I'm so confused

This commit is contained in:
2025-09-14 11:25:41 -04:00
parent f779fedb37
commit 87d0c4bbb5
3 changed files with 74 additions and 12 deletions
+32 -12
View File
@@ -1,9 +1,12 @@
library(readr)
library(EnvStats)
# install.packages(c("readr", "EnvStats"))
# set working directory (relative path)
setwd("~/Desktop/R/Lab 1/")
# paste function my beloved <3
setwd(paste(getwd(), "Lab 1", sep="/"))
# read data
epi.data <- read_csv("epi_results_2024_pop_gdp.csv")
@@ -12,7 +15,7 @@ epi.data <- read_csv("epi_results_2024_pop_gdp.csv")
View(epi.data)
# print summary of variables in dataframe
summary(epi.data$RLI.new)
summary(epi.data$epi_results_2024_pop_gdp.csv.new)
# print values in variable
epi.data$RLI.new
@@ -58,7 +61,7 @@ PHL.noNA
PHL.above30 <- PHL.noNA[PHL.noNA>30]
PHL.above30
# stats
summary(PHL.above30)
@@ -69,21 +72,38 @@ boxplot(RLI, PHL.above30, names = c("RHI","PHL"))
### Histograms ###
# histogram (frequency distribution)
hist(RLI)
# hist(RLI)
# define sequence of values over which to plot histogram
x <- seq(20., 80., 10)
# I have NO IDEA why this keep breaking but I just started using the range func
rng <- range(RLI, na.rm = TRUE)
lo <- floor(rng[1] / 5) * 5
hi <- ceiling(rng[2] / 5) * 5
brks <- seq(lo, hi, by = 1)
# WHY????? WHY IS IT BREAKING????
# [1] "range 0 lo 0 hi 100 brks 50" "range 97.7 lo 0 hi 100 brks 50"
# Error in freq && !equidist : 'length = 15' in coercion to 'logical(1)'
# Calls: hist -> hist.default -> plot -> plot.histogram
# Execution halted
print(paste("range", rng, "lo", lo, "hi", hi, "brks", brks))
hist(RLI,
breaks = brks,
prob = TRUE)
x <- seq(20, 90, by = 5)
# histogram (frequency distribution) over range
hist(RLI, x, prob=TRUE)
hist(RLI, x, breaks=brks, prob=TRUE)
# print estimated density curve for variable
lines(density(RLI,na.rm=TRUE,bw=1.)) # or try bw=“SJ”
lines(density(RLI, na.rm=TRUE)) # or try bw=“SJ”
# print rug
rug(RLI)
x <- seq(20., 80., 5)
x <- seq(5., 95., 5)
# histogram (frequency distribution) over rabge
hist(RLI, breaks = "FD", prob=TRUE)
@@ -99,7 +119,7 @@ rug(RLI)
hist(RLI.new, breaks = "FD", prob=TRUE)
# range
x1<-seq(20,80,1)
x1<-seq(5,95,1)
# generate probability density values for a normal distribution with given mean and sd
d1 <- dnorm(x1,mean=45, sd=11,log=FALSE)
@@ -136,8 +156,8 @@ qqnorm(x); qqline(x)
# print quantile-quantile plot for variable with any theoretical distribution
qqplot(rnorm(180), RLI.new.sub, xlab = "Q-Q plot for norm dsn")
qqline(RLI.new.sub)
qqplot(rnorm(180), RLI.sub, xlab = "Q-Q plot for norm dsn")
qqline(RLI.sub)
# print quantile-quantile plot for 2 variables
qqplot(RLI, PHL, xlab = "Q-Q plot for RHI vs PHL")
BIN
View File
Binary file not shown.
+42
View File
@@ -0,0 +1,42 @@
awk -F, '
NR==1{
for(i=1;i<=NF;i++){
h=$i; gsub(/\r/,"",h)
if(h=="RLI.new") rli=i
if(h=="PHL.new") phl=i
if(h=="country") country=i
if(h=="iso") iso=i
}
next
}
{
# RLI.new
if(rli){
v=$rli; gsub(/"/,"",v)
if(v ~ /^[+-]?[0-9]*\.?[0-9]+([eE][+-]?[0-9]+)?$/){
v+=0
if(!rli_min_set || v<rli_min){ rli_min=v; rli_min_country=$(country); rli_min_iso=$(iso); rli_min_set=1 }
if(!rli_max_set || v>rli_max){ rli_max=v; rli_max_country=$(country); rli_max_iso=$(iso); rli_max_set=1 }
}
}
# PHL.new
if(phl){
w=$phl; gsub(/"/,"",w)
if(w ~ /^[+-]?[0-9]*\.?[0-9]+([eE][+-]?[0-9]+)?$/){
w+=0
if(!phl_min_set || w<phl_min){ phl_min=w; phl_min_country=$(country); phl_min_iso=$(iso); phl_min_set=1 }
if(!phl_max_set || w>phl_max){ phl_max=w; phl_max_country=$(country); phl_max_iso=$(iso); phl_max_set=1 }
}
}
}
END{
if(rli){
print "RLI.new min:", rli_min, " (", rli_min_iso, "-", rli_min_country, ")"
print "RLI.new max:", rli_max, " (", rli_max_iso, "-", rli_max_country, ")"
} else { print "naur col RLI.new" }
if(phl){
print "PHL.new min:", phl_min, " (", phl_min_iso, "-", phl_min_country, ")"
print "PHL.new max:", phl_max, " (", phl_max_iso, "-", phl_max_country, ")"
} else { print "naur col PHL.new" }
}
' epi_results_2024_pop_gdp.csv