merge

Lab 1/Lab1_code_sample.R

@@ -1,12 +1,13 @@
 library(readr)
 library(EnvStats)
+library(nortest)
 
 # install.packages(c("readr", "EnvStats"))
 
 # set working directory (relative path)
+setwd("~/Desktop/Data Analytics/Lab 1")
 
-# paste function my beloved <3
-setwd(paste(getwd(), "Lab 1", sep="/"))
+pdf("all_plots.pdf", width = 8, height = 6)
 
 # read data
 epi.data <- read_csv("epi_results_2024_pop_gdp.csv")
@@ -20,9 +21,7 @@ summary(epi.data$epi_results_2024_pop_gdp.csv.new)
 # print values in variable
 epi.data$RLI.new
 
-
-######## Optional ########
-## If you want to reference the variable without using the dataframe:
+# AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
 
 # attach dataframe
 attach(epi.data)
@@ -46,6 +45,15 @@ 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)
 
@@ -75,24 +83,7 @@ boxplot(RLI, PHL.above30, names = c("RHI","PHL"))
 # hist(RLI)
 
 # define sequence of values over which to plot histogram
-# 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)
+x <- seq(0., 100., 10)
   
 # histogram (frequency distribution) over range
 hist(RLI, x, breaks=brks, prob=TRUE)
@@ -103,7 +94,7 @@ lines(density(RLI, na.rm=TRUE)) # or try bw=“SJ”
 # print rug
 rug(RLI)
 
-x <- seq(5., 95., 5)
+x <- seq(0., 100., 5)
 
 # histogram (frequency distribution) over rabge
 hist(RLI, breaks = "FD", prob=TRUE) 
@@ -156,8 +147,8 @@ qqnorm(x); qqline(x)
 
 
 # print quantile-quantile plot for variable with any theoretical distribution
-qqplot(rnorm(180), RLI.sub, xlab = "Q-Q plot for norm dsn") 
-qqline(RLI.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") 
@@ -191,3 +182,5 @@ wilcox.test(x,y)
 
 var.test(x,y)
 t.test(x,y)
+
+dev.off()