From 5f326aa66bc8f6375a46f96d0c3f5ae46ca1946b Mon Sep 17 00:00:00 2001
From: eml113 <celestialsucculent@gmail.com>
Date: Fri, 5 Nov 2021 06:22:14 -0400
Subject: [PATCH] Created R Studio script for Exercise 7

---
 Exercise 7 - Erin Lewis.R | 48 ++++++++++++++++++++++++++++++++++++
 setosa.csv                | 51 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)
 create mode 100644 Exercise 7 - Erin Lewis.R
 create mode 100644 setosa.csv

diff --git a/Exercise 7 - Erin Lewis.R b/Exercise 7 - Erin Lewis.R
new file mode 100644
index 0000000..c6a55d7
--- /dev/null
+++ b/Exercise 7 - Erin Lewis.R	
@@ -0,0 +1,48 @@
+#navigate to working directory 
+setwd('/Users/erinlewis/Desktop/Biocomp_tutorial9/')
+
+#1. Write R code that replicates the functionality of the head function we used in bash.
+
+#define a variable with the file to return lines from
+exampleFile <- read.csv(file = 'wages.csv')
+#wages.csv is used as a test file in this case, any file could be inserted
+
+#define a variable representing the number of lines to be returned from the top of the indicated file. 
+n <- seq(1:10)
+#in this case, just had n be the typical amount read by bash head function, could be changed
+
+#replicate bash function using variables
+exampleFile[n, ]
+
+
+
+## 2. Load the data contained in the provided ‘iris.csv’ file and write R code to do the following things:
+data <- read.table(file="iris.csv",header=TRUE, sep=",")
+
+##print the last 2 rows in the last 2 columns to the R terminal
+tail(data, n= c(2,2)) 
+
+##get the number of observations for each species included in the data set
+unique(data$Species)
+#setosa
+nrow(data[data$Species=="setosa",])
+#versicolor
+nrow(data[data$Species=="versicolor",])
+#virginica
+nrow(data[data$Species=="virginica",])
+
+##get rows with Sepal.Width > 3.5
+data[data[,2]>3.5,]
+
+##write the data for the species setosa to a comma-delimited file names ‘setosa.csv’
+write.table(x = data[data$Species=="setosa",], file="setosa.csv",sep=",",col.names=TRUE)
+
+##calculate the mean, minimum, and maximum of Petal.Length for observations from virginica
+uniquePlant<-data[data$Species=="virginica",]
+sortedPlant<-sort(x=uniquePlant$Petal.Length,decreasing = FALSE)
+#mean
+mean(uniquePlant$Petal.Length,)
+#minimum
+sortedPlant[1]
+#maximum
+tail(sortedPlant, n=1)
\ No newline at end of file
diff --git a/setosa.csv b/setosa.csv
new file mode 100644
index 0000000..3c63e48
--- /dev/null
+++ b/setosa.csv
@@ -0,0 +1,51 @@
+"Sepal.Length","Sepal.Width","Petal.Length","Petal.Width","Species"
+"1",5.1,3.5,1.4,0.2,"setosa"
+"2",4.9,3,1.4,0.2,"setosa"
+"3",4.7,3.2,1.3,0.2,"setosa"
+"4",4.6,3.1,1.5,0.2,"setosa"
+"5",5,3.6,1.4,0.2,"setosa"
+"6",5.4,3.9,1.7,0.4,"setosa"
+"7",4.6,3.4,1.4,0.3,"setosa"
+"8",5,3.4,1.5,0.2,"setosa"
+"9",4.4,2.9,1.4,0.2,"setosa"
+"10",4.9,3.1,1.5,0.1,"setosa"
+"11",5.4,3.7,1.5,0.2,"setosa"
+"12",4.8,3.4,1.6,0.2,"setosa"
+"13",4.8,3,1.4,0.1,"setosa"
+"14",4.3,3,1.1,0.1,"setosa"
+"15",5.8,4,1.2,0.2,"setosa"
+"16",5.7,4.4,1.5,0.4,"setosa"
+"17",5.4,3.9,1.3,0.4,"setosa"
+"18",5.1,3.5,1.4,0.3,"setosa"
+"19",5.7,3.8,1.7,0.3,"setosa"
+"20",5.1,3.8,1.5,0.3,"setosa"
+"21",5.4,3.4,1.7,0.2,"setosa"
+"22",5.1,3.7,1.5,0.4,"setosa"
+"23",4.6,3.6,1,0.2,"setosa"
+"24",5.1,3.3,1.7,0.5,"setosa"
+"25",4.8,3.4,1.9,0.2,"setosa"
+"26",5,3,1.6,0.2,"setosa"
+"27",5,3.4,1.6,0.4,"setosa"
+"28",5.2,3.5,1.5,0.2,"setosa"
+"29",5.2,3.4,1.4,0.2,"setosa"
+"30",4.7,3.2,1.6,0.2,"setosa"
+"31",4.8,3.1,1.6,0.2,"setosa"
+"32",5.4,3.4,1.5,0.4,"setosa"
+"33",5.2,4.1,1.5,0.1,"setosa"
+"34",5.5,4.2,1.4,0.2,"setosa"
+"35",4.9,3.1,1.5,0.2,"setosa"
+"36",5,3.2,1.2,0.2,"setosa"
+"37",5.5,3.5,1.3,0.2,"setosa"
+"38",4.9,3.6,1.4,0.1,"setosa"
+"39",4.4,3,1.3,0.2,"setosa"
+"40",5.1,3.4,1.5,0.2,"setosa"
+"41",5,3.5,1.3,0.3,"setosa"
+"42",4.5,2.3,1.3,0.3,"setosa"
+"43",4.4,3.2,1.3,0.2,"setosa"
+"44",5,3.5,1.6,0.6,"setosa"
+"45",5.1,3.8,1.9,0.4,"setosa"
+"46",4.8,3,1.4,0.3,"setosa"
+"47",5.1,3.8,1.6,0.2,"setosa"
+"48",4.6,3.2,1.4,0.2,"setosa"
+"49",5.3,3.7,1.5,0.2,"setosa"
+"50",5,3.3,1.4,0.2,"setosa"