513 lines
18 KiB
R
513 lines
18 KiB
R
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1,2)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1,2,3)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
#g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.breaks <- g.hist$breaks # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
alpha.LM
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=5)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2, lwd=3)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3, lwd=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4, lwd=3)
|
|
plot(yeast)
|
|
hist(yeast)
|
|
hist(g.vec)
|
|
g.pois
|
|
g.mean
|
|
alpha.LM
|
|
alpha.ML
|
|
degree(g)
|
|
sort(degree(g))
|
|
sort(degree(g),decreasing=FALSE)
|
|
sort(degree(g),decreasing=F)
|
|
sort(degree(g),decreasing=false)
|
|
sort(degree(g), decreasing = TRUE)
|
|
head(sort(degree(g), decreasing = TRUE))
|
|
stddev(degree(g))
|
|
sd(degree(g))
|
|
tail(sort(degree(g), decreasing = TRUE))
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2, lwd=3)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3, lwd=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4, lwd=3)
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
# Lab 9 for the University of Tulsa's CS-6643 Bioinformatics Course
|
|
# Pairwise Sequence Alignment with Dynamic Programming
|
|
# Professor: Dr. McKinney, Fall 2022
|
|
# Noah L. Schrick - 1492657
|
|
## Set Working Directory to file directory - RStudio approach
|
|
setwd(dirname(rstudioapi::getActiveDocumentContext()$path))
|
|
#### Part A: Specifying the Input
|
|
## Score Rules and Seqs
|
|
x_str <- "ATAC" # side sequence
|
|
y_str <- "GTGTAC" # top sequence
|
|
match_score <- 3
|
|
mismatch_score <- -1
|
|
gap_penalty <- -4
|
|
## Substitution Matrix
|
|
dna.letters<-c("A","C","G","T")
|
|
num.letters <- length(dna.letters)
|
|
S<-data.frame(matrix(0,nrow=num.letters,ncol=num.letters)) # data frame
|
|
rownames(S)<-dna.letters; colnames(S)<-dna.letters
|
|
for (i in 1:4){
|
|
for (j in 1:4){
|
|
if(dna.letters[i]==dna.letters[j]){
|
|
S[i,j]<- match_score
|
|
}
|
|
else{
|
|
S[i,j]<- mismatch_score
|
|
}
|
|
}
|
|
}
|
|
len(S)
|
|
size(S)
|
|
nrows(S)
|
|
nrow(S)
|
|
col(S)
|
|
S
|
|
S[A][T]
|
|
S[A,T]
|
|
S
|
|
S[A]
|
|
S.A
|
|
S.at(A)
|
|
S[1.1]
|
|
S[1,1]
|
|
S["A", "T"]
|
|
dna.letters("A")
|
|
dna.letters
|
|
?index()
|
|
match("A", dna.letters)
|
|
match("T", dna.letters)
|
|
S[1,4]
|