Laboe Exercise10

ChicagoMarathon2.csv

@@ -0,0 +1,28 @@
+Miles run,HR
+1,163
+2,172
+3,174
+4,177
+5,179
+6,178
+7,180
+8,179
+9,180
+10,181
+11,179
+12,175
+13,181
+14,189
+15,190
+16,180
+17,175
+18,182
+19,194
+20,195
+21,192
+22,187
+23,167
+24,163
+25,160
+26,167
+26.1,174

Exercise10.R

@@ -0,0 +1,37 @@
+# Exercise 10 - Analysis and plotting
+
+# Loading the packages
+library(ggplot2)
+library(cowplot)
+
+# First problem
+chithonHR = read.csv("ChicagoMarathon2.csv", header=TRUE, stringsAsFactors=FALSE)
+ggplot(data=chithonHR, aes(x=Miles.run,y=HR)) +
+  geom_point() +
+  theme_classic() +
+  stat_smooth(method="loess") +
+  xlab("Miles Run") +
+  ylab("Heart Rate") +
+  ggtitle("Chicago Marathon")
+
+# Second problem
+popdata = read.table("data.txt", header=TRUE, sep=",", stringsAsFactors=FALSE)
+# Show a barplot of the means of the four populations
+popbarplot = ggplot(data=popdata, aes(x=region,y=observations)) + 
+  stat_summary(fun=mean, geom="bar") + 
+  xlab("Region") + 
+  ylab("Population Mean") + 
+  theme_classic()
+# Show a scatterplot of all of the observations
+popscatterplot = ggplot(data=popdata, aes(x=region,y=observations)) + 
+  geom_point() + geom_jitter(alpha=0.1) + 
+  xlab("Region") + 
+  ylab("Observation") + 
+  theme_classic()
+# Display plots together for comparison
+popcomparison = plot_grid(popbarplot, popscatterplot)
+popcomparison
+# These two plots do give very different representations of the data.
+# The bar plot demonstrates that the population means of each region are similar.
+# The scatter plot shows how there are different ranges of observations. 
+# While the means are similar, the distribution of observations is very different.