Chen-Buynak-Guinness Tutorial 5 Submission

Exercise_5.py

@@ -0,0 +1,22 @@
+# Challenge 1
+import pandas as pd
+data=pd.read_csv("/Users/chenyingying/Documents/Intro_Biocom_ND_319_Tutorial5/wages.csv")
+data1=data.iloc[:,0:2]
+stdout=data1.drop_duplicates().sort_values(['gender','yearsExperience'])
+stdout=pd.DataFrame(stdout)
+stdout.to_csv('stdout.csv',sep=',',index=False)
+# Challenge 2 
+#The gender, yearsExperience, wage for the lowest earners
+data.sort_values('wage').head(n=1).loc[:,['gender','yearsExperience','wage']]
+#The gender, yearsExperience, wage for the highest earners
+data.sort_values('wage').tail(n=1).loc[:,['gender','yearsExperience','wage']]
+#females in the top ten earners 
+sum(data.sort_values('wage').tail(n=10).iloc[:,0]=='female')
+# Challenge 3
+import matplotlib.pyplot as plt
+y=[data.loc[data.iloc[:,2].values==12,'wage'].min(),data.loc[data.iloc[:,2].values==16,'wage'].min()]
+x=[12,16]
+plt.scatter(x,y)
+plt.title('Effect of graduating college on the min wage')
+plt.xlabel('yearsSchool')
+plt.ylabel('Minimum wage')

stdout.csv

@@ -0,0 +1,34 @@
+gender,yearsExperience
+female,1
+female,2
+female,3
+female,4
+female,5
+female,6
+female,7
+female,8
+female,9
+female,10
+female,11
+female,12
+female,13
+female,14
+female,15
+female,16
+male,2
+male,3
+male,4
+male,5
+male,6
+male,7
+male,8
+male,9
+male,10
+male,11
+male,12
+male,13
+male,14
+male,15
+male,16
+male,17
+male,18