raiho-arnold submission

ExtraPractice.R

@@ -0,0 +1,68 @@
+#Monday Activity: Wage for all males and all females 
+fwage = 0
+mwage = 0
+
+for (i in 1:nrow(wages)){
+  if (wages[i,1] == "female"){
+    fwage = fwage + wages[i,]$wage
+  }
+  else if (wages[i,1] == "male"){
+    mwage = mwage + wages[i,]$wage
+  }
+
+}
+
+#DNA Script
+
+#Initializing Data vectors to empty
+sequenceID <- NULL
+sequenceLENGTH <- NULL
+percentCG <- NULL
+meltTEMP <- NULL
+
+#Reading the File
+fileName <- "Lecture11.fasta"
+readFile<- file(fileName,open="r") #Makng fileName readable
+linn <-readLines(readFile) #Setting linn to the lines of conn
+
+
+#Looping through contents of file
+j = 1
+k = 1
+for (i in 1:length(linn)){
+  linn_split <- strsplit(linn[i], "")[[1]] #Splits line into series of characters to be accessed
+
+  #Conditional to see if the ith line is a sequence ID
+  if(linn_split[1] == ">"){    
+    sequenceID[j] = substring(linn[i],5)
+    j = j + 1
+
+    #Calculations for the base pairs
+  } else {
+
+    #Getting length of sequence
+    sequenceLENGTH[k] = nchar(linn[i], type = "chars")
+
+    #Calculating percentCG
+    CG = 0
+    for (base in linn_split) {
+      if (base == "G" || base == "C") {
+        CG = CG + 1
+      }
+    }
+    percentCG[k] = CG/sequenceLENGTH[k]*100
+
+    #Calculating melting temp
+    if (sequenceLENGTH[k] > 14){
+      meltTEMP[k] = -9999
+    } else {
+      meltTEMP[k] = 4*CG + 2*(sequenceLENGTH[k] - CG)
+    }
+
+    k = k + 1
+  }
+}
+close(readFile)
+
+#Putting everything into a table called DNA.dat
+DNA.dat <- data.frame(sequenceID, sequenceLENGTH, percentCG, meltTEMP)

Tutorial5Challenge.R

@@ -0,0 +1,54 @@
+#Reading in the Data (make sure your working directory is correct)
+wages=read.csv(file="wages.csv", header = TRUE, stringsAsFactors = FALSE)
+attach(wages)
+
+#Part 1
+data1 <- wages[order(gender,yearsExperience),]
+data1 <- (data1[,1:2])
+UNIQUE <- unique(data1)
+write.table(UNIQUE, file = "Tutorial5Output.dat", sep = " ")
+
+#Part 2
+data2 <- wages[order(wage),]
+min.wage <- data2[1,]
+max.wage <- data2[nrow(wages),]
+bottom = nrow(wages) -9
+top = nrow(wages)
+top.10 <- data2[bottom:top,]
+
+counter = 0
+for (i in 1:10){
+  if (top.10[i,]$gender == "female") {
+    counter = counter + 1
+  }
+}
+print("The person with the lowest wage is")
+min.wage[,c(1,2,4)]
+print("The person with the highest wage is")
+max.wage[,c(1,2,4)]
+
+print("The number of females in the top 10 earners is")
+counter
+
+#Part 3
+highSchoolWages <- NULL
+collegeWages <- NULL
+
+j = 1
+k = 1
+for (i in 1:nrow(wages)){
+  if (wages[i,3] == "12"){
+    highSchoolWages[j] = wages [i,4]
+    j = j+1
+  }else if (wages[i,3] == "16"){
+    collegeWages[k] = wages[i,4]
+    k = k+1
+  }
+}
+
+print("The minimum wage of a high school graduate is:")
+min(highSchoolWages)
+print("The minimum wage of a college graduate is:")
+min(collegeWages)
+print("The difference in these wages is")
+min(collegeWages) - min(highSchoolWages)