$Count))
plot(u$Distance, u$Count, log(xy))
plot(u$Distance, u$Count, log=xy)
plot(u$Distance, u$Count, log='xy')
plot(u$Distance+1, u$Count, log='xy')
plot(u$Distance, u$Count, log='xy')
?plot
s = read.table('/Users/tiayyba/Desktop/UU_FdistRef1.txt', header = T)
plot(s$Distance, s$Count)
plot(log(s$Distance), log(s$Count))
plot(s$Distance, s$Count, log='xy')
plot(s$Distance, log(s$Count))
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef1.old.txt', header = T)
s
sNew = s[order(s$Count),]
sNew
plot(s$Distance, s$Count)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef1.old.txt', header = T)
t = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef2.old.txt', header = T)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef2.old.txt', header = T)
u = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef1.old.txt', header = T)
t = data.frame(count=s$Count,uu=u$Distance,cs=s$Distance,col=(s$Distance < u$Distance)+1)
plot(s$Distance,s$Count,log='xy',col=t$col)
par(mfrow=c(1,2))
plot(s$Distance+1,s$Count,log='xy',col=t$col)
plot(u$Distance+1,u$Count,log='xy',col=t$col)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef2.old.txt', header = T)
u = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_distRef1.old.txt', header = T)
t = data.frame(count=s$Count,uu=u$Distance,cs=s$Distance,col=(s$Distance < u$Distance)+1)
plot(u$Distance+1,u$Count,log='xy',col=t$col)
par(mfrow=c(1,2))
plot(s$Distance+1,s$Count,log='xy',col=t$col)
plot(u$Distance+1,u$Count,log='xy',col=t$col)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F82/plots/F82_distRef1.txt', header = F)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F82/plots/F82_distRef1.txt', header = T)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F82/plots/F82_distRef2.txt', header = T)
u = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F82/plots/F82_distRef1.txt', header = T)
t = data.frame(count=s$Count,uu=u$Distance,cs=s$Distance,col=(s$Distance < u$Distance)+1)
t = data.frame(count=u$Count,uu=u$Distance,cs=s$Distance,col=(s$Distance < u$Distance)+1)
s = read.table('/Users/tiayyba/Desktop/abc'header = F)
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
plot(s)
s
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
s
plot(s$V2, s$V1)
plot(s$V1, s$V2)
plot(s$V1, s$V2, xlab="sequence number", ylab="sequence count")
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
s
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
s
Sr tacg gcta ctag actg
par(mfrow=c(2,2))
plot(s$V1, s$V2, xlab="sequence number", ylab="sequence count", main = "sample: tacg")
plot(s$V1, s$V3, xlab="sequence number", ylab="sequence count", main = "sample: gcta")
plot(s$V1, s$V4, xlab="sequence number", ylab="sequence count", main = "sample: ctag")
plot(s$V1, s$V5, xlab="sequence number", ylab="sequence count", main = "sample: actg")
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
s
plot(s$V1, s$V2, xlab="sequence number", ylab="sequence count", main = "sample: Ranunculus_acris")
Sr tacg gcta ctag actg
par(mfrow=c(2,2))
plot(s$V1, s$V2, xlab="sequence number", ylab="sequence count", main = "sample: Ranunculus_acris")
plot(s$V1, s$V3, xlab="sequence number", ylab="sequence count", main = "sample: Luzula_sudetica")
plot(s$V1, s$V4, xlab="sequence number", ylab="sequence count", main = "sample: Deschampsia_cespitosa")
plot(s$V1, s$V5, xlab="sequence number", ylab="sequence count", main = "sample: Cardamine_pratensis_paludosa")
s = read.table('/Users/tiayyba/Desktop/abc', header = F)
par(mfrow=c(2,2))
plot(s$V1, s$V2, xlab="sequence number", ylab="sequence count", main = "sample 1: Ranunculus_acris")
plot(s$V1, s$V3, xlab="sequence number", ylab="sequence count", main = "sample 2: Luzula_sudetica")
plot(s$V1, s$V4, xlab="sequence number", ylab="sequence count", main = "sample 3: Deschampsia_cespitosa")
plot(s$V1, s$V5, xlab="sequence number", ylab="sequence count", main = "sample 4: Cardamine_pratensis_paludosa")
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt', header = F)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt', header = F, row.names = 1)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt', header = F, row.names=1)
s = read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt',row.names=1)
s
plot(s$count, s$uu)
plot(s$uu, s$count)
plot(s$uu, s$count, col = s$col)
plot(s$cs, s$count, col = s$col)
plot(s$cs, s$count, col = s$col, col = (s$uu < s$cs) +1)
plot(s$uu, s$count)
plot(log(s$uu), log(s$count))
plot(s$uu, log(s$count))
plot(log(s$uu), log(s$count))
plot(s$uu, s$count)
plot(s$uu, log(s$count))
plot(s$uu, log(s$count), xlab = "distance from Uncia uncia", ylab = "log(SequenceCount)")
= read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt', header = T)
s= read.table('/Users/tiayyba/Desktop/ErrModel/Borneo/UnciaUncia/UU_F83/plots/F83_dist.txt', header = T)
s
par(mfrow = c(1,2))
plot(s$cs, s$count, col = s$col)
plot(s$cs, s$count,log = 'xy', col = s$col)
par(mfrow = c(1,2))
plot(s$cs, s$count,log = 'xy', col = s$col)
plot(s$uu, s$count,log = 'xy', col = s$col)
score = (0.407)*0.890*exp(-sqrt(692.33/1.247))
score
score1 = (0.511)*0.904*exp(-sqrt(481/148.5))
score1
score1 = sqrt(481/148.5)
score1
score = sqrt(692.33/1.247)
score
score = (0.407)^2*0.890*sqrt(692.33/1.247)
score
score1 = (0.511)^2*0.904*sqrt(481/148.5)
score1
score = (0.407)*0.890*sqrt(692.33/1.247)
score
score1 = (0.511)*0.904*sqrt(481/148.5)
score1
score = (0.407)*0.890*692.33/sqrt(1.247)
score
score1 = (0.511)*0.904*481/sqrt(148.5)
score1
sum = 714 + 710 + 699
sum
2123/3
1760+3210+4950+2090
12010+3300+220
4400+385+55+495+715+800+450+2200+1540+1210+550
944 - 220
724 - 40
684 -10
364-278
944-657
250+220
7*9
q
quit
s = read.table('metazoas_Mdyn_T50.gv')
s = read.table('metazoas_Mdyn_T50.gv.hist.gv')
t = read.table('test.gv')