added new lab

Lab 1/Lab1_code_sample.R

@@ -1,9 +1,12 @@
 library(readr)
 library(EnvStats)
+library(nortest)
 
 
 # set working directory (relative path)
-setwd("~/Desktop/R/Lab 1/")
+setwd("~/Desktop/Data Analytics/Lab 1")
+
+pdf("all_plots.pdf", width = 8, height = 6)
 
 # read data
 epi.data <- read_csv("epi_results_2024_pop_gdp.csv")
@@ -17,9 +20,7 @@ summary(epi.data$RLI.new)
 # print values in variable
 epi.data$RLI.new
 
-
-######## Optional ########
-## If you want to reference the variable without using the dataframe:
+# AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
 
 # attach dataframe
 attach(epi.data)
@@ -43,6 +44,15 @@ PHL <- epi.data$PHL.new
 
 PHL
 
+# no NAs
+RLI_noNA <- epi.data$RLI.new[!is.na(epi.data$RLI.new)];
+PHL_noNA <- epi.data$PHL.new[!is.na(epi.data$PHL.new)];
+
+set.seed(1);
+RLI_sub <- sample(RLI_noNA, size = min(180, length(RLI_noNA)));
+RLI_new_sub <- RLI_sub;  # only if you truly need a second alias
+
+
 # find NAs inv variavle - outputs vector of logical values, true if NA, false otherwise
 NAs <- is.na(PHL)
 
@@ -72,7 +82,7 @@ boxplot(RLI, PHL.above30, names = c("RHI","PHL"))
 hist(RLI)
 
 # define sequence of values over which to plot histogram
-x <- seq(20., 80., 10)
+x <- seq(0., 100., 10)
   
 # histogram (frequency distribution) over range
 hist(RLI, x, prob=TRUE)
@@ -83,7 +93,7 @@ lines(density(RLI,na.rm=TRUE,bw=1.)) # or try bw=“SJ”
 # print rug
 rug(RLI)
 
-x <- seq(20., 80., 5)
+x <- seq(0., 100., 5)
 
 # histogram (frequency distribution) over rabge
 hist(RLI, breaks = "FD", prob=TRUE) 
@@ -136,8 +146,8 @@ 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") 
@@ -171,3 +181,5 @@ wilcox.test(x,y)
 
 var.test(x,y)
 t.test(x,y)
+
+dev.off()