holm-loh submission

challenge.py

@@ -0,0 +1,34 @@
+import pandas
+
+wages = pandas.read_csv("wages.csv")
+
+genderYears = pandas.DataFrame(wages,columns=['gender','yearsExperience'])
+genderYears.drop_duplicates(['gender','yearsExperience'], keep='first', inplace=True)
+genderYears.sort_values(['gender','yearsExperience'], ascending=[True, True], inplace=True)
+genderYears.to_csv('uniqueGenderYears.txt', sep=' ')
+
+print("Highest earner:")
+print(wages.loc[wages['wage'].argmax(), ['gender', 'yearsExperience', 'wage']])
+
+print("Lowest earner:")
+print(wages.loc[wages['wage'].argmin(), ['gender', 'yearsExperience', 'wage']])
+
+collegeSalery = 0;
+highSchoolSalery = 0;
+collegeCount = 0;
+highSchoolCount = 0;
+
+for index in range(0, 3294 ,1):
+    if wages.loc[index, 'yearsSchool'] >= 16:
+        collegeCount += 1
+        collegeSalery += wages.loc[index, 'wage']
+    if wages.loc[index, 'yearsSchool'] <= 12:
+        highSchoolCount += 1
+        highSchoolSalery += wages.loc[index, 'wage']
+
+collegeSalery = collegeSalery / collegeCount
+highSchoolSalery = highSchoolSalery / highSchoolCount
+print("Average salery for college graduates:")
+print(collegeSalery)
+print("Average salery for high school graduates:")
+print(highSchoolSalery)

solution.py

@@ -0,0 +1,12 @@
+import numpy 
+import os
+os.listdir(".")
+os.chdir('/Users/zoeloh/Desktop/Intro_Biocom_ND_319_Tutorial5')
+data = numpy.loadtxt(fname="test.dat",delimiter=" ")
+data
+
+data[:,0]==0
+
+data[;,0]>2
+
+data[data[:,0]>2,:]

uniqueGenderYears.txt

@@ -0,0 +1,34 @@
+ gender yearsExperience
+168 female 1
+215 female 2
+15 female 3
+37 female 4
+23 female 5
+27 female 6
+9 female 7
+4 female 8
+0 female 9
+7 female 10
+2 female 11
+1 female 12
+17 female 13
+350 female 14
+46 female 15
+623 female 16
+1784 male 2
+1658 male 3
+1650 male 4
+1599 male 5
+1594 male 6
+1570 male 7
+1581 male 8
+1579 male 9
+1569 male 10
+1573 male 11
+1571 male 12
+1617 male 13
+1589 male 14
+1605 male 15
+1608 male 16
+1959 male 17
+1942 male 18