merge

Lab 1/Lab1_code_sample.R

@@ -2,6 +2,7 @@ library(readr)
 library(EnvStats)
 library(nortest)
 
+# install.packages(c("readr", "EnvStats"))
 
 # set working directory (relative path)
 setwd("~/Desktop/Data Analytics/Lab 1")
@@ -15,7 +16,7 @@ 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
@@ -68,7 +69,7 @@ PHL.noNA
 PHL.above30 <- PHL.noNA[PHL.noNA>30]
 
 PHL.above30
-  
+
 # stats
 summary(PHL.above30)
 
@@ -79,16 +80,16 @@ 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(0., 100., 10)
   
 # 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)
@@ -109,7 +110,7 @@ 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)

Lab 1/findMinMax.sh

@@ -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