job_title_analysis.py

import re
import nltk
from nltk.corpus import stopwords
import pandas as pd
stop_words = set(stopwords.words("english"))


def get_first_title(title):
    # keep "co-founder, co-ceo, etc"
    title = re.sub(r"[Cc]o[\-\ ]","", title)
    split_titles = re.split(r"\,|\-|\||\&|\:|\/|and", title)
    return split_titles[0].strip()


def get_title_features(title):
    features = {}
    word_tokens = nltk.word_tokenize(title)
    filtered_words = [w for w in word_tokens if not w in stop_words] 
    for word in filtered_words:
        features['contains({})'.format(word.lower())] = True
    if len(filtered_words) > 0:
        first_key = 'first({})'.format(filtered_words[0].lower())
        last_key = 'last({})'.format(filtered_words[-1].lower())
        features[first_key] = True
        features[last_key] = True
    return features

## build feature sets
# Responsibilities
responsibilities_features = [
    (
         get_title_features(job_title["title"]),
         job_title["responsibility"]
    )
    for job_title in raw_job_titles
    if job_title["responsibility"] is not None
]

# Departments
departments_features = [
    (
         get_title_features(job_title["title"]),
         job_title["department"]
    )
    for job_title in raw_job_titles
    if job_title["department"] is not None
]

## Train classifier
# Responsibilities
r_size = int(len(responsibilities_features) * 0.5)
r_train_set = responsibilities_features[r_size:]
r_test_set = responsibilities_features[:r_size]
responsibilities_classifier = nltk.NaiveBayesClassifier.train(
    r_train_set
)
print("Responsibility classification accuracy: {}".format(
    nltk.classify.accuracy(
        responsibilities_classifier,
        r_test_set
    )
))

# Departments
d_size = int(len(departments_features) * 0.5)
d_train_set = departments_features[d_size:]
d_test_set = departments_features[:d_size]
departments_classifier = nltk.NaiveBayesClassifier.train(
    d_train_set
)
print("Department classification accuracy: {}".format(
    nltk.classify.accuracy(
        departments_classifier,
        d_test_set
    )
))

## Test Classifier
title = "Director of Communications"
responsibility = responsibilities_classifier.classify(
    get_title_features(title)
)
department = departments_classifier.classify(
    get_title_features(title)
)
print("Job title: '{}'".format(title))
print("Responsibility: '{}'".format(responsibility))
print("Department: '{}'".format(department))

## Grade Classifier
# Responsibility
responsibility_probability = \
    responsibilities_classifier.prob_classify(
        get_title_features(title)
    )
responsibility_probability = 100 * responsibility_probability.prob(
    responsibility_probability.max()
)
print("Responsibility confidence: {}%".format(
    round(responsibility_probability)
))
# Department
department_probability = \
    departments_classifier.prob_classify(
        get_title_features(title)
    )
department_probability = 100 * department_probability.prob(
    department_probability.max()
)
print("Department confidence: {}%".format(
    round(department_probability)
))

raw_job_titles?

raw_job_titles?

raw_job_titles = [
{
"title": "Business Development",
"responsibility": "Strategy",
"department": "Business Development"
},
{
"title": "Inside Sales Consultant",
"responsibility": "Execution",
"department": "Sales"
},

]

Did you compile the list manually?
Can you please share it?
Thanks!

If you could share the list that would be great! I am working on a similar problem, manually tagging job titles!

i am sharing my Dataset using DATATURK Annotation tool please i was actually looking for python code to do it for me

…

On Tue, 30 Jul 2019 at 01:36, nush12 ***@***.***> wrote: If you could share the list that would be great! I am working on a similar problem, manually tagging job titles! — You are receiving this because you commented. Reply to this email directly, view it on GitHub <https://gist.github.com/f355126042513188c484db5ef91650cd?email_source=notifications&email_token=AADJDPL6KEXWSYWJZJHFHX3QB5IDHA5CNFSM4H5ROYCKYY3PNVWWK3TUL52HS4DFVNDWS43UINXW23LFNZ2KUY3PNVWWK3TUL5UWJTQAFWEQK#gistcomment-2984197>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AADJDPKRL6H4QPKGXTLHM6TQB5IDHANCNFSM4H5ROYCA> .

Hi guys,
I found a few nice websites and datasets. This dataset is pretty great :
https://www.kaggle.com/estasney/job-title-synonyms

I found that manually scraping a couple of websites should get you a pretty decent list and only takes half an hour...

Thanks @danFromTelAviv this helps!

Hello, Original post & dataset by @danFromTelAviv helped a lot - Thank you very much!

From my side, I propose JSON version of the dataset with small alterations, hope it helps:

1. raw titles to normalized title mapping
2. normalized title to raw title mapping

Hi Dan @danFromTelAviv ! The dataset you shared for raw job titles is not of the form "Title" "Responsibility" "Department". How will this work exactly?

Hi @asinghal3644 - At least in my case, all I needed was the title. You could try to use different language models like "fast text" or "bert" to find out which responsibility and department each job title is most closely related to.

Any chance of making that dataset available?

raw_job_titles

anyone who figure out the data set and formed any data set for this code please share it with me as well I will be thankful for you.

I also require this dataset, if anyone has it can you please send it to me

Same here!

Working on similar problem, I would like the dataset too

good working