{ "cells": [ { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "# Clean and Analyze Employee Exit Surveys\n", "\n", "In this project, we'll work with exit surveys from employees of the [Department of Education, Training and Employment](https://en.wikipedia.org/wiki/Department_of_Education_and_Training_(Queensland)) (DETE) and the Technical and Further Education (TAFE) institute in Queensland, Australia. The TAFE exit survey can be finded [here](https://data.gov.au/dataset/ds-qld-89970a3b-182b-41ea-aea2-6f9f17b5907e/details?q=exit%20survey) and the survey for the DETE [here](https://data.gov.au/dataset/ds-qld-fe96ff30-d157-4a81-851d-215f2a0fe26d/details?q=exit%20survey).\n", "\n", "The aim of this project is to explore, transform and clean these datasets to answer the following questiongs to stakeholders:\n", "- Are employees who only worked for the institutes for a short period of time resigning due to some kind of dissatisfaction? What about employees who have been there longer?\n", "- Are younger employees resigning due to some kind of dissatisfaction? What about older employees?\n", "\n", "For this project, we'll use our general knowledge to define the columns.\n", "\n", "Below is a preview of a couple columns we'll work with from the dete_survey.csv:\n", "\n", "- ID: An id used to identify the participant of the survey\n", "- SeparationType: The reason why the person's employment ended\n", "- Cease Date: The year or month the person's employment ended\n", "- DETE Start Date: The year the person began employment with the DETE\n", "\n", "Below is a preview of a couple columns we'll work with from the tafe_survey.csv:\n", "\n", "- Record ID: An id used to identify the participant of the survey\n", "- Reason for ceasing employment: The reason why the person's employment ended\n", "- LengthofServiceOverall. Overall Length of Service at Institute (in years): The length of the person's employment (in years)\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "dete_survey = pd.read_csv('dete_survey.csv')\n", "tafe_survey = pd.read_csv('tafe_survey.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Datasets Description\n", "In this section, we will briefly present the description of both datasets.\n", "\n", "**Dete Survey Description**" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 822 entries, 0 to 821\n", "Data columns (total 56 columns):\n", "ID 822 non-null int64\n", "SeparationType 822 non-null object\n", "Cease Date 822 non-null object\n", "DETE Start Date 822 non-null object\n", "Role Start Date 822 non-null object\n", "Position 817 non-null object\n", "Classification 455 non-null object\n", "Region 822 non-null object\n", "Business Unit 126 non-null object\n", "Employment Status 817 non-null object\n", "Career move to public sector 822 non-null bool\n", "Career move to private sector 822 non-null bool\n", "Interpersonal conflicts 822 non-null bool\n", "Job dissatisfaction 822 non-null bool\n", "Dissatisfaction with the department 822 non-null bool\n", "Physical work environment 822 non-null bool\n", "Lack of recognition 822 non-null bool\n", "Lack of job security 822 non-null bool\n", "Work location 822 non-null bool\n", "Employment conditions 822 non-null bool\n", "Maternity/family 822 non-null bool\n", "Relocation 822 non-null bool\n", "Study/Travel 822 non-null bool\n", "Ill Health 822 non-null bool\n", "Traumatic incident 822 non-null bool\n", "Work life balance 822 non-null bool\n", "Workload 822 non-null bool\n", "None of the above 822 non-null bool\n", "Professional Development 808 non-null object\n", "Opportunities for promotion 735 non-null object\n", "Staff morale 816 non-null object\n", "Workplace issue 788 non-null object\n", "Physical environment 817 non-null object\n", "Worklife balance 815 non-null object\n", "Stress and pressure support 810 non-null object\n", "Performance of supervisor 813 non-null object\n", "Peer support 812 non-null object\n", "Initiative 813 non-null object\n", "Skills 811 non-null object\n", "Coach 767 non-null object\n", "Career Aspirations 746 non-null object\n", "Feedback 792 non-null object\n", "Further PD 768 non-null object\n", "Communication 814 non-null object\n", "My say 812 non-null object\n", "Information 816 non-null object\n", "Kept informed 813 non-null object\n", "Wellness programs 766 non-null object\n", "Health & Safety 793 non-null object\n", "Gender 798 non-null object\n", "Age 811 non-null object\n", "Aboriginal 16 non-null object\n", "Torres Strait 3 non-null object\n", "South Sea 7 non-null object\n", "Disability 23 non-null object\n", "NESB 32 non-null object\n", "dtypes: bool(18), int64(1), object(37)\n", "memory usage: 258.6+ KB\n" ] } ], "source": [ "dete_survey.info()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IDSeparationTypeCease DateDETE Start DateRole Start DatePositionClassificationRegionBusiness UnitEmployment Status...Kept informedWellness programsHealth & SafetyGenderAgeAboriginalTorres StraitSouth SeaDisabilityNESB
01Ill Health Retirement08/201219842004Public ServantA01-A04Central OfficeCorporate Strategy and PeformancePermanent Full-time...NNNMale56-60NaNNaNNaNNaNYes
12Voluntary Early Retirement (VER)08/2012Not StatedNot StatedPublic ServantAO5-AO7Central OfficeCorporate Strategy and PeformancePermanent Full-time...NNNMale56-60NaNNaNNaNNaNNaN
23Voluntary Early Retirement (VER)05/201220112011Schools OfficerNaNCentral OfficeEducation QueenslandPermanent Full-time...NNNMale61 or olderNaNNaNNaNNaNNaN
34Resignation-Other reasons05/201220052006TeacherPrimaryCentral QueenslandNaNPermanent Full-time...ANAFemale36-40NaNNaNNaNNaNNaN
45Age Retirement05/201219701989Head of Curriculum/Head of Special EducationNaNSouth EastNaNPermanent Full-time...NAMFemale61 or olderNaNNaNNaNNaNNaN
\n", "

5 rows × 56 columns

\n", "
" ], "text/plain": [ " ID SeparationType Cease Date DETE Start Date \\\n", "0 1 Ill Health Retirement 08/2012 1984 \n", "1 2 Voluntary Early Retirement (VER) 08/2012 Not Stated \n", "2 3 Voluntary Early Retirement (VER) 05/2012 2011 \n", "3 4 Resignation-Other reasons 05/2012 2005 \n", "4 5 Age Retirement 05/2012 1970 \n", "\n", " Role Start Date Position \\\n", "0 2004 Public Servant \n", "1 Not Stated Public Servant \n", "2 2011 Schools Officer \n", "3 2006 Teacher \n", "4 1989 Head of Curriculum/Head of Special Education \n", "\n", " Classification Region Business Unit \\\n", "0 A01-A04 Central Office Corporate Strategy and Peformance \n", "1 AO5-AO7 Central Office Corporate Strategy and Peformance \n", "2 NaN Central Office Education Queensland \n", "3 Primary Central Queensland NaN \n", "4 NaN South East NaN \n", "\n", " Employment Status ... Kept informed Wellness programs \\\n", "0 Permanent Full-time ... N N \n", "1 Permanent Full-time ... N N \n", "2 Permanent Full-time ... N N \n", "3 Permanent Full-time ... A N \n", "4 Permanent Full-time ... N A \n", "\n", " Health & Safety Gender Age Aboriginal Torres Strait South Sea \\\n", "0 N Male 56-60 NaN NaN NaN \n", "1 N Male 56-60 NaN NaN NaN \n", "2 N Male 61 or older NaN NaN NaN \n", "3 A Female 36-40 NaN NaN NaN \n", "4 M Female 61 or older NaN NaN NaN \n", "\n", " Disability NESB \n", "0 NaN Yes \n", "1 NaN NaN \n", "2 NaN NaN \n", "3 NaN NaN \n", "4 NaN NaN \n", "\n", "[5 rows x 56 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_survey.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/plain": [ "ID 0\n", "SeparationType 0\n", "Cease Date 0\n", "DETE Start Date 0\n", "Role Start Date 0\n", "Position 5\n", "Classification 367\n", "Region 0\n", "Business Unit 696\n", "Employment Status 5\n", "Career move to public sector 0\n", "Career move to private sector 0\n", "Interpersonal conflicts 0\n", "Job dissatisfaction 0\n", "Dissatisfaction with the department 0\n", "Physical work environment 0\n", "Lack of recognition 0\n", "Lack of job security 0\n", "Work location 0\n", "Employment conditions 0\n", "Maternity/family 0\n", "Relocation 0\n", "Study/Travel 0\n", "Ill Health 0\n", "Traumatic incident 0\n", "Work life balance 0\n", "Workload 0\n", "None of the above 0\n", "Professional Development 14\n", "Opportunities for promotion 87\n", "Staff morale 6\n", "Workplace issue 34\n", "Physical environment 5\n", "Worklife balance 7\n", "Stress and pressure support 12\n", "Performance of supervisor 9\n", "Peer support 10\n", "Initiative 9\n", "Skills 11\n", "Coach 55\n", "Career Aspirations 76\n", "Feedback 30\n", "Further PD 54\n", "Communication 8\n", "My say 10\n", "Information 6\n", "Kept informed 9\n", "Wellness programs 56\n", "Health & Safety 29\n", "Gender 24\n", "Age 11\n", "Aboriginal 806\n", "Torres Strait 819\n", "South Sea 815\n", "Disability 799\n", "NESB 790\n", "dtype: int64" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_survey.isnull().sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This information shows how the dataset contains 56 columns, most of which are string. A deeper analysis need to be done to select only the columns needed to achive our aim. \n", "\n", "Six columns (* Business Unit, Aboriginal, Torres Strait, South Sea, Disability, NESB*) have more than ~80% null values. Notice that, the dataset represent the missing values as *Not Stated*. \n", "\n", "Then, we will replace this value to *NaN* in order to the pandas library recognize it as null value." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "dete_survey = pd.read_csv('dete_survey.csv', na_values='Not Stated')" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "ID 0\n", "SeparationType 0\n", "Cease Date 34\n", "DETE Start Date 73\n", "Role Start Date 98\n", "Position 5\n", "Classification 367\n", "Region 105\n", "Business Unit 696\n", "Employment Status 5\n", "Career move to public sector 0\n", "Career move to private sector 0\n", "Interpersonal conflicts 0\n", "Job dissatisfaction 0\n", "Dissatisfaction with the department 0\n", "Physical work environment 0\n", "Lack of recognition 0\n", "Lack of job security 0\n", "Work location 0\n", "Employment conditions 0\n", "Maternity/family 0\n", "Relocation 0\n", "Study/Travel 0\n", "Ill Health 0\n", "Traumatic incident 0\n", "Work life balance 0\n", "Workload 0\n", "None of the above 0\n", "Professional Development 14\n", "Opportunities for promotion 87\n", "Staff morale 6\n", "Workplace issue 34\n", "Physical environment 5\n", "Worklife balance 7\n", "Stress and pressure support 12\n", "Performance of supervisor 9\n", "Peer support 10\n", "Initiative 9\n", "Skills 11\n", "Coach 55\n", "Career Aspirations 76\n", "Feedback 30\n", "Further PD 54\n", "Communication 8\n", "My say 10\n", "Information 6\n", "Kept informed 9\n", "Wellness programs 56\n", "Health & Safety 29\n", "Gender 24\n", "Age 11\n", "Aboriginal 806\n", "Torres Strait 819\n", "South Sea 815\n", "Disability 799\n", "NESB 790\n", "dtype: int64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_survey.isnull().sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can see how the number of missing values increase in some columns as *DETE Start Date, Role Start Date* and *Region*\n", "\n", "**Tafe Survey Description**" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 702 entries, 0 to 701\n", "Data columns (total 72 columns):\n", "Record ID 702 non-null float64\n", "Institute 702 non-null object\n", "WorkArea 702 non-null object\n", "CESSATION YEAR 695 non-null float64\n", "Reason for ceasing employment 701 non-null object\n", "Contributing Factors. Career Move - Public Sector 437 non-null object\n", "Contributing Factors. Career Move - Private Sector 437 non-null object\n", "Contributing Factors. Career Move - Self-employment 437 non-null object\n", "Contributing Factors. Ill Health 437 non-null object\n", "Contributing Factors. Maternity/Family 437 non-null object\n", "Contributing Factors. Dissatisfaction 437 non-null object\n", "Contributing Factors. Job Dissatisfaction 437 non-null object\n", "Contributing Factors. Interpersonal Conflict 437 non-null object\n", "Contributing Factors. Study 437 non-null object\n", "Contributing Factors. Travel 437 non-null object\n", "Contributing Factors. Other 437 non-null object\n", "Contributing Factors. NONE 437 non-null object\n", "Main Factor. Which of these was the main factor for leaving? 113 non-null object\n", "InstituteViews. Topic:1. I feel the senior leadership had a clear vision and direction 608 non-null object\n", "InstituteViews. Topic:2. I was given access to skills training to help me do my job better 613 non-null object\n", "InstituteViews. Topic:3. I was given adequate opportunities for personal development 610 non-null object\n", "InstituteViews. Topic:4. I was given adequate opportunities for promotion within %Institute]Q25LBL% 608 non-null object\n", "InstituteViews. Topic:5. I felt the salary for the job was right for the responsibilities I had 615 non-null object\n", "InstituteViews. Topic:6. The organisation recognised when staff did good work 607 non-null object\n", "InstituteViews. Topic:7. Management was generally supportive of me 614 non-null object\n", "InstituteViews. Topic:8. Management was generally supportive of my team 608 non-null object\n", "InstituteViews. Topic:9. I was kept informed of the changes in the organisation which would affect me 610 non-null object\n", "InstituteViews. Topic:10. Staff morale was positive within the Institute 602 non-null object\n", "InstituteViews. Topic:11. If I had a workplace issue it was dealt with quickly 601 non-null object\n", "InstituteViews. Topic:12. If I had a workplace issue it was dealt with efficiently 597 non-null object\n", "InstituteViews. Topic:13. If I had a workplace issue it was dealt with discreetly 601 non-null object\n", "WorkUnitViews. Topic:14. I was satisfied with the quality of the management and supervision within my work unit 609 non-null object\n", "WorkUnitViews. Topic:15. I worked well with my colleagues 605 non-null object\n", "WorkUnitViews. Topic:16. My job was challenging and interesting 607 non-null object\n", "WorkUnitViews. Topic:17. I was encouraged to use my initiative in the course of my work 610 non-null object\n", "WorkUnitViews. Topic:18. I had sufficient contact with other people in my job 613 non-null object\n", "WorkUnitViews. Topic:19. I was given adequate support and co-operation by my peers to enable me to do my job 609 non-null object\n", "WorkUnitViews. Topic:20. I was able to use the full range of my skills in my job 609 non-null object\n", "WorkUnitViews. Topic:21. I was able to use the full range of my abilities in my job. ; Category:Level of Agreement; Question:YOUR VIEWS ABOUT YOUR WORK UNIT] 608 non-null object\n", "WorkUnitViews. Topic:22. I was able to use the full range of my knowledge in my job 608 non-null object\n", "WorkUnitViews. Topic:23. My job provided sufficient variety 611 non-null object\n", "WorkUnitViews. Topic:24. I was able to cope with the level of stress and pressure in my job 610 non-null object\n", "WorkUnitViews. Topic:25. My job allowed me to balance the demands of work and family to my satisfaction 611 non-null object\n", "WorkUnitViews. Topic:26. My supervisor gave me adequate personal recognition and feedback on my performance 606 non-null object\n", "WorkUnitViews. Topic:27. My working environment was satisfactory e.g. sufficient space, good lighting, suitable seating and working area 610 non-null object\n", "WorkUnitViews. Topic:28. I was given the opportunity to mentor and coach others in order for me to pass on my skills and knowledge prior to my cessation date 609 non-null object\n", "WorkUnitViews. Topic:29. There was adequate communication between staff in my unit 603 non-null object\n", "WorkUnitViews. Topic:30. Staff morale was positive within my work unit 606 non-null object\n", "Induction. Did you undertake Workplace Induction? 619 non-null object\n", "InductionInfo. Topic:Did you undertake a Corporate Induction? 432 non-null object\n", "InductionInfo. Topic:Did you undertake a Institute Induction? 483 non-null object\n", "InductionInfo. Topic: Did you undertake Team Induction? 440 non-null object\n", "InductionInfo. Face to Face Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 555 non-null object\n", "InductionInfo. On-line Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 555 non-null object\n", "InductionInfo. Induction Manual Topic:Did you undertake a Corporate Induction? 555 non-null object\n", "InductionInfo. Face to Face Topic:Did you undertake a Institute Induction? 530 non-null object\n", "InductionInfo. On-line Topic:Did you undertake a Institute Induction? 555 non-null object\n", "InductionInfo. Induction Manual Topic:Did you undertake a Institute Induction? 553 non-null object\n", "InductionInfo. Face to Face Topic: Did you undertake Team Induction; Category? 555 non-null object\n", "InductionInfo. On-line Topic: Did you undertake Team Induction?process you undertook and how it was conducted.] 555 non-null object\n", "InductionInfo. Induction Manual Topic: Did you undertake Team Induction? 555 non-null object\n", "Workplace. Topic:Did you and your Manager develop a Performance and Professional Development Plan (PPDP)? 608 non-null object\n", "Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination? 594 non-null object\n", "Workplace. Topic:Does your workplace promote and practice the principles of employment equity? 587 non-null object\n", "Workplace. Topic:Does your workplace value the diversity of its employees? 586 non-null object\n", "Workplace. Topic:Would you recommend the Institute as an employer to others? 581 non-null object\n", "Gender. What is your Gender? 596 non-null object\n", "CurrentAge. Current Age 596 non-null object\n", "Employment Type. Employment Type 596 non-null object\n", "Classification. Classification 596 non-null object\n", "LengthofServiceOverall. Overall Length of Service at Institute (in years) 596 non-null object\n", "LengthofServiceCurrent. Length of Service at current workplace (in years) 596 non-null object\n", "dtypes: float64(2), object(70)\n", "memory usage: 395.0+ KB\n" ] } ], "source": [ "tafe_survey.info()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Record IDInstituteWorkAreaCESSATION YEARReason for ceasing employmentContributing Factors. Career Move - Public SectorContributing Factors. Career Move - Private SectorContributing Factors. Career Move - Self-employmentContributing Factors. Ill HealthContributing Factors. Maternity/Family...Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination?Workplace. Topic:Does your workplace promote and practice the principles of employment equity?Workplace. Topic:Does your workplace value the diversity of its employees?Workplace. Topic:Would you recommend the Institute as an employer to others?Gender. What is your Gender?CurrentAge. Current AgeEmployment Type. Employment TypeClassification. ClassificationLengthofServiceOverall. Overall Length of Service at Institute (in years)LengthofServiceCurrent. Length of Service at current workplace (in years)
06.341330e+17Southern Queensland Institute of TAFENon-Delivery (corporate)2010.0Contract ExpiredNaNNaNNaNNaNNaN...YesYesYesYesFemale26 30Temporary Full-timeAdministration (AO)1-21-2
16.341337e+17Mount Isa Institute of TAFENon-Delivery (corporate)2010.0Retirement-----...YesYesYesYesNaNNaNNaNNaNNaNNaN
26.341388e+17Mount Isa Institute of TAFEDelivery (teaching)2010.0Retirement-----...YesYesYesYesNaNNaNNaNNaNNaNNaN
36.341399e+17Mount Isa Institute of TAFENon-Delivery (corporate)2010.0Resignation-----...YesYesYesYesNaNNaNNaNNaNNaNNaN
46.341466e+17Southern Queensland Institute of TAFEDelivery (teaching)2010.0Resignation-Career Move - Private Sector---...YesYesYesYesMale41 45Permanent Full-timeTeacher (including LVT)3-43-4
\n", "

5 rows × 72 columns

\n", "
" ], "text/plain": [ " Record ID Institute \\\n", "0 6.341330e+17 Southern Queensland Institute of TAFE \n", "1 6.341337e+17 Mount Isa Institute of TAFE \n", "2 6.341388e+17 Mount Isa Institute of TAFE \n", "3 6.341399e+17 Mount Isa Institute of TAFE \n", "4 6.341466e+17 Southern Queensland Institute of TAFE \n", "\n", " WorkArea CESSATION YEAR Reason for ceasing employment \\\n", "0 Non-Delivery (corporate) 2010.0 Contract Expired \n", "1 Non-Delivery (corporate) 2010.0 Retirement \n", "2 Delivery (teaching) 2010.0 Retirement \n", "3 Non-Delivery (corporate) 2010.0 Resignation \n", "4 Delivery (teaching) 2010.0 Resignation \n", "\n", " Contributing Factors. Career Move - Public Sector \\\n", "0 NaN \n", "1 - \n", "2 - \n", "3 - \n", "4 - \n", "\n", " Contributing Factors. Career Move - Private Sector \\\n", "0 NaN \n", "1 - \n", "2 - \n", "3 - \n", "4 Career Move - Private Sector \n", "\n", " Contributing Factors. Career Move - Self-employment \\\n", "0 NaN \n", "1 - \n", "2 - \n", "3 - \n", "4 - \n", "\n", " Contributing Factors. Ill Health Contributing Factors. Maternity/Family \\\n", "0 NaN NaN \n", "1 - - \n", "2 - - \n", "3 - - \n", "4 - - \n", "\n", " ... \\\n", "0 ... \n", "1 ... \n", "2 ... \n", "3 ... \n", "4 ... \n", "\n", " Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination? \\\n", "0 Yes \n", "1 Yes \n", "2 Yes \n", "3 Yes \n", "4 Yes \n", "\n", " Workplace. Topic:Does your workplace promote and practice the principles of employment equity? \\\n", "0 Yes \n", "1 Yes \n", "2 Yes \n", "3 Yes \n", "4 Yes \n", "\n", " Workplace. Topic:Does your workplace value the diversity of its employees? \\\n", "0 Yes \n", "1 Yes \n", "2 Yes \n", "3 Yes \n", "4 Yes \n", "\n", " Workplace. Topic:Would you recommend the Institute as an employer to others? \\\n", "0 Yes \n", "1 Yes \n", "2 Yes \n", "3 Yes \n", "4 Yes \n", "\n", " Gender. What is your Gender? CurrentAge. Current Age \\\n", "0 Female 26 30 \n", "1 NaN NaN \n", "2 NaN NaN \n", "3 NaN NaN \n", "4 Male 41 45 \n", "\n", " Employment Type. Employment Type Classification. Classification \\\n", "0 Temporary Full-time Administration (AO) \n", "1 NaN NaN \n", "2 NaN NaN \n", "3 NaN NaN \n", "4 Permanent Full-time Teacher (including LVT) \n", "\n", " LengthofServiceOverall. Overall Length of Service at Institute (in years) \\\n", "0 1-2 \n", "1 NaN \n", "2 NaN \n", "3 NaN \n", "4 3-4 \n", "\n", " LengthofServiceCurrent. Length of Service at current workplace (in years) \n", "0 1-2 \n", "1 NaN \n", "2 NaN \n", "3 NaN \n", "4 3-4 \n", "\n", "[5 rows x 72 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_survey.head()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Record ID 0\n", "Institute 0\n", "WorkArea 0\n", "CESSATION YEAR 7\n", "Reason for ceasing employment 1\n", "Contributing Factors. Career Move - Public Sector 265\n", "Contributing Factors. Career Move - Private Sector 265\n", "Contributing Factors. Career Move - Self-employment 265\n", "Contributing Factors. Ill Health 265\n", "Contributing Factors. Maternity/Family 265\n", "Contributing Factors. Dissatisfaction 265\n", "Contributing Factors. Job Dissatisfaction 265\n", "Contributing Factors. Interpersonal Conflict 265\n", "Contributing Factors. Study 265\n", "Contributing Factors. Travel 265\n", "Contributing Factors. Other 265\n", "Contributing Factors. NONE 265\n", "Main Factor. Which of these was the main factor for leaving? 589\n", "InstituteViews. Topic:1. I feel the senior leadership had a clear vision and direction 94\n", "InstituteViews. Topic:2. I was given access to skills training to help me do my job better 89\n", "InstituteViews. Topic:3. I was given adequate opportunities for personal development 92\n", "InstituteViews. Topic:4. I was given adequate opportunities for promotion within %Institute]Q25LBL% 94\n", "InstituteViews. Topic:5. I felt the salary for the job was right for the responsibilities I had 87\n", "InstituteViews. Topic:6. The organisation recognised when staff did good work 95\n", "InstituteViews. Topic:7. Management was generally supportive of me 88\n", "InstituteViews. Topic:8. Management was generally supportive of my team 94\n", "InstituteViews. Topic:9. I was kept informed of the changes in the organisation which would affect me 92\n", "InstituteViews. Topic:10. Staff morale was positive within the Institute 100\n", "InstituteViews. Topic:11. If I had a workplace issue it was dealt with quickly 101\n", "InstituteViews. Topic:12. If I had a workplace issue it was dealt with efficiently 105\n", " ... \n", "WorkUnitViews. Topic:25. My job allowed me to balance the demands of work and family to my satisfaction 91\n", "WorkUnitViews. Topic:26. My supervisor gave me adequate personal recognition and feedback on my performance 96\n", "WorkUnitViews. Topic:27. My working environment was satisfactory e.g. sufficient space, good lighting, suitable seating and working area 92\n", "WorkUnitViews. Topic:28. I was given the opportunity to mentor and coach others in order for me to pass on my skills and knowledge prior to my cessation date 93\n", "WorkUnitViews. Topic:29. There was adequate communication between staff in my unit 99\n", "WorkUnitViews. Topic:30. Staff morale was positive within my work unit 96\n", "Induction. Did you undertake Workplace Induction? 83\n", "InductionInfo. Topic:Did you undertake a Corporate Induction? 270\n", "InductionInfo. Topic:Did you undertake a Institute Induction? 219\n", "InductionInfo. Topic: Did you undertake Team Induction? 262\n", "InductionInfo. Face to Face Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 147\n", "InductionInfo. On-line Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 147\n", "InductionInfo. Induction Manual Topic:Did you undertake a Corporate Induction? 147\n", "InductionInfo. Face to Face Topic:Did you undertake a Institute Induction? 172\n", "InductionInfo. On-line Topic:Did you undertake a Institute Induction? 147\n", "InductionInfo. Induction Manual Topic:Did you undertake a Institute Induction? 149\n", "InductionInfo. Face to Face Topic: Did you undertake Team Induction; Category? 147\n", "InductionInfo. On-line Topic: Did you undertake Team Induction?process you undertook and how it was conducted.] 147\n", "InductionInfo. Induction Manual Topic: Did you undertake Team Induction? 147\n", "Workplace. Topic:Did you and your Manager develop a Performance and Professional Development Plan (PPDP)? 94\n", "Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination? 108\n", "Workplace. Topic:Does your workplace promote and practice the principles of employment equity? 115\n", "Workplace. Topic:Does your workplace value the diversity of its employees? 116\n", "Workplace. Topic:Would you recommend the Institute as an employer to others? 121\n", "Gender. What is your Gender? 106\n", "CurrentAge. Current Age 106\n", "Employment Type. Employment Type 106\n", "Classification. Classification 106\n", "LengthofServiceOverall. Overall Length of Service at Institute (in years) 106\n", "LengthofServiceCurrent. Length of Service at current workplace (in years) 106\n", "Length: 72, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_survey.isnull().sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This information shows how the dataset contains 72 columns, most of which are string. We can see how the dataset contain many columns that we don't need to complete our analysis and many of them represent the same information that some columns from dete_survey dataset, but with different names.\n", "\n", "There are multiple columns/answers that indicate an employee resigned because they were dissatisfied. \n", "\n", "Most of the columns have null values, but only a few of them have more than ~30% null values.\n", "\n", "## Cleaning the *dete_survey* and *tafe_survey* datasets\n", "\n", "**Identify Missing Values and Drop Unnecessary Columns**\n", "\n", "Let's drop some columns from each dataframe that we won't use in our analysis to make the dataframes easier to work with. " ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "dete_survey_updated = dete_survey.drop(dete_survey.columns[28:49], axis=1)\n", "tafe_survey_updated = tafe_survey.drop(tafe_survey.columns[17:66], axis=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Clean Column Names**\n", "\n", "Let's turn the attention to the column names. Each dataframe contains many of the same columns, but the column names are different.\n", "\n", "First, we will rename columns in the *dete_survey_updated* dataframe using the following criteria to update the column names:\n", "- Make all the capitalization lowercase.\n", "- Remove any trailing whitespace from the end of the strings.\n", "- Replace spaces with underscores ('_')." ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Index(['id', 'separationtype', 'cease_date', 'dete_start_date',\n", " 'role_start_date', 'position', 'classification', 'region',\n", " 'business_unit', 'employment_status', 'career_move_to_public_sector',\n", " 'career_move_to_private_sector', 'interpersonal_conflicts',\n", " 'job_dissatisfaction', 'dissatisfaction_with_the_department',\n", " 'physical_work_environment', 'lack_of_recognition',\n", " 'lack_of_job_security', 'work_location', 'employment_conditions',\n", " 'maternity/family', 'relocation', 'study/travel', 'ill_health',\n", " 'traumatic_incident', 'work_life_balance', 'workload',\n", " 'none_of_the_above', 'gender', 'age', 'aboriginal', 'torres_strait',\n", " 'south_sea', 'disability', 'nesb'],\n", " dtype='object')" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_survey_updated.columns = dete_survey_updated.columns.str.replace(' ', '_').str.strip().str.lower()\n", "dete_survey_updated.columns" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Second, we will rename columns in the tafe_survey_updated dataframe as follows:\n", "- 'Record ID': 'id'\n", "- 'CESSATION YEAR': 'cease_date'\n", "- 'Reason for ceasing employment': 'separationtype'\n", "- 'Gender. What is your Gender?': 'gender'\n", "- 'CurrentAge. Current Age': 'age'\n", "- 'Employment Type. Employment Type': 'employment_status'\n", "- 'Classification. Classification': 'position'\n", "- 'LengthofServiceOverall. Overall Length of Service at -Institute (in years)': 'institute_service'\n", "- 'LengthofServiceCurrent. Length of Service at current workplace (in years)': 'role_service'\n", "\n", "The columns renamed are the one that we will use in our analysis." ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Index(['id', 'Institute', 'WorkArea', 'cease_date', 'separationtype',\n", " 'Contributing Factors. Career Move - Public Sector ',\n", " 'Contributing Factors. Career Move - Private Sector ',\n", " 'Contributing Factors. Career Move - Self-employment',\n", " 'Contributing Factors. Ill Health',\n", " 'Contributing Factors. Maternity/Family',\n", " 'Contributing Factors. Dissatisfaction',\n", " 'Contributing Factors. Job Dissatisfaction',\n", " 'Contributing Factors. Interpersonal Conflict',\n", " 'Contributing Factors. Study', 'Contributing Factors. Travel',\n", " 'Contributing Factors. Other', 'Contributing Factors. NONE', 'gender',\n", " 'age', 'employment_status', 'position', 'institute_service',\n", " 'role_service'],\n", " dtype='object')" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_survey_updated.rename(columns = { 'Record ID': 'id', 'CESSATION YEAR': 'cease_date', 'Reason for ceasing employment':'separationtype', 'Gender. What is your Gender?':'gender', 'CurrentAge. Current Age': 'age', 'Employment Type. Employment Type': 'employment_status', 'Classification. Classification': 'position', 'LengthofServiceOverall. Overall Length of Service at Institute (in years)': 'institute_service', 'LengthofServiceCurrent. Length of Service at current workplace (in years)': 'role_service'}, inplace=True)\n", "tafe_survey_updated.columns" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Filter the Data**\n", "\n", "Let's remove more of the data we don't need. Since our goal is to analyse the employees who resigned, we will only consider the respondents that contains the string *'Resignation'* in the *'separationtype*' column." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Age Retirement 285\n", "Resignation-Other reasons 150\n", "Resignation-Other employer 91\n", "Resignation-Move overseas/interstate 70\n", "Voluntary Early Retirement (VER) 67\n", "Ill Health Retirement 61\n", "Other 49\n", "Contract Expired 34\n", "Termination 15\n", "Name: separationtype, dtype: int64" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_survey_updated['separationtype'].value_counts()" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(311, 35)\n" ] }, { "data": { "text/plain": [ "Resignation-Other reasons 150\n", "Resignation-Other employer 91\n", "Resignation-Move overseas/interstate 70\n", "Name: separationtype, dtype: int64" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pattern_resignation = r\"Resignation\"\n", "dete_resignations = dete_survey_updated.loc[dete_survey_updated['separationtype'].str.contains(pattern_resignation)].copy()\n", "print(dete_resignations.shape)\n", "dete_resignations['separationtype'].value_counts()" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Resignation 340\n", "Contract Expired 127\n", "Retrenchment/ Redundancy 104\n", "Retirement 82\n", "Transfer 25\n", "Termination 23\n", "Name: separationtype, dtype: int64" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_survey_updated['separationtype'].value_counts()" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(340, 23)\n" ] }, { "data": { "text/plain": [ "Resignation 340\n", "Name: separationtype, dtype: int64" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_resignations = tafe_survey_updated.loc[tafe_survey_updated['separationtype'] == 'Resignation'].copy()\n", "print(tafe_resignations.shape)\n", "tafe_resignations['separationtype'].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In the last steps, we have saved in the *dete_resignations* and *tafe_resignations* dataframes the rows who represent the resignations from dete_survey_updated and tafe_survey_updated datasets, respectively.\n", "\n", "**Verify the Data**\n", "\n", "We'll focus on verifying that the years in the *cease_date* and *dete_start_date* columns make sense. We will check the following:\n", "- Since the cease_date is the last year of the person's employment and the dete_start_date is the person's first year of employment, it wouldn't make sense to have years after the current date.\n", "- Given that most people in this field start working in their 20s, it's also unlikely that the dete_start_date was before the year 1940.\n" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "2012 126\n", "2013 74\n", "01/2014 22\n", "12/2013 17\n", "06/2013 14\n", "09/2013 11\n", "11/2013 9\n", "07/2013 9\n", "10/2013 6\n", "08/2013 4\n", "05/2012 2\n", "05/2013 2\n", "2010 1\n", "07/2006 1\n", "07/2012 1\n", "09/2010 1\n", "Name: cease_date, dtype: int64" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_resignations['cease_date'].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As can be seen, we need to clean the *cease_date* column in the dete_resignations dataset." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2013.0 146\n", "2012.0 129\n", "2014.0 22\n", "2010.0 2\n", "2006.0 1\n", "Name: cease_date, dtype: int64" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pattern_year = r\"(?P[1-2][0-9]{3})\"\n", "dete_resignations['cease_date'] = dete_resignations['cease_date'].str.extract(pattern_year).astype(float)\n", "dete_resignations['cease_date'].value_counts()" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1963.0 1\n", "1971.0 1\n", "1972.0 1\n", "1973.0 1\n", "1974.0 2\n", "1975.0 1\n", "1976.0 2\n", "1977.0 1\n", "1980.0 5\n", "1982.0 1\n", "1983.0 2\n", "1984.0 1\n", "1985.0 3\n", "1986.0 3\n", "1987.0 1\n", "1988.0 4\n", "1989.0 4\n", "1990.0 5\n", "1991.0 4\n", "1992.0 6\n", "1993.0 5\n", "1994.0 6\n", "1995.0 4\n", "1996.0 6\n", "1997.0 5\n", "1998.0 6\n", "1999.0 8\n", "2000.0 9\n", "2001.0 3\n", "2002.0 6\n", "2003.0 6\n", "2004.0 14\n", "2005.0 15\n", "2006.0 13\n", "2007.0 21\n", "2008.0 22\n", "2009.0 13\n", "2010.0 17\n", "2011.0 24\n", "2012.0 21\n", "2013.0 10\n", "Name: dete_start_date, dtype: int64" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_resignations['dete_start_date'].value_counts().sort_index()" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "2009.0 2\n", "2010.0 68\n", "2011.0 116\n", "2012.0 94\n", "2013.0 55\n", "Name: cease_date, dtype: int64" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_resignations['cease_date'].value_counts().sort_index()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We will plot the values of these columns with a boxplot to identify any values that look wrong." ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5,1,'Distribution of cease_date in the tafe_resignations dataset')" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", "import seaborn as sns\n", "\n", "df_columns_plot = dete_resignations[['dete_start_date','cease_date']]\n", "fig = plt.figure(figsize=(15, 3))\n", "ax = fig.add_subplot(1,2,1)\n", "df_columns_plot.boxplot(ax=ax)\n", "ax.spines[\"right\"].set_visible(False) \n", "ax.spines[\"left\"].set_visible(False)\n", "ax.spines[\"top\"].set_visible(False) \n", "ax.spines[\"bottom\"].set_visible(False)\n", "ax.set_ylim(1960,2016)\n", "ax.set_yticks([1960,2016])\n", "ax.grid(False)\n", "ax.set_title('Distribution of dete_start_date and cease_date in the dete_resignations dataset')\n", "\n", "ax = fig.add_subplot(1,2,2)\n", "tafe_resignations['cease_date'].plot.box(ax=ax)\n", "ax.spines[\"right\"].set_visible(False) \n", "ax.spines[\"left\"].set_visible(False)\n", "ax.spines[\"top\"].set_visible(False) \n", "ax.spines[\"bottom\"].set_visible(False)\n", "ax.set_ylim(1960,2016)\n", "ax.set_yticks([1960,2016])\n", "ax.set_title('Distribution of cease_date in the tafe_resignations dataset')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can see how the years's values are logical. However, there are some outliers values from the *dete_start_date* column.\n", "\n", "## Transforming the datasets\n", "\n", "**Create column to represent years of service**\n", "\n", "To get all the information needed to achive our goals, we need to create a new column that represents the length of time an employee spent in a workplace, called years of service in the Human Resources field. \n", "\n", "Notice that the *tafe_resignations* dataframe already contains a \"service\" column, which we renamed to *institute_service*. In order to analyze both surveys together, we'll have to create a corresponding institute_service column in dete_resignations. To do so, we will create an institute_service column in dete_resignations, substracting the *dete_start_date* from *the cease_date*. \n" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " dete_start_date cease_date institute_service\n", "3 2005.0 2012.0 7.0\n", "5 1994.0 2012.0 18.0\n", "8 2009.0 2012.0 3.0\n", "9 1997.0 2012.0 15.0\n", "11 2009.0 2012.0 3.0\n", "\n", "Int64Index: 340 entries, 3 to 701\n", "Data columns (total 23 columns):\n", "id 340 non-null float64\n", "Institute 340 non-null object\n", "WorkArea 340 non-null object\n", "cease_date 335 non-null float64\n", "separationtype 340 non-null object\n", "Contributing Factors. Career Move - Public Sector 332 non-null object\n", "Contributing Factors. Career Move - Private Sector 332 non-null object\n", "Contributing Factors. Career Move - Self-employment 332 non-null object\n", "Contributing Factors. Ill Health 332 non-null object\n", "Contributing Factors. Maternity/Family 332 non-null object\n", "Contributing Factors. Dissatisfaction 332 non-null object\n", "Contributing Factors. Job Dissatisfaction 332 non-null object\n", "Contributing Factors. Interpersonal Conflict 332 non-null object\n", "Contributing Factors. Study 332 non-null object\n", "Contributing Factors. Travel 332 non-null object\n", "Contributing Factors. Other 332 non-null object\n", "Contributing Factors. NONE 332 non-null object\n", "gender 290 non-null object\n", "age 290 non-null object\n", "employment_status 290 non-null object\n", "position 290 non-null object\n", "institute_service 290 non-null object\n", "role_service 290 non-null object\n", "dtypes: float64(2), object(21)\n", "memory usage: 63.8+ KB\n" ] } ], "source": [ "dete_resignations['institute_service'] = dete_resignations['cease_date'] - dete_resignations['dete_start_date']\n", "print(dete_resignations[['dete_start_date', 'cease_date', 'institute_service']].head())\n", "dete_resignations['institute_service'].value_counts(dropna=False)\n", "tafe_resignations.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Identify Dissatisfied Employees**\n", "\n", "We'll identify any employees who resigned because they were dissatisfied.\n", "\n", "Below are the columns we'll use to categorize employees as \"dissatisfied\" from each dataframe. \n", "\n", "*tafe_survey_updated*:\n", "- Contributing Factors. Dissatisfaction\n", "- Contributing Factors. Job Dissatisfaction\n", "\n", "*dete_survey_updated*:\n", "- job_dissatisfaction\n", "- dissatisfaction_with_the_department\n", "- physical_work_environment\n", "- lack_of_recognition\n", "- lack_of_job_security\n", "- work_location\n", "- employment_conditions\n", "- work_life_balance\n", "- workload\n", "\n", "If the employee indicated any of the factors above caused them to resign, we'll mark them as dissatisfied in a new column.\n", "\n", "To create the new column, we'll do the following:\n", "\n", "1. Convert the values in the 'Contributing Factors. Dissatisfaction' and 'Contributing Factors. Job Dissatisfaction' columns in the tafe_resignations dataframe to True, False, or NaN values.\n", "2. If any of the columns listed above contain a True value, we'll add a True value to a new column named dissatisfied." ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "- 277\n", "Contributing Factors. Dissatisfaction 55\n", "NaN 8\n", "Name: Contributing Factors. Dissatisfaction, dtype: int64" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_resignations['Contributing Factors. Dissatisfaction'].value_counts(dropna=False)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "- 270\n", "Job Dissatisfaction 62\n", "NaN 8\n", "Name: Contributing Factors. Job Dissatisfaction, dtype: int64" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tafe_resignations['Contributing Factors. Job Dissatisfaction'].value_counts(dropna=False)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False 241\n", "True 91\n", "NaN 8\n", "Name: dissatisfied, dtype: int64" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def update_vals(element):\n", " if pd.isnull(element):\n", " return np.nan\n", " if element == '-':\n", " return False\n", " else:\n", " return True\n", "factor_dissatisfaction_tafe = tafe_resignations[['Contributing Factors. Dissatisfaction', 'Contributing Factors. Job Dissatisfaction']].applymap(update_vals)\n", "tafe_resignations['dissatisfied'] = factor_dissatisfaction_tafe.any(axis=1, skipna=False)\n", "tafe_resignations['dissatisfied'].value_counts(dropna=False)" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False 162\n", "True 149\n", "Name: dissatisfied, dtype: int64" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "factor_dissatisfaction_dete = dete_resignations[['job_dissatisfaction', 'dissatisfaction_with_the_department', 'physical_work_environment','lack_of_recognition','lack_of_job_security','work_location','employment_conditions','work_life_balance','workload']]\n", "dete_resignations['dissatisfied'] = factor_dissatisfaction_dete.any(axis=1, skipna=False)\n", "dete_resignations['dissatisfied'].value_counts(dropna=False)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [], "source": [ "dete_resignations_up = dete_resignations.copy()\n", "tafe_resignations_up = tafe_resignations.copy()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Combine the datasets\n", "\n", "In the last steps, we have transformed the dataframes to be ready to combine them. \n", "\n", "First, let's add a column to each dataframe that will allow us to easily distinguish between the two." ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(651, 53)" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dete_resignations_up['institute'] = 'DETE'\n", "tafe_resignations_up['institute'] = 'TAFE'\n", "combined = pd.concat([dete_resignations_up, tafe_resignations_up], ignore_index = True, sort=True)\n", "combined.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We still have some columns left in the dataframe that we don't need to complete our analysis. For this reason, we will drop any columns with less than 500 non null values." ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(651, 10)" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated = combined.dropna(thresh=500, axis=1).copy()\n", "combined_updated.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can see how the number of columns is reduced to 10." ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agecease_datedissatisfiedemployment_statusgenderidinstituteinstitute_servicepositionseparationtype
036-402012.0FalsePermanent Full-timeFemale4.0DETE7TeacherResignation-Other reasons
141-452012.0TruePermanent Full-timeFemale6.0DETE18Guidance OfficerResignation-Other reasons
231-352012.0FalsePermanent Full-timeFemale9.0DETE3TeacherResignation-Other reasons
346-502012.0TruePermanent Part-timeFemale10.0DETE15Teacher AideResignation-Other employer
431-352012.0FalsePermanent Full-timeMale12.0DETE3TeacherResignation-Move overseas/interstate
\n", "
" ], "text/plain": [ " age cease_date dissatisfied employment_status gender id \\\n", "0 36-40 2012.0 False Permanent Full-time Female 4.0 \n", "1 41-45 2012.0 True Permanent Full-time Female 6.0 \n", "2 31-35 2012.0 False Permanent Full-time Female 9.0 \n", "3 46-50 2012.0 True Permanent Part-time Female 10.0 \n", "4 31-35 2012.0 False Permanent Full-time Male 12.0 \n", "\n", " institute institute_service position \\\n", "0 DETE 7 Teacher \n", "1 DETE 18 Guidance Officer \n", "2 DETE 3 Teacher \n", "3 DETE 15 Teacher Aide \n", "4 DETE 3 Teacher \n", "\n", " separationtype \n", "0 Resignation-Other reasons \n", "1 Resignation-Other reasons \n", "2 Resignation-Other reasons \n", "3 Resignation-Other employer \n", "4 Resignation-Move overseas/interstate " ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Clean the *institute_service* column**\n", "\n", "We'll have to clean up the institute_service column, since it currently contains values in a couple different forms" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "NaN 88\n", "Less than 1 year 73\n", "1-2 64\n", "3-4 63\n", "5-6 33\n", "11-20 26\n", "5.0 23\n", "1.0 22\n", "7-10 21\n", "0.0 20\n", "3.0 20\n", "6.0 17\n", "4.0 16\n", "9.0 14\n", "2.0 14\n", "7.0 13\n", "More than 20 years 10\n", "8.0 8\n", "13.0 8\n", "15.0 7\n", "20.0 7\n", "10.0 6\n", "12.0 6\n", "14.0 6\n", "17.0 6\n", "22.0 6\n", "18.0 5\n", "16.0 5\n", "11.0 4\n", "23.0 4\n", "24.0 4\n", "19.0 3\n", "32.0 3\n", "39.0 3\n", "21.0 3\n", "28.0 2\n", "30.0 2\n", "26.0 2\n", "36.0 2\n", "25.0 2\n", "29.0 1\n", "31.0 1\n", "27.0 1\n", "34.0 1\n", "35.0 1\n", "38.0 1\n", "41.0 1\n", "42.0 1\n", "49.0 1\n", "33.0 1\n", "Name: institute_service, dtype: int64" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated['institute_service'].value_counts(dropna=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To analyze the data, we'll convert these numbers into categories. We'll base our anlaysis on this [article](https://www.businesswire.com/news/home/20171108006002/en/Age-Number-Engage-Employees-Career-Stage). \n", "\n", "We'll use the slightly modified definitions below:\n", "\n", "- New: Less than 3 years at a company\n", "- Experienced: 3-6 years at a company\n", "- Established: 7-10 years at a company\n", "- Veteran: 11 or more years at a company\n", "\n", "Let's categorize the values in the *institute_service* column using the definitions above.\n", "\n", "First, we'll extract the years of service from each value in the institute_service column.\n" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "combined_updated['institute_service_up'] = combined_updated.loc[:,'institute_service'].astype('str').str.extract(r'(\\d{1,2})').astype('float')\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we'll map each value to one of the career stage definitions above store them at a new column *service_cat*" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "New 193\n", "Experienced 172\n", "Veteran 136\n", "NaN 88\n", "Established 62\n", "Name: service_cat, dtype: int64" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def category(val):\n", " if pd.isnull(val):\n", " return np.nan\n", " elif val < 3:\n", " return 'New'\n", " elif 3 <= val <= 6:\n", " return 'Experienced'\n", " elif 7 <= val <= 10:\n", " return 'Established'\n", " elif val >= 11:\n", " return 'Veteran'\n", "\n", "combined_updated['service_cat'] = combined_updated['institute_service_up'].apply(category) \n", "combined_updated['service_cat'].value_counts(dropna = False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Clean the *age* column**\n", "\n", "We'll have to clean up the *age* column, since it currently contains values in a couple different forms" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "51-55 71\n", "NaN 55\n", "41-45 48\n", "41 45 45\n", "46-50 42\n", "36-40 41\n", "46 50 39\n", "26-30 35\n", "21 25 33\n", "26 30 32\n", "36 40 32\n", "31 35 32\n", "56 or older 29\n", "21-25 29\n", "31-35 29\n", "56-60 26\n", "61 or older 23\n", "20 or younger 10\n", "Name: age, dtype: int64" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated['age'].value_counts(dropna=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To analyze the data, we'll convert these ages into categories.\n", "\n", "We'll use the definitions below:\n", "\n", "- Young: Less than 35 years old\n", "- Middle Age: 35-45 years old\n", "- Old: 46 or more \n", "\n", "Let's categorize the values in the *age* column using the definitions above.\n", "\n", "First, we'll extract the years of each value in the *age* column.\n" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "data": { "text/plain": [ " 41.0 93\n", " 46.0 81\n", " 36.0 73\n", " 51.0 71\n", " 26.0 67\n", " 21.0 62\n", " 31.0 61\n", "NaN 55\n", " 56.0 55\n", " 61.0 23\n", " 20.0 10\n", "Name: age_up, dtype: int64" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated['age_up'] = combined_updated.loc[:,'age'].astype('str').str.extract(r'(\\d{2})').astype('float')\n", "combined_updated['age_up'].value_counts(dropna=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we'll map each value to one of the age categories defined above and store them at a new column *age_category*" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Old 230\n", "Young 200\n", "Middle Age 166\n", "NaN 55\n", "Name: age_category, dtype: int64" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def age_category(val):\n", " if pd.isnull(val):\n", " return np.nan\n", " elif val < 35:\n", " return 'Young'\n", " elif 35 <= val <= 45:\n", " return 'Middle Age'\n", " elif val >= 46:\n", " return 'Old'\n", "\n", "combined_updated['age_category'] = combined_updated['age_up'].apply(age_category) \n", "combined_updated['age_category'].value_counts(dropna = False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Fill missing values in dissatisfied column**\n", "\n", "Now, we will fill missing values in the dissatisfied column with the value that occurs most frequently in this column." ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False 403\n", "True 240\n", "NaN 8\n", "Name: dissatisfied, dtype: int64" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated['dissatisfied'].value_counts(dropna = False)" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False 411\n", "True 240\n", "Name: dissatisfied, dtype: int64" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_updated['dissatisfied'] = combined_updated['dissatisfied'].fillna(False)\n", "combined_updated['dissatisfied'].value_counts(dropna = False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Initial Analysis\n", "\n", "**Percentage of dissatisfied employees in each *service_cat* group**\n", "\n", "We will aggregate the dissatisfied column to calculate the percentage of dissatisfied employees in each *service_cat* group. Since a *True* value is considered to be 1, calculating the mean will also calculate the percentage of dissatisfied employees. " ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
dissatisfied
service_cat
Established0.516129
Experienced0.343023
New0.295337
Veteran0.485294
\n", "
" ], "text/plain": [ " dissatisfied\n", "service_cat \n", "Established 0.516129\n", "Experienced 0.343023\n", "New 0.295337\n", "Veteran 0.485294" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "percentage_service_dissatisfied = combined_updated.pivot_table('dissatisfied','service_cat')\n", "percentage_service_dissatisfied" ] }, { "cell_type": "code", "execution_count": 52, "metadata": { "scrolled": true }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ax = percentage_service_dissatisfied.plot(kind='bar')\n", "ax.set_title('Percentage of dissatisfied employees for each service_cat category')\n", "ax.spines[\"right\"].set_visible(False) \n", "ax.spines[\"left\"].set_visible(False)\n", "ax.spines[\"top\"].set_visible(False) \n", "ax.spines[\"bottom\"].set_visible(False)\n", "ax.tick_params(bottom=False, top=False, left=False, right=False, labelbottom=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The figure shows how the higuer percentage of dissatisfied employees belongs to the *Established* and *Veteran* groups with values close to 50% of the employees. Then, the employees who have been longer period of time in the institues resigning due to some kind of dissatisfaction more than the one who have been shorter time.\n", "\n", "**Percentage of dissatisfied employees in each age category group**\n", "\n", "Let's agregate the dissatisfied column to calculate the percentage of dissatisfied employees in each *age* group." ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
dissatisfied
age_category
Middle Age0.361446
Old0.408696
Young0.360000
\n", "
" ], "text/plain": [ " dissatisfied\n", "age_category \n", "Middle Age 0.361446\n", "Old 0.408696\n", "Young 0.360000" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "percentage_age_dissatisfied = combined_updated.pivot_table('dissatisfied','age_category')\n", "percentage_age_dissatisfied" ] }, { "cell_type": "code", "execution_count": 53, "metadata": { "scrolled": true }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ax = percentage_age_dissatisfied.plot(kind='bar')\n", "ax.set_title('Percentage of dissatisfied employees for each age category')\n", "ax.spines[\"right\"].set_visible(False) \n", "ax.spines[\"left\"].set_visible(False)\n", "ax.spines[\"top\"].set_visible(False) \n", "ax.spines[\"bottom\"].set_visible(False)\n", "ax.tick_params(bottom=False, top=False, left=False, right=False, labelbottom=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The figure shows how the higuer percentage of dissatisfied employees belongs to the older people. However, almost the 36% of the younger people resigning due to some kind of dissatisfaction." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Conclusion\n", "\n", "In this project, we analyzed survey data from employees of the Department of Education, Training and Employment (DETE) and the Technical and Further Education (TAFE) institute in Australia to analyse the characteristics of the employees who resigning due to some kind of dissatisfaction. We reached that older employees who spend more time in the institues present higher probabilities to resigning because dissatisfaction than younger people who work less time in these institues.\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }