From fda367ef4012d2565b7a58cca1b6a6891bc1d3de Mon Sep 17 00:00:00 2001 From: sorenh25 Date: Fri, 22 Sep 2017 11:08:16 -0400 Subject: [PATCH 1/6] initial file --- solution.py | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 solution.py diff --git a/solution.py b/solution.py new file mode 100644 index 0000000..e69de29 From 9cbaddf4dd8a4a635faa66034d902b28dd422760 Mon Sep 17 00:00:00 2001 From: Zoe Loh Date: Fri, 22 Sep 2017 11:16:23 -0400 Subject: [PATCH 2/6] first part --- solution.py | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 solution.py diff --git a/solution.py b/solution.py new file mode 100644 index 0000000..2ea6512 --- /dev/null +++ b/solution.py @@ -0,0 +1,6 @@ +import numpy +import os +os.listdir(".") +os.chdir('/Users/zoeloh/Desktop/Intro_Biocom_ND_319_Tutorial5') +data = numpy.loadtxt(fname="test.dat",delimiter=" ") +data From 74fbe74b92c56b1f436e8e483cd904991b32d9d2 Mon Sep 17 00:00:00 2001 From: sorenh25 Date: Fri, 22 Sep 2017 11:22:30 -0400 Subject: [PATCH 3/6] Second part by Soren --- solution.py | 6 ++++++ 1 file changed, 6 insertions(+) mode change 100644 => 100755 solution.py diff --git a/solution.py b/solution.py old mode 100644 new mode 100755 index 2ea6512..b23b2b2 --- a/solution.py +++ b/solution.py @@ -4,3 +4,9 @@ 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,:] From 0437eae86fbeca6503758c2b8efe93a7dd4341cf Mon Sep 17 00:00:00 2001 From: Soren Holm Date: Thu, 28 Sep 2017 22:19:34 -0400 Subject: [PATCH 4/6] First part done --- challenge.py | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 challenge.py diff --git a/challenge.py b/challenge.py new file mode 100644 index 0000000..d145869 --- /dev/null +++ b/challenge.py @@ -0,0 +1,9 @@ +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=' ') + From 4f9087db783d19bcec6394a43b8b813177e8265e Mon Sep 17 00:00:00 2001 From: Zoe Loh Date: Thu, 28 Sep 2017 22:21:13 -0400 Subject: [PATCH 5/6] part 1 and 2 --- challenge.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/challenge.py b/challenge.py index d145869..9fefc24 100644 --- a/challenge.py +++ b/challenge.py @@ -7,3 +7,22 @@ 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'] + From 505343f719b6ec6d7c79c0d71d8830ae0b69d65e Mon Sep 17 00:00:00 2001 From: Soren Holm Date: Thu, 28 Sep 2017 22:23:28 -0400 Subject: [PATCH 6/6] Final commit, problem solved --- challenge.py | 6 ++++++ uniqueGenderYears.txt | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) create mode 100644 uniqueGenderYears.txt diff --git a/challenge.py b/challenge.py index 9fefc24..1f92266 100644 --- a/challenge.py +++ b/challenge.py @@ -26,3 +26,9 @@ 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) \ No newline at end of file diff --git a/uniqueGenderYears.txt b/uniqueGenderYears.txt new file mode 100644 index 0000000..a4ec58a --- /dev/null +++ b/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