In this guided project, we'll work with exit surveys from employees of the Department of Education, Training and Employment (DETE) and the Technical and Further Education (TAFE) institute in Queensland, Australia. The TAFE exit survey here and the survey for the DETE here. There are some slight modifications in the data set we used comparing to the original, including changing the encoding to UTF-8 (the original ones are encoded using cp1252.)
Witht the above dataset we want to ask the below questions:
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?
Are younger employees resigning due to some kind of dissatisfaction? What about older employees?
# import libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
# import dataset
dete_survey = pd.read_csv('dete_survey.csv')
tafe_survey = pd.read_csv('tafe_survey.csv')
dete_survey.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 822 entries, 0 to 821 Data columns (total 56 columns): ID 822 non-null int64 SeparationType 822 non-null object Cease Date 822 non-null object DETE Start Date 822 non-null object Role Start Date 822 non-null object Position 817 non-null object Classification 455 non-null object Region 822 non-null object Business Unit 126 non-null object Employment Status 817 non-null object Career move to public sector 822 non-null bool Career move to private sector 822 non-null bool Interpersonal conflicts 822 non-null bool Job dissatisfaction 822 non-null bool Dissatisfaction with the department 822 non-null bool Physical work environment 822 non-null bool Lack of recognition 822 non-null bool Lack of job security 822 non-null bool Work location 822 non-null bool Employment conditions 822 non-null bool Maternity/family 822 non-null bool Relocation 822 non-null bool Study/Travel 822 non-null bool Ill Health 822 non-null bool Traumatic incident 822 non-null bool Work life balance 822 non-null bool Workload 822 non-null bool None of the above 822 non-null bool Professional Development 808 non-null object Opportunities for promotion 735 non-null object Staff morale 816 non-null object Workplace issue 788 non-null object Physical environment 817 non-null object Worklife balance 815 non-null object Stress and pressure support 810 non-null object Performance of supervisor 813 non-null object Peer support 812 non-null object Initiative 813 non-null object Skills 811 non-null object Coach 767 non-null object Career Aspirations 746 non-null object Feedback 792 non-null object Further PD 768 non-null object Communication 814 non-null object My say 812 non-null object Information 816 non-null object Kept informed 813 non-null object Wellness programs 766 non-null object Health & Safety 793 non-null object Gender 798 non-null object Age 811 non-null object Aboriginal 16 non-null object Torres Strait 3 non-null object South Sea 7 non-null object Disability 23 non-null object NESB 32 non-null object dtypes: bool(18), int64(1), object(37) memory usage: 258.6+ KB
# finding the number & percentage of missing value
dete_len = dete_survey.shape[0] # total number of columns
n = 0 # columns with missing value counter
for col in dete_survey.columns:
if dete_survey[col].isnull().any():
n += 1
missing = dete_survey[col].isnull().sum()
print('{}: {}, {:.2%}'.format(col, missing, missing / dete_len))
print('\n', n, ' columns with missing value in dete_survey.')
Position: 5, 0.61% Classification: 367, 44.65% Business Unit: 696, 84.67% Employment Status: 5, 0.61% Professional Development: 14, 1.70% Opportunities for promotion: 87, 10.58% Staff morale: 6, 0.73% Workplace issue: 34, 4.14% Physical environment: 5, 0.61% Worklife balance: 7, 0.85% Stress and pressure support: 12, 1.46% Performance of supervisor: 9, 1.09% Peer support: 10, 1.22% Initiative: 9, 1.09% Skills: 11, 1.34% Coach: 55, 6.69% Career Aspirations: 76, 9.25% Feedback: 30, 3.65% Further PD: 54, 6.57% Communication: 8, 0.97% My say: 10, 1.22% Information: 6, 0.73% Kept informed: 9, 1.09% Wellness programs: 56, 6.81% Health & Safety: 29, 3.53% Gender: 24, 2.92% Age: 11, 1.34% Aboriginal: 806, 98.05% Torres Strait: 819, 99.64% South Sea: 815, 99.15% Disability: 799, 97.20% NESB: 790, 96.11% 32 columns with missing value in dete_survey.
dete_survey.head(2)
ID | SeparationType | Cease Date | DETE Start Date | Role Start Date | Position | Classification | Region | Business Unit | Employment Status | ... | Kept informed | Wellness programs | Health & Safety | Gender | Age | Aboriginal | Torres Strait | South Sea | Disability | NESB | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | Ill Health Retirement | 08/2012 | 1984 | 2004 | Public Servant | A01-A04 | Central Office | Corporate Strategy and Peformance | Permanent Full-time | ... | N | N | N | Male | 56-60 | NaN | NaN | NaN | NaN | Yes |
1 | 2 | Voluntary Early Retirement (VER) | 08/2012 | Not Stated | Not Stated | Public Servant | AO5-AO7 | Central Office | Corporate Strategy and Peformance | Permanent Full-time | ... | N | N | N | Male | 56-60 | NaN | NaN | NaN | NaN | NaN |
2 rows × 56 columns
DETE Start Date
and Role Start Date
have the value Not Stated, which should be regconized as missing value as well.
tafe_survey.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 702 entries, 0 to 701 Data columns (total 72 columns): Record ID 702 non-null float64 Institute 702 non-null object WorkArea 702 non-null object CESSATION YEAR 695 non-null float64 Reason for ceasing employment 701 non-null object Contributing Factors. Career Move - Public Sector 437 non-null object Contributing Factors. Career Move - Private Sector 437 non-null object Contributing Factors. Career Move - Self-employment 437 non-null object Contributing Factors. Ill Health 437 non-null object Contributing Factors. Maternity/Family 437 non-null object Contributing Factors. Dissatisfaction 437 non-null object Contributing Factors. Job Dissatisfaction 437 non-null object Contributing Factors. Interpersonal Conflict 437 non-null object Contributing Factors. Study 437 non-null object Contributing Factors. Travel 437 non-null object Contributing Factors. Other 437 non-null object Contributing Factors. NONE 437 non-null object Main Factor. Which of these was the main factor for leaving? 113 non-null object InstituteViews. Topic:1. I feel the senior leadership had a clear vision and direction 608 non-null object InstituteViews. Topic:2. I was given access to skills training to help me do my job better 613 non-null object InstituteViews. Topic:3. I was given adequate opportunities for personal development 610 non-null object InstituteViews. Topic:4. I was given adequate opportunities for promotion within %Institute]Q25LBL% 608 non-null object InstituteViews. Topic:5. I felt the salary for the job was right for the responsibilities I had 615 non-null object InstituteViews. Topic:6. The organisation recognised when staff did good work 607 non-null object InstituteViews. Topic:7. Management was generally supportive of me 614 non-null object InstituteViews. Topic:8. Management was generally supportive of my team 608 non-null object InstituteViews. Topic:9. I was kept informed of the changes in the organisation which would affect me 610 non-null object InstituteViews. Topic:10. Staff morale was positive within the Institute 602 non-null object InstituteViews. Topic:11. If I had a workplace issue it was dealt with quickly 601 non-null object InstituteViews. Topic:12. If I had a workplace issue it was dealt with efficiently 597 non-null object InstituteViews. Topic:13. If I had a workplace issue it was dealt with discreetly 601 non-null object WorkUnitViews. Topic:14. I was satisfied with the quality of the management and supervision within my work unit 609 non-null object WorkUnitViews. Topic:15. I worked well with my colleagues 605 non-null object WorkUnitViews. Topic:16. My job was challenging and interesting 607 non-null object WorkUnitViews. Topic:17. I was encouraged to use my initiative in the course of my work 610 non-null object WorkUnitViews. Topic:18. I had sufficient contact with other people in my job 613 non-null object 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 WorkUnitViews. Topic:20. I was able to use the full range of my skills in my job 609 non-null object 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 WorkUnitViews. Topic:22. I was able to use the full range of my knowledge in my job 608 non-null object WorkUnitViews. Topic:23. My job provided sufficient variety 611 non-null object WorkUnitViews. Topic:24. I was able to cope with the level of stress and pressure in my job 610 non-null object WorkUnitViews. Topic:25. My job allowed me to balance the demands of work and family to my satisfaction 611 non-null object WorkUnitViews. Topic:26. My supervisor gave me adequate personal recognition and feedback on my performance 606 non-null object WorkUnitViews. Topic:27. My working environment was satisfactory e.g. sufficient space, good lighting, suitable seating and working area 610 non-null object 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 WorkUnitViews. Topic:29. There was adequate communication between staff in my unit 603 non-null object WorkUnitViews. Topic:30. Staff morale was positive within my work unit 606 non-null object Induction. Did you undertake Workplace Induction? 619 non-null object InductionInfo. Topic:Did you undertake a Corporate Induction? 432 non-null object InductionInfo. Topic:Did you undertake a Institute Induction? 483 non-null object InductionInfo. Topic: Did you undertake Team Induction? 440 non-null object InductionInfo. Face to Face Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 555 non-null object InductionInfo. On-line Topic:Did you undertake a Corporate Induction; Category:How it was conducted? 555 non-null object InductionInfo. Induction Manual Topic:Did you undertake a Corporate Induction? 555 non-null object InductionInfo. Face to Face Topic:Did you undertake a Institute Induction? 530 non-null object InductionInfo. On-line Topic:Did you undertake a Institute Induction? 555 non-null object InductionInfo. Induction Manual Topic:Did you undertake a Institute Induction? 553 non-null object InductionInfo. Face to Face Topic: Did you undertake Team Induction; Category? 555 non-null object InductionInfo. On-line Topic: Did you undertake Team Induction?process you undertook and how it was conducted.] 555 non-null object InductionInfo. Induction Manual Topic: Did you undertake Team Induction? 555 non-null object Workplace. Topic:Did you and your Manager develop a Performance and Professional Development Plan (PPDP)? 608 non-null object Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination? 594 non-null object Workplace. Topic:Does your workplace promote and practice the principles of employment equity? 587 non-null object Workplace. Topic:Does your workplace value the diversity of its employees? 586 non-null object Workplace. Topic:Would you recommend the Institute as an employer to others? 581 non-null object Gender. What is your Gender? 596 non-null object CurrentAge. Current Age 596 non-null object Employment Type. Employment Type 596 non-null object Classification. Classification 596 non-null object LengthofServiceOverall. Overall Length of Service at Institute (in years) 596 non-null object LengthofServiceCurrent. Length of Service at current workplace (in years) 596 non-null object dtypes: float64(2), object(70) memory usage: 395.0+ KB
# finding the number & percentage of missing value
tafe_len = tafe_survey.shape[0] # total number of columns
n = 0 # columns with missing value counter
for col in tafe_survey.columns:
if tafe_survey[col].isnull().any():
n += 1
missing = tafe_survey[col].isnull().sum()
print('{}: {}, {:.2%}'.format(col, missing, missing / dete_len))
print('\n', n, 'columns with missing values in tafe_survey.')
CESSATION YEAR: 7, 0.85% Reason for ceasing employment: 1, 0.12% Contributing Factors. Career Move - Public Sector : 265, 32.24% Contributing Factors. Career Move - Private Sector : 265, 32.24% Contributing Factors. Career Move - Self-employment: 265, 32.24% Contributing Factors. Ill Health: 265, 32.24% Contributing Factors. Maternity/Family: 265, 32.24% Contributing Factors. Dissatisfaction: 265, 32.24% Contributing Factors. Job Dissatisfaction: 265, 32.24% Contributing Factors. Interpersonal Conflict: 265, 32.24% Contributing Factors. Study: 265, 32.24% Contributing Factors. Travel: 265, 32.24% Contributing Factors. Other: 265, 32.24% Contributing Factors. NONE: 265, 32.24% Main Factor. Which of these was the main factor for leaving?: 589, 71.65% InstituteViews. Topic:1. I feel the senior leadership had a clear vision and direction: 94, 11.44% InstituteViews. Topic:2. I was given access to skills training to help me do my job better: 89, 10.83% InstituteViews. Topic:3. I was given adequate opportunities for personal development: 92, 11.19% InstituteViews. Topic:4. I was given adequate opportunities for promotion within %Institute]Q25LBL%: 94, 11.44% InstituteViews. Topic:5. I felt the salary for the job was right for the responsibilities I had: 87, 10.58% InstituteViews. Topic:6. The organisation recognised when staff did good work: 95, 11.56% InstituteViews. Topic:7. Management was generally supportive of me: 88, 10.71% InstituteViews. Topic:8. Management was generally supportive of my team: 94, 11.44% InstituteViews. Topic:9. I was kept informed of the changes in the organisation which would affect me: 92, 11.19% InstituteViews. Topic:10. Staff morale was positive within the Institute: 100, 12.17% InstituteViews. Topic:11. If I had a workplace issue it was dealt with quickly: 101, 12.29% InstituteViews. Topic:12. If I had a workplace issue it was dealt with efficiently: 105, 12.77% InstituteViews. Topic:13. If I had a workplace issue it was dealt with discreetly: 101, 12.29% WorkUnitViews. Topic:14. I was satisfied with the quality of the management and supervision within my work unit: 93, 11.31% WorkUnitViews. Topic:15. I worked well with my colleagues: 97, 11.80% WorkUnitViews. Topic:16. My job was challenging and interesting: 95, 11.56% WorkUnitViews. Topic:17. I was encouraged to use my initiative in the course of my work: 92, 11.19% WorkUnitViews. Topic:18. I had sufficient contact with other people in my job: 89, 10.83% WorkUnitViews. Topic:19. I was given adequate support and co-operation by my peers to enable me to do my job: 93, 11.31% WorkUnitViews. Topic:20. I was able to use the full range of my skills in my job: 93, 11.31% 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]: 94, 11.44% WorkUnitViews. Topic:22. I was able to use the full range of my knowledge in my job: 94, 11.44% WorkUnitViews. Topic:23. My job provided sufficient variety: 91, 11.07% WorkUnitViews. Topic:24. I was able to cope with the level of stress and pressure in my job: 92, 11.19% WorkUnitViews. Topic:25. My job allowed me to balance the demands of work and family to my satisfaction: 91, 11.07% WorkUnitViews. Topic:26. My supervisor gave me adequate personal recognition and feedback on my performance: 96, 11.68% WorkUnitViews. Topic:27. My working environment was satisfactory e.g. sufficient space, good lighting, suitable seating and working area: 92, 11.19% 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, 11.31% WorkUnitViews. Topic:29. There was adequate communication between staff in my unit: 99, 12.04% WorkUnitViews. Topic:30. Staff morale was positive within my work unit: 96, 11.68% Induction. Did you undertake Workplace Induction?: 83, 10.10% InductionInfo. Topic:Did you undertake a Corporate Induction?: 270, 32.85% InductionInfo. Topic:Did you undertake a Institute Induction?: 219, 26.64% InductionInfo. Topic: Did you undertake Team Induction?: 262, 31.87% InductionInfo. Face to Face Topic:Did you undertake a Corporate Induction; Category:How it was conducted?: 147, 17.88% InductionInfo. On-line Topic:Did you undertake a Corporate Induction; Category:How it was conducted?: 147, 17.88% InductionInfo. Induction Manual Topic:Did you undertake a Corporate Induction?: 147, 17.88% InductionInfo. Face to Face Topic:Did you undertake a Institute Induction?: 172, 20.92% InductionInfo. On-line Topic:Did you undertake a Institute Induction?: 147, 17.88% InductionInfo. Induction Manual Topic:Did you undertake a Institute Induction?: 149, 18.13% InductionInfo. Face to Face Topic: Did you undertake Team Induction; Category?: 147, 17.88% InductionInfo. On-line Topic: Did you undertake Team Induction?process you undertook and how it was conducted.]: 147, 17.88% InductionInfo. Induction Manual Topic: Did you undertake Team Induction?: 147, 17.88% Workplace. Topic:Did you and your Manager develop a Performance and Professional Development Plan (PPDP)?: 94, 11.44% Workplace. Topic:Does your workplace promote a work culture free from all forms of unlawful discrimination?: 108, 13.14% Workplace. Topic:Does your workplace promote and practice the principles of employment equity?: 115, 13.99% Workplace. Topic:Does your workplace value the diversity of its employees?: 116, 14.11% Workplace. Topic:Would you recommend the Institute as an employer to others?: 121, 14.72% Gender. What is your Gender?: 106, 12.90% CurrentAge. Current Age: 106, 12.90% Employment Type. Employment Type: 106, 12.90% Classification. Classification: 106, 12.90% LengthofServiceOverall. Overall Length of Service at Institute (in years): 106, 12.90% LengthofServiceCurrent. Length of Service at current workplace (in years): 106, 12.90% 69 columns with missing values in tafe_survey.
tafe_survey.head(2)
Record ID | Institute | WorkArea | CESSATION YEAR | Reason for ceasing employment | Contributing Factors. Career Move - Public Sector | Contributing Factors. Career Move - Private Sector | Contributing Factors. Career Move - Self-employment | Contributing Factors. Ill Health | Contributing 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 Age | Employment Type. Employment Type | Classification. Classification | LengthofServiceOverall. Overall Length of Service at Institute (in years) | LengthofServiceCurrent. Length of Service at current workplace (in years) | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 6.341330e+17 | Southern Queensland Institute of TAFE | Non-Delivery (corporate) | 2010.0 | Contract Expired | NaN | NaN | NaN | NaN | NaN | ... | Yes | Yes | Yes | Yes | Female | 26 30 | Temporary Full-time | Administration (AO) | 1-2 | 1-2 |
1 | 6.341337e+17 | Mount Isa Institute of TAFE | Non-Delivery (corporate) | 2010.0 | Retirement | - | - | - | - | - | ... | Yes | Yes | Yes | Yes | NaN | NaN | NaN | NaN | NaN | NaN |
2 rows × 72 columns
In some columns like Career Move - Public Secotr
contains the value -, which should be regconized as missing value.
dete_survey = pd.read_csv('dete_survey.csv',
na_values = 'Not Stated')
As mentioned before, we consider only dissatification as the target reason in this project. We will drop all other reasons to trim the dataset.
dete_survey_updated = dete_survey.drop(dete_survey.columns[28:49],
axis = 1)
tafe_survey_updated = tafe_survey.drop(tafe_survey.columns[17:66],
axis = 1)
In order to combine both data sets, we need a common and standardized column names for both data sets.
# lower case, remove trailing whitesapce and replace ' ' as '_'
dete_survey_updated.columns = dete_survey_updated.columns.str.lower().str.strip().str.replace(' ', '_')
dete_survey_updated.columns
Index(['id', 'separationtype', 'cease_date', 'dete_start_date', 'role_start_date', 'position', 'classification', 'region', 'business_unit', 'employment_status', 'career_move_to_public_sector', 'career_move_to_private_sector', 'interpersonal_conflicts', 'job_dissatisfaction', 'dissatisfaction_with_the_department', 'physical_work_environment', 'lack_of_recognition', 'lack_of_job_security', 'work_location', 'employment_conditions', 'maternity/family', 'relocation', 'study/travel', 'ill_health', 'traumatic_incident', 'work_life_balance', 'workload', 'none_of_the_above', 'gender', 'age', 'aboriginal', 'torres_strait', 'south_sea', 'disability', 'nesb'], dtype='object')
column_names = {'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'}
# lower case, remove trailing whitesapce and replace ' ' as '_'
tafe_survey_updated = tafe_survey_updated.rename(column_names, axis=1)
tafe_survey_updated.columns
Index(['id', 'Institute', 'WorkArea', 'cease_date', 'separationtype', 'Contributing Factors. Career Move - Public Sector ', 'Contributing Factors. Career Move - Private Sector ', 'Contributing Factors. Career Move - Self-employment', 'Contributing Factors. Ill Health', 'Contributing Factors. Maternity/Family', 'Contributing Factors. Dissatisfaction', 'Contributing Factors. Job Dissatisfaction', 'Contributing Factors. Interpersonal Conflict', 'Contributing Factors. Study', 'Contributing Factors. Travel', 'Contributing Factors. Other', 'Contributing Factors. NONE', 'gender', 'age', 'employment_status', 'position', 'institute_service', 'role_service'], dtype='object')
There are many reason an employee leaves the institute, but we oonly need the data from those resigned. Therefore, we will keep those rows which contain Resgination in separationtype
, excluding NaN.
dete_survey_updated['separationtype'].value_counts()
Age Retirement 285 Resignation-Other reasons 150 Resignation-Other employer 91 Resignation-Move overseas/interstate 70 Voluntary Early Retirement (VER) 67 Ill Health Retirement 61 Other 49 Contract Expired 34 Termination 15 Name: separationtype, dtype: int64
dete_resignations = dete_survey_updated[
dete_survey_updated['separationtype'].str.contains('Resignation', na=False)
].copy()
tafe_survey_updated['separationtype'].value_counts()
Resignation 340 Contract Expired 127 Retrenchment/ Redundancy 104 Retirement 82 Transfer 25 Termination 23 Name: separationtype, dtype: int64
tafe_resignations = tafe_survey_updated[
tafe_survey_updated['separationtype'].str.contains('Resignation', na=False)
].copy()
In this step, we'll focus on verifying that the years in the cease_date
and dete_start_date
columns make sense.
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.dete_start_date
was before the year 1940.dete_resignations['cease_date'].value_counts()
2012 126 2013 74 01/2014 22 12/2013 17 06/2013 14 09/2013 11 07/2013 9 11/2013 9 10/2013 6 08/2013 4 05/2012 2 05/2013 2 07/2006 1 2010 1 07/2012 1 09/2010 1 Name: cease_date, dtype: int64
pattern =r"([1-2][0-9]{3})"
dete_resignations['cease_date'] = dete_resignations['cease_date'].str.extract(pattern).astype('float')
dete_resignations['cease_date'].value_counts().sort_index()
/dataquest/system/env/python3/lib/python3.4/site-packages/ipykernel/__main__.py:2: FutureWarning: currently extract(expand=None) means expand=False (return Index/Series/DataFrame) but in a future version of pandas this will be changed to expand=True (return DataFrame)
2006.0 1 2010.0 2 2012.0 129 2013.0 146 2014.0 22 Name: cease_date, dtype: int64
dete_resignations['dete_start_date'].value_counts().sort_index()
1963.0 1 1971.0 1 1972.0 1 1973.0 1 1974.0 2 1975.0 1 1976.0 2 1977.0 1 1980.0 5 1982.0 1 1983.0 2 1984.0 1 1985.0 3 1986.0 3 1987.0 1 1988.0 4 1989.0 4 1990.0 5 1991.0 4 1992.0 6 1993.0 5 1994.0 6 1995.0 4 1996.0 6 1997.0 5 1998.0 6 1999.0 8 2000.0 9 2001.0 3 2002.0 6 2003.0 6 2004.0 14 2005.0 15 2006.0 13 2007.0 21 2008.0 22 2009.0 13 2010.0 17 2011.0 24 2012.0 21 2013.0 10 Name: dete_start_date, dtype: int64
pattern =r"([1-2][0-9]{3})"
tafe_resignations['cease_date'].value_counts().sort_index()
2009.0 2 2010.0 68 2011.0 116 2012.0 94 2013.0 55 Name: cease_date, dtype: int64
tafe_resignations['cease_date'].value_counts().sort_index()
2009.0 2 2010.0 68 2011.0 116 2012.0 94 2013.0 55 Name: cease_date, dtype: int64
dete_resignations.boxplot(['cease_date','dete_start_date'])
plt.title('Cease_date and dete_Start_date in dete_survey')
<matplotlib.text.Text at 0x7fb295387a58>
The cease_date
are all between 2009 and 2013 while the dete_start_date
is starting from 1963.
tafe_resignations.boxplot(['cease_date'])
plt.title('Cease_date in tafe_survey')
plt.ylim(2008, 2020)
(2008, 2020)
The range of cease_date
in tafe_survey is similar to dete_survey.
In general, both data set do not have any major issues with the years.
As we also want to know if there are any relationship between service length of an employee and the resignation due to dissatisfaction, we need extract the length of service from cease_date
and dete_start_date
.
dete_resignations['institute_service'] = dete_resignations['cease_date'] - dete_resignations['dete_start_date']
dete_resignations.boxplot('institute_service')
plt.title('Length of institute service before resignation')
<matplotlib.text.Text at 0x7fb2931835c0>
Meanwhile, we have to classify the data into dissatisfcation or not.
Let's check with tafe_survey first. There are two columns about dissatiscfaction: Contributing Factors. Dissatisfaction
and Contributing Factors. Job Dissatisfaction
. We will create a new column to combine these information.
tafe_resignations['Contributing Factors. Dissatisfaction'].value_counts(dropna = False)
- 277 Contributing Factors. Dissatisfaction 55 NaN 8 Name: Contributing Factors. Dissatisfaction, dtype: int64
tafe_resignations['Contributing Factors. Job Dissatisfaction'].value_counts(dropna = False)
- 270 Job Dissatisfaction 62 NaN 8 Name: Contributing Factors. Job Dissatisfaction, dtype: int64
Both columns have only 2 values so we can change them into boolean type.
# function to change variables into boolean
def update_vals(string):
if string is np.nan: return np.nan
elif string is '-': return False
else: return True
tafe_resignations['Contributing Factors. Dissatisfaction'] = tafe_resignations['Contributing Factors. Dissatisfaction'].map(update_vals)
tafe_resignations['Contributing Factors. Job Dissatisfaction'] = tafe_resignations['Contributing Factors. Job Dissatisfaction'].map(update_vals)
# create dissatisfied column. True if any column is true.
tafe_resignations['dissatisfied'] = tafe_resignations[['Contributing Factors. Dissatisfaction',
'Contributing Factors. Job Dissatisfaction']].any(axis=1,
skipna=False)
For dete_survey, we have more columns regarding dissatisification. Unluckily, all those columns are already in boolean type.
dissatisfaction_col = ['job_dissatisfaction','dissatisfaction_with_the_department','physical_work_environment',
'lack_of_recognition','lack_of_job_security','work_location','employment_conditions',
'work_life_balance','workload']
for col in dissatisfaction_col:
print(col, ': \n')
print(dete_resignations[col].value_counts(dropna = False))
job_dissatisfaction : False 270 True 41 Name: job_dissatisfaction, dtype: int64 dissatisfaction_with_the_department : False 282 True 29 Name: dissatisfaction_with_the_department, dtype: int64 physical_work_environment : False 305 True 6 Name: physical_work_environment, dtype: int64 lack_of_recognition : False 278 True 33 Name: lack_of_recognition, dtype: int64 lack_of_job_security : False 297 True 14 Name: lack_of_job_security, dtype: int64 work_location : False 293 True 18 Name: work_location, dtype: int64 employment_conditions : False 288 True 23 Name: employment_conditions, dtype: int64 work_life_balance : False 243 True 68 Name: work_life_balance, dtype: int64 workload : False 284 True 27 Name: workload, dtype: int64
# create dissatisfied column. True if any column is true.
dete_resignations['dissatisfied'] = dete_resignations[dissatisfaction_col].any(axis=1, skipna=False)
dete_resignations_up = dete_resignations.copy()
tafe_resignations_up = tafe_resignations.copy()
Since both data sets are clean and ready, we will combine them together. In order to distinguish both institute, we will create an extra column institute
. Also we will only keep the necessay columns existing in both data set. Considering that both data set have more than 500 rows, we can exclude all columns which has less than 500 non missing values.
dete_resignations_up['institute'] = 'DETE'
tafe_resignations_up['institute'] = 'TAFE'
combined = pd.concat([dete_resignations_up, tafe_resignations_up],
axis = 0,
ignore_index = True)
combined_updated = combined.dropna(axis = 1, thresh = 500)
Now that we've combined our dataframes, we're almost at a place where we can perform some kind of analysis! First, though, we'll have to clean up the institute_service
column. This column is tricky to clean because it currently contains values in a couple different forms:
combined_updated['institute_service'].value_counts(dropna=False)
NaN 88 Less than 1 year 73 1-2 64 3-4 63 5-6 33 11-20 26 5.0 23 1.0 22 7-10 21 0.0 20 3.0 20 6.0 17 4.0 16 2.0 14 9.0 14 7.0 13 More than 20 years 10 8.0 8 13.0 8 15.0 7 20.0 7 12.0 6 22.0 6 17.0 6 10.0 6 14.0 6 18.0 5 16.0 5 23.0 4 24.0 4 11.0 4 39.0 3 21.0 3 32.0 3 19.0 3 36.0 2 30.0 2 26.0 2 28.0 2 25.0 2 29.0 1 31.0 1 49.0 1 33.0 1 34.0 1 35.0 1 38.0 1 41.0 1 42.0 1 27.0 1 Name: institute_service, dtype: int64
To analyze the data, we'll convert these numbers into categories. We'll base our analysis on this article, which makes the argument that understanding employee's needs according to career stage instead of age is more effective.
We'll use the slightly modified definitions below:
Let's categorize the values in the institute_service
column using the definitions above.
# extract the first digit from institute_service for grouping
combined_updated['institute_service'] = combined_updated['institute_service'].astype('str').str.extract(r'(\d+)').astype('float')
/dataquest/system/env/python3/lib/python3.4/site-packages/ipykernel/__main__.py:2: FutureWarning: currently extract(expand=None) means expand=False (return Index/Series/DataFrame) but in a future version of pandas this will be changed to expand=True (return DataFrame) /dataquest/system/env/python3/lib/python3.4/site-packages/ipykernel/__main__.py:2: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
# mapping value into group
def service_level(num):
if pd.isnull(num): return np.nan
elif num < 3: return 'New'
elif num < 7: return 'Experienced'
elif num < 11: return 'Established'
else: return 'Veteran'
combined_updated['service_cat'] = combined_updated['institute_service'].map(service_level)
/dataquest/system/env/python3/lib/python3.4/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
# create service_cat for the new group
combined_updated['service_cat'].value_counts(dropna = False)
New 193 Experienced 172 Veteran 136 NaN 88 Established 62 Name: service_cat, dtype: int64
Before heading to analysis, we have to fill in all missing value to prevent any errors. We will use the mode as the filling value.
combined_updated['dissatisfied'].value_counts(dropna = False)
False 403 True 240 NaN 8 Name: dissatisfied, dtype: int64
combined_updated['dissatisfied'].fillna(False, inplace=True)
/dataquest/system/env/python3/lib/python3.4/site-packages/pandas/core/generic.py:4355: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
table = pd.pivot_table(combined_updated, index = 'service_cat', values = 'dissatisfied')
table['pos'] = [2,1,0,3]
table['pos'] = table['pos'].astype('int')
table.sort_values(by=['pos'])['dissatisfied'].plot(kind='barh')
plt.title('Percentage of dissatisfied employees among service_cat')
# sns.set_style('white')
sns.despine(bottom = True, left= True)
Above plot provides us a clear answer to our first questions: Around 1/3 of the employees who worked for a short period resigned due to dissatisfaction. Meanwhile, half of the employees who worked for a longer period is much higher, around 50%.