Solution of practical task 1
Task: Ranking of potential candidates by professional responsibilities
The solution of the practical task is performed in two stages. At the first stage it is necessary to use the OCEAN-AI library to obtain predictions (personality traits scores). The second step is to use the methods _candidate_ranking and _priority_skill_calculation from the OCEAN-AI library to solve the presented practical task. Examples of the results of the work and implementation are presented below.
Thus, the OCEAN-AI library provides tools to analyze the personality traits of candidates and their suitability for the position, which can significantly improve the recruitment process and help to make more
FI V2
[2]:
# Import required tools
import os
import pandas as pd
# Module import
from oceanai.modules.lab.build import Run
# Creating an instance of a class
_b5 = Run(lang = 'en')
# Core setup
_b5.path_to_save_ = './models' # Directory to save the models
_b5.chunk_size_ = 2000000 # File download size from network in one step
corpus = 'fi'
# Building audio models
res_load_model_hc = _b5.load_audio_model_hc()
res_load_model_nn = _b5.load_audio_model_nn()
# Loading audio model weights
url = _b5.weights_for_big5_['audio'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_audio_model_weights_hc(url = url)
url = _b5.weights_for_big5_['audio'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_audio_model_weights_nn(url = url)
# Loading audio model weights
res_load_model_hc = _b5.load_video_model_hc(lang='en')
res_load_model_deep_fe = _b5.load_video_model_deep_fe()
res_load_model_nn = _b5.load_video_model_nn()
# Loading video model weights
url = _b5.weights_for_big5_['video'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_video_model_weights_hc(url = url)
url = _b5.weights_for_big5_['video'][corpus]['fe']['sberdisk']
res_load_model_weights_deep_fe = _b5.load_video_model_weights_deep_fe(url = url)
url = _b5.weights_for_big5_['video'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_video_model_weights_nn(url = url)
# Loading a dictionary with hand-crafted features (text modality)
res_load_text_features = _b5.load_text_features()
# Building text models
res_setup_translation_model = _b5.setup_translation_model()
res_setup_translation_model = _b5.setup_bert_encoder()
res_load_text_model_hc_fi = _b5.load_text_model_hc(corpus=corpus)
res_load_text_model_nn_fi = _b5.load_text_model_nn(corpus=corpus)
# Loading text model weights
url = _b5.weights_for_big5_['text'][corpus]['hc']['sberdisk']
res_load_text_model_weights_hc_fi = _b5.load_text_model_weights_hc(url = url)
url = _b5.weights_for_big5_['text'][corpus]['nn']['sberdisk']
res_load_text_model_weights_nn_fi = _b5.load_text_model_weights_nn(url = url)
# Building model for multimodal information fusion
res_load_avt_model_b5 = _b5.load_avt_model_b5()
# Loading model weights for multimodal information fusion
url = _b5.weights_for_big5_['avt'][corpus]['b5']['sberdisk']
res_load_avt_model_weights_b5 = _b5.load_avt_model_weights_b5(url = url)
PATH_TO_DIR = './video_FI/'
PATH_SAVE_VIDEO = './video_FI/test/'
_b5.path_to_save_ = PATH_SAVE_VIDEO
# Loading 10 test files from the First Impressions V2 corpus
# URL: https://chalearnlap.cvc.uab.cat/dataset/24/description/
domain = 'https://download.sberdisk.ru/download/file/'
tets_name_files = [
'429713680?token=FqHdMLSSh7zYSZt&filename=_plk5k7PBEg.003.mp4',
'429713681?token=Hz9b4lQkrLfic33&filename=be0DQawtVkE.002.mp4',
'429713683?token=EgUXS9Xs8xHm5gz&filename=2d6btbaNdfo.000.mp4',
'429713684?token=1U26753kmPYdIgt&filename=300gK3CnzW0.003.mp4',
'429713685?token=LyigAWLTzDNwKJO&filename=300gK3CnzW0.001.mp4',
'429713686?token=EpfRbCKHyuc4HPu&filename=cLaZxEf1nE4.004.mp4',
'429713687?token=FNTkwqBr4jOS95l&filename=g24JGYuT74A.004.mp4',
'429713688?token=qDT95nz7hfm2Nki&filename=JZNMxa3OKHY.000.mp4',
'429713689?token=noLguEGXDpbcKhg&filename=nvlqJbHk_Lc.003.mp4',
'429713679?token=9L7RQ0hgdJlcek6&filename=4vdJGgZpj4k.003.mp4'
]
for curr_files in tets_name_files:
_b5.download_file_from_url(url = domain + curr_files, out = True)
# Getting scores
_b5.path_to_dataset_ = PATH_TO_DIR # Dataset directory
_b5.ext_ = ['.mp4'] # Search file extensions
# Full path to the file with ground truth scores for accuracy calculation
url_accuracy = _b5.true_traits_[corpus]['sberdisk']
_b5.get_avt_predictions(url_accuracy = url_accuracy, lang = 'en')
[2023-12-16 18:42:02] Feature extraction (hand-crafted and deep) from text …
[2023-12-16 18:42:05] Getting scores and accuracy calculation (multimodal fusion) …
10 from 10 (100.0%) … GitHub:nbsphinx-math:OCEANAI\docs\source\user_guide:nbsphinx-math:notebooks\video_FI:nbsphinx-math:test_plk5k7PBEg.003.mp4 …
| Path | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| Person ID | ||||||
| 1 | 2d6btbaNdfo.000.mp4 | 0.581159 | 0.628822 | 0.466609 | 0.622129 | 0.553832 |
| 2 | 300gK3CnzW0.001.mp4 | 0.463991 | 0.418851 | 0.41301 | 0.493329 | 0.423093 |
| 3 | 300gK3CnzW0.003.mp4 | 0.454281 | 0.415049 | 0.39189 | 0.485114 | 0.420741 |
| 4 | 4vdJGgZpj4k.003.mp4 | 0.588461 | 0.643233 | 0.530789 | 0.603038 | 0.593398 |
| 5 | be0DQawtVkE.002.mp4 | 0.633433 | 0.533295 | 0.523742 | 0.608591 | 0.588456 |
| 6 | cLaZxEf1nE4.004.mp4 | 0.636944 | 0.542386 | 0.558461 | 0.570975 | 0.558983 |
| 7 | g24JGYuT74A.004.mp4 | 0.531518 | 0.376987 | 0.393309 | 0.4904 | 0.447881 |
| 8 | JZNMxa3OKHY.000.mp4 | 0.610342 | 0.541418 | 0.563163 | 0.595013 | 0.569461 |
| 9 | nvlqJbHk_Lc.003.mp4 | 0.495809 | 0.458526 | 0.414436 | 0.469152 | 0.435461 |
| 10 | _plk5k7PBEg.003.mp4 | 0.60707 | 0.591893 | 0.520662 | 0.603938 | 0.565726 |
[2023-12-16 18:42:05] Trait-wise accuracy …
| Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | Mean | |
|---|---|---|---|---|---|---|
| Metrics | ||||||
| MAE | 0.0589 | 0.0612 | 0.0864 | 0.0697 | 0.0582 | 0.0669 |
| Accuracy | 0.9411 | 0.9388 | 0.9136 | 0.9303 | 0.9418 | 0.9331 |
[2023-12-16 18:42:05] Mean absolute errors: 0.0669, average accuracy: 0.9331 …
Log files saved successfully …
— Runtime: 64.481 sec. —
[2]:
True
Thus, the OCEAN-AI library provides tools to analyze the personality traits of candidates and their suitability for the position, which can significantly improve the recruitment process and help to make more objective and systematic decisions when ranking candidates.
The weight coefficients for 5 professions based on scientific articles are proposed:
Sajjad H. et al. Personality and Career Choices // African Journal of Business Management. - 2012. – Vol. 6 (6) – pp. 2255-2260.
Alkhelil A. H. The Relationship between Personality Traits and Career Choice: A Case Study of Secondary School Students // International Journal of Academic Research in Progressive Education and Development. – 2016. – Vol. 5(2). – pp. 2226-6348.
De Jong N. et al. Personality Traits and Career Role Enactment: Career Role Preferences as a Mediator // Frontiers in Psychology. – 2019. – Vol. 10. – pp. 1720.
The user can set their own weights; the sum of the weights must be equal to 100.
[3]:
# Loading a dataframe with weights
url = 'https://download.sberdisk.ru/download/file/478675798?token=fF5fNZVpthQlEV0&filename=traits_priority_for_professions.csv'
traits_priority_for_professions = pd.read_csv(url)
traits_priority_for_professions.index.name = 'ID'
traits_priority_for_professions.index += 1
traits_priority_for_professions.index = traits_priority_for_professions.index.map(str)
traits_priority_for_professions
[3]:
| Profession | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Managers/executives | 15 | 35 | 15 | 30 | 5 |
| 2 | Entrepreneurship | 30 | 30 | 5 | 5 | 30 |
| 3 | Social/Non profit making professions | 5 | 5 | 35 | 35 | 20 |
| 4 | Public sector professions | 15 | 50 | 15 | 15 | 5 |
| 5 | Scientists/researchers, and engineers | 50 | 15 | 5 | 15 | 15 |
Ranking of candidates for the position of engineer
[4]:
weights = traits_priority_for_professions.iloc[4].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'engineer_candidate_ranking_fi_en', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[4]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 5 | be0DQawtVkE.002.mp4 | 0.633 | 0.533 | 0.524 | 0.609 | 0.588 | 60.246 |
| 6 | cLaZxEf1nE4.004.mp4 | 0.637 | 0.542 | 0.558 | 0.571 | 0.559 | 59.725 |
| 4 | 4vdJGgZpj4k.003.mp4 | 0.588 | 0.643 | 0.531 | 0.603 | 0.593 | 59.672 |
| 10 | _plk5k7PBEg.003.mp4 | 0.607 | 0.592 | 0.521 | 0.604 | 0.566 | 59.380 |
| 8 | JZNMxa3OKHY.000.mp4 | 0.610 | 0.541 | 0.563 | 0.595 | 0.569 | 58.921 |
| 1 | 2d6btbaNdfo.000.mp4 | 0.581 | 0.629 | 0.467 | 0.622 | 0.554 | 58.463 |
| 7 | g24JGYuT74A.004.mp4 | 0.532 | 0.377 | 0.393 | 0.490 | 0.448 | 48.271 |
| 9 | nvlqJbHk_Lc.003.mp4 | 0.496 | 0.459 | 0.414 | 0.469 | 0.435 | 47.310 |
| 2 | 300gK3CnzW0.001.mp4 | 0.464 | 0.419 | 0.413 | 0.493 | 0.423 | 45.294 |
| 3 | 300gK3CnzW0.003.mp4 | 0.454 | 0.415 | 0.392 | 0.485 | 0.421 | 44.487 |
Ranking of candidates for the position of manager
[5]:
weights = traits_priority_for_professions.iloc[0].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'executive_candidate_ranking_fi_en', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[5]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 4 | 4vdJGgZpj4k.003.mp4 | 0.588 | 0.643 | 0.531 | 0.603 | 0.593 | 60.360 |
| 1 | 2d6btbaNdfo.000.mp4 | 0.581 | 0.629 | 0.467 | 0.622 | 0.554 | 59.158 |
| 10 | _plk5k7PBEg.003.mp4 | 0.607 | 0.592 | 0.521 | 0.604 | 0.566 | 58.579 |
| 8 | JZNMxa3OKHY.000.mp4 | 0.610 | 0.541 | 0.563 | 0.595 | 0.569 | 57.250 |
| 5 | be0DQawtVkE.002.mp4 | 0.633 | 0.533 | 0.524 | 0.609 | 0.588 | 57.223 |
| 6 | cLaZxEf1nE4.004.mp4 | 0.637 | 0.542 | 0.558 | 0.571 | 0.559 | 56.839 |
| 9 | nvlqJbHk_Lc.003.mp4 | 0.496 | 0.459 | 0.414 | 0.469 | 0.435 | 45.954 |
| 2 | 300gK3CnzW0.001.mp4 | 0.464 | 0.419 | 0.413 | 0.493 | 0.423 | 44.730 |
| 7 | g24JGYuT74A.004.mp4 | 0.532 | 0.377 | 0.393 | 0.490 | 0.448 | 44.018 |
| 3 | 300gK3CnzW0.003.mp4 | 0.454 | 0.415 | 0.392 | 0.485 | 0.421 | 43.876 |
To rank candidates by skills, two correlation coefficients must be set for each personality trait and skill, as well as a threshold for the polarity of the traits. These coefficients should show how a person’s trait score changes when it is above or below a given trait polarity threshold.
As an example, the use of correlation coefficients between five traits and four professional skills presented in the article is suggested:
Wehner C., de Grip A., Pfeifer H. Do recruiters select workers with different personality traits for different tasks? A discrete choice experiment // Labour Economics. - 2022. - vol. 78. - pp. 102186.
There are 4 professional skills presented:
Analytical. The ability to effectively solve new problems that require in-depth analysis.
Interactive. The ability to persuade and compromise with clients and colleagues.
Routine. The ability to perform routine tasks effectively with accuracy and attention to detail.
Non-Routine. The ability to respond to and solve problems that have no set order, demonstrating adaptability and creative problem solving skills.
The users can set their own correlation coefficients and rank candidates by other professional skills.
Ranking candidates by professional skills
[6]:
# Loading a dataframe with correlation coefficients
url = 'https://download.sberdisk.ru/download/file/478678231?token=0qiZwliLtHWWYMv&filename=professional_skills.csv'
df_professional_skills = pd.read_csv(url)
df_professional_skills.index.name = 'ID'
df_professional_skills.index += 1
df_professional_skills.index = df_professional_skills.index.map(str)
df_professional_skills
[6]:
| Trait | Score_level | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Openness | high | 0.082 | 0.348 | 0.571 | 0.510 |
| 2 | Openness | low | 0.196 | 0.152 | 0.148 | 0.218 |
| 3 | Conscientiousness | high | 0.994 | 1.333 | 1.507 | 1.258 |
| 4 | Conscientiousness | low | 0.241 | 0.188 | 0.191 | 0.267 |
| 5 | Extraversion | high | 0.169 | -0.060 | 0.258 | 0.017 |
| 6 | Extraversion | low | 0.181 | 0.135 | 0.130 | 0.194 |
| 7 | Agreeableness | high | 1.239 | 0.964 | 1.400 | 1.191 |
| 8 | Agreeableness | low | 0.226 | 0.180 | 0.189 | 0.259 |
| 9 | Non-Neuroticism | high | 0.636 | 0.777 | 0.876 | 0.729 |
| 10 | Non-Neuroticism | low | 0.207 | 0.159 | 0.166 | 0.238 |
[7]:
_b5._priority_skill_calculation(
correlation_coefficients = df_professional_skills,
threshold = 0.5,
out = True
)
_b5._save_logs(df = _b5.df_files_priority_skill_, name = 'skill_candidate_ranking_fi_en', out = True)
# Optional
df = _b5.df_files_priority_skill_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[7]:
| Path | OPE | CON | EXT | AGR | NNEU | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|---|---|---|---|
| Person ID | ||||||||||
| 4 | 4vdJGgZpj4k.003.mp4 | 0.588 | 0.643 | 0.531 | 0.603 | 0.593 | 0.380 | 0.415 | 0.561 | 0.454 |
| 1 | 2d6btbaNdfo.000.mp4 | 0.581 | 0.629 | 0.467 | 0.622 | 0.554 | 0.376 | 0.427 | 0.539 | 0.465 |
| 10 | _plk5k7PBEg.003.mp4 | 0.607 | 0.592 | 0.521 | 0.604 | 0.566 | 0.367 | 0.398 | 0.543 | 0.439 |
| 5 | be0DQawtVkE.002.mp4 | 0.633 | 0.533 | 0.524 | 0.609 | 0.588 | 0.360 | 0.389 | 0.534 | 0.431 |
| 8 | JZNMxa3OKHY.000.mp4 | 0.610 | 0.541 | 0.563 | 0.595 | 0.569 | 0.357 | 0.383 | 0.528 | 0.425 |
| 6 | cLaZxEf1nE4.004.mp4 | 0.637 | 0.542 | 0.558 | 0.571 | 0.559 | 0.350 | 0.379 | 0.523 | 0.421 |
| 9 | nvlqJbHk_Lc.003.mp4 | 0.496 | 0.459 | 0.414 | 0.469 | 0.435 | 0.096 | 0.074 | 0.075 | 0.107 |
| 2 | 300gK3CnzW0.001.mp4 | 0.464 | 0.419 | 0.413 | 0.493 | 0.423 | 0.093 | 0.072 | 0.073 | 0.104 |
| 3 | 300gK3CnzW0.003.mp4 | 0.454 | 0.415 | 0.392 | 0.485 | 0.421 | 0.091 | 0.071 | 0.072 | 0.102 |
| 7 | g24JGYuT74A.004.mp4 | 0.532 | 0.377 | 0.393 | 0.490 | 0.448 | 0.082 | 0.094 | 0.119 | 0.136 |
MuPTA (ru)
[9]:
import os
import pandas as pd
# Module import
from oceanai.modules.lab.build import Run
# Creating an instance of a class
_b5 = Run(lang = 'en')
corpus = 'mupta'
lang = 'ru'
# Core setup
_b5.path_to_save_ = './models' # Directory to save the models
_b5.chunk_size_ = 2000000 # File download size from network in one step
# Building audio models
res_load_model_hc = _b5.load_audio_model_hc()
res_load_model_nn = _b5.load_audio_model_nn()
# Loading audio model weights
url = _b5.weights_for_big5_['audio'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_audio_model_weights_hc(url = url)
url = _b5.weights_for_big5_['audio'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_audio_model_weights_nn(url = url)
# Building video models
res_load_model_hc = _b5.load_video_model_hc(lang=lang)
res_load_model_deep_fe = _b5.load_video_model_deep_fe()
res_load_model_nn = _b5.load_video_model_nn()
# Loading video model weights
url = _b5.weights_for_big5_['video'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_video_model_weights_hc(url = url)
url = _b5.weights_for_big5_['video'][corpus]['fe']['sberdisk']
res_load_model_weights_deep_fe = _b5.load_video_model_weights_deep_fe(url = url)
url = _b5.weights_for_big5_['video'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_video_model_weights_nn(url = url)
# Loading a dictionary with hand-crafted features (text modality)
res_load_text_features = _b5.load_text_features()
# Building text models
res_setup_translation_model = _b5.setup_translation_model()
res_setup_translation_model = _b5.setup_bert_encoder()
res_load_text_model_hc_fi = _b5.load_text_model_hc(corpus=corpus)
res_load_text_model_nn_fi = _b5.load_text_model_nn(corpus=corpus)
# Loading text model weights
url = _b5.weights_for_big5_['text'][corpus]['hc']['sberdisk']
res_load_text_model_weights_hc_fi = _b5.load_text_model_weights_hc(url = url)
url = _b5.weights_for_big5_['text'][corpus]['nn']['sberdisk']
res_load_text_model_weights_nn_fi = _b5.load_text_model_weights_nn(url = url)
# Building model for multimodal information fusion
res_load_avt_model_b5 = _b5.load_avt_model_b5()
# Loading model weights for multimodal information fusion
url = _b5.weights_for_big5_['avt'][corpus]['b5']['sberdisk']
res_load_avt_model_weights_b5 = _b5.load_avt_model_weights_b5(url = url)
PATH_TO_DIR = './video_MuPTA/'
PATH_SAVE_VIDEO = './video_MuPTA/test/'
_b5.path_to_save_ = PATH_SAVE_VIDEO
# Loading 10 test files from the MuPTA corpus
# URL: https://hci.nw.ru/en/pages/mupta-corpus
domain = 'https://download.sberdisk.ru/download/file/'
tets_name_files = [
'477995979?token=2cvyk7CS0mHx2MJ&filename=speaker_06_center_83.mov',
'477995980?token=jGPtBPS69uzFU6Y&filename=speaker_01_center_83.mov',
'477995967?token=zCaRbNB6ht5wMPq&filename=speaker_11_center_83.mov',
'477995966?token=B1rbinDYRQKrI3T&filename=speaker_15_center_83.mov',
'477995978?token=dEpVDtZg1EQiEQ9&filename=speaker_07_center_83.mov',
'477995961?token=o1hVjw8G45q9L9Z&filename=speaker_19_center_83.mov',
'477995964?token=5K220Aqf673VHPq&filename=speaker_23_center_83.mov',
'477995965?token=v1LVD2KT1cU7Lpb&filename=speaker_24_center_83.mov',
'477995962?token=tmaSGyyWLA6XCy9&filename=speaker_27_center_83.mov',
'477995963?token=bTpo96qNDPcwGqb&filename=speaker_10_center_83.mov',
]
for curr_files in tets_name_files:
_b5.download_file_from_url(url = domain + curr_files, out = True)
# Getting scores
_b5.path_to_dataset_ = PATH_TO_DIR # Dataset directory
_b5.ext_ = ['.mov'] # Search file extensions
# Full path to the file with ground truth scores for accuracy calculation
url_accuracy = _b5.true_traits_['mupta']['sberdisk']
_b5.get_avt_predictions(url_accuracy = url_accuracy, lang = lang)
[2023-12-16 18:51:57] Feature extraction (hand-crafted and deep) from text …
[2023-12-16 18:52:01] Getting scores and accuracy calculation (multimodal fusion) …
10 from 10 (100.0%) … GitHub:nbsphinx-math:OCEANAI\docs\source\user_guide:nbsphinx-math:notebooks\video_MuPTA:nbsphinx-math:test\speaker_27_center_83.mov …
| Path | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| Person ID | ||||||
| 1 | speaker_01_center_83.mov | 0.758137 | 0.693356 | 0.650108 | 0.744589 | 0.488671 |
| 2 | speaker_06_center_83.mov | 0.681602 | 0.654339 | 0.607156 | 0.731282 | 0.417908 |
| 3 | speaker_07_center_83.mov | 0.666104 | 0.656836 | 0.567863 | 0.685067 | 0.378102 |
| 4 | speaker_10_center_83.mov | 0.694171 | 0.596195 | 0.571414 | 0.66223 | 0.348639 |
| 5 | speaker_11_center_83.mov | 0.712885 | 0.594764 | 0.571709 | 0.716696 | 0.37802 |
| 6 | speaker_15_center_83.mov | 0.664158 | 0.670411 | 0.60421 | 0.696056 | 0.399842 |
| 7 | speaker_19_center_83.mov | 0.761213 | 0.652635 | 0.651028 | 0.788677 | 0.459676 |
| 8 | speaker_23_center_83.mov | 0.692788 | 0.68324 | 0.616737 | 0.795205 | 0.447242 |
| 9 | speaker_24_center_83.mov | 0.705923 | 0.658382 | 0.610645 | 0.697415 | 0.411988 |
| 10 | speaker_27_center_83.mov | 0.753417 | 0.708372 | 0.654608 | 0.816416 | 0.504743 |
[2023-12-16 18:52:01] Trait-wise accuracy …
| Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | Mean | |
|---|---|---|---|---|---|---|
| Metrics | ||||||
| MAE | 0.0673 | 0.0789 | 0.1325 | 0.102 | 0.1002 | 0.0962 |
| Accuracy | 0.9327 | 0.9211 | 0.8675 | 0.898 | 0.8998 | 0.9038 |
[2023-12-16 18:52:01] Mean absolute errors: 0.0962, average accuracy: 0.9038 …
Log files saved successfully …
— Runtime: 415.41 sec. —
[9]:
True
Thus, the OCEAN-AI library provides tools to analyze the personality traits of candidates and their suitability for the position, which can significantly improve the recruitment process and help to make more objective and systematic decisions when ranking candidates.
The weight coefficients for 5 professions based on scientific articles are proposed:
Sajjad H. et al. Personality and Career Choices // African Journal of Business Management. - 2012. – Vol. 6 (6) – pp. 2255-2260.
Alkhelil A. H. The Relationship between Personality Traits and Career Choice: A Case Study of Secondary School Students // International Journal of Academic Research in Progressive Education and Development. – 2016. – Vol. 5(2). – pp. 2226-6348.
De Jong N. et al. Personality Traits and Career Role Enactment: Career Role Preferences as a Mediator // Frontiers in Psychology. – 2019. – Vol. 10. – pp. 1720.
The user can set their own weights; the sum of the weights must be equal to 100.
[10]:
# Loading a dataframe with weights
url = 'https://download.sberdisk.ru/download/file/478675798?token=fF5fNZVpthQlEV0&filename=traits_priority_for_professions.csv'
traits_priority_for_professions = pd.read_csv(url)
traits_priority_for_professions.index.name = 'ID'
traits_priority_for_professions.index += 1
traits_priority_for_professions.index = traits_priority_for_professions.index.map(str)
traits_priority_for_professions
[10]:
| Profession | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Managers/executives | 15 | 35 | 15 | 30 | 5 |
| 2 | Entrepreneurship | 30 | 30 | 5 | 5 | 30 |
| 3 | Social/Non profit making professions | 5 | 5 | 35 | 35 | 20 |
| 4 | Public sector professions | 15 | 50 | 15 | 15 | 5 |
| 5 | Scientists/researchers, and engineers | 50 | 15 | 5 | 15 | 15 |
Ranking of candidates for the position of engineer
[11]:
weights = traits_priority_for_professions.iloc[4].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'engineer_candidate_ranking_mupta_ru', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[11]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 10 | speaker_27_center_83.mov | 0.753 | 0.708 | 0.655 | 0.816 | 0.505 | 71.387 |
| 1 | speaker_01_center_83.mov | 0.758 | 0.693 | 0.650 | 0.745 | 0.489 | 70.057 |
| 7 | speaker_19_center_83.mov | 0.761 | 0.653 | 0.651 | 0.789 | 0.460 | 69.831 |
| 8 | speaker_23_center_83.mov | 0.693 | 0.683 | 0.617 | 0.795 | 0.447 | 66.608 |
| 9 | speaker_24_center_83.mov | 0.706 | 0.658 | 0.611 | 0.697 | 0.412 | 64.866 |
| 2 | speaker_06_center_83.mov | 0.682 | 0.654 | 0.607 | 0.731 | 0.418 | 64.169 |
| 5 | speaker_11_center_83.mov | 0.713 | 0.595 | 0.572 | 0.717 | 0.378 | 63.845 |
| 6 | speaker_15_center_83.mov | 0.664 | 0.670 | 0.604 | 0.696 | 0.400 | 62.724 |
| 3 | speaker_07_center_83.mov | 0.666 | 0.657 | 0.568 | 0.685 | 0.378 | 61.945 |
| 4 | speaker_10_center_83.mov | 0.694 | 0.596 | 0.571 | 0.662 | 0.349 | 61.672 |
Ranking of candidates for the position of manager
[12]:
weights = traits_priority_for_professions.iloc[0].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'executive_candidate_ranking_mupta_ru', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[12]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 10 | speaker_27_center_83.mov | 0.753 | 0.708 | 0.655 | 0.816 | 0.505 | 72.930 |
| 1 | speaker_01_center_83.mov | 0.758 | 0.693 | 0.650 | 0.745 | 0.489 | 70.172 |
| 7 | speaker_19_center_83.mov | 0.761 | 0.653 | 0.651 | 0.789 | 0.460 | 69.985 |
| 8 | speaker_23_center_83.mov | 0.693 | 0.683 | 0.617 | 0.795 | 0.447 | 69.649 |
| 2 | speaker_06_center_83.mov | 0.682 | 0.654 | 0.607 | 0.731 | 0.418 | 66.261 |
| 9 | speaker_24_center_83.mov | 0.706 | 0.658 | 0.611 | 0.697 | 0.412 | 65.774 |
| 6 | speaker_15_center_83.mov | 0.664 | 0.670 | 0.604 | 0.696 | 0.400 | 65.371 |
| 3 | speaker_07_center_83.mov | 0.666 | 0.657 | 0.568 | 0.685 | 0.378 | 63.941 |
| 5 | speaker_11_center_83.mov | 0.713 | 0.595 | 0.572 | 0.717 | 0.378 | 63.477 |
| 4 | speaker_10_center_83.mov | 0.694 | 0.596 | 0.571 | 0.662 | 0.349 | 61.461 |
To rank candidates by skills, two correlation coefficients must be set for each personality trait and skill, as well as a threshold for the polarity of the traits. These coefficients should show how a person’s trait score changes when it is above or below a given trait polarity threshold.
As an example, the use of correlation coefficients between five traits and four professional skills presented in the article is suggested:
Wehner C., de Grip A., Pfeifer H. Do recruiters select workers with different personality traits for different tasks? A discrete choice experiment // Labour Economics. - 2022. - vol. 78. - pp. 102186.
There are 4 professional skills presented:
Analytical. The ability to effectively solve new problems that require in-depth analysis.
Interactive. The ability to persuade and compromise with clients and colleagues.
Routine. The ability to perform routine tasks effectively with accuracy and attention to detail.
Non-Routine. The ability to respond to and solve problems that have no set order, demonstrating adaptability and creative problem solving skills.
The users can set their own correlation coefficients and rank candidates by other professional skills.
Ranking candidates by professional skills
[13]:
# Loading a dataframe with correlation coefficients
url = 'https://download.sberdisk.ru/download/file/478678231?token=0qiZwliLtHWWYMv&filename=professional_skills.csv'
df_professional_skills = pd.read_csv(url)
df_professional_skills.index.name = 'ID'
df_professional_skills.index += 1
df_professional_skills.index = df_professional_skills.index.map(str)
df_professional_skills
[13]:
| Trait | Score_level | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Openness | high | 0.082 | 0.348 | 0.571 | 0.510 |
| 2 | Openness | low | 0.196 | 0.152 | 0.148 | 0.218 |
| 3 | Conscientiousness | high | 0.994 | 1.333 | 1.507 | 1.258 |
| 4 | Conscientiousness | low | 0.241 | 0.188 | 0.191 | 0.267 |
| 5 | Extraversion | high | 0.169 | -0.060 | 0.258 | 0.017 |
| 6 | Extraversion | low | 0.181 | 0.135 | 0.130 | 0.194 |
| 7 | Agreeableness | high | 1.239 | 0.964 | 1.400 | 1.191 |
| 8 | Agreeableness | low | 0.226 | 0.180 | 0.189 | 0.259 |
| 9 | Non-Neuroticism | high | 0.636 | 0.777 | 0.876 | 0.729 |
| 10 | Non-Neuroticism | low | 0.207 | 0.159 | 0.166 | 0.238 |
[14]:
_b5._priority_skill_calculation(
correlation_coefficients = df_professional_skills,
threshold = 0.5,
out = True
)
_b5._save_logs(df = _b5.df_files_priority_skill_, name = 'skill_candidate_ranking_mupta_ru', out = True)
# Optional
df = _b5.df_files_priority_skill_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[14]:
| Path | OPE | CON | EXT | AGR | NNEU | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|---|---|---|---|
| Person ID | ||||||||||
| 10 | speaker_27_center_83.mov | 0.753 | 0.708 | 0.655 | 0.816 | 0.505 | 0.442 | 0.469 | 0.650 | 0.525 |
| 8 | speaker_23_center_83.mov | 0.693 | 0.683 | 0.617 | 0.795 | 0.447 | 0.384 | 0.391 | 0.554 | 0.455 |
| 7 | speaker_19_center_83.mov | 0.761 | 0.653 | 0.651 | 0.789 | 0.460 | 0.379 | 0.386 | 0.553 | 0.454 |
| 1 | speaker_01_center_83.mov | 0.758 | 0.693 | 0.650 | 0.745 | 0.489 | 0.377 | 0.389 | 0.554 | 0.455 |
| 2 | speaker_06_center_83.mov | 0.682 | 0.654 | 0.607 | 0.731 | 0.418 | 0.360 | 0.369 | 0.525 | 0.430 |
| 6 | speaker_15_center_83.mov | 0.664 | 0.670 | 0.604 | 0.696 | 0.400 | 0.354 | 0.365 | 0.517 | 0.423 |
| 9 | speaker_24_center_83.mov | 0.706 | 0.658 | 0.611 | 0.697 | 0.412 | 0.353 | 0.365 | 0.520 | 0.425 |
| 3 | speaker_07_center_83.mov | 0.666 | 0.657 | 0.568 | 0.685 | 0.378 | 0.346 | 0.359 | 0.508 | 0.416 |
| 5 | speaker_11_center_83.mov | 0.713 | 0.595 | 0.572 | 0.717 | 0.378 | 0.343 | 0.352 | 0.503 | 0.413 |
| 4 | speaker_10_center_83.mov | 0.694 | 0.596 | 0.571 | 0.662 | 0.349 | 0.328 | 0.339 | 0.485 | 0.397 |
MuPTA (en)
[15]:
import os
import pandas as pd
# Module import
from oceanai.modules.lab.build import Run
# Creating an instance of a class
_b5 = Run(lang = 'en')
corpus = 'fi'
lang = 'en'
# Core setup
_b5.path_to_save_ = './models' # Directory to save the models
_b5.chunk_size_ = 2000000 # File download size from network in one step
# Building audio models
res_load_model_hc = _b5.load_audio_model_hc()
res_load_model_nn = _b5.load_audio_model_nn()
# Loading audio model weights
url = _b5.weights_for_big5_['audio'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_audio_model_weights_hc(url = url)
url = _b5.weights_for_big5_['audio'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_audio_model_weights_nn(url = url)
# Building video models
res_load_model_hc = _b5.load_video_model_hc(lang=lang)
res_load_model_deep_fe = _b5.load_video_model_deep_fe()
res_load_model_nn = _b5.load_video_model_nn()
# Loading video model weights
url = _b5.weights_for_big5_['video'][corpus]['hc']['sberdisk']
res_load_model_weights_hc = _b5.load_video_model_weights_hc(url = url)
url = _b5.weights_for_big5_['video'][corpus]['fe']['sberdisk']
res_load_model_weights_deep_fe = _b5.load_video_model_weights_deep_fe(url = url)
url = _b5.weights_for_big5_['video'][corpus]['nn']['sberdisk']
res_load_model_weights_nn = _b5.load_video_model_weights_nn(url = url)
# Loading a dictionary with hand-crafted features (text modality)
res_load_text_features = _b5.load_text_features()
# Building text models
res_setup_translation_model = _b5.setup_translation_model()
res_setup_translation_model = _b5.setup_bert_encoder()
res_load_text_model_hc_fi = _b5.load_text_model_hc(corpus=corpus)
res_load_text_model_nn_fi = _b5.load_text_model_nn(corpus=corpus)
# Loading text model weights
url = _b5.weights_for_big5_['text'][corpus]['hc']['sberdisk']
res_load_text_model_weights_hc_fi = _b5.load_text_model_weights_hc(url = url)
url = _b5.weights_for_big5_['text'][corpus]['nn']['sberdisk']
res_load_text_model_weights_nn_fi = _b5.load_text_model_weights_nn(url = url)
# Building model for multimodal information fusion
res_load_avt_model_b5 = _b5.load_avt_model_b5()
# Building model for multimodal information fusion
url = _b5.weights_for_big5_['avt'][corpus]['b5']['sberdisk']
res_load_avt_model_weights_b5 = _b5.load_avt_model_weights_b5(url = url)
PATH_TO_DIR = './video_MuPTA/'
PATH_SAVE_VIDEO = './video_MuPTA/test/'
_b5.path_to_save_ = PATH_SAVE_VIDEO
# Loading 10 test files from the MuPTA corpus
# URL: https://hci.nw.ru/en/pages/mupta-corpus
domain = 'https://download.sberdisk.ru/download/file/'
tets_name_files = [
'477995979?token=2cvyk7CS0mHx2MJ&filename=speaker_06_center_83.mov',
'477995980?token=jGPtBPS69uzFU6Y&filename=speaker_01_center_83.mov',
'477995967?token=zCaRbNB6ht5wMPq&filename=speaker_11_center_83.mov',
'477995966?token=B1rbinDYRQKrI3T&filename=speaker_15_center_83.mov',
'477995978?token=dEpVDtZg1EQiEQ9&filename=speaker_07_center_83.mov',
'477995961?token=o1hVjw8G45q9L9Z&filename=speaker_19_center_83.mov',
'477995964?token=5K220Aqf673VHPq&filename=speaker_23_center_83.mov',
'477995965?token=v1LVD2KT1cU7Lpb&filename=speaker_24_center_83.mov',
'477995962?token=tmaSGyyWLA6XCy9&filename=speaker_27_center_83.mov',
'477995963?token=bTpo96qNDPcwGqb&filename=speaker_10_center_83.mov',
]
for curr_files in tets_name_files:
_b5.download_file_from_url(url = domain + curr_files, out = True)
# Getting scores
_b5.path_to_dataset_ = PATH_TO_DIR # Dataset directory
_b5.ext_ = ['.mov'] # Search file extensions
# Full path to the file with ground truth scores for accuracy calculation
url_accuracy = _b5.true_traits_['mupta']['sberdisk']
_b5.get_avt_predictions(url_accuracy = url_accuracy, lang = lang)
[2023-12-16 19:00:49] Feature extraction (hand-crafted and deep) from text …
[2023-12-16 19:00:52] Getting scores and accuracy calculation (multimodal fusion) …
10 from 10 (100.0%) … GitHub:nbsphinx-math:OCEANAI\docs\source\user_guide:nbsphinx-math:notebooks\video_MuPTA:nbsphinx-math:test\speaker_27_center_83.mov …
| Path | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| Person ID | ||||||
| 1 | speaker_01_center_83.mov | 0.564985 | 0.539052 | 0.440615 | 0.59251 | 0.488763 |
| 2 | speaker_06_center_83.mov | 0.650774 | 0.663849 | 0.607308 | 0.643847 | 0.620627 |
| 3 | speaker_07_center_83.mov | 0.435976 | 0.486683 | 0.313828 | 0.415446 | 0.396618 |
| 4 | speaker_10_center_83.mov | 0.498542 | 0.511243 | 0.412592 | 0.468947 | 0.44399 |
| 5 | speaker_11_center_83.mov | 0.394776 | 0.341608 | 0.327082 | 0.427304 | 0.354936 |
| 6 | speaker_15_center_83.mov | 0.566107 | 0.543811 | 0.492766 | 0.587411 | 0.499433 |
| 7 | speaker_19_center_83.mov | 0.506271 | 0.438215 | 0.430894 | 0.456177 | 0.44075 |
| 8 | speaker_23_center_83.mov | 0.486463 | 0.521755 | 0.309894 | 0.432291 | 0.433601 |
| 9 | speaker_24_center_83.mov | 0.417404 | 0.473339 | 0.320714 | 0.445086 | 0.414649 |
| 10 | speaker_27_center_83.mov | 0.526112 | 0.661107 | 0.443167 | 0.558965 | 0.554224 |
[2023-12-16 19:00:52] Trait-wise accuracy …
| Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | Mean | |
|---|---|---|---|---|---|---|
| Metrics | ||||||
| MAE | 0.1727 | 0.1672 | 0.1661 | 0.2579 | 0.107 | 0.1742 |
| Accuracy | 0.8273 | 0.8328 | 0.8339 | 0.7421 | 0.893 | 0.8258 |
[2023-12-16 19:00:52] Mean absolute errors: 0.1742, average accuracy: 0.8258 …
Log files saved successfully …
— Runtime: 372.823 sec. —
[15]:
True
Thus, the OCEAN-AI library provides tools to analyze the personality traits of candidates and their suitability for the position, which can significantly improve the recruitment process and help to make more objective and systematic decisions when ranking candidates.
The weight coefficients for 5 professions based on scientific articles are proposed:
Sajjad H. et al. Personality and Career Choices // African Journal of Business Management. - 2012. – Vol. 6 (6) – pp. 2255-2260.
Alkhelil A. H. The Relationship between Personality Traits and Career Choice: A Case Study of Secondary School Students // International Journal of Academic Research in Progressive Education and Development. – 2016. – Vol. 5(2). – pp. 2226-6348.
De Jong N. et al. Personality Traits and Career Role Enactment: Career Role Preferences as a Mediator // Frontiers in Psychology. – 2019. – Vol. 10. – pp. 1720.
The user can set their own weights; the sum of the weights must be equal to 100.
[16]:
# Loading a dataframe with weights
url = 'https://download.sberdisk.ru/download/file/478675798?token=fF5fNZVpthQlEV0&filename=traits_priority_for_professions.csv'
traits_priority_for_professions = pd.read_csv(url)
traits_priority_for_professions.index.name = 'ID'
traits_priority_for_professions.index += 1
traits_priority_for_professions.index = traits_priority_for_professions.index.map(str)
traits_priority_for_professions
[16]:
| Profession | Openness | Conscientiousness | Extraversion | Agreeableness | Non-Neuroticism | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Managers/executives | 15 | 35 | 15 | 30 | 5 |
| 2 | Entrepreneurship | 30 | 30 | 5 | 5 | 30 |
| 3 | Social/Non profit making professions | 5 | 5 | 35 | 35 | 20 |
| 4 | Public sector professions | 15 | 50 | 15 | 15 | 5 |
| 5 | Scientists/researchers, and engineers | 50 | 15 | 5 | 15 | 15 |
Ranking of candidates for the position of engineer
[17]:
weights = traits_priority_for_professions.iloc[4].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'engineer_candidate_ranking_mupta_en', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[17]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 2 | speaker_06_center_83.mov | 0.651 | 0.664 | 0.607 | 0.644 | 0.621 | 64.500 |
| 6 | speaker_15_center_83.mov | 0.566 | 0.544 | 0.493 | 0.587 | 0.499 | 55.229 |
| 10 | speaker_27_center_83.mov | 0.526 | 0.661 | 0.443 | 0.559 | 0.554 | 55.136 |
| 1 | speaker_01_center_83.mov | 0.565 | 0.539 | 0.441 | 0.593 | 0.489 | 54.757 |
| 4 | speaker_10_center_83.mov | 0.499 | 0.511 | 0.413 | 0.469 | 0.444 | 48.353 |
| 7 | speaker_19_center_83.mov | 0.506 | 0.438 | 0.431 | 0.456 | 0.441 | 47.495 |
| 8 | speaker_23_center_83.mov | 0.486 | 0.522 | 0.310 | 0.432 | 0.434 | 46.687 |
| 3 | speaker_07_center_83.mov | 0.436 | 0.487 | 0.314 | 0.415 | 0.397 | 42.849 |
| 9 | speaker_24_center_83.mov | 0.417 | 0.473 | 0.321 | 0.445 | 0.415 | 42.470 |
| 5 | speaker_11_center_83.mov | 0.395 | 0.342 | 0.327 | 0.427 | 0.355 | 38.232 |
Ranking of candidates for the position of manager
[18]:
weights = traits_priority_for_professions.iloc[0].values[1:]
weights = list(map(int, weights))
_b5._candidate_ranking(
weigths_openness = weights[0],
weigths_conscientiousness = weights[1],
weigths_extraversion = weights[2],
weigths_agreeableness = weights[3],
weigths_non_neuroticism = weights[4],
out = False
)
_b5._save_logs(df = _b5.df_files_ranking_, name = 'executive_candidate_ranking_mupta_en', out = True)
# Optional
df = _b5.df_files_ranking_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[18]:
| Path | OPE | CON | EXT | AGR | NNEU | Candidate score | |
|---|---|---|---|---|---|---|---|
| Person ID | |||||||
| 2 | speaker_06_center_83.mov | 0.651 | 0.664 | 0.607 | 0.644 | 0.621 | 64.524 |
| 10 | speaker_27_center_83.mov | 0.526 | 0.661 | 0.443 | 0.559 | 0.554 | 57.218 |
| 6 | speaker_15_center_83.mov | 0.566 | 0.544 | 0.493 | 0.587 | 0.499 | 55.036 |
| 1 | speaker_01_center_83.mov | 0.565 | 0.539 | 0.441 | 0.593 | 0.489 | 54.170 |
| 4 | speaker_10_center_83.mov | 0.499 | 0.511 | 0.413 | 0.469 | 0.444 | 47.849 |
| 8 | speaker_23_center_83.mov | 0.486 | 0.522 | 0.310 | 0.432 | 0.434 | 45.344 |
| 7 | speaker_19_center_83.mov | 0.506 | 0.438 | 0.431 | 0.456 | 0.441 | 45.284 |
| 9 | speaker_24_center_83.mov | 0.417 | 0.473 | 0.321 | 0.445 | 0.415 | 43.064 |
| 3 | speaker_07_center_83.mov | 0.436 | 0.487 | 0.314 | 0.415 | 0.397 | 42.727 |
| 5 | speaker_11_center_83.mov | 0.395 | 0.342 | 0.327 | 0.427 | 0.355 | 37.378 |
To rank candidates by skills, two correlation coefficients must be set for each personality trait and skill, as well as a threshold for the polarity of the traits. These coefficients should show how a person’s trait score changes when it is above or below a given trait polarity threshold.
As an example, the use of correlation coefficients between five traits and four professional skills presented in the article is suggested:
Wehner C., de Grip A., Pfeifer H. Do recruiters select workers with different personality traits for different tasks? A discrete choice experiment // Labour Economics. - 2022. - vol. 78. - pp. 102186.
There are 4 professional skills presented:
Analytical. The ability to effectively solve new problems that require in-depth analysis.
Interactive. The ability to persuade and compromise with clients and colleagues.
Routine. The ability to perform routine tasks effectively with accuracy and attention to detail.
Non-Routine. The ability to respond to and solve problems that have no set order, demonstrating adaptability and creative problem solving skills.
The users can set their own correlation coefficients and rank candidates by other professional skills.
Ranking candidates by professional skills
[19]:
# Loading a dataframe with correlation coefficients
url = 'https://download.sberdisk.ru/download/file/478678231?token=0qiZwliLtHWWYMv&filename=professional_skills.csv'
df_professional_skills = pd.read_csv(url)
df_professional_skills.index.name = 'ID'
df_professional_skills.index += 1
df_professional_skills.index = df_professional_skills.index.map(str)
df_professional_skills
[19]:
| Trait | Score_level | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|
| ID | ||||||
| 1 | Openness | high | 0.082 | 0.348 | 0.571 | 0.510 |
| 2 | Openness | low | 0.196 | 0.152 | 0.148 | 0.218 |
| 3 | Conscientiousness | high | 0.994 | 1.333 | 1.507 | 1.258 |
| 4 | Conscientiousness | low | 0.241 | 0.188 | 0.191 | 0.267 |
| 5 | Extraversion | high | 0.169 | -0.060 | 0.258 | 0.017 |
| 6 | Extraversion | low | 0.181 | 0.135 | 0.130 | 0.194 |
| 7 | Agreeableness | high | 1.239 | 0.964 | 1.400 | 1.191 |
| 8 | Agreeableness | low | 0.226 | 0.180 | 0.189 | 0.259 |
| 9 | Non-Neuroticism | high | 0.636 | 0.777 | 0.876 | 0.729 |
| 10 | Non-Neuroticism | low | 0.207 | 0.159 | 0.166 | 0.238 |
[20]:
_b5._priority_skill_calculation(
correlation_coefficients = df_professional_skills,
threshold = 0.5,
out = True
)
_b5._save_logs(df = _b5.df_files_priority_skill_, name = 'skill_candidate_ranking_mupta_en', out = True)
# Optional
df = _b5.df_files_priority_skill_.rename(columns = {'Openness':'OPE', 'Conscientiousness':'CON', 'Extraversion': 'EXT', 'Agreeableness': 'AGR', 'Non-Neuroticism': 'NNEU'})
columns_to_round = df.columns[1:]
df[columns_to_round] = df[columns_to_round].apply(lambda x: [round(i, 3) for i in x])
df
[20]:
| Path | OPE | CON | EXT | AGR | NNEU | Analytical | Interactive | Routine | Non-Routine | |
|---|---|---|---|---|---|---|---|---|---|---|
| Person ID | ||||||||||
| 2 | speaker_06_center_83.mov | 0.651 | 0.664 | 0.607 | 0.644 | 0.621 | 0.402 | 0.436 | 0.595 | 0.479 |
| 10 | speaker_27_center_83.mov | 0.526 | 0.661 | 0.443 | 0.559 | 0.554 | 0.365 | 0.419 | 0.524 | 0.451 |
| 6 | speaker_15_center_83.mov | 0.566 | 0.544 | 0.493 | 0.587 | 0.499 | 0.301 | 0.327 | 0.422 | 0.377 |
| 1 | speaker_01_center_83.mov | 0.565 | 0.539 | 0.441 | 0.593 | 0.489 | 0.299 | 0.325 | 0.421 | 0.375 |
| 4 | speaker_10_center_83.mov | 0.499 | 0.511 | 0.413 | 0.469 | 0.444 | 0.176 | 0.194 | 0.212 | 0.212 |
| 8 | speaker_23_center_83.mov | 0.486 | 0.522 | 0.310 | 0.432 | 0.434 | 0.172 | 0.192 | 0.210 | 0.208 |
| 9 | speaker_24_center_83.mov | 0.417 | 0.473 | 0.321 | 0.445 | 0.415 | 0.088 | 0.068 | 0.069 | 0.099 |
| 3 | speaker_07_center_83.mov | 0.436 | 0.487 | 0.314 | 0.415 | 0.397 | 0.087 | 0.068 | 0.069 | 0.098 |
| 7 | speaker_19_center_83.mov | 0.506 | 0.438 | 0.431 | 0.456 | 0.441 | 0.084 | 0.094 | 0.118 | 0.136 |
| 5 | speaker_11_center_83.mov | 0.395 | 0.342 | 0.327 | 0.427 | 0.355 | 0.078 | 0.060 | 0.061 | 0.087 |