diff --git a/GrayKangaroo.txt b/GrayKangaroo.txt
new file mode 100644
index 0000000..23d7089
--- /dev/null
+++ b/GrayKangaroo.txt
@@ -0,0 +1,49 @@
+Nasal Length	Nasal Width
+609	241
+629	222
+620	233
+564	207
+645	247
+493	189
+606	226
+660	240
+630	215
+672	231
+778	263
+616	220
+727	271
+810	284
+778	279
+823	272
+755	268
+710	278
+701	238
+803	255
+855	308
+838	281
+830	288
+864	306
+635	236
+565	204
+562	216
+580	225
+596	220
+597	219
+636	201
+559	213
+615	228
+740	234
+677	237
+675	217
+629	211
+692	238
+710	221
+730	281
+763	292
+686	251
+717	231
+737	275
+816	275
+
+
+
diff --git a/TutorialEx09.py b/TutorialEx09.py
new file mode 100644
index 0000000..dea77a4
--- /dev/null
+++ b/TutorialEx09.py
@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Nov  7 22:37:17 2018
+
+@author: Alicia
+"""
+import numpy
+import pandas
+from plotnine import *
+#Question 1 - sample data for Gray Kangaroos
+data=pandas.read_csv("GrayKangaroo.txt",sep="\t",header=0)
+data.head(5)
+a=ggplot(data,aes(x="Nasal Length",y="Nasal Width"))
+a+geom_point()+coord_cartesian()+theme_classic()+stat_smooth(method="lm")
+
+#Question 2
+data=pandas.read_csv("data.txt",sep=",",header=0)
+data.head(5)
+df=ggplot(data)+theme_classic()+xlab("region")+ylab("observations")
+df+geom_bar(aes(x="factor(region)",y="observations"),stat="summary",fun_y=numpy.mean)
+#To check barplot mean values are correct
+data.groupby(['region'])['observations'].mean()
+
+a=ggplot(data,aes(x="region",y="observations"))
+a+geom_point()+coord_cartesian()+theme_classic()+geom_jitter()
+
+
+#The bar plot shows you that the mean number of observations for each region is about the same
+#When you create the scatter plot you see that even though the means are similar, the actual points of observation vary for each region
+#While the east and west regions are fairly evenly spread in terms of observations, the north region is clumped together around 15 and the south region is clumped around 5 and 25
+#These various sets of observations all return similar means, but the scatterplot gives a more accurate depiction of what is going on for number of observations in each region
\ No newline at end of file