diff --git a/SAT.csv b/SAT.csv
new file mode 100644
index 0000000..2a3fd5f
--- /dev/null
+++ b/SAT.csv
@@ -0,0 +1,14 @@
+GPA,Math SAT Score
+3.4,705
+3.65,750
+2.9,610
+2.5,400
+3.07,570
+2.3,400
+2.75,550
+3.3,660
+3.4,680
+3,575
+3.7,770
+3.1,575
+3,600
\ No newline at end of file
diff --git a/exercise-9-q1 b/exercise-9-q1
new file mode 100644
index 0000000..293b7c4
--- /dev/null
+++ b/exercise-9-q1
@@ -0,0 +1,20 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Nov  7 20:31:47 2018
+
+@author: atatarian
+"""
+
+import numpy
+import pandas
+from plotnine import *
+
+sat=pandas.read_csv("SAT.txt",sep="\t",header=0)
+sat.shape
+
+print (sat)
+
+a=ggplot(sat,aes(x="GPA",y="SAT-Score"))+theme_classic()+geom_point()+coord_cartesian()
+
+print a+xlab("GPA")+ylab("SAT-Score")+stat_smooth(method="lm")
diff --git a/exercise-9-q2 b/exercise-9-q2
new file mode 100644
index 0000000..37aae6f
--- /dev/null
+++ b/exercise-9-q2
@@ -0,0 +1,34 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Nov  7 20:49:52 2018
+
+@author: atatarian
+"""
+
+import numpy
+import pandas
+from plotnine import *
+
+data=pandas.read_csv("data.txt",sep=",",header=0)
+data.shape
+
+
+#bar plot
+
+
+d=ggplot(data)+theme_classic()+xlab("region")+ylab("observations")
+
+print d+geom_bar(aes(x="factor(region)",y="observations"),stat="summary",fun_y=numpy.mean)
+
+#scatter plot
+
+a=ggplot(data,aes(x="region",y="observations"))+theme_classic()+geom_jitter()
+
+print a
+
+
+# The scatter plots tell different stories, most notably for the north and
+# south regions. While the means are similar, as shown by the bar plot, the
+# spreads, or distributions, of the data are different, as shown by the scatter
+# plot.
\ No newline at end of file
diff --git a/sat.txt b/sat.txt
new file mode 100644
index 0000000..00f376c
--- /dev/null
+++ b/sat.txt
@@ -0,0 +1,14 @@
+GPA	SAT-Score
+3.4	705
+3.65	750
+2.9	610
+2.5	400
+3.07	570
+2.3	400
+2.75	550
+3.3	660
+3.4	680
+3	575
+3.7	770
+3.1	575
+3	600