From bf89f1deede7d939162ebd23e78f5212e632c082 Mon Sep 17 00:00:00 2001
From: Emily Chen <echen5@nd.edu>
Date: Tue, 23 Nov 2021 13:11:56 -0500
Subject: [PATCH 1/3] progress

---
 Exercise 10 Script.R | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100644 Exercise 10 Script.R

diff --git a/Exercise 10 Script.R b/Exercise 10 Script.R
new file mode 100644
index 0000000..901b3cf
--- /dev/null
+++ b/Exercise 10 Script.R	
@@ -0,0 +1,13 @@
+# read in data
+crime = read.table("crime.txt", header=TRUE, sep="\t", stringsAsFactors=FALSE)
+
+# use ggplot to produce scatterplot
+library(ggplot2)
+ggplot(crime, aes(x=Year, y=Crime.Rate)) +
+  geom_point() +
+  xlab("Year") +
+  ylab("Crime Rate (per 100,000 population)") +
+  ggtitle("Crime Rate Overtime") +
+  stat_smooth(method="loess") +
+  theme_classic() 
+  

From c28023528bbf62a299c189f504ae8c3736de1aed Mon Sep 17 00:00:00 2001
From: Emily Chen <echen5@nd.edu>
Date: Tue, 23 Nov 2021 13:33:45 -0500
Subject: [PATCH 2/3] turn in homework

---
 crime.txt | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 crime.txt

diff --git a/crime.txt b/crime.txt
new file mode 100644
index 0000000..7d69fd5
--- /dev/null
+++ b/crime.txt
@@ -0,0 +1,27 @@
+Year	Crime Rate												
+1965	26036												
+1966	27857												
+1967	28846												
+1968	33209												
+1969	38801												
+1970	38018												
+1971	41645												
+1972	44785												
+1973	49433												
+1974	52398												
+1975	61966												
+1976	62207												
+1977	58980												
+1978	60462												
+1979	62037												
+1980	56457												
+1981	65949												
+1982	62126												
+1983	60186												
+1984	61152												
+1985	58770												
+1986	62459												
+1987	53775												
+1988	49216												
+1989	47799												
+													
\ No newline at end of file

From 79b5e2b4ba51250f447b2682573f3448ae3750e9 Mon Sep 17 00:00:00 2001
From: Emily Chen <echen5@nd.edu>
Date: Tue, 23 Nov 2021 13:35:09 -0500
Subject: [PATCH 3/3] updated submission

---
 Exercise 10 Script.R | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/Exercise 10 Script.R b/Exercise 10 Script.R
index 901b3cf..01cfc65 100644
--- a/Exercise 10 Script.R	
+++ b/Exercise 10 Script.R	
@@ -1,8 +1,11 @@
+## PROBLEM 1
 # read in data
 crime = read.table("crime.txt", header=TRUE, sep="\t", stringsAsFactors=FALSE)
 
-# use ggplot to produce scatterplot
+# load ggplot
 library(ggplot2)
+
+# use ggplot to produce scatterplot
 ggplot(crime, aes(x=Year, y=Crime.Rate)) +
   geom_point() +
   xlab("Year") +
@@ -11,3 +14,26 @@ ggplot(crime, aes(x=Year, y=Crime.Rate)) +
   stat_smooth(method="loess") +
   theme_classic() 
   
+
+## PROBLEM 2
+# read in data
+data = read.table("data.txt", header=TRUE, sep=",", stringsAsFactors = FALSE)
+
+# use ggplot to produce barplot
+ggplot(data, aes(x = region, y = observations)) +
+  stat_summary(fun = mean, geom = "bar") +
+  xlab("Region") +
+  ylab("Average Population") +
+  theme_classic()
+
+# produce scatterplot
+ggplot(data = data, aes(x = region, y = observations)) +
+  geom_point() +
+  geom_jitter() +
+  theme_classic()
+
+# the barplot and scatterplot are different because the scatterplot will show 
+# the distribution of the data, whereas the barplot just reports the average.
+# the barplot does not report very precisely. the scatterplot shows that for
+# south, the data is very split (bimodal distribution). The barplot does not
+# show this.
\ No newline at end of file