In [9]:
#Load needed modules and functions
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
from pylab import figure, show
import pandas as pd
from pandas import DataFrame, Series
In [12]:
#set up path to the data files
import os
data_folder = os.path.join(os.pardir, "data")
In [13]:
import glob
file_names = glob.glob(data_folder + "/*")
file_names
Out[13]:
['..\\data\\Abilities.txt',
'..\\data\\Content Model Reference.txt',
'..\\data\\DWA Reference.txt',
'..\\data\\Education, Training, and Experience Categories.txt',
'..\\data\\Education, Training, and Experience.txt',
'..\\data\\Green DWA Reference.txt',
'..\\data\\Green Occupations.txt',
'..\\data\\Green Task Statements.txt',
'..\\data\\Interests.txt',
'..\\data\\IWA Reference.txt',
'..\\data\\Job Zone Reference.txt',
'..\\data\\Job Zones.txt',
'..\\data\\Knowledge.txt',
'..\\data\\Level Scale Anchors.txt',
'..\\data\\Occupation Data.txt',
'..\\data\\Occupation Level Metadata.txt',
'..\\data\\Read Me.txt',
'..\\data\\Scales Reference.txt',
'..\\data\\Skills.txt',
'..\\data\\Survey Booklet Locations.txt',
'..\\data\\Task Categories.txt',
'..\\data\\Task Ratings.txt',
'..\\data\\Task Statements.txt',
'..\\data\\Tasks to DWAs.txt',
'..\\data\\Tasks to Green DWAs.txt',
'..\\data\\Work Activities.txt',
'..\\data\\Work Context Categories.txt',
'..\\data\\Work Context.txt',
'..\\data\\Work Styles.txt',
'..\\data\\Work Values.txt']
In [14]:
import re
p = re.compile('data\\\(.*).txt')
name_list = []
for name in file_names:
frame_name = p.findall(name)[0]
frame_name = frame_name.lower().replace(" ","_")
frame_name = frame_name.replace(",","")
name_list.append(frame_name)
frame = pd.read_table(name, sep= '\t')
#reformat column names
columns = frame.columns
columns = [x.lower().replace("*","").replace("-","_").replace(" ","_") for x in columns]
frame.columns = columns
#create a variable named the frame_name
vars()[frame_name] = frame
#print file_name
#name_list.append(p.findall(name)[0])
In [15]:
#here is a data frame with all of the data frames we now have
name_list
Out[15]:
['abilities',
'content_model_reference',
'dwa_reference',
'education_training_and_experience_categories',
'education_training_and_experience',
'green_dwa_reference',
'green_occupations',
'green_task_statements',
'interests',
'iwa_reference',
'job_zone_reference',
'job_zones',
'knowledge',
'level_scale_anchors',
'occupation_data',
'occupation_level_metadata',
'read_me',
'scales_reference',
'skills',
'survey_booklet_locations',
'task_categories',
'task_ratings',
'task_statements',
'tasks_to_dwas',
'tasks_to_green_dwas',
'work_activities',
'work_context_categories',
'work_context',
'work_styles',
'work_values']
In [16]:
#create a dictionary that contains all of the dataframe column names, and the number of times they occur
from collections import Counter
column_names = Counter()
for name in name_list:
data = vars()[name]
for column in data.columns:
column_names[column]+=1
column_names
Out[16]:
Counter({'onet_soc_code': 18, 'element_id': 17, 'date': 16, 'scale_id': 16, 'domain_source': 15, 'element_name': 14, 'data_value': 10, 'n': 9, 'standard_error': 8, 'upper_ci_bound': 8, 'lower_ci_bound': 8, 'recommend_suppress': 8, 'category': 6, 'not_relevant': 5, 'task_id': 5, 'category_description': 3, 'green_dwa_id': 2, 'dwa_id': 2, 'description': 2, 'job_zone': 2, 'task': 2, 'iwa_id': 2, 'scale_name': 1, 'green_dwa_title': 1, 'anchor_value': 1, 'survey_item_number': 1, 'minimum': 1, 'experience': 1, 'education': 1, 'anchor_description': 1, 'title': 1, 'percent': 1, 'response': 1, 'svp_range': 1, 'task_type': 1, 'iwa_title': 1, 'job_training': 1, 'name': 1, 'dwa_title': 1, 'green_task_type': 1, 'maximum': 1, 'green_occupational_category': 1, 'item': 1, 'incumbents_responding': 1, 'onet_18.1_database': 1, 'examples': 1})
In [46]:
#function that calculates the number of features available in a dataframe (the # rows divided by # of jobs)
def feature(dataframe):
return len(dataframe)/len(dataframe.onet_soc_code.unique())
In [31]:
#function that gets unique values of a dataframe column and merges it with another data frame
def getDescriptions(data, metadata, column_name):
uniques = pd.DataFrame(data[column_name].unique())
uniques.columns = [column_name]
return pd.merge(uniques,metadata,on=column_name)
In [45]:
#function to calculate the percentage of rows in an onet data table are relevant to the given job
def getRelevance(dataframe):
relevant_rows = dataframe[dataframe['not_relevant']== 'Y']
relevance = float(len(relevant_rows))/float(len(dataframe))
return relevance*100
In [44]:
#function to calculate how many rows are recommended for exclusion in an onet data table
def getExclusions(dataframe):
excluded_rows = dataframe[dataframe['recommend_suppress'] == 'Y']
exclusions = float(len(excluded_rows))/float(len(dataframe))
return exclusions * 100
In [78]:
abilities.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum).head()
#abilities[['onet_soc_code','data_value']].groupby('onet_soc_code').apply(sum)
Out[78]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
1.A.1.a.1
Oral Comprehension
IM
11-1011.00
1.A.1.a.1
Oral Comprehension
IM
4.5
8
0.19
4.13
4.87
N
n/a
06/2006
Analyst
LV
11-1011.00
1.A.1.a.1
Oral Comprehension
LV
4.75
8
0.25
4.26
5.24
N
N
06/2006
Analyst
1.A.1.a.2
Written Comprehension
IM
11-1011.00
1.A.1.a.2
Written Comprehension
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2006
Analyst
LV
11-1011.00
1.A.1.a.2
Written Comprehension
LV
4.63
8
0.32
3.99
5.26
N
N
06/2006
Analyst
1.A.1.a.3
Oral Expression
IM
11-1011.00
1.A.1.a.3
Oral Expression
IM
4.5
8
0.19
4.13
4.87
N
n/a
06/2006
Analyst
5 rows × 13 columns
In [19]:
#what are the unique element names?
abilities.element_id.unique()
Out[19]:
array(['Oral Comprehension', 'Written Comprehension', 'Oral Expression',
'Written Expression', 'Fluency of Ideas', 'Originality',
'Problem Sensitivity', 'Deductive Reasoning', 'Inductive Reasoning',
'Information Ordering', 'Category Flexibility',
'Mathematical Reasoning', 'Number Facility', 'Memorization',
'Speed of Closure', 'Flexibility of Closure', 'Perceptual Speed',
'Spatial Orientation', 'Visualization', 'Selective Attention',
'Time Sharing', 'Arm-Hand Steadiness', 'Manual Dexterity',
'Finger Dexterity', 'Control Precision', 'Multilimb Coordination',
'Response Orientation', 'Rate Control', 'Reaction Time',
'Wrist-Finger Speed', 'Speed of Limb Movement', 'Static Strength',
'Explosive Strength', 'Dynamic Strength', 'Trunk Strength',
'Stamina', 'Extent Flexibility', 'Dynamic Flexibility',
'Gross Body Coordination', 'Gross Body Equilibrium', 'Near Vision',
'Far Vision', 'Visual Color Discrimination', 'Night Vision',
'Peripheral Vision', 'Depth Perception', 'Glare Sensitivity',
'Hearing Sensitivity', 'Auditory Attention', 'Sound Localization',
'Speech Recognition', 'Speech Clarity'], dtype=object)
In [20]:
#how many different ability element names are there?
len(abilities.element_name.unique())
Out[20]:
52
In [43]:
#what are the scales of each ability?
getDescriptions(abilities,scales_reference,"scale_id")
Out[43]:
scale_id
scale_name
minimum
maximum
0
IM
Importance
1
5
1
LV
Level
0
7
2 rows × 4 columns
In [47]:
#how many abilities features are there?
feature(abilities)
Out[47]:
104
In [48]:
#percentage of relevant ability rows?
getRelevance(abilities)
Out[48]:
9.665388782398534
In [49]:
#percentage of rows to be excluded
getExclusions(abilities)
Out[49]:
0.5042086840570048
In [40]:
#domain data set #2- what doe the education, training, and experience data look like
#it has onet_soc_code-element_id/_name-scale_id-category
education_training_and_experience.groupby(['onet_soc_code','element_id','element_name','scale_id',"category"]).apply(sum)
Out[40]:
onet_soc_code
element_id
element_name
scale_id
category
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
date
domain_source
onet_soc_code
element_id
element_name
scale_id
category
11-1011.00
2.D.1
Required Level of Education
RL
1
11-1011.00
2.D.1
Required Level of Education
RL
1
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
2
11-1011.00
2.D.1
Required Level of Education
RL
2
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
3
11-1011.00
2.D.1
Required Level of Education
RL
3
0.53
30
0.57
0.06
4.69
N
06/2006
Incumbent
4
11-1011.00
2.D.1
Required Level of Education
RL
4
2.77
30
2.39
0.46
14.86
N
06/2006
Incumbent
5
11-1011.00
2.D.1
Required Level of Education
RL
5
0.09
30
0.09
0.01
0.78
N
06/2006
Incumbent
6
11-1011.00
2.D.1
Required Level of Education
RL
6
50.34
30
20.55
15.87
84.49
Y
06/2006
Incumbent
7
11-1011.00
2.D.1
Required Level of Education
RL
7
13.4
30
12.71
1.62
59.25
N
06/2006
Incumbent
8
11-1011.00
2.D.1
Required Level of Education
RL
8
24.68
30
14.29
6.37
61.22
N
06/2006
Incumbent
9
11-1011.00
2.D.1
Required Level of Education
RL
9
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
10
11-1011.00
2.D.1
Required Level of Education
RL
10
6.76
30
6.87
0.77
40.24
N
06/2006
Incumbent
11
11-1011.00
2.D.1
Required Level of Education
RL
11
1.43
30
1.40
0.19
9.99
N
06/2006
Incumbent
12
11-1011.00
2.D.1
Required Level of Education
RL
12
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
3.A.1
Related Work Experience
RW
1
11-1011.00
3.A.1
Related Work Experience
RW
1
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
2
11-1011.00
3.A.1
Related Work Experience
RW
2
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
3
11-1011.00
3.A.1
Related Work Experience
RW
3
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
4
11-1011.00
3.A.1
Related Work Experience
RW
4
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
5
11-1011.00
3.A.1
Related Work Experience
RW
5
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
6
11-1011.00
3.A.1
Related Work Experience
RW
6
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
7
11-1011.00
3.A.1
Related Work Experience
RW
7
2.68
30
2.41
0.42
15.39
N
06/2006
Incumbent
8
11-1011.00
3.A.1
Related Work Experience
RW
8
28.63
30
17.17
6.71
69.10
N
06/2006
Incumbent
9
11-1011.00
3.A.1
Related Work Experience
RW
9
3.16
30
2.22
0.73
12.55
N
06/2006
Incumbent
10
11-1011.00
3.A.1
Related Work Experience
RW
10
14.68
30
12.82
2.08
58.24
N
06/2006
Incumbent
11
11-1011.00
3.A.1
Related Work Experience
RW
11
50.86
30
20.42
16.29
84.62
Y
06/2006
Incumbent
3.A.2
On-Site or In-Plant Training
PT
1
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
1
24.9
30
14.97
6.06
63.03
N
06/2006
Incumbent
2
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
2
3.38
30
2.56
0.70
14.79
N
06/2006
Incumbent
3
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
3
2.16
30
2.24
0.25
16.18
N
06/2006
Incumbent
4
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
4
15.49
30
12.94
2.37
58.05
N
06/2006
Incumbent
5
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
5
3.21
30
2.01
0.87
11.09
N
06/2006
Incumbent
6
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
6
0.45
30
0.42
0.07
2.94
N
06/2006
Incumbent
7
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
7
13.64
30
12.91
1.65
59.76
N
06/2006
Incumbent
8
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
8
3.93
30
2.60
0.99
14.35
N
06/2006
Incumbent
9
11-1011.00
3.A.2
On-Site or In-Plant Training
PT
9
32.85
30
23.58
5.21
81.33
Y
06/2006
Incumbent
3.A.3
On-the-Job Training
OJ
1
11-1011.00
3.A.3
On-the-Job Training
OJ
1
21.6
30
14.37
4.63
60.98
N
06/2006
Incumbent
2
11-1011.00
3.A.3
On-the-Job Training
OJ
2
0.0
30
0.00
n/a
n/a
N
06/2006
Incumbent
3
11-1011.00
3.A.3
On-the-Job Training
OJ
3
1.56
30
1.29
0.28
8.15
N
06/2006
Incumbent
4
11-1011.00
3.A.3
On-the-Job Training
OJ
4
21.78
30
13.87
5.00
59.55
N
06/2006
Incumbent
5
11-1011.00
3.A.3
On-the-Job Training
OJ
5
3.3
30
2.16
0.85
11.97
N
06/2006
Incumbent
6
11-1011.00
3.A.3
On-the-Job Training
OJ
6
14.26
30
12.93
1.88
59.14
N
06/2006
Incumbent
7
11-1011.00
3.A.3
On-the-Job Training
OJ
7
2.02
30
1.65
0.37
10.19
N
06/2006
Incumbent
8
11-1011.00
3.A.3
On-the-Job Training
OJ
8
1.86
30
1.73
0.27
11.58
N
06/2006
Incumbent
9
11-1011.00
3.A.3
On-the-Job Training
OJ
9
33.63
30
23.42
5.60
81.24
Y
06/2006
Incumbent
11-1011.03
2.D.1
Required Level of Education
RL
1
11-1011.03
2.D.1
Required Level of Education
RL
1
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
2
11-1011.03
2.D.1
Required Level of Education
RL
2
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
3
11-1011.03
2.D.1
Required Level of Education
RL
3
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
4
11-1011.03
2.D.1
Required Level of Education
RL
4
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
5
11-1011.03
2.D.1
Required Level of Education
RL
5
3.85
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
6
11-1011.03
2.D.1
Required Level of Education
RL
6
42.31
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
7
11-1011.03
2.D.1
Required Level of Education
RL
7
19.23
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
8
11-1011.03
2.D.1
Required Level of Education
RL
8
30.77
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
9
11-1011.03
2.D.1
Required Level of Education
RL
9
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
10
11-1011.03
2.D.1
Required Level of Education
RL
10
3.85
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
11
11-1011.03
2.D.1
Required Level of Education
RL
11
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
12
11-1011.03
2.D.1
Required Level of Education
RL
12
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
3.A.1
Related Work Experience
RW
1
11-1011.03
3.A.1
Related Work Experience
RW
1
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
2
11-1011.03
3.A.1
Related Work Experience
RW
2
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
3
11-1011.03
3.A.1
Related Work Experience
RW
3
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
4
11-1011.03
3.A.1
Related Work Experience
RW
4
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
5
11-1011.03
3.A.1
Related Work Experience
RW
5
0.0
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
6
11-1011.03
3.A.1
Related Work Experience
RW
6
3.85
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
7
11-1011.03
3.A.1
Related Work Experience
RW
7
19.23
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
...
...
...
...
...
...
...
...
...
...
...
...
...
37679 rows × 13 columns
In [50]:
#what are the unique element_names and what do they mean?
getDescriptions(education_training_and_experience,content_model_reference,"element_name")
Out[50]:
element_name
element_id
description
0
Required Level of Education
2.D.1
The level of education required to perform a job.
1
Related Work Experience
3.A.1
Amount of related work experience required to ...
2
On-Site or In-Plant Training
3.A.2
Amount of on-site or in-plant training (e.g., ...
3
On-the-Job Training
3.A.3
Amount of on the job training required to perf...
4
On-the-Job Training
3.D.2.c
Obtaining the licenses, certificates, or regis...
5 rows × 3 columns
In [51]:
#what are the unique scales in the education training data and what do they mean?
getDescriptions(education_training_and_experience, scales_reference, "scale_id")
#looks like there is a one-to-one relationship between the element names and the
Out[51]:
scale_id
scale_name
minimum
maximum
0
RL
Required Level Of Education (Categories 1-12)
0
100
1
RW
Related Work Experience (Categories 1-11)
0
100
2
PT
On-Site Or In-Plant Training (Categories 1-9)
0
100
3
OJ
On-The-Job Training (Categories 1-9)
0
100
4 rows × 4 columns
In [42]:
#what are the different categories in the education training data and what do they mean?
getDescriptions(education_training_and_experience, education_training_and_experience_categories, "category")
#meaning of category is dependent on the scale_id/element-name/element-id
Out[42]:
category
element_id
element_name
scale_id
category_description
0
1
2.D.1
Required Level of Education
RL
Less than a High School Diploma
1
1
3.A.1
Related Work Experience
RW
None
2
1
3.A.2
On-Site or In-Plant Training
PT
None
3
1
3.A.3
On-the-Job Training
OJ
None or short demonstration
4
2
2.D.1
Required Level of Education
RL
High School Diploma (or GED or High School Equ...
5
2
3.A.1
Related Work Experience
RW
Up to and including 1 month
6
2
3.A.2
On-Site or In-Plant Training
PT
Up to and including 1 month
7
2
3.A.3
On-the-Job Training
OJ
Anything beyond short demonstration, up to and...
8
3
2.D.1
Required Level of Education
RL
Post-Secondary Certificate - awarded for train...
9
3
3.A.1
Related Work Experience
RW
Over 1 month, up to and including 3 months
10
3
3.A.2
On-Site or In-Plant Training
PT
Over 1 month, up to and including 3 months
11
3
3.A.3
On-the-Job Training
OJ
Over 1 month, up to and including 3 months
12
4
2.D.1
Required Level of Education
RL
Some College Courses
13
4
3.A.1
Related Work Experience
RW
Over 3 months, up to and including 6 months
14
4
3.A.2
On-Site or In-Plant Training
PT
Over 3 months, up to and including 6 months
15
4
3.A.3
On-the-Job Training
OJ
Over 3 months, up to and including 6 months
16
5
2.D.1
Required Level of Education
RL
Associate's Degree (or other 2-year degree)
17
5
3.A.1
Related Work Experience
RW
Over 6 months, up to and including 1 year
18
5
3.A.2
On-Site or In-Plant Training
PT
Over 6 months, up to and including 1 year
19
5
3.A.3
On-the-Job Training
OJ
Over 6 months, up to and including 1 year
20
6
2.D.1
Required Level of Education
RL
Bachelor's Degree
21
6
3.A.1
Related Work Experience
RW
Over 1 year, up to and including 2 years
22
6
3.A.2
On-Site or In-Plant Training
PT
Over 1 year, up to and including 2 years
23
6
3.A.3
On-the-Job Training
OJ
Over 1 year, up to and including 2 years
24
7
2.D.1
Required Level of Education
RL
Post-Baccalaureate Certificate - awarded for c...
25
7
3.A.1
Related Work Experience
RW
Over 2 years, up to and including 4 years
26
7
3.A.2
On-Site or In-Plant Training
PT
Over 2 years, up to and including 4 years
27
7
3.A.3
On-the-Job Training
OJ
Over 2 years, up to and including 4 years
28
8
2.D.1
Required Level of Education
RL
Master's Degree
29
8
3.A.1
Related Work Experience
RW
Over 4 years, up to and including 6 years
30
8
3.A.2
On-Site or In-Plant Training
PT
Over 4 years, up to and including 10 years
31
8
3.A.3
On-the-Job Training
OJ
Over 4 years, up to and including 10 years
32
9
2.D.1
Required Level of Education
RL
Post-Master's Certificate - awarded for comple...
33
9
3.A.1
Related Work Experience
RW
Over 6 years, up to and including 8 years
34
9
3.A.2
On-Site or In-Plant Training
PT
Over 10 years
35
9
3.A.3
On-the-Job Training
OJ
Over 10 years
36
10
2.D.1
Required Level of Education
RL
First Professional Degree - awarded for comple...
37
10
3.A.1
Related Work Experience
RW
Over 8 years, up to and including 10 years
38
11
2.D.1
Required Level of Education
RL
Doctoral Degree
39
11
3.A.1
Related Work Experience
RW
Over 10 years
40
12
2.D.1
Required Level of Education
RL
Post-Doctoral Training
41 rows × 5 columns
In [116]:
#how many education and training features are there
feature(education_training_and_experience)
#len(education_training_and_experience)/len(education_training_and_experience.onet_soc_code.unique())
41
In [151]:
#what percentage of rows are relevant to the job?
#getRelevance(education_training_and_experience)
#this throws an error because there is no relevance column- everything is relevant
In [152]:
#percentage recommended suppressed
getExclusions(education_training_and_experience)
1.96395870379
In [68]:
#what does it look like?
knowledge.head()
Out[68]:
onet_soc_code
element_id
element_name
scale_id
data_value
date
domain_source
0
11-1011.00
1.B.1.a
Realistic
OI
1.33
06/2008
Analyst
1
11-1011.00
1.B.1.b
Investigative
OI
2.00
06/2008
Analyst
2
11-1011.00
1.B.1.c
Artistic
OI
2.67
06/2008
Analyst
3
11-1011.00
1.B.1.d
Social
OI
3.67
06/2008
Analyst
4
11-1011.00
1.B.1.e
Enterprising
OI
7.00
06/2008
Analyst
5 rows × 7 columns
In [69]:
#what does it look like grouped by the factors?
knowledge.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
#like abilities, it's grouped by onet_soc_code-element_id/name-scale_id
Out[69]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
2.C.1.a
Administration and Management
IM
11-1011.00
2.C.1.a
Administration and Management
IM
4.45
30
0.20
4.04
4.86
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.a
Administration and Management
LV
6.25
30
0.24
5.75
6.75
N
N
06/2006
Incumbent
2.C.1.b
Clerical
IM
11-1011.00
2.C.1.b
Clerical
IM
2.46
30
0.28
1.89
3.04
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.b
Clerical
LV
3.5
30
0.42
2.65
4.35
N
N
06/2006
Incumbent
2.C.1.c
Economics and Accounting
IM
11-1011.00
2.C.1.c
Economics and Accounting
IM
4.0
30
0.24
3.51
4.49
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.c
Economics and Accounting
LV
4.89
30
0.12
4.63
5.14
N
N
06/2006
Incumbent
2.C.1.d
Sales and Marketing
IM
11-1011.00
2.C.1.d
Sales and Marketing
IM
3.68
30
0.18
3.31
4.05
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.d
Sales and Marketing
LV
4.86
30
0.28
4.28
5.44
N
N
06/2006
Incumbent
2.C.1.e
Customer and Personal Service
IM
11-1011.00
2.C.1.e
Customer and Personal Service
IM
3.9
30
0.32
3.25
4.54
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.e
Customer and Personal Service
LV
4.9
28
0.64
3.58
6.22
N
N
06/2006
Incumbent
2.C.1.f
Personnel and Human Resources
IM
11-1011.00
2.C.1.f
Personnel and Human Resources
IM
3.29
30
0.26
2.76
3.82
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.1.f
Personnel and Human Resources
LV
4.65
30
0.33
3.98
5.33
N
N
06/2006
Incumbent
2.C.10
Transportation
IM
11-1011.00
2.C.10
Transportation
IM
2.13
30
0.44
1.23
3.04
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.10
Transportation
LV
1.89
30
0.84
0.17
3.61
N
N
06/2006
Incumbent
2.C.2.a
Production and Processing
IM
11-1011.00
2.C.2.a
Production and Processing
IM
2.21
30
0.37
1.46
2.95
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.2.a
Production and Processing
LV
2.67
30
0.66
1.32
4.01
N
N
06/2006
Incumbent
2.C.2.b
Food Production
IM
11-1011.00
2.C.2.b
Food Production
IM
1.44
29
0.22
1.00
1.89
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.2.b
Food Production
LV
1.27
29
0.66
0.00
2.62
Y
N
06/2006
Incumbent
2.C.3.a
Computers and Electronics
IM
11-1011.00
2.C.3.a
Computers and Electronics
IM
2.91
30
0.17
2.57
3.26
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.3.a
Computers and Electronics
LV
3.6
30
0.22
3.14
4.06
N
N
06/2006
Incumbent
2.C.3.b
Engineering and Technology
IM
11-1011.00
2.C.3.b
Engineering and Technology
IM
1.59
30
0.40
1.00
2.42
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.3.b
Engineering and Technology
LV
1.06
29
0.68
0.00
2.46
Y
Y
06/2006
Incumbent
2.C.3.c
Design
IM
11-1011.00
2.C.3.c
Design
IM
2.03
30
0.45
1.10
2.95
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.3.c
Design
LV
1.9
30
0.78
0.30
3.50
N
N
06/2006
Incumbent
2.C.3.d
Building and Construction
IM
11-1011.00
2.C.3.d
Building and Construction
IM
1.99
29
0.31
1.35
2.64
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.3.d
Building and Construction
LV
2.0
29
0.57
0.82
3.17
N
N
06/2006
Incumbent
2.C.3.e
Mechanical
IM
11-1011.00
2.C.3.e
Mechanical
IM
1.79
29
0.23
1.33
2.26
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.3.e
Mechanical
LV
1.92
29
0.58
0.74
3.10
N
N
06/2006
Incumbent
2.C.4.a
Mathematics
IM
11-1011.00
2.C.4.a
Mathematics
IM
2.99
29
0.20
2.59
3.40
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.a
Mathematics
LV
4.29
29
0.19
3.89
4.69
N
N
06/2006
Incumbent
2.C.4.b
Physics
IM
11-1011.00
2.C.4.b
Physics
IM
1.52
28
0.23
1.05
1.98
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.b
Physics
LV
1.41
28
0.65
0.07
2.75
N
N
06/2006
Incumbent
2.C.4.c
Chemistry
IM
11-1011.00
2.C.4.c
Chemistry
IM
1.6
28
0.26
1.07
2.12
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.c
Chemistry
LV
1.46
28
0.65
0.13
2.78
N
N
06/2006
Incumbent
2.C.4.d
Biology
IM
11-1011.00
2.C.4.d
Biology
IM
1.54
27
0.23
1.06
2.01
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.d
Biology
LV
1.31
27
0.66
0.00
2.66
Y
N
06/2006
Incumbent
2.C.4.e
Psychology
IM
11-1011.00
2.C.4.e
Psychology
IM
2.89
30
0.30
2.27
3.50
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.e
Psychology
LV
3.4
30
0.55
2.28
4.53
N
N
06/2006
Incumbent
2.C.4.f
Sociology and Anthropology
IM
11-1011.00
2.C.4.f
Sociology and Anthropology
IM
1.66
28
0.35
1.00
2.38
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.f
Sociology and Anthropology
LV
1.18
28
0.58
0.00
2.37
N
N
06/2006
Incumbent
2.C.4.g
Geography
IM
11-1011.00
2.C.4.g
Geography
IM
1.96
29
0.42
1.10
2.82
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.4.g
Geography
LV
1.75
29
0.63
0.45
3.04
N
N
06/2006
Incumbent
2.C.5.a
Medicine and Dentistry
IM
11-1011.00
2.C.5.a
Medicine and Dentistry
IM
2.99
29
0.47
2.02
3.95
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.5.a
Medicine and Dentistry
LV
2.41
29
0.64
1.09
3.73
N
N
06/2006
Incumbent
2.C.5.b
Therapy and Counseling
IM
11-1011.00
2.C.5.b
Therapy and Counseling
IM
2.19
29
0.38
1.42
2.96
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.5.b
Therapy and Counseling
LV
1.91
29
0.58
0.73
3.10
N
N
06/2006
Incumbent
2.C.6
Education and Training
IM
11-1011.00
2.C.6
Education and Training
IM
2.96
29
0.34
2.27
3.65
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.6
Education and Training
LV
4.35
29
0.71
2.89
5.82
N
N
06/2006
Incumbent
2.C.7.a
English Language
IM
11-1011.00
2.C.7.a
English Language
IM
3.93
30
0.31
3.29
4.57
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.7.a
English Language
LV
4.69
30
0.27
4.15
5.24
N
N
06/2006
Incumbent
2.C.7.b
Foreign Language
IM
11-1011.00
2.C.7.b
Foreign Language
IM
1.44
30
0.22
1.00
1.89
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.7.b
Foreign Language
LV
0.88
30
0.46
0.00
1.82
Y
N
06/2006
Incumbent
2.C.7.c
Fine Arts
IM
11-1011.00
2.C.7.c
Fine Arts
IM
1.23
29
0.16
1.00
1.55
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.7.c
Fine Arts
LV
0.29
29
0.18
0.00
0.65
Y
Y
06/2006
Incumbent
2.C.7.d
History and Archeology
IM
11-1011.00
2.C.7.d
History and Archeology
IM
1.32
28
0.19
1.00
1.72
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.7.d
History and Archeology
LV
0.84
28
0.49
0.00
1.84
Y
Y
06/2006
Incumbent
2.C.7.e
Philosophy and Theology
IM
11-1011.00
2.C.7.e
Philosophy and Theology
IM
2.08
28
0.38
1.30
2.85
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.7.e
Philosophy and Theology
LV
2.5
28
0.74
0.99
4.01
N
N
06/2006
Incumbent
2.C.8.a
Public Safety and Security
IM
11-1011.00
2.C.8.a
Public Safety and Security
IM
3.04
29
0.47
2.09
4.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
2.C.8.a
Public Safety and Security
LV
3.56
28
0.71
2.10
5.02
N
N
06/2006
Incumbent
...
...
...
...
...
...
...
...
...
...
...
...
...
60918 rows × 13 columns
In [41]:
#what are the unique element_names and what do they mean?
getDescriptions(knowledge, content_model_reference, "element_name")
Out[41]:
element_name
element_id
description
0
Administration and Management
2.C.1.a
Knowledge of business and management principle...
1
Clerical
2.C.1.b
Knowledge of administrative and clerical proce...
2
Economics and Accounting
2.C.1.c
Knowledge of economic and accounting principle...
3
Sales and Marketing
2.C.1.d
Knowledge of principles and methods for showin...
4
Customer and Personal Service
2.C.1.e
Knowledge of principles and processes for prov...
5
Personnel and Human Resources
2.C.1.f
Knowledge of principles and procedures for per...
6
Production and Processing
2.C.2.a
Knowledge of raw materials, production process...
7
Food Production
2.C.2.b
Knowledge of techniques and equipment for plan...
8
Computers and Electronics
2.C.3.a
Knowledge of circuit boards, processors, chips...
9
Engineering and Technology
2.C.3
Knowledge of the design, development, and appl...
10
Engineering and Technology
2.C.3.b
Knowledge of the practical application of engi...
11
Design
2.C.3.c
Knowledge of design techniques, tools, and pri...
12
Building and Construction
2.C.3.d
Knowledge of materials, methods, and the tools...
13
Mechanical
2.C.3.e
Knowledge of machines and tools, including the...
14
Mathematics
2.A.1.e
Using mathematics to solve problems.
15
Mathematics
2.C.4.a
Knowledge of arithmetic, algebra, geometry, ca...
16
Physics
2.C.4.b
Knowledge and prediction of physical principle...
17
Chemistry
2.C.4.c
Knowledge of the chemical composition, structu...
18
Biology
2.C.4.d
Knowledge of plant and animal organisms, their...
19
Psychology
2.C.4.e
Knowledge of human behavior and performance; i...
20
Sociology and Anthropology
2.C.4.f
Knowledge of group behavior and dynamics, soci...
21
Geography
2.C.4.g
Knowledge of principles and methods for descri...
22
Medicine and Dentistry
2.C.5.a
Knowledge of the information and techniques ne...
23
Therapy and Counseling
2.C.5.b
Knowledge of principles, methods, and procedur...
24
Education and Training
2.C.6
Knowledge of principles and methods for curric...
25
English Language
2.C.7.a
Knowledge of the structure and content of the ...
26
Foreign Language
2.C.7.b
Knowledge of the structure and content of a fo...
27
Fine Arts
2.C.7.c
Knowledge of the theory and techniques require...
28
History and Archeology
2.C.7.d
Knowledge of historical events and their cause...
29
Philosophy and Theology
2.C.7.e
Knowledge of different philosophical systems a...
30
Public Safety and Security
2.C.8.a
Knowledge of relevant equipment, policies, pro...
31
Law and Government
2.C.8.b
Knowledge of laws, legal codes, court procedur...
32
Telecommunications
2.C.9.a
Knowledge of transmission, broadcasting, switc...
33
Communications and Media
2.C.9.b
Knowledge of media production, communication, ...
34
Transportation
2.C.10
Knowledge of principles and methods for moving...
35 rows × 3 columns
In [40]:
#what are the different knowledge scales and what do they mean?
getDescriptions(knowledge, scales_reference, "scale_id")
#these are the same as for ability
Out[40]:
scale_id
scale_name
minimum
maximum
0
IM
Importance
1
5
1
LV
Level
0
7
2 rows × 4 columns
In [115]:
#how many different knowledge features are there?
feature(knowledge)
66
In [153]:
#percentage relevant
getRelevance(knowledge)
10.9081059785
In [154]:
#percent to be excluded
getExclusions(knowledge)
8.58202830034
In [118]:
#what does it look like?
interests.head()
Out[118]:
onet_soc_code
element_id
element_name
scale_id
data_value
date
domain_source
0
11-1011.00
1.B.1.a
Realistic
OI
1.33
06/2008
Analyst
1
11-1011.00
1.B.1.b
Investigative
OI
2.00
06/2008
Analyst
2
11-1011.00
1.B.1.c
Artistic
OI
2.67
06/2008
Analyst
3
11-1011.00
1.B.1.d
Social
OI
3.67
06/2008
Analyst
4
11-1011.00
1.B.1.e
Enterprising
OI
7.00
06/2008
Analyst
5 rows × 7 columns
In [119]:
#what does it look like grouped by the factors?
interests.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
#looks like one-to-one matching between element_name and scale_id
Out[119]:
onet_soc_code
element_id
element_name
scale_id
data_value
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
1.B.1.a
Realistic
OI
11-1011.00
1.B.1.a
Realistic
OI
1.33
06/2008
Analyst
1.B.1.b
Investigative
OI
11-1011.00
1.B.1.b
Investigative
OI
2.0
06/2008
Analyst
1.B.1.c
Artistic
OI
11-1011.00
1.B.1.c
Artistic
OI
2.67
06/2008
Analyst
1.B.1.d
Social
OI
11-1011.00
1.B.1.d
Social
OI
3.67
06/2008
Analyst
1.B.1.e
Enterprising
OI
11-1011.00
1.B.1.e
Enterprising
OI
7.0
06/2008
Analyst
1.B.1.f
Conventional
OI
11-1011.00
1.B.1.f
Conventional
OI
5.33
06/2008
Analyst
1.B.1.g
First Interest High-Point
IH
11-1011.00
1.B.1.g
First Interest High-Point
IH
5.0
06/2008
Analyst
1.B.1.h
Second Interest High-Point
IH
11-1011.00
1.B.1.h
Second Interest High-Point
IH
6.0
06/2008
Analyst
1.B.1.i
Third Interest High-Point
IH
11-1011.00
1.B.1.i
Third Interest High-Point
IH
0.0
06/2008
Analyst
11-1011.03
1.B.1.a
Realistic
OI
11-1011.03
1.B.1.a
Realistic
OI
1.0
07/2013
Analyst
1.B.1.b
Investigative
OI
11-1011.03
1.B.1.b
Investigative
OI
4.33
07/2013
Analyst
1.B.1.c
Artistic
OI
11-1011.03
1.B.1.c
Artistic
OI
2.67
07/2013
Analyst
1.B.1.d
Social
OI
11-1011.03
1.B.1.d
Social
OI
2.33
07/2013
Analyst
1.B.1.e
Enterprising
OI
11-1011.03
1.B.1.e
Enterprising
OI
7.0
07/2013
Analyst
1.B.1.f
Conventional
OI
11-1011.03
1.B.1.f
Conventional
OI
4.33
07/2013
Analyst
1.B.1.g
First Interest High-Point
IH
11-1011.03
1.B.1.g
First Interest High-Point
IH
5.0
07/2013
Analyst
1.B.1.h
Second Interest High-Point
IH
11-1011.03
1.B.1.h
Second Interest High-Point
IH
6.0
07/2013
Analyst
1.B.1.i
Third Interest High-Point
IH
11-1011.03
1.B.1.i
Third Interest High-Point
IH
2.0
07/2013
Analyst
11-1021.00
1.B.1.a
Realistic
OI
11-1021.00
1.B.1.a
Realistic
OI
1.33
06/2008
Analyst
1.B.1.b
Investigative
OI
11-1021.00
1.B.1.b
Investigative
OI
1.33
06/2008
Analyst
1.B.1.c
Artistic
OI
11-1021.00
1.B.1.c
Artistic
OI
1.0
06/2008
Analyst
1.B.1.d
Social
OI
11-1021.00
1.B.1.d
Social
OI
3.33
06/2008
Analyst
1.B.1.e
Enterprising
OI
11-1021.00
1.B.1.e
Enterprising
OI
7.0
06/2008
Analyst
1.B.1.f
Conventional
OI
11-1021.00
1.B.1.f
Conventional
OI
3.67
06/2008
Analyst
1.B.1.g
First Interest High-Point
IH
11-1021.00
1.B.1.g
First Interest High-Point
IH
5.0
06/2008
Analyst
1.B.1.h
Second Interest High-Point
IH
11-1021.00
1.B.1.h
Second Interest High-Point
IH
6.0
06/2008
Analyst
1.B.1.i
Third Interest High-Point
IH
11-1021.00
1.B.1.i
Third Interest High-Point
IH
4.0
06/2008
Analyst
11-1031.00
1.B.1.a
Realistic
OI
11-1031.00
1.B.1.a
Realistic
OI
1.0
06/2008
Analyst
1.B.1.b
Investigative
OI
11-1031.00
1.B.1.b
Investigative
OI
3.67
06/2008
Analyst
1.B.1.c
Artistic
OI
11-1031.00
1.B.1.c
Artistic
OI
3.67
06/2008
Analyst
1.B.1.d
Social
OI
11-1031.00
1.B.1.d
Social
OI
4.67
06/2008
Analyst
1.B.1.e
Enterprising
OI
11-1031.00
1.B.1.e
Enterprising
OI
7.0
06/2008
Analyst
1.B.1.f
Conventional
OI
11-1031.00
1.B.1.f
Conventional
OI
3.0
06/2008
Analyst
1.B.1.g
First Interest High-Point
IH
11-1031.00
1.B.1.g
First Interest High-Point
IH
5.0
06/2008
Analyst
1.B.1.h
Second Interest High-Point
IH
11-1031.00
1.B.1.h
Second Interest High-Point
IH
4.0
06/2008
Analyst
1.B.1.i
Third Interest High-Point
IH
11-1031.00
1.B.1.i
Third Interest High-Point
IH
0.0
06/2008
Analyst
11-2011.00
1.B.1.a
Realistic
OI
11-2011.00
1.B.1.a
Realistic
OI
1.67
06/2008
Analyst
1.B.1.b
Investigative
OI
11-2011.00
1.B.1.b
Investigative
OI
2.0
06/2008
Analyst
1.B.1.c
Artistic
OI
11-2011.00
1.B.1.c
Artistic
OI
5.33
06/2008
Analyst
1.B.1.d
Social
OI
11-2011.00
1.B.1.d
Social
OI
2.33
06/2008
Analyst
1.B.1.e
Enterprising
OI
11-2011.00
1.B.1.e
Enterprising
OI
7.0
06/2008
Analyst
1.B.1.f
Conventional
OI
11-2011.00
1.B.1.f
Conventional
OI
4.67
06/2008
Analyst
1.B.1.g
First Interest High-Point
IH
11-2011.00
1.B.1.g
First Interest High-Point
IH
5.0
06/2008
Analyst
1.B.1.h
Second Interest High-Point
IH
11-2011.00
1.B.1.h
Second Interest High-Point
IH
3.0
06/2008
Analyst
1.B.1.i
Third Interest High-Point
IH
11-2011.00
1.B.1.i
Third Interest High-Point
IH
6.0
06/2008
Analyst
11-2011.01
1.B.1.a
Realistic
OI
11-2011.01
1.B.1.a
Realistic
OI
1.0
07/2013
Analyst
1.B.1.b
Investigative
OI
11-2011.01
1.B.1.b
Investigative
OI
5.33
07/2013
Analyst
1.B.1.c
Artistic
OI
11-2011.01
1.B.1.c
Artistic
OI
4.33
07/2013
Analyst
1.B.1.d
Social
OI
11-2011.01
1.B.1.d
Social
OI
2.33
07/2013
Analyst
1.B.1.e
Enterprising
OI
11-2011.01
1.B.1.e
Enterprising
OI
5.33
07/2013
Analyst
1.B.1.f
Conventional
OI
11-2011.01
1.B.1.f
Conventional
OI
3.0
07/2013
Analyst
1.B.1.g
First Interest High-Point
IH
11-2011.01
1.B.1.g
First Interest High-Point
IH
5.0
07/2013
Analyst
1.B.1.h
Second Interest High-Point
IH
11-2011.01
1.B.1.h
Second Interest High-Point
IH
3.0
07/2013
Analyst
1.B.1.i
Third Interest High-Point
IH
11-2011.01
1.B.1.i
Third Interest High-Point
IH
2.0
07/2013
Analyst
11-2021.00
1.B.1.a
Realistic
OI
11-2021.00
1.B.1.a
Realistic
OI
1.0
06/2008
Analyst
1.B.1.b
Investigative
OI
11-2021.00
1.B.1.b
Investigative
OI
2.33
06/2008
Analyst
1.B.1.c
Artistic
OI
11-2021.00
1.B.1.c
Artistic
OI
3.67
06/2008
Analyst
1.B.1.d
Social
OI
11-2021.00
1.B.1.d
Social
OI
2.67
06/2008
Analyst
1.B.1.e
Enterprising
OI
11-2021.00
1.B.1.e
Enterprising
OI
7.0
06/2008
Analyst
1.B.1.f
Conventional
OI
11-2021.00
1.B.1.f
Conventional
OI
5.33
06/2008
Analyst
...
...
...
...
...
...
...
8766 rows × 7 columns
In [39]:
#what do these element names mean?
getDescriptions(interests, content_model_reference, "element_name")
Out[39]:
element_name
element_id
description
0
Realistic
1.B.1.a
Realistic occupations frequently involve work ...
1
Investigative
1.B.1.b
Investigative occupations frequently involve w...
2
Artistic
1.B.1.c
Artistic occupations frequently involve workin...
3
Social
1.B.1.d
Social occupations frequently involve working ...
4
Enterprising
1.B.1.e
Enterprising occupations frequently involve st...
5
Conventional
1.B.1.f
Conventional occupations frequently involve fo...
6
First Interest High-Point
1.B.1.g
Primary-Rank Descriptiveness
7
Second Interest High-Point
1.B.1.h
Secondary-Cutoff/Rank Descriptiveness
8
Third Interest High-Point
1.B.1.i
Tertiary-Cutoff/Rank Descriptiveness
9 rows × 3 columns
In [121]:
#what do the scale_ids mean?
getDescriptions(interests, scales_reference, "scale_id")
scale_id scale_name minimum maximum
0 OI Occupational Interests 1 7
1 IH Occupational Interest High-Point 0 6
[2 rows x 4 columns]
In [122]:
#how many total interests features are there?
feature(interests)
9
In [125]:
#What do the job zones look like?
job_zones.head()
#there's a one-to-one relationship between jobs and job_zone, so we don't need to group_by
Out[125]:
onet_soc_code
job_zone
date
domain_source
0
11-1011.00
5
06/2006
Analyst
1
11-1011.03
5
07/2013
Analyst
2
11-1021.00
3
06/2008
Analyst
3
11-1031.00
4
06/2008
Analyst
4
11-2011.00
4
06/2010
Analyst
5 rows × 4 columns
In [38]:
#what is a job zone?
getDescriptions(job_zones, job_zone_reference, "job_zone")
#these seem to be very closely related, simplified version of the education training information
Out[38]:
job_zone
name
experience
education
job_training
examples
svp_range
0
5
Job Zone Five: Extensive Preparation Needed
Extensive skill, knowledge, and experience are...
Most of these occupations require graduate sch...
Employees may need some on-the-job training, b...
These occupations often involve coordinating, ...
(8.0 and above)
1
3
Job Zone Three: Medium Preparation Needed
Previous work-related skill, knowledge, or exp...
Most occupations in this zone require training...
Employees in these occupations usually need on...
These occupations usually involve using commun...
(6.0 to < 7.0)
2
4
Job Zone Four: Considerable Preparation Needed
A considerable amount of work-related skill, k...
Most of these occupations require a four-year ...
Employees in these occupations usually need se...
Many of these occupations involve coordinating...
(7.0 to < 8.0)
3
2
Job Zone Two: Some Preparation Needed
Some previous work-related skill, knowledge, o...
These occupations usually require a high schoo...
Employees in these occupations need anywhere f...
These occupations often involve using your kno...
(4.0 to < 6.0)
4
1
Job Zone One: Little or No Preparation Needed
Little or no previous work-related skill, know...
Some of these occupations may require a high s...
Employees in these occupations need anywhere f...
These occupations involve following instructio...
(Below 4.0)
5 rows × 7 columns
In [128]:
#how many features are in the job zone data
feature(job_zones)
1
In [129]:
#what do the skills look like?
skills.head()
Out[129]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
0
11-1011.00
2.A.1.a
Reading Comprehension
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
1
11-1011.00
2.A.1.a
Reading Comprehension
LV
4.75
8
0.25
4.26
5.24
N
N
06/2010
Analyst
2
11-1011.00
2.A.1.b
Active Listening
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
3
11-1011.00
2.A.1.b
Active Listening
LV
4.88
8
0.35
4.19
5.56
N
N
06/2010
Analyst
4
11-1011.00
2.A.1.c
Writing
IM
4.12
8
0.23
3.68
4.57
N
n/a
06/2010
Analyst
5 rows × 13 columns
In [131]:
#what do the skills look like grouped by factor
skills.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
Out[131]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
2.A.1.a
Reading Comprehension
IM
11-1011.00
2.A.1.a
Reading Comprehension
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.a
Reading Comprehension
LV
4.75
8
0.25
4.26
5.24
N
N
06/2010
Analyst
2.A.1.b
Active Listening
IM
11-1011.00
2.A.1.b
Active Listening
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.b
Active Listening
LV
4.88
8
0.35
4.19
5.56
N
N
06/2010
Analyst
2.A.1.c
Writing
IM
11-1011.00
2.A.1.c
Writing
IM
4.12
8
0.23
3.68
4.57
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.c
Writing
LV
4.5
8
0.19
4.13
4.87
N
N
06/2010
Analyst
2.A.1.d
Speaking
IM
11-1011.00
2.A.1.d
Speaking
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.d
Speaking
LV
4.88
8
0.13
4.63
5.12
N
N
06/2010
Analyst
2.A.1.e
Mathematics
IM
11-1011.00
2.A.1.e
Mathematics
IM
3.0
8
0.19
2.63
3.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.e
Mathematics
LV
3.38
8
0.46
2.47
4.28
N
N
06/2010
Analyst
2.A.1.f
Science
IM
11-1011.00
2.A.1.f
Science
IM
1.62
8
0.26
1.11
2.14
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.1.f
Science
LV
1.38
8
0.56
0.27
2.48
Y
N
06/2010
Analyst
2.A.2.a
Critical Thinking
IM
11-1011.00
2.A.2.a
Critical Thinking
IM
4.38
8
0.18
4.02
4.73
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.2.a
Critical Thinking
LV
4.62
8
0.18
4.27
4.98
N
N
06/2010
Analyst
2.A.2.b
Active Learning
IM
11-1011.00
2.A.2.b
Active Learning
IM
4.0
8
0.19
3.63
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.2.b
Active Learning
LV
4.75
8
0.16
4.43
5.07
N
N
06/2010
Analyst
2.A.2.c
Learning Strategies
IM
11-1011.00
2.A.2.c
Learning Strategies
IM
3.38
8
0.18
3.02
3.73
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.2.c
Learning Strategies
LV
4.12
8
0.23
3.68
4.57
N
N
06/2010
Analyst
2.A.2.d
Monitoring
IM
11-1011.00
2.A.2.d
Monitoring
IM
4.12
8
0.13
3.88
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.A.2.d
Monitoring
LV
5.5
8
0.33
4.86
6.14
N
N
06/2010
Analyst
2.B.1.a
Social Perceptiveness
IM
11-1011.00
2.B.1.a
Social Perceptiveness
IM
4.12
8
0.13
3.88
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.a
Social Perceptiveness
LV
4.38
8
0.18
4.02
4.73
N
N
06/2010
Analyst
2.B.1.b
Coordination
IM
11-1011.00
2.B.1.b
Coordination
IM
4.25
8
0.16
3.93
4.57
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.b
Coordination
LV
5.12
8
0.40
4.34
5.91
N
N
06/2010
Analyst
2.B.1.c
Persuasion
IM
11-1011.00
2.B.1.c
Persuasion
IM
4.12
8
0.13
3.88
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.c
Persuasion
LV
5.0
8
0.33
4.36
5.64
N
N
06/2010
Analyst
2.B.1.d
Negotiation
IM
11-1011.00
2.B.1.d
Negotiation
IM
4.0
8
0.19
3.63
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.d
Negotiation
LV
4.5
8
0.19
4.13
4.87
N
N
06/2010
Analyst
2.B.1.e
Instructing
IM
11-1011.00
2.B.1.e
Instructing
IM
3.25
8
0.16
2.93
3.57
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.e
Instructing
LV
4.0
8
0.27
3.48
4.52
N
N
06/2010
Analyst
2.B.1.f
Service Orientation
IM
11-1011.00
2.B.1.f
Service Orientation
IM
3.25
8
0.37
2.53
3.97
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.1.f
Service Orientation
LV
3.5
8
0.63
2.27
4.73
Y
N
06/2010
Analyst
2.B.2.i
Complex Problem Solving
IM
11-1011.00
2.B.2.i
Complex Problem Solving
IM
4.5
8
0.19
4.13
4.87
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.2.i
Complex Problem Solving
LV
4.88
8
0.23
4.43
5.32
N
N
06/2010
Analyst
2.B.3.a
Operations Analysis
IM
11-1011.00
2.B.3.a
Operations Analysis
IM
3.5
8
0.19
3.13
3.87
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.a
Operations Analysis
LV
4.0
8
0.33
3.36
4.64
N
N
06/2010
Analyst
2.B.3.b
Technology Design
IM
11-1011.00
2.B.3.b
Technology Design
IM
1.75
8
0.31
1.14
2.36
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.b
Technology Design
LV
1.0
8
0.42
0.17
1.83
N
N
06/2010
Analyst
2.B.3.c
Equipment Selection
IM
11-1011.00
2.B.3.c
Equipment Selection
IM
1.0
8
0.00
1.00
1.00
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.c
Equipment Selection
LV
0.0
8
0.00
0.00
0.00
N
Y
06/2010
Analyst
2.B.3.d
Installation
IM
11-1011.00
2.B.3.d
Installation
IM
1.0
8
0.00
1.00
1.00
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.d
Installation
LV
0.0
8
0.00
0.00
0.00
N
Y
06/2010
Analyst
2.B.3.e
Programming
IM
11-1011.00
2.B.3.e
Programming
IM
1.88
8
0.23
1.43
2.32
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.e
Programming
LV
1.12
8
0.35
0.44
1.81
N
N
06/2010
Analyst
2.B.3.g
Operation Monitoring
IM
11-1011.00
2.B.3.g
Operation Monitoring
IM
2.25
8
0.25
1.76
2.74
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.g
Operation Monitoring
LV
2.12
8
0.44
1.26
2.99
N
N
06/2010
Analyst
2.B.3.h
Operation and Control
IM
11-1011.00
2.B.3.h
Operation and Control
IM
1.88
8
0.13
1.63
2.12
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.h
Operation and Control
LV
1.75
8
0.31
1.14
2.36
N
N
06/2010
Analyst
2.B.3.j
Equipment Maintenance
IM
11-1011.00
2.B.3.j
Equipment Maintenance
IM
1.0
8
0.00
1.00
1.00
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.j
Equipment Maintenance
LV
0.0
8
0.00
0.00
0.00
N
Y
06/2010
Analyst
2.B.3.k
Troubleshooting
IM
11-1011.00
2.B.3.k
Troubleshooting
IM
1.0
8
0.00
1.00
1.00
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.k
Troubleshooting
LV
0.0
8
0.00
0.00
0.00
N
Y
06/2010
Analyst
2.B.3.l
Repairing
IM
11-1011.00
2.B.3.l
Repairing
IM
1.0
8
0.00
1.00
1.00
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.l
Repairing
LV
0.0
8
0.00
0.00
0.00
N
Y
06/2010
Analyst
2.B.3.m
Quality Control Analysis
IM
11-1011.00
2.B.3.m
Quality Control Analysis
IM
1.62
8
0.32
1.00
2.26
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.3.m
Quality Control Analysis
LV
1.0
8
0.53
0.00
2.05
Y
N
06/2010
Analyst
2.B.4.e
Judgment and Decision Making
IM
11-1011.00
2.B.4.e
Judgment and Decision Making
IM
4.5
8
0.19
4.13
4.87
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.4.e
Judgment and Decision Making
LV
5.62
8
0.18
5.27
5.98
N
N
06/2010
Analyst
2.B.4.g
Systems Analysis
IM
11-1011.00
2.B.4.g
Systems Analysis
IM
4.12
8
0.13
3.88
4.37
N
n/a
06/2010
Analyst
LV
11-1011.00
2.B.4.g
Systems Analysis
LV
5.12
8
0.35
4.44
5.81
N
N
06/2010
Analyst
...
...
...
...
...
...
...
...
...
...
...
...
...
64610 rows × 13 columns
In [132]:
#what are the different element names?
getDescriptions(skills, content_model_reference, "element_name")
element_name element_id \
0 Reading Comprehension 2.A.1.a
1 Active Listening 2.A.1.b
2 Writing 2.A.1.c
3 Speaking 2.A.1.d
4 Mathematics 2.A.1.e
5 Mathematics 2.C.4.a
6 Science 2.A.1.f
7 Critical Thinking 2.A.2.a
8 Active Learning 2.A.2.b
9 Learning Strategies 2.A.2.c
10 Monitoring 2.A.2.d
11 Social Perceptiveness 2.B.1.a
12 Coordination 2.B.1.b
13 Persuasion 2.B.1.c
14 Negotiation 2.B.1.d
15 Instructing 2.B.1.e
16 Service Orientation 2.B.1.f
17 Complex Problem Solving 2.B.2.i
18 Operations Analysis 2.B.3.a
19 Technology Design 2.B.3.b
20 Equipment Selection 2.B.3.c
21 Installation 2.B.3.d
22 Programming 2.B.3.e
23 Operation Monitoring 2.B.3.g
24 Operation and Control 2.B.3.h
25 Equipment Maintenance 2.B.3.j
26 Troubleshooting 2.B.3.k
27 Repairing 2.B.3.l
28 Quality Control Analysis 2.B.3.m
29 Judgment and Decision Making 2.B.4.e
30 Systems Analysis 2.B.4.g
31 Systems Evaluation 2.B.4.h
32 Time Management 2.B.5.a
33 Management of Financial Resources 2.B.5.b
34 Management of Material Resources 2.B.5.c
35 Management of Personnel Resources 2.B.5.d
description
0 Understanding written sentences and paragraphs...
1 Giving full attention to what other people are...
2 Communicating effectively in writing as approp...
3 Talking to others to convey information effect...
4 Using mathematics to solve problems.
5 Knowledge of arithmetic, algebra, geometry, ca...
6 Using scientific rules and methods to solve pr...
7 Using logic and reasoning to identify the stre...
8 Understanding the implications of new informat...
9 Selecting and using training/instructional met...
10 Monitoring/Assessing performance of yourself, ...
11 Being aware of others' reactions and understan...
12 Adjusting actions in relation to others' actions.
13 Persuading others to change their minds or beh...
14 Bringing others together and trying to reconci...
15 Teaching others how to do something.
16 Actively looking for ways to help people.
17 Identifying complex problems and reviewing rel...
18 Analyzing needs and product requirements to cr...
19 Generating or adapting equipment and technolog...
20 Determining the kind of tools and equipment ne...
21 Installing equipment, machines, wiring, or pro...
22 Writing computer programs for various purposes.
23 Watching gauges, dials, or other indicators to...
24 Controlling operations of equipment or systems.
25 Performing routine maintenance on equipment an...
26 Determining causes of operating errors and dec...
27 Repairing machines or systems using the needed...
28 Conducting tests and inspections of products, ...
29 Considering the relative costs and benefits of...
30 Determining how a system should work and how c...
31 Identifying measures or indicators of system p...
32 Managing one's own time and the time of others.
33 Determining how money will be spent to get the...
34 Obtaining and seeing to the appropriate use of...
35 Motivating, developing, and directing people a...
[36 rows x 3 columns]
In [37]:
#What do the different scales mean?
getDescriptions(skills, scales_reference, "scale_id")
#they are the same skills as in abilities
Out[37]:
scale_id
scale_name
minimum
maximum
0
IM
Importance
1
5
1
LV
Level
0
7
2 rows × 4 columns
In [134]:
#how many skills features are there?
feature(skills)
70
In [146]:
#what fraction of the skill combinations are relevant to the job
getRelevance(skills)
6.43863179074
In [147]:
#what percentage of skill combinations are recommended to be excluded?
getExclusions(skills)
1.34499303513
In [155]:
#what does it look like?
work_activities.head()
Out[155]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
0
11-1011.00
4.A.1.a.1
Getting Information
IM
4.75
24
0.15
4.44
5.00
N
n/a
06/2006
Incumbent
1
11-1011.00
4.A.1.a.1
Getting Information
LV
5.03
24
0.15
4.73
5.33
N
N
06/2006
Incumbent
2
11-1011.00
4.A.1.a.2
Monitor Processes, Materials, or Surroundings
IM
3.18
24
0.57
2.01
4.36
N
n/a
06/2006
Incumbent
3
11-1011.00
4.A.1.a.2
Monitor Processes, Materials, or Surroundings
LV
3.57
24
0.95
1.61
5.52
N
N
06/2006
Incumbent
4
11-1011.00
4.A.1.b.1
Identifying Objects, Actions, and Events
IM
3.64
24
0.40
2.81
4.48
N
n/a
06/2006
Incumbent
5 rows × 13 columns
In [156]:
#grouped by the factors
work_activities.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
#grouped same as most of the other data frames- same scale_id
Out[156]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
4.A.1.a.1
Getting Information
IM
11-1011.00
4.A.1.a.1
Getting Information
IM
4.75
24
0.15
4.44
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.1.a.1
Getting Information
LV
5.03
24
0.15
4.73
5.33
N
N
06/2006
Incumbent
4.A.1.a.2
Monitor Processes, Materials, or Surroundings
IM
11-1011.00
4.A.1.a.2
Monitor Processes, Materials, or Surroundings
IM
3.18
24
0.57
2.01
4.36
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.1.a.2
Monitor Processes, Materials, or Surroundings
LV
3.57
24
0.95
1.61
5.52
N
N
06/2006
Incumbent
4.A.1.b.1
Identifying Objects, Actions, and Events
IM
11-1011.00
4.A.1.b.1
Identifying Objects, Actions, and Events
IM
3.64
24
0.40
2.81
4.48
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.1.b.1
Identifying Objects, Actions, and Events
LV
3.89
24
0.65
2.55
5.23
N
N
06/2006
Incumbent
4.A.1.b.2
Inspecting Equipment, Structures, or Material
IM
11-1011.00
4.A.1.b.2
Inspecting Equipment, Structures, or Material
IM
1.49
24
0.33
1.00
2.17
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.1.b.2
Inspecting Equipment, Structures, or Material
LV
0.86
24
0.55
0.00
2.00
Y
Y
06/2006
Incumbent
4.A.1.b.3
Estimating the Quantifiable Characteristics of Products, Events, or Information
IM
11-1011.00
4.A.1.b.3
Estimating the Quantifiable Characteristics of...
IM
2.68
24
0.50
1.65
3.71
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.1.b.3
Estimating the Quantifiable Characteristics of...
LV
3.0
24
0.56
1.84
4.17
N
N
06/2006
Incumbent
4.A.2.a.1
Judging the Qualities of Things, Services, or People
IM
11-1011.00
4.A.2.a.1
Judging the Qualities of Things, Services, or ...
IM
3.97
24
0.13
3.70
4.25
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.a.1
Judging the Qualities of Things, Services, or ...
LV
4.93
24
0.26
4.39
5.47
N
N
06/2006
Incumbent
4.A.2.a.2
Processing Information
IM
11-1011.00
4.A.2.a.2
Processing Information
IM
3.13
24
0.48
2.15
4.12
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.a.2
Processing Information
LV
3.53
24
0.80
1.89
5.18
N
N
06/2006
Incumbent
4.A.2.a.3
Evaluating Information to Determine Compliance with Standards
IM
11-1011.00
4.A.2.a.3
Evaluating Information to Determine Compliance...
IM
3.5
24
0.23
3.02
3.98
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.a.3
Evaluating Information to Determine Compliance...
LV
3.88
24
0.37
3.10
4.65
N
N
06/2006
Incumbent
4.A.2.a.4
Analyzing Data or Information
IM
11-1011.00
4.A.2.a.4
Analyzing Data or Information
IM
4.19
24
0.34
3.49
4.90
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.a.4
Analyzing Data or Information
LV
4.82
24
0.29
4.22
5.42
N
N
06/2006
Incumbent
4.A.2.b.1
Making Decisions and Solving Problems
IM
11-1011.00
4.A.2.b.1
Making Decisions and Solving Problems
IM
4.76
24
0.15
4.45
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.1
Making Decisions and Solving Problems
LV
6.15
24
0.08
5.98
6.31
N
N
06/2006
Incumbent
4.A.2.b.2
Thinking Creatively
IM
11-1011.00
4.A.2.b.2
Thinking Creatively
IM
4.11
24
0.21
3.68
4.55
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.2
Thinking Creatively
LV
5.1
24
0.34
4.40
5.81
N
N
06/2006
Incumbent
4.A.2.b.3
Updating and Using Relevant Knowledge
IM
11-1011.00
4.A.2.b.3
Updating and Using Relevant Knowledge
IM
3.75
24
0.41
2.91
4.59
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.3
Updating and Using Relevant Knowledge
LV
4.62
24
0.66
3.24
5.99
N
N
06/2006
Incumbent
4.A.2.b.4
Developing Objectives and Strategies
IM
11-1011.00
4.A.2.b.4
Developing Objectives and Strategies
IM
4.63
24
0.23
4.16
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.4
Developing Objectives and Strategies
LV
5.69
24
0.28
5.11
6.27
N
N
06/2006
Incumbent
4.A.2.b.5
Scheduling Work and Activities
IM
11-1011.00
4.A.2.b.5
Scheduling Work and Activities
IM
3.14
24
0.40
2.30
3.97
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.5
Scheduling Work and Activities
LV
3.8
24
0.75
2.24
5.36
N
N
06/2006
Incumbent
4.A.2.b.6
Organizing, Planning, and Prioritizing Work
IM
11-1011.00
4.A.2.b.6
Organizing, Planning, and Prioritizing Work
IM
4.16
24
0.14
3.86
4.46
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.2.b.6
Organizing, Planning, and Prioritizing Work
LV
5.4
24
0.21
4.97
5.83
N
N
06/2006
Incumbent
4.A.3.a.1
Performing General Physical Activities
IM
11-1011.00
4.A.3.a.1
Performing General Physical Activities
IM
1.39
24
0.32
1.00
2.04
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.a.1
Performing General Physical Activities
LV
0.78
24
0.63
0.00
2.09
Y
Y
06/2006
Incumbent
4.A.3.a.2
Handling and Moving Objects
IM
11-1011.00
4.A.3.a.2
Handling and Moving Objects
IM
1.48
24
0.35
1.00
2.20
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.a.2
Handling and Moving Objects
LV
1.1
24
0.77
0.00
2.69
Y
N
06/2006
Incumbent
4.A.3.a.3
Controlling Machines and Processes
IM
11-1011.00
4.A.3.a.3
Controlling Machines and Processes
IM
1.32
24
0.22
1.00
1.77
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.a.3
Controlling Machines and Processes
LV
0.65
24
0.44
0.00
1.56
Y
Y
06/2006
Incumbent
4.A.3.a.4
Operating Vehicles, Mechanized Devices, or Equipment
IM
11-1011.00
4.A.3.a.4
Operating Vehicles, Mechanized Devices, or Equ...
IM
1.35
24
0.31
1.00
2.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.a.4
Operating Vehicles, Mechanized Devices, or Equ...
LV
0.59
24
0.52
0.00
1.67
Y
Y
06/2006
Incumbent
4.A.3.b.1
Interacting With Computers
IM
11-1011.00
4.A.3.b.1
Interacting With Computers
IM
3.28
24
0.37
2.51
4.05
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.b.1
Interacting With Computers
LV
3.38
24
0.38
2.58
4.17
N
N
06/2006
Incumbent
4.A.3.b.2
Drafting, Laying Out, and Specifying Technical Devices, Parts, and Equipment
IM
11-1011.00
4.A.3.b.2
Drafting, Laying Out, and Specifying Technical...
IM
1.22
24
0.21
1.00
1.65
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.b.2
Drafting, Laying Out, and Specifying Technical...
LV
0.45
24
0.42
0.00
1.32
Y
Y
06/2006
Incumbent
4.A.3.b.4
Repairing and Maintaining Mechanical Equipment
IM
11-1011.00
4.A.3.b.4
Repairing and Maintaining Mechanical Equipment
IM
1.46
24
0.35
1.00
2.17
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.b.4
Repairing and Maintaining Mechanical Equipment
LV
0.93
24
0.68
0.00
2.33
Y
Y
06/2006
Incumbent
4.A.3.b.5
Repairing and Maintaining Electronic Equipment
IM
11-1011.00
4.A.3.b.5
Repairing and Maintaining Electronic Equipment
IM
1.61
24
0.47
1.00
2.58
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.b.5
Repairing and Maintaining Electronic Equipment
LV
0.97
24
0.70
0.00
2.42
Y
Y
06/2006
Incumbent
4.A.3.b.6
Documenting/Recording Information
IM
11-1011.00
4.A.3.b.6
Documenting/Recording Information
IM
2.19
24
0.47
1.22
3.16
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.3.b.6
Documenting/Recording Information
LV
1.88
24
0.72
0.39
3.38
N
N
06/2006
Incumbent
4.A.4.a.1
Interpreting the Meaning of Information for Others
IM
11-1011.00
4.A.4.a.1
Interpreting the Meaning of Information for Ot...
IM
3.59
23
0.21
3.15
4.04
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.1
Interpreting the Meaning of Information for Ot...
LV
3.74
23
0.35
3.02
4.46
N
N
06/2006
Incumbent
4.A.4.a.2
Communicating with Supervisors, Peers, or Subordinates
IM
11-1011.00
4.A.4.a.2
Communicating with Supervisors, Peers, or Subo...
IM
4.75
24
0.15
4.45
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.2
Communicating with Supervisors, Peers, or Subo...
LV
6.11
24
0.34
5.40
6.82
N
N
06/2006
Incumbent
4.A.4.a.3
Communicating with Persons Outside Organization
IM
11-1011.00
4.A.4.a.3
Communicating with Persons Outside Organization
IM
4.62
24
0.23
4.15
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.3
Communicating with Persons Outside Organization
LV
6.45
24
0.32
5.78
7.00
N
N
06/2006
Incumbent
4.A.4.a.4
Establishing and Maintaining Interpersonal Relationships
IM
11-1011.00
4.A.4.a.4
Establishing and Maintaining Interpersonal Rel...
IM
4.64
24
0.23
4.17
5.00
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.4
Establishing and Maintaining Interpersonal Rel...
LV
6.23
24
0.33
5.55
6.92
N
N
06/2006
Incumbent
4.A.4.a.5
Assisting and Caring for Others
IM
11-1011.00
4.A.4.a.5
Assisting and Caring for Others
IM
2.22
24
0.25
1.70
2.75
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.5
Assisting and Caring for Others
LV
2.42
24
0.45
1.49
3.34
N
N
06/2006
Incumbent
4.A.4.a.6
Selling or Influencing Others
IM
11-1011.00
4.A.4.a.6
Selling or Influencing Others
IM
4.34
24
0.29
3.73
4.95
N
n/a
06/2006
Incumbent
LV
11-1011.00
4.A.4.a.6
Selling or Influencing Others
LV
5.47
23
0.34
4.76
6.17
N
N
06/2006
Incumbent
...
...
...
...
...
...
...
...
...
...
...
...
...
75686 rows × 13 columns
In [36]:
#what do each of the elements mean?
getDescriptions(work_activities, content_model_reference, "element_name")
Out[36]:
element_name
element_id
description
0
Getting Information
4.A.1.a.1
Observing, receiving, and otherwise obtaining ...
1
Monitor Processes, Materials, or Surroundings
4.A.1.a.2
Monitoring and reviewing information from mate...
2
Identifying Objects, Actions, and Events
4.A.1.b.1
Identifying information by categorizing, estim...
3
Inspecting Equipment, Structures, or Material
4.A.1.b.2
Inspecting equipment, structures, or materials...
4
Estimating the Quantifiable Characteristics of...
4.A.1.b.3
Estimating sizes, distances, and quantities; o...
5
Judging the Qualities of Things, Services, or ...
4.A.2.a.1
Assessing the value, importance, or quality of...
6
Processing Information
4.A.2.a.2
Compiling, coding, categorizing, calculating, ...
7
Evaluating Information to Determine Compliance...
4.A.2.a.3
Using relevant information and individual judg...
8
Analyzing Data or Information
4.A.2.a.4
Identifying the underlying principles, reasons...
9
Making Decisions and Solving Problems
4.A.2.b.1
Analyzing information and evaluating results t...
10
Thinking Creatively
4.A.2.b.2
Developing, designing, or creating new applica...
11
Updating and Using Relevant Knowledge
4.A.2.b.3
Keeping up-to-date technically and applying ne...
12
Developing Objectives and Strategies
4.A.2.b.4
Establishing long-range objectives and specify...
13
Scheduling Work and Activities
4.A.2.b.5
Scheduling events, programs, and activities, a...
14
Organizing, Planning, and Prioritizing Work
4.A.2.b.6
Developing specific goals and plans to priorit...
15
Performing General Physical Activities
4.A.3.a.1
Performing physical activities that require co...
16
Handling and Moving Objects
4.A.3.a.2
Using hands and arms in handling, installing, ...
17
Controlling Machines and Processes
4.A.3.a.3
Using either control mechanisms or direct phys...
18
Operating Vehicles, Mechanized Devices, or Equ...
4.A.3.a.4
Running, maneuvering, navigating, or driving v...
19
Interacting With Computers
4.A.3.b.1
Using computers and computer systems (includin...
20
Drafting, Laying Out, and Specifying Technical...
4.A.3.b.2
Providing documentation, detailed instructions...
21
Repairing and Maintaining Mechanical Equipment
4.A.3.b.4
Servicing, repairing, adjusting, and testing m...
22
Repairing and Maintaining Electronic Equipment
4.A.3.b.5
Servicing, repairing, calibrating, regulating,...
23
Documenting/Recording Information
4.A.3.b.6
Entering, transcribing, recording, storing, or...
24
Interpreting the Meaning of Information for Ot...
4.A.4.a.1
Translating or explaining what information mea...
25
Communicating with Supervisors, Peers, or Subo...
4.A.4.a.2
Providing information to supervisors, co-worke...
26
Communicating with Persons Outside Organization
4.A.4.a.3
Communicating with people outside the organiza...
27
Establishing and Maintaining Interpersonal Rel...
4.A.4.a.4
Developing constructive and cooperative workin...
28
Assisting and Caring for Others
4.A.4.a.5
Providing personal assistance, medical attenti...
29
Selling or Influencing Others
4.A.4.a.6
Convincing others to buy merchandise/goods or ...
30
Resolving Conflicts and Negotiating with Others
4.A.4.a.7
Handling complaints, settling disputes, and re...
31
Performing for or Working Directly with the Pu...
4.A.4.a.8
Performing for people or dealing directly with...
32
Coordinating the Work and Activities of Others
4.A.4.b.1
Getting members of a group to work together to...
33
Developing and Building Teams
4.A.4.b.2
Encouraging and building mutual trust, respect...
34
Training and Teaching Others
4.A.4.b.3
Identifying the educational needs of others, d...
35
Guiding, Directing, and Motivating Subordinates
4.A.4.b.4
Providing guidance and direction to subordinat...
36
Coaching and Developing Others
4.A.4.b.5
Identifying the developmental needs of others ...
37
Provide Consultation and Advice to Others
4.A.4.b.6
Providing guidance and expert advice to manage...
38
Performing Administrative Activities
4.A.4.c.1
Performing day-to-day administrative tasks suc...
39
Staffing Organizational Units
4.A.4.c.2
Recruiting, interviewing, selecting, hiring, a...
40
Monitoring and Controlling Resources
4.A.4.c.3
Monitoring and controlling resources and overs...
41 rows × 3 columns
In [ ]:
#don't need to do scale- it's the same as abilities and a bunch of other data frames- importance and level
In [158]:
#how many total features are there?
feature(work_activities)
82
In [159]:
#percentage of rows that are relevant
getRelevance(work_activities)
1.81143144042
In [160]:
#percentage of rows that should be excluded
getExclusions(work_activities)
1.77311523928
In [21]:
work_context.head()
Out[21]:
onet_soc_code
element_id
element_name
scale_id
category
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
not_relevant
date
domain_source
0
11-1011.00
4.C.1.a.2.c
Public Speaking
CX
n/a
3.47
27
0.55
2.33
4.61
N
n/a
06/2006
Incumbent
1
11-1011.00
4.C.1.a.2.c
Public Speaking
CXP
1
14.55
27
13.42
1.82
61.04
N
n/a
06/2006
Incumbent
2
11-1011.00
4.C.1.a.2.c
Public Speaking
CXP
2
2.39
27
1.82
0.49
10.86
N
n/a
06/2006
Incumbent
3
11-1011.00
4.C.1.a.2.c
Public Speaking
CXP
3
31.56
27
15.59
9.47
67.03
N
n/a
06/2006
Incumbent
4
11-1011.00
4.C.1.a.2.c
Public Speaking
CXP
4
24.71
27
15.87
5.38
65.47
N
n/a
06/2006
Incumbent
5 rows × 14 columns
In [61]:
#group by the factors
work_context.groupby(['onet_soc_code','element_id','element_name','scale_id','category']).apply(sum)
---------------------------------------------------------------------------
KeyboardInterrupt Traceback (most recent call last)
<ipython-input-61-5909484bb988> in <module>()
1 #group by the factors
----> 2 work_context.groupby(['onet_soc_code','element_id','element_name','scale_id','category']).apply(sum)
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\groupby.pyc in apply(self, func, *args, **kwargs)
422 return func(g, *args, **kwargs)
423
--> 424 return self._python_apply_general(f)
425
426 def _python_apply_general(self, f):
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\groupby.pyc in _python_apply_general(self, f)
425
426 def _python_apply_general(self, f):
--> 427 keys, values, mutated = self.grouper.apply(f, self.obj, self.axis)
428
429 return self._wrap_applied_output(keys, values,
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\groupby.pyc in apply(self, f, data, axis)
868 hasattr(splitter, 'fast_apply') and axis == 0):
869 try:
--> 870 values, mutated = splitter.fast_apply(f, group_keys)
871 return group_keys, values, mutated
872 except Exception:
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\groupby.pyc in fast_apply(self, f, names)
2754
2755 sdata = self._get_sorted_data()
-> 2756 results, mutated = lib.apply_frame_axis0(sdata, f, names, starts, ends)
2757
2758 return results, mutated
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\lib.pyd in pandas.lib.apply_frame_axis0 (pandas\lib.c:28305)()
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\groupby.pyc in f(g)
420 @wraps(func)
421 def f(g):
--> 422 return func(g, *args, **kwargs)
423
424 return self._python_apply_general(f)
c:\Users\Tiffany\Anaconda\lib\site-packages\numpy\core\fromnumeric.pyc in sum(a, axis, dtype, out, keepdims)
1709 out=out, keepdims=keepdims)
1710 # NOTE: Dropping the keepdims parameters here...
-> 1711 return sum(axis=axis, dtype=dtype, out=out)
1712 else:
1713 return _methods._sum(a, axis=axis, dtype=dtype,
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\generic.pyc in stat_func(self, axis, skipna, level, numeric_only, **kwargs)
3488 skipna=skipna)
3489 return self._reduce(f, axis=axis,
-> 3490 skipna=skipna, numeric_only=numeric_only)
3491 stat_func.__name__ = name
3492 return stat_func
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\frame.pyc in _reduce(self, op, axis, skipna, numeric_only, filter_type, **kwds)
4026 result = com._coerce_to_dtypes(result, self.dtypes)
4027
-> 4028 return Series(result, index=labels)
4029
4030 def idxmin(self, axis=0, skipna=True):
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\series.pyc in __init__(self, data, index, dtype, name, copy, fastpath)
220 raise_cast_failure=True)
221
--> 222 data = SingleBlockManager(data, index, fastpath=True)
223
224 generic.NDFrame.__init__(self, data, fastpath=True)
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\internals.pyc in __init__(self, block, axis, do_integrity_check, fastpath)
3590 block = block[0]
3591 if not isinstance(block, Block):
-> 3592 block = make_block(block, axis, axis, ndim=1, fastpath=True)
3593
3594 else:
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\internals.pyc in make_block(values, items, ref_items, klass, ndim, dtype, fastpath, placement)
1990
1991 return klass(values, items, ref_items, ndim=ndim, fastpath=fastpath,
-> 1992 placement=placement)
1993
1994
c:\Users\Tiffany\Anaconda\lib\site-packages\pandas\core\internals.pyc in __init__(self, values, items, ref_items, ndim, fastpath, placement)
1355 super(ObjectBlock, self).__init__(values, items, ref_items, ndim=ndim,
1356 fastpath=fastpath,
-> 1357 placement=placement)
1358
1359 @property
KeyboardInterrupt:
In [35]:
#what are the scales?
getDescriptions(work_context, scales_reference, "scale_id")
Out[35]:
scale_id
scale_name
minimum
maximum
0
CX
Context
1
5
1
CXP
Context (Categories 1-5)
0
100
2
CT
Context
1
3
3
CTP
Context (Categories 1-3)
0
100
4 rows × 4 columns
In [23]:
#what are the categories? These definitions are in the work_context_categories dataframe
#need to change work_context.category from dtype object to dtype int
work_context.category.replace("n/a","0", inplace=True)
In [24]:
work_context.category = work_context.category.astype(int)
In [52]:
categories_desc = getDescriptions(work_context, work_context_categories, "category")
categories_desc
#looks like they are dependent on the element name/id and the scale, let's groupby
Out[52]:
category
element_id
element_name
scale_id
category_description
0
1
4.C.1.a.2.c
Public Speaking
CXP
Never
1
1
4.C.1.a.2.f
Telephone
CXP
Never
2
1
4.C.1.a.2.h
Electronic Mail
CXP
Never
3
1
4.C.1.a.2.j
Letters and Memos
CXP
Never
4
1
4.C.1.a.2.l
Face-to-Face Discussions
CXP
Never
5
1
4.C.1.a.4
Contact With Others
CXP
No contact with others
6
1
4.C.1.b.1.e
Work With Work Group or Team
CXP
Not important at all
7
1
4.C.1.b.1.f
Deal With External Customers
CXP
Not important at all
8
1
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Not important at all
9
1
4.C.1.c.1
Responsible for Others' Health and Safety
CXP
No responsibility
10
1
4.C.1.c.2
Responsibility for Outcomes and Results
CXP
No responsibility
11
1
4.C.1.d.1
Frequency of Conflict Situations
CXP
Never
12
1
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Never
13
1
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Never
14
1
4.C.2.a.1.a
Indoors, Environmentally Controlled
CXP
Never
15
1
4.C.2.a.1.b
Indoors, Not Environmentally Controlled
CXP
Never
16
1
4.C.2.a.1.c
Outdoors, Exposed to Weather
CXP
Never
17
1
4.C.2.a.1.d
Outdoors, Under Cover
CXP
Never
18
1
4.C.2.a.1.e
In an Open Vehicle or Equipment
CXP
Never
19
1
4.C.2.a.1.f
In an Enclosed Vehicle or Equipment
CXP
Never
20
1
4.C.2.a.3
Physical Proximity
CXP
I don't work near other people (beyond 100 ft.)
21
1
4.C.2.b.1.a
Sounds, Noise Levels Are Distracting or Uncomf...
CXP
Never
22
1
4.C.2.b.1.b
Very Hot or Cold Temperatures
CXP
Never
23
1
4.C.2.b.1.c
Extremely Bright or Inadequate Lighting
CXP
Never
24
1
4.C.2.b.1.d
Exposed to Contaminants
CXP
Never
25
1
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Never
26
1
4.C.2.b.1.f
Exposed to Whole Body Vibration
CXP
Never
27
1
4.C.2.c.1.a
Exposed to Radiation
CXP
Never
28
1
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Never
29
1
4.C.2.c.1.c
Exposed to High Places
CXP
Never
30
1
4.C.2.c.1.d
Exposed to Hazardous Conditions
CXP
Never
31
1
4.C.2.c.1.e
Exposed to Hazardous Equipment
CXP
Never
32
1
4.C.2.c.1.f
Exposed to Minor Burns, Cuts, Bites, or Stings
CXP
Never
33
1
4.C.2.d.1.a
Spend Time Sitting
CXP
Never
34
1
4.C.2.d.1.b
Spend Time Standing
CXP
Never
35
1
4.C.2.d.1.c
Spend Time Climbing Ladders, Scaffolds, or Poles
CXP
Never
36
1
4.C.2.d.1.d
Spend Time Walking and Running
CXP
Never
37
1
4.C.2.d.1.e
Spend Time Kneeling, Crouching, Stooping, or C...
CXP
Never
38
1
4.C.2.d.1.f
Spend Time Keeping or Regaining Balance
CXP
Never
39
1
4.C.2.d.1.g
Spend Time Using Your Hands to Handle, Control...
CXP
Never
40
1
4.C.2.d.1.h
Spend Time Bending or Twisting the Body
CXP
Never
41
1
4.C.2.d.1.i
Spend Time Making Repetitive Motions
CXP
Never
42
1
4.C.2.e.1.d
Wear Common Protective or Safety Equipment suc...
CXP
Never
43
1
4.C.2.e.1.e
Wear Specialized Protective or Safety Equipmen...
CXP
Never
44
1
4.C.3.a.1
Consequence of Error
CXP
Not serious at all
45
1
4.C.3.a.2.a
Impact of Decisions on Co-workers or Company R...
CXP
No results
46
1
4.C.3.a.2.b
Frequency of Decision Making
CXP
Never
47
1
4.C.3.a.4
Freedom to Make Decisions
CXP
No freedom
48
1
4.C.3.b.2
Degree of Automation
CXP
Not at all automated
49
1
4.C.3.b.4
Importance of Being Exact or Accurate
CXP
Not important at all
50
1
4.C.3.b.7
Importance of Repeating Same Tasks
CXP
Not important at all
51
1
4.C.3.b.8
Structured versus Unstructured Work
CXP
No freedom
52
1
4.C.3.c.1
Level of Competition
CXP
Not at all competitive
53
1
4.C.3.d.1
Time Pressure
CXP
Never
54
1
4.C.3.d.3
Pace Determined by Speed of Equipment
CXP
Not important at all
55
1
4.C.3.d.4
Work Schedules
CTP
Regular (established routine, set schedule)
56
1
4.C.3.d.8
Duration of Typical Work Week
CTP
Less than 40 hours
57
2
4.C.1.a.2.c
Public Speaking
CXP
Once a year or more but not every month
58
2
4.C.1.a.2.f
Telephone
CXP
Once a year or more but not every month
59
2
4.C.1.a.2.h
Electronic Mail
CXP
Once a year or more but not every month
...
...
...
...
...
281 rows × 5 columns
In [55]:
#let's group the category description to figure out what's going on
categories_desc.groupby(['element_name','scale_id','category']).apply(sum)
Out[55]:
category
element_id
element_name
scale_id
category_description
element_name
scale_id
category
Consequence of Error
CXP
1
1
4.C.3.a.1
Consequence of Error
CXP
Not serious at all
2
2
4.C.3.a.1
Consequence of Error
CXP
Fairly serious
3
3
4.C.3.a.1
Consequence of Error
CXP
Serious
4
4
4.C.3.a.1
Consequence of Error
CXP
Very serious
5
5
4.C.3.a.1
Consequence of Error
CXP
Extremely serious
Contact With Others
CXP
1
1
4.C.1.a.4
Contact With Others
CXP
No contact with others
2
2
4.C.1.a.4
Contact With Others
CXP
Occasional contact with others
3
3
4.C.1.a.4
Contact With Others
CXP
Contact with others about half the time
4
4
4.C.1.a.4
Contact With Others
CXP
Contact with others most of the time
5
5
4.C.1.a.4
Contact With Others
CXP
Constant contact with others
Coordinate or Lead Others
CXP
1
1
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Not important at all
2
2
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Fairly important
3
3
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Important
4
4
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Very important
5
5
4.C.1.b.1.g
Coordinate or Lead Others
CXP
Extremely important
Cramped Work Space, Awkward Positions
CXP
1
1
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Never
2
2
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Once a year or more but not every month
3
3
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Once a month or more but not every week
4
4
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Once a week or more but not every day
5
5
4.C.2.b.1.e
Cramped Work Space, Awkward Positions
CXP
Every day
Deal With External Customers
CXP
1
1
4.C.1.b.1.f
Deal With External Customers
CXP
Not important at all
2
2
4.C.1.b.1.f
Deal With External Customers
CXP
Fairly important
3
3
4.C.1.b.1.f
Deal With External Customers
CXP
Important
4
4
4.C.1.b.1.f
Deal With External Customers
CXP
Very important
5
5
4.C.1.b.1.f
Deal With External Customers
CXP
Extremely important
Deal With Physically Aggressive People
CXP
1
1
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Never
2
2
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Once a year or more but not every month
3
3
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Once a month or more but not every week
4
4
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Once a week or more but not every day
5
5
4.C.1.d.3
Deal With Physically Aggressive People
CXP
Every day
Deal With Unpleasant or Angry People
CXP
1
1
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Never
2
2
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Once a year or more but not every month
3
3
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Once a month or more but not every week
4
4
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Once a week or more but not every day
5
5
4.C.1.d.2
Deal With Unpleasant or Angry People
CXP
Every day
Degree of Automation
CXP
1
1
4.C.3.b.2
Degree of Automation
CXP
Not at all automated
2
2
4.C.3.b.2
Degree of Automation
CXP
Slightly automated
3
3
4.C.3.b.2
Degree of Automation
CXP
Moderately automated
4
4
4.C.3.b.2
Degree of Automation
CXP
Highly automated
5
5
4.C.3.b.2
Degree of Automation
CXP
Completely automated
Duration of Typical Work Week
CTP
1
1
4.C.3.d.8
Duration of Typical Work Week
CTP
Less than 40 hours
2
2
4.C.3.d.8
Duration of Typical Work Week
CTP
40 hours
3
3
4.C.3.d.8
Duration of Typical Work Week
CTP
More than 40 hours
Electronic Mail
CXP
1
1
4.C.1.a.2.h
Electronic Mail
CXP
Never
2
2
4.C.1.a.2.h
Electronic Mail
CXP
Once a year or more but not every month
3
3
4.C.1.a.2.h
Electronic Mail
CXP
Once a month or more but not every week
4
4
4.C.1.a.2.h
Electronic Mail
CXP
Once a week or more but not every day
5
5
4.C.1.a.2.h
Electronic Mail
CXP
Every day
Exposed to Contaminants
CXP
1
1
4.C.2.b.1.d
Exposed to Contaminants
CXP
Never
2
2
4.C.2.b.1.d
Exposed to Contaminants
CXP
Once a year or more but not every month
3
3
4.C.2.b.1.d
Exposed to Contaminants
CXP
Once a month or more but not every week
4
4
4.C.2.b.1.d
Exposed to Contaminants
CXP
Once a week or more but not every day
5
5
4.C.2.b.1.d
Exposed to Contaminants
CXP
Every day
Exposed to Disease or Infections
CXP
1
1
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Never
2
2
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Once a year or more but not every month
3
3
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Once a month or more but not every week
4
4
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Once a week or more but not every day
5
5
4.C.2.c.1.b
Exposed to Disease or Infections
CXP
Every day
Exposed to Hazardous Conditions
CXP
1
1
4.C.2.c.1.d
Exposed to Hazardous Conditions
CXP
Never
2
2
4.C.2.c.1.d
Exposed to Hazardous Conditions
CXP
Once a year or more but not every month
...
...
...
...
...
281 rows × 5 columns
In [27]:
#how many features are in work context?
feature(work_context)
336
In [28]:
#percent that are relevant
getRelevance(work_context)
0.0
In [30]:
#percent to be excluded
getExclusions(work_context)
2.56119885082
In [56]:
work_styles.head()
Out[56]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
date
domain_source
0
11-1011.00
1.C.1.a
Achievement/Effort
IM
4.66
30
0.18
4.30
5.00
N
06/2006
Incumbent
1
11-1011.00
1.C.1.b
Persistence
IM
4.61
30
0.19
4.23
4.99
N
06/2006
Incumbent
2
11-1011.00
1.C.1.c
Initiative
IM
4.79
30
0.14
4.51
5.00
N
06/2006
Incumbent
3
11-1011.00
1.C.2.b
Leadership
IM
4.84
30
0.13
4.57
5.00
N
06/2006
Incumbent
4
11-1011.00
1.C.3.a
Cooperation
IM
4.42
30
0.19
4.02
4.81
N
06/2006
Incumbent
5 rows × 12 columns
In [57]:
work_styles.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
Out[57]:
onet_soc_code
element_id
element_name
scale_id
data_value
n
standard_error
lower_ci_bound
upper_ci_bound
recommend_suppress
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
1.C.1.a
Achievement/Effort
IM
11-1011.00
1.C.1.a
Achievement/Effort
IM
4.66
30
0.18
4.30
5.00
N
06/2006
Incumbent
1.C.1.b
Persistence
IM
11-1011.00
1.C.1.b
Persistence
IM
4.61
30
0.19
4.23
4.99
N
06/2006
Incumbent
1.C.1.c
Initiative
IM
11-1011.00
1.C.1.c
Initiative
IM
4.79
30
0.14
4.51
5.00
N
06/2006
Incumbent
1.C.2.b
Leadership
IM
11-1011.00
1.C.2.b
Leadership
IM
4.84
30
0.13
4.57
5.00
N
06/2006
Incumbent
1.C.3.a
Cooperation
IM
11-1011.00
1.C.3.a
Cooperation
IM
4.42
30
0.19
4.02
4.81
N
06/2006
Incumbent
1.C.3.b
Concern for Others
IM
11-1011.00
1.C.3.b
Concern for Others
IM
3.95
30
0.15
3.64
4.26
N
06/2006
Incumbent
1.C.3.c
Social Orientation
IM
11-1011.00
1.C.3.c
Social Orientation
IM
4.02
29
0.04
3.94
4.09
N
06/2006
Incumbent
1.C.4.a
Self Control
IM
11-1011.00
1.C.4.a
Self Control
IM
4.28
30
0.15
3.97
4.59
N
06/2006
Incumbent
1.C.4.b
Stress Tolerance
IM
11-1011.00
1.C.4.b
Stress Tolerance
IM
4.75
30
0.15
4.45
5.00
N
06/2006
Incumbent
1.C.4.c
Adaptability/Flexibility
IM
11-1011.00
1.C.4.c
Adaptability/Flexibility
IM
4.48
30
0.21
4.05
4.90
N
06/2006
Incumbent
1.C.5.a
Dependability
IM
11-1011.00
1.C.5.a
Dependability
IM
4.67
30
0.18
4.31
5.00
N
06/2006
Incumbent
1.C.5.b
Attention to Detail
IM
11-1011.00
1.C.5.b
Attention to Detail
IM
4.26
30
0.31
3.62
4.90
N
06/2006
Incumbent
1.C.5.c
Integrity
IM
11-1011.00
1.C.5.c
Integrity
IM
4.85
30
0.13
4.59
5.00
N
06/2006
Incumbent
1.C.6
Independence
IM
11-1011.00
1.C.6
Independence
IM
4.63
30
0.18
4.26
5.00
N
06/2006
Incumbent
1.C.7.a
Innovation
IM
11-1011.00
1.C.7.a
Innovation
IM
4.22
30
0.14
3.94
4.50
N
06/2006
Incumbent
1.C.7.b
Analytical Thinking
IM
11-1011.00
1.C.7.b
Analytical Thinking
IM
4.24
30
0.14
3.95
4.53
N
06/2006
Incumbent
11-1011.03
1.C.1.a
Achievement/Effort
IM
11-1011.03
1.C.1.a
Achievement/Effort
IM
4.19
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.1.b
Persistence
IM
11-1011.03
1.C.1.b
Persistence
IM
4.31
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.1.c
Initiative
IM
11-1011.03
1.C.1.c
Initiative
IM
4.6
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.2.b
Leadership
IM
11-1011.03
1.C.2.b
Leadership
IM
4.64
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.3.a
Cooperation
IM
11-1011.03
1.C.3.a
Cooperation
IM
4.32
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.3.b
Concern for Others
IM
11-1011.03
1.C.3.b
Concern for Others
IM
3.48
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.3.c
Social Orientation
IM
11-1011.03
1.C.3.c
Social Orientation
IM
3.35
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.4.a
Self Control
IM
11-1011.03
1.C.4.a
Self Control
IM
4.0
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.4.b
Stress Tolerance
IM
11-1011.03
1.C.4.b
Stress Tolerance
IM
4.08
25
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.4.c
Adaptability/Flexibility
IM
11-1011.03
1.C.4.c
Adaptability/Flexibility
IM
4.23
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.5.a
Dependability
IM
11-1011.03
1.C.5.a
Dependability
IM
4.23
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.5.b
Attention to Detail
IM
11-1011.03
1.C.5.b
Attention to Detail
IM
4.12
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.5.c
Integrity
IM
11-1011.03
1.C.5.c
Integrity
IM
4.58
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.6
Independence
IM
11-1011.03
1.C.6
Independence
IM
4.27
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.7.a
Innovation
IM
11-1011.03
1.C.7.a
Innovation
IM
4.38
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
1.C.7.b
Analytical Thinking
IM
11-1011.03
1.C.7.b
Analytical Thinking
IM
4.31
26
n/a
n/a
n/a
n/a
07/2013
Occupational Expert
11-1021.00
1.C.1.a
Achievement/Effort
IM
11-1021.00
1.C.1.a
Achievement/Effort
IM
4.07
44
0.14
3.80
4.35
N
06/2008
Incumbent
1.C.1.b
Persistence
IM
11-1021.00
1.C.1.b
Persistence
IM
4.24
44
0.11
4.03
4.46
N
06/2008
Incumbent
1.C.1.c
Initiative
IM
11-1021.00
1.C.1.c
Initiative
IM
4.36
44
0.14
4.09
4.64
N
06/2008
Incumbent
1.C.2.b
Leadership
IM
11-1021.00
1.C.2.b
Leadership
IM
4.5
44
0.10
4.29
4.71
N
06/2008
Incumbent
1.C.3.a
Cooperation
IM
11-1021.00
1.C.3.a
Cooperation
IM
4.26
44
0.14
3.98
4.53
N
06/2008
Incumbent
1.C.3.b
Concern for Others
IM
11-1021.00
1.C.3.b
Concern for Others
IM
3.96
44
0.18
3.61
4.32
N
06/2008
Incumbent
1.C.3.c
Social Orientation
IM
11-1021.00
1.C.3.c
Social Orientation
IM
3.56
44
0.18
3.19
3.93
N
06/2008
Incumbent
1.C.4.a
Self Control
IM
11-1021.00
1.C.4.a
Self Control
IM
4.38
44
0.15
4.08
4.68
N
06/2008
Incumbent
1.C.4.b
Stress Tolerance
IM
11-1021.00
1.C.4.b
Stress Tolerance
IM
4.35
44
0.14
4.07
4.64
N
06/2008
Incumbent
1.C.4.c
Adaptability/Flexibility
IM
11-1021.00
1.C.4.c
Adaptability/Flexibility
IM
4.21
44
0.18
3.84
4.58
N
06/2008
Incumbent
1.C.5.a
Dependability
IM
11-1021.00
1.C.5.a
Dependability
IM
4.73
44
0.08
4.57
4.89
N
06/2008
Incumbent
1.C.5.b
Attention to Detail
IM
11-1021.00
1.C.5.b
Attention to Detail
IM
4.52
44
0.11
4.29
4.75
N
06/2008
Incumbent
1.C.5.c
Integrity
IM
11-1021.00
1.C.5.c
Integrity
IM
4.36
44
0.14
4.07
4.65
N
06/2008
Incumbent
1.C.6
Independence
IM
11-1021.00
1.C.6
Independence
IM
3.96
44
0.15
3.66
4.27
N
06/2008
Incumbent
1.C.7.a
Innovation
IM
11-1021.00
1.C.7.a
Innovation
IM
3.88
44
0.22
3.44
4.32
N
06/2008
Incumbent
1.C.7.b
Analytical Thinking
IM
11-1021.00
1.C.7.b
Analytical Thinking
IM
4.22
44
0.17
3.88
4.55
N
06/2008
Incumbent
11-2011.00
1.C.1.a
Achievement/Effort
IM
11-2011.00
1.C.1.a
Achievement/Effort
IM
4.3
24
0.12
4.06
4.55
N
06/2010
Incumbent
1.C.1.b
Persistence
IM
11-2011.00
1.C.1.b
Persistence
IM
4.23
24
0.13
3.96
4.50
N
06/2010
Incumbent
1.C.1.c
Initiative
IM
11-2011.00
1.C.1.c
Initiative
IM
4.71
24
0.11
4.49
4.94
N
06/2010
Incumbent
1.C.2.b
Leadership
IM
11-2011.00
1.C.2.b
Leadership
IM
4.23
24
0.12
3.99
4.48
N
06/2010
Incumbent
1.C.3.a
Cooperation
IM
11-2011.00
1.C.3.a
Cooperation
IM
4.4
24
0.17
4.06
4.75
N
06/2010
Incumbent
1.C.3.b
Concern for Others
IM
11-2011.00
1.C.3.b
Concern for Others
IM
3.93
24
0.16
3.59
4.26
N
06/2010
Incumbent
1.C.3.c
Social Orientation
IM
11-2011.00
1.C.3.c
Social Orientation
IM
3.99
24
0.17
3.64
4.34
N
06/2010
Incumbent
1.C.4.a
Self Control
IM
11-2011.00
1.C.4.a
Self Control
IM
4.42
24
0.17
4.07
4.76
N
06/2010
Incumbent
1.C.4.b
Stress Tolerance
IM
11-2011.00
1.C.4.b
Stress Tolerance
IM
4.39
24
0.21
3.96
4.81
N
06/2010
Incumbent
1.C.4.c
Adaptability/Flexibility
IM
11-2011.00
1.C.4.c
Adaptability/Flexibility
IM
4.54
24
0.14
4.25
4.84
N
06/2010
Incumbent
1.C.5.a
Dependability
IM
11-2011.00
1.C.5.a
Dependability
IM
4.74
24
0.09
4.56
4.93
N
06/2010
Incumbent
1.C.5.b
Attention to Detail
IM
11-2011.00
1.C.5.b
Attention to Detail
IM
4.7
24
0.11
4.48
4.93
N
06/2010
Incumbent
...
...
...
...
...
...
...
...
...
...
...
...
14752 rows × 12 columns
In [59]:
#what are the elements
getDescriptions(work_styles, content_model_reference, "element_name")
Out[59]:
element_name
element_id
description
0
Achievement/Effort
1.C.1.a
Job requires establishing and maintaining pers...
1
Persistence
1.C.1.b
Job requires persistence in the face of obstac...
2
Initiative
1.C.1.c
Job requires a willingness to take on responsi...
3
Leadership
1.C.2.b
Job requires a willingness to lead, take charg...
4
Cooperation
1.C.3.a
Job requires being pleasant with others on the...
5
Concern for Others
1.C.3.b
Job requires being sensitive to others' needs ...
6
Social Orientation
1.C.3.c
Job requires preferring to work with others ra...
7
Self Control
1.C.4.a
Job requires maintaining composure, keeping em...
8
Stress Tolerance
1.C.4.b
Job requires accepting criticism and dealing c...
9
Adaptability/Flexibility
1.C.4.c
Job requires being open to change (positive or...
10
Dependability
1.C.5.a
Job requires being reliable, responsible, and ...
11
Attention to Detail
1.C.5.b
Job requires being careful about detail and th...
12
Integrity
1.C.5.c
Job requires being honest and ethical.
13
Independence
1.B.2.b.2
Workers on this job do their work alone.
14
Independence
1.B.2.f
Occupations that satisfy this work value allow...
15
Independence
1.C.6
Job requires developing one's own ways of doin...
16
Innovation
1.C.7.a
Job requires creativity and alternative thinki...
17
Innovation
4.B.2.c.1.a.7
Innovation; finding new and better ways of doi...
18
Analytical Thinking
1.C.7.b
Job requires analyzing information and using l...
19 rows × 3 columns
In [60]:
#what are the different scales?
getDescriptions(work_styles, scales_reference, "scale_id")
Out[60]:
scale_id
scale_name
minimum
maximum
0
IM
Importance
1
5
1 rows × 4 columns
In [62]:
#how many features are there?
feature(work_styles)
Out[62]:
16
In [64]:
#what percentage should be excluded?
getExclusions(work_styles)
Out[64]:
0.0
In [65]:
work_values.head()
Out[65]:
onet_soc_code
element_id
element_name
scale_id
data_value
date
domain_source
0
11-1011.00
1.B.2.a
Achievement
EX
6.33
06/2008
Analyst
1
11-1011.00
1.B.2.b
Working Conditions
EX
6.33
06/2008
Analyst
2
11-1011.00
1.B.2.c
Recognition
EX
7.00
06/2008
Analyst
3
11-1011.00
1.B.2.d
Relationships
EX
5.00
06/2008
Analyst
4
11-1011.00
1.B.2.e
Support
EX
5.33
06/2008
Analyst
5 rows × 7 columns
In [66]:
work_values.groupby(['onet_soc_code','element_id','element_name','scale_id']).apply(sum)
Out[66]:
onet_soc_code
element_id
element_name
scale_id
data_value
date
domain_source
onet_soc_code
element_id
element_name
scale_id
11-1011.00
1.B.2.a
Achievement
EX
11-1011.00
1.B.2.a
Achievement
EX
6.33
06/2008
Analyst
1.B.2.b
Working Conditions
EX
11-1011.00
1.B.2.b
Working Conditions
EX
6.33
06/2008
Analyst
1.B.2.c
Recognition
EX
11-1011.00
1.B.2.c
Recognition
EX
7.0
06/2008
Analyst
1.B.2.d
Relationships
EX
11-1011.00
1.B.2.d
Relationships
EX
5.0
06/2008
Analyst
1.B.2.e
Support
EX
11-1011.00
1.B.2.e
Support
EX
5.33
06/2008
Analyst
1.B.2.f
Independence
EX
11-1011.00
1.B.2.f
Independence
EX
7.0
06/2008
Analyst
1.B.2.g
First Work Value High-Point
VH
11-1011.00
1.B.2.g
First Work Value High-Point
VH
3.0
06/2008
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-1011.00
1.B.2.h
Second Work Value High-Point
VH
6.0
06/2008
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-1011.00
1.B.2.i
Third Work Value High-Point
VH
1.0
06/2008
Analyst
11-1011.03
1.B.2.a
Achievement
EX
11-1011.03
1.B.2.a
Achievement
EX
6.67
07/2012
Analyst
1.B.2.b
Working Conditions
EX
11-1011.03
1.B.2.b
Working Conditions
EX
6.33
07/2012
Analyst
1.B.2.c
Recognition
EX
11-1011.03
1.B.2.c
Recognition
EX
6.0
07/2012
Analyst
1.B.2.d
Relationships
EX
11-1011.03
1.B.2.d
Relationships
EX
5.0
07/2012
Analyst
1.B.2.e
Support
EX
11-1011.03
1.B.2.e
Support
EX
3.33
07/2012
Analyst
1.B.2.f
Independence
EX
11-1011.03
1.B.2.f
Independence
EX
6.67
07/2012
Analyst
1.B.2.g
First Work Value High-Point
VH
11-1011.03
1.B.2.g
First Work Value High-Point
VH
1.0
07/2012
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-1011.03
1.B.2.h
Second Work Value High-Point
VH
6.0
07/2012
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-1011.03
1.B.2.i
Third Work Value High-Point
VH
2.0
07/2012
Analyst
11-1021.00
1.B.2.a
Achievement
EX
11-1021.00
1.B.2.a
Achievement
EX
5.33
06/2008
Analyst
1.B.2.b
Working Conditions
EX
11-1021.00
1.B.2.b
Working Conditions
EX
6.0
06/2008
Analyst
1.B.2.c
Recognition
EX
11-1021.00
1.B.2.c
Recognition
EX
5.67
06/2008
Analyst
1.B.2.d
Relationships
EX
11-1021.00
1.B.2.d
Relationships
EX
6.33
06/2008
Analyst
1.B.2.e
Support
EX
11-1021.00
1.B.2.e
Support
EX
4.67
06/2008
Analyst
1.B.2.f
Independence
EX
11-1021.00
1.B.2.f
Independence
EX
6.0
06/2008
Analyst
1.B.2.g
First Work Value High-Point
VH
11-1021.00
1.B.2.g
First Work Value High-Point
VH
4.0
06/2008
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-1021.00
1.B.2.h
Second Work Value High-Point
VH
6.0
06/2008
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-1021.00
1.B.2.i
Third Work Value High-Point
VH
2.0
06/2008
Analyst
11-1031.00
1.B.2.a
Achievement
EX
11-1031.00
1.B.2.a
Achievement
EX
5.33
06/2008
Analyst
1.B.2.b
Working Conditions
EX
11-1031.00
1.B.2.b
Working Conditions
EX
4.33
06/2008
Analyst
1.B.2.c
Recognition
EX
11-1031.00
1.B.2.c
Recognition
EX
5.0
06/2008
Analyst
1.B.2.d
Relationships
EX
11-1031.00
1.B.2.d
Relationships
EX
5.67
06/2008
Analyst
1.B.2.e
Support
EX
11-1031.00
1.B.2.e
Support
EX
4.0
06/2008
Analyst
1.B.2.f
Independence
EX
11-1031.00
1.B.2.f
Independence
EX
5.0
06/2008
Analyst
1.B.2.g
First Work Value High-Point
VH
11-1031.00
1.B.2.g
First Work Value High-Point
VH
4.0
06/2008
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-1031.00
1.B.2.h
Second Work Value High-Point
VH
1.0
06/2008
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-1031.00
1.B.2.i
Third Work Value High-Point
VH
3.0
06/2008
Analyst
11-2011.00
1.B.2.a
Achievement
EX
11-2011.00
1.B.2.a
Achievement
EX
5.33
06/2008
Analyst
1.B.2.b
Working Conditions
EX
11-2011.00
1.B.2.b
Working Conditions
EX
5.33
06/2008
Analyst
1.B.2.c
Recognition
EX
11-2011.00
1.B.2.c
Recognition
EX
5.33
06/2008
Analyst
1.B.2.d
Relationships
EX
11-2011.00
1.B.2.d
Relationships
EX
5.0
06/2008
Analyst
1.B.2.e
Support
EX
11-2011.00
1.B.2.e
Support
EX
4.0
06/2008
Analyst
1.B.2.f
Independence
EX
11-2011.00
1.B.2.f
Independence
EX
5.33
06/2008
Analyst
1.B.2.g
First Work Value High-Point
VH
11-2011.00
1.B.2.g
First Work Value High-Point
VH
2.0
06/2008
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-2011.00
1.B.2.h
Second Work Value High-Point
VH
1.0
06/2008
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-2011.00
1.B.2.i
Third Work Value High-Point
VH
6.0
06/2008
Analyst
11-2011.01
1.B.2.a
Achievement
EX
11-2011.01
1.B.2.a
Achievement
EX
5.33
07/2012
Analyst
1.B.2.b
Working Conditions
EX
11-2011.01
1.B.2.b
Working Conditions
EX
4.83
07/2012
Analyst
1.B.2.c
Recognition
EX
11-2011.01
1.B.2.c
Recognition
EX
5.0
07/2012
Analyst
1.B.2.d
Relationships
EX
11-2011.01
1.B.2.d
Relationships
EX
5.0
07/2012
Analyst
1.B.2.e
Support
EX
11-2011.01
1.B.2.e
Support
EX
4.0
07/2012
Analyst
1.B.2.f
Independence
EX
11-2011.01
1.B.2.f
Independence
EX
5.33
07/2012
Analyst
1.B.2.g
First Work Value High-Point
VH
11-2011.01
1.B.2.g
First Work Value High-Point
VH
6.0
07/2012
Analyst
1.B.2.h
Second Work Value High-Point
VH
11-2011.01
1.B.2.h
Second Work Value High-Point
VH
1.0
07/2012
Analyst
1.B.2.i
Third Work Value High-Point
VH
11-2011.01
1.B.2.i
Third Work Value High-Point
VH
3.0
07/2012
Analyst
11-2021.00
1.B.2.a
Achievement
EX
11-2021.00
1.B.2.a
Achievement
EX
6.0
06/2008
Analyst
1.B.2.b
Working Conditions
EX
11-2021.00
1.B.2.b
Working Conditions
EX
6.17
06/2008
Analyst
1.B.2.c
Recognition
EX
11-2021.00
1.B.2.c
Recognition
EX
5.33
06/2008
Analyst
1.B.2.d
Relationships
EX
11-2021.00
1.B.2.d
Relationships
EX
5.67
06/2008
Analyst
1.B.2.e
Support
EX
11-2021.00
1.B.2.e
Support
EX
5.0
06/2008
Analyst
1.B.2.f
Independence
EX
11-2021.00
1.B.2.f
Independence
EX
5.67
06/2008
Analyst
...
...
...
...
...
...
...
8766 rows × 7 columns
In [67]:
#what are the different element names?
getDescriptions(work_values, content_model_reference, "element_name")
Out[67]:
element_name
element_id
description
0
Achievement
1.B.2.a
Occupations that satisfy this work value are r...
1
Achievement
1.B.2.a.2
Workers on this job get a feeling of accomplis...
2
Working Conditions
1.B.2.b
Occupations that satisfy this work value offer...
3
Working Conditions
1.B.2.b.6
Workers on this job have good working conditions.
4
Recognition
1.B.2.c
Occupations that satisfy this work value offer...
5
Recognition
1.B.2.c.2
Workers on this job receive recognition for th...
6
Relationships
1.B.2.d
Occupations that satisfy this work value allow...
7
Support
1.B.2.e
Occupations that satisfy this work value offer...
8
Independence
1.B.2.b.2
Workers on this job do their work alone.
9
Independence
1.B.2.f
Occupations that satisfy this work value allow...
10
Independence
1.C.6
Job requires developing one's own ways of doin...
11
First Work Value High-Point
1.B.2.g
Primary-Rank Descriptiveness
12
Second Work Value High-Point
1.B.2.h
Secondary-Cutoff/Rank Descriptiveness
13
Third Work Value High-Point
1.B.2.i
Tertiary-Cutoff/Rank Descriptiveness
14 rows × 3 columns
In [68]:
#get scales
getDescriptions(work_values, scales_reference, "scale_id")
Out[68]:
scale_id
scale_name
minimum
maximum
0
EX
Extent
1
7
1
VH
Work Value High-Point
1
6
2 rows × 4 columns
In [69]:
#what are the number of features
feature(work_values)
Out[69]:
9
In [ ]:
#wh
Content source: annaswigart/career-xplorer
Similar notebooks: