From 0c8ac19dc64dd9e0a2b3c8f0a75398b66ae1cc5b Mon Sep 17 00:00:00 2001 From: Rosemary Date: Fri, 28 Sep 2018 21:07:19 -0700 Subject: [PATCH 1/2] indentations --- ...18-team-2_project1_data_analysis_by_YL.sas | 102 +++++++++--------- 1 file changed, 51 insertions(+), 51 deletions(-) diff --git a/STAT660-01_f18-team-2_project1_data_analysis_by_YL.sas b/STAT660-01_f18-team-2_project1_data_analysis_by_YL.sas index 04a6cff..dbaaf43 100644 --- a/STAT660-01_f18-team-2_project1_data_analysis_by_YL.sas +++ b/STAT660-01_f18-team-2_project1_data_analysis_by_YL.sas @@ -58,35 +58,35 @@ Follow-up Steps: use a CLASS statement in PROC MEANS to get the summary statistics for each employee ; proc means - mean median maxdec=2 - data = absenteeism_analytic_file - ; + mean median maxdec=2 + data = absenteeism_analytic_file + ; var - Absenteeism_time_in_hours - ; + Absenteeism_time_in_hours + ; run; proc univariate - noprint - data=absenteeism_analytic_file - ; + noprint + data=absenteeism_analytic_file + ; var - Absenteeism_time_in_hours - ; - histogram; + Absenteeism_time_in_hours + ; + histogram; run; proc means - mean median maxdec=2 - data=absenteeism_analytic_file - ; + mean median maxdec=2 + data=absenteeism_analytic_file + ; class - id - ; - var - Absenteeism_time_in_hours - ; + id + ; + var + Absenteeism_time_in_hours + ; run; title; @@ -125,16 +125,16 @@ create a subset of the dataset, which only has the 36 employees with a binary variable to indicate if he or she is ever absent. ; proc logistic - data=Absenteeism_analytic_file - ; - model absence = Work_load_Average_day - ; + data=Absenteeism_analytic_file + ; + model absence = Work_load_Average_day + ; run; proc glm - ; - model absenteeism_time_in_hours = Work_load_Average_day - ; + ; + model absenteeism_time_in_hours = Work_load_Average_day + ; run; title; @@ -174,37 +174,37 @@ compare the histograms between workers -- data visualizaion often helps to quickly identify the change. ; proc freq - data = Absenteeism_analytic_file - ; - tables - id*reason_for_absence - / nopercent norow nocol - ; - format - reason_for_absence reasonofabsence.; + data = Absenteeism_analytic_file + ; + tables + id*reason_for_absence + / nopercent norow nocol + ; + format + reason_for_absence reasonofabsence.; run; proc freq - data = Absenteeism_analytic_file - ; - tables - id*reason_for_absence - /nopercent norow nocol - ; - where - absence = 1 - ; - format - reason_for_absence reasonofabsence.; + data = Absenteeism_analytic_file + ; + tables + id*reason_for_absence + /nopercent norow nocol + ; + where + absence = 1 + ; + format + reason_for_absence reasonofabsence.; run; proc sgplot - data=absenteeism_analytic_file - ; - vbar - ID - ; - where + data=absenteeism_analytic_file + ; + vbar + ID + ; + where absence = 1; run; quit; From ef617835dd9febeb0eca5244ae5875a304882455 Mon Sep 17 00:00:00 2001 From: Rosemary Date: Fri, 28 Sep 2018 21:09:55 -0700 Subject: [PATCH 2/2] indentations changed --- ...1_f18-team-2_project1_data_preparation.sas | 66 +++++++++---------- 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/STAT660-01_f18-team-2_project1_data_preparation.sas b/STAT660-01_f18-team-2_project1_data_preparation.sas index 733cd8e..eb19c18 100644 --- a/STAT660-01_f18-team-2_project1_data_preparation.sas +++ b/STAT660-01_f18-team-2_project1_data_preparation.sas @@ -29,36 +29,36 @@ downloaded from the UCI machine learning repository. *create output formats; proc format; value reasonofabsence - 0 = 'NA' - 1 = 'Infectious and parasitic disease' - 2 = 'neoplasm' - 3 = 'blood disease' - 4 = 'endocrine disease' - 5 = 'mental and behaviour disorder' - 6 = 'nervous disease' - 7 = 'eye' - 8 = 'ear' - 9 = 'circulatory' - 10= 'respiratory' - 11= 'digestive' - 12= 'skin' - 13= 'muscle' - 14= 'genitourinary' - 15= 'pregnancy' - 16= 'perinatal' - 17= 'congenital' - 18= 'clinical' - 19= 'injury' - 20= 'morbidity and mortality' - 21= 'factors' - 22= 'followup' - 23= 'medical consultation' - 24= 'blodd donation' - 25= 'lab' - 26= 'unjustified' - 27= 'physiotherapy' - 28= 'dental' - ; + 0 = 'NA' + 1 = 'Infectious and parasitic disease' + 2 = 'neoplasm' + 3 = 'blood disease' + 4 = 'endocrine disease' + 5 = 'mental and behaviour disorder' + 6 = 'nervous disease' + 7 = 'eye' + 8 = 'ear' + 9 = 'circulatory' + 10= 'respiratory' + 11= 'digestive' + 12= 'skin' + 13= 'muscle' + 14= 'genitourinary' + 15= 'pregnancy' + 16= 'perinatal' + 17= 'congenital' + 18= 'clinical' + 19= 'injury' + 20= 'morbidity and mortality' + 21= 'factors' + 22= 'followup' + 23= 'medical consultation' + 24= 'blodd donation' + 25= 'lab' + 26= 'unjustified' + 27= 'physiotherapy' + 28= 'dental' + ; run; *setup environmental parameters; @@ -104,9 +104,9 @@ https://github.com/stat660/team-2_project1/blob/master/Absenteeism_at_work.xls?r *check raw absenteeism_at_work dataset for duplicate records; proc sort noduprecs - data=Absenteeism_at_work_raw - dupout=Absenteeism_at_work_dups - out=Absenteeism_at_work_noduprecs + data=Absenteeism_at_work_raw + dupout=Absenteeism_at_work_dups + out=Absenteeism_at_work_noduprecs ; by id