The Tealhinator (occupation by RNN)

Home/Blog/The Tealhinator (occupation by RNN)

The Tealhinator (occupation by RNN)

Becoming a Pinter, Garner, Pepytatil Nurse, Chief Infospation Officer or Tealhinator, as a career choice, seems to be completely fine in the eyes of a Recurrent Neural Network

The context? Generating new occupations based on existing ones

Wiki fetch

In order to get existing job titles – Wikipedia was consulted

At start, plan was to write a crawler, but the idea was remised in favor of a more “cavalier” code that utilizes MediaWiki API

To retrieve all known professions, URL walk through initial lists of occupations is required. Titles from second level are subsequently fetched, and the special ones (e.g. Category:, Talk:) or references to nested lists are removed

import json
import urllib.request

base_url = '' \

def get_links(title):
resp = json.loads(urllib.request.urlopen(
base_url + title.replace(" ", "%20"), timeout=10).read(
return resp[[k for k in resp.keys()][0]]["links"]

for l1 in get_links("Lists of occupations"):
for l2 in get_links(l1["title"]):
if not any(c in l2["title"] for c in [":", "List"]):

Handling exceptions (i.e. JSONDecodeError, {URL,HTTP}Error) is barbarically neglected

The output? First level salvage returns 14 categories (scientific, healthcare, artistic…), while the second one, final set of all known job titles, barely gets to 865


In order to mash things up and model a probability distribution – Recurrent Neural Network implementation from Andrej Karpathy (director of AI @ Tesla) was used

Since we’ve already prepared code to bootstrap Karpathy’s RNN before, next step was merely gluing it to abovementioned Python code for getting input data

Based on the previous experience, Amazon Linux distribution was used (~7-11x faster processing than remaining default EC2 distros), now in the updated flavor of AL2

echo -n "> bootstrap rnn ... "
curl -s | bash >/dev/null 2>&1
rm /opt/rnn-karpathy/data/tinyshakespeare/ -rf && echo done

echo -n "> fetch occupations from wikipedia ... "
amazon-linux-extras install python3 >/dev/null 2>&1
curl -s | python3 > /opt/rnn-karpathy/data/input.txt && echo done

echo -n "> train a model ... "
cd /opt/rnn-karpathy
th train.lua -data_dir /opt/rnn-karpathy/data -rnn_size 128 -batch_size 2 -num_layers 3 -dropout 0.6 -gpuid -1 >/dev/null 2>&1 && echo done

echo "> generate occupations ..."
sudo th sample.lua cv/$(ls cv/ -1t | head -1) -gpuid -1

echo "all done \o/"

The ∑

Machine Learning and Neural networks thrive on large input datasets, while we’re dealing with less than 1k records here. Hence, in order to make the most of it, we’re forced to heavily tweak and try various arrangements of hidden layers, dropouts, RNN and batch sizes

On more than a dozen t2.medium instances with Amazon Linux 2 planted, after multiple train setups tested, three configurations yielded the most:

rnn_size num_layers batch_size dropout
256 5 1 0.5
128 4 2 0.5
128 3 2 0.6

Automated job title generation on a new VM, with last row’s parameters for RNN can be triggered via:

$ curl -s | sudo bash

… producing output of:

Occupations generated on fresh VM.png

In all variations, however, generated titles were mostly random. Roughly 10% is meaningful, which is, having in mind dreadfully terse input, quite expected:

  • Runter
  • Uthoratist
  • Pimicityer
  • Newtor
  • Phailic Onsinter
  • Chestacge Corinner
  • Stogh Cliter
  • Orertricion Director
  • Staeler
  • Meddermaderog
  • Elergogoot Nursing
  • Werhine Pance Thayerist
  • Amcrofiin Araryst
  • Mashor
  • Perecoty Danncer
  • Fomiatrilian
  • Futhion Suncyror
  • Rodugion Mesigner
  • Makeniatar
  • Chief Buctunel Officer
  • Cledus Tanagerer
  • Photlac
  • Garner
  • Pecsion Monicer
  • Totrulical Technician
  • Ipestralocist
  • Foltinist
  • Partiol Apant
  • Twipo
  • Corpossere
  • Rushyr
  • Sealoet
  • Mathor Crale
  • Remianecetist
  • Pepytatil Nurse
  • Dontor Operation
  • Dytor Padmer
  • Chenm Efficistrator
  • Soal Stater
  • Tant Daster
  • Chief Vart Officer
  • Dontore Designer
  • Foafer
  • Pinter
  • Stile Enminderent Aderator
  • Gereuttapher
  • Aptoroteg
  • Bare Telhanicalisirsitc
  • Bathuder
  • Mirk-tomkar
  • Srelhor
  • Chief Rimensiol Officer
  • Olmhicastor

Still, author’s Linkedin job position is updated with one from the headline – who knows, Tealhinator might become highly demanded position in close future