Nemera-Holm submission

exercise7.py

@@ -0,0 +1,21 @@
+import pandas
+InFile=open("Lecture11.fasta","r")
+sequenceLength=[]
+percentGC = []
+for line in InFile:
+    line = line.strip() #remove extra space
+    if ">" in line:
+        next
+    else: 
+        sequenceLength.append(len(line)-1)
+        percentGC.append(1.0*(line.count("G")+line.count("C"))/len(line))
+print(percentGC)
+
+#Puts data in dataframe
+data=pandas.DataFrame({"Sequence Length": sequenceLength, "Percent GC": percentGC})
+from plotnine import *
+length=ggplot(data,aes(x="Sequence Length"))
+length+geom_histogram()+theme_classic()
+
+gc=ggplot(data,aes(x="Percent GC"))
+gc+geom_histogram()+theme_classic()

exercise72.py

@@ -0,0 +1,8 @@
+import numpy
+import pandas
+from plotnine import *
+ice=pandas.read_csv("icecream.txt",sep=",",header=0)
+
+
+scatter=ggplot(ice,aes(x="Temperature C",y="How much I want ice cream"))
+scatter+geom_point()+coord_cartesian() + stat_smooth(method="lm")

exercise73.py

@@ -0,0 +1,17 @@
+import numpy
+import pandas
+from plotnine import *
+data=pandas.read_csv("data.txt",sep=",",header=0)
+
+
+#produces bar plot for means of populations
+barplot=ggplot(data)+theme_classic()+xlab("region")+ylab("observations")
+barplot+geom_bar(aes(x="factor(region)",y="observations"),stat="summary",fun_y=numpy.mean)
+
+
+#produces scatter plot with jittering of observations
+scatterplot=ggplot(data,aes(x="region",y="observations"))
+scatterplot+geom_point()+coord_cartesian()+geom_jitter()
+
+#The bar plot clearly shows that the mean is about the same for each population. The scatterplot also shows that but less clearly.
+#The new information the scatter plot reaveals is the spread abd grouping of data which was hidden in the bar plot

icecream.txt

@@ -0,0 +1,18 @@
+"Temperature C","How much I want ice cream"
+2,5
+1,5
+3,4
+5,5
+6,7
+10,7
+9,7
+8,6
+11,7
+15,8
+13,8
+20,9
+25,10
+29,10
+31,11
+22,8
+27,9