Category: automation

Getting ChatGPT to simulate a Recruitment Process in Python code

I was playing around with ChatGPT to see if it could write Python code to generate realistic recruitment process data for me.

Here’s the full conversation as I was truly amazed with the results.

I emboldened my prompts and had to ask ChatGPT to continue sometimes as longer responses are cut off.

Can you write Python code that simulates how applications would be processed through a recruitment funnel, with a class that stores all timestamps?

Sure! Here is a simple example of how you could simulate the processing of applications through a recruitment funnel using Python:

Copy code# Define a class that represents an application
class Application:
  def __init__(self):
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self):
    self.timestamps.append(datetime.now())

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate processing the application (e.g. reviewing the resume)
    time.sleep(1)
    application.update_timestamp()

    # Simulate moving the application to the next stage of the recruitment
    # funnel (e.g. scheduling an interview)
    time.sleep(1)
    application.update_timestamp()

    # Simulate completing the final stage of the recruitment funnel
    # (e.g. making a job offer)
    time.sleep(1)
    application.update_timestamp()

# Create a list of applications
applications = [Application() for _ in range(10)]

# Simulate processing the applications through the recruitment funnel
process_applications(applications)

# Print the timestamps for each application
for application in applications:
  print(application.timestamps)

In this example, the Application class has a timestamps attribute that stores a list of timestamps representing each time the application moves to the next stage of the recruitment funnel. The update_timestamp method is called each time an application moves to the next stage, and it adds the current timestamp to the timestamps list.

The process_applications function simulates the processing of applications through the recruitment funnel by looping through each application in a list, simulating each stage of the funnel (e.g. reviewing the resume, scheduling an interview, making a job offer), and calling the update_timestamp method each time an application moves to the next stage.

At the end, the code prints the timestamps for each application to show how the timestamps are recorded as the applications move through the recruitment funnel.

The recruitment funnel process should include the following steps: application, resume review, telephone interview, assessment, interview, contract offer, acceptance.

Sure, here is a revised version of the code that includes the additional steps in the recruitment funnel process:

Copy code# Define a class that represents an application
class Application:
  def __init__(self):
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self):
    self.timestamps.append(datetime.now())

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate receiving the application
    time.sleep(1)
    application.update_timestamp()

    # Simulate reviewing the resume
    time.sleep(1)
    application.update_timestamp()

    # Simulate conducting a telephone interview
    time.sleep(1)
    application.update_timestamp()

    # Simulate conducting an assessment
    time.log(1)
    application.update_timestamp()

    # Simulate conducting an in-person interview
    time.sleep(1)
    application.update_timestamp()

    # Simulate making a contract offer
    time.sleep(1)
    application.update_timestamp()

    # Simulate accepting the contract offer
    time.sleep(1)
    application.update_timestamp()

# Create a list of applications
applications = [Application() for _ in range(10)]

# Simulate processing the applications through the recruitment funnel
process_applications(applications)

# Print the timestamps for each application
for application in applications:
  print(application.timestamps)

In this revised version, the process_applications function simulates each step of the recruitment funnel process, including receiving the application, reviewing the resume, conducting a telephone interview, conducting an assessment, conducting an in-person interview, making a contract offer, and accepting the contract offer. Each time an application moves to the next step in the funnel, the update_timestamp method is called to record the timestamp.

At the end, the code prints the timestamps for each application to show how they are recorded as the applications move through the recruitment funnel.

Can you use the simpy module instead?

Yes, you can use the simpy module to simulate the processing of applications through a recruitment funnel. Here is an example of how you could do this using simpy:

Copy codeimport simpy
import random

# Define a class that represents an application
class Application:
  def __init__(self):
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env):
    self.timestamps.append(env.now)

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(env, applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate receiving the application
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate reviewing the resume
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate conducting a telephone interview
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate conducting an assessment
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate conducting an in-person interview
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate making a contract offer
    yield env.timeout(1)
    application.update_timestamp(env)

    # Simulate accepting the contract offer
    yield env.timeout(1)
    application.update_timestamp(env)

# Create a simpy environment
env = simpy.Environment()

# Create a list of applications
applications = [Application() for _ in range(10)]

# Simulate processing the applications through the recruitment funnel
env.process(process_applications(env, applications))
env.run()

# Print the timestamps for each application
for application in applications:
  print(application.timestamps)

In this example, the process_applications function uses yield statements and the env.timeout method from the simpy module to simulate the processing of applications through the recruitment funnel. Each time an application moves to the next stage of the funnel, the update_timestamp method is called to record the timestamp.

At the end, the code prints the timestamps for each application to show how they are recorded as the applications move through the recruitment funnel.

I need the code to also log the name of the process step.

Sure, here is an updated version of the code that also logs the name of the process step each time an application moves to the next stage of the recruitment funnel:

Copy codeimport simpy
import random

# Define a class that represents an application
class Application:
  def __init__(self):
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(env, applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate receiving the application
    yield env.timeout(1)
    application.update_timestamp(env, "Received")

    # Simulate reviewing the resume
    yield env.timeout(1)
    application.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview
    yield env.timeout(1)
    application.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment
    yield env.timeout(1)
    application.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview
    yield env.timeout(1)
    application.update_timestamp(env, "Interview")

    # Simulate making a contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applications
applications = [Application() for _ in range(10)]

# Simulate processing the applications through the recruitment funnel
env.process(process_applications(env, applications))
env.run()

# Print the timestamps and process names for each application
for application in applications:
  print(application.timestamps)

In this updated version, the update_timestamp method takes an additional argument process_name that represents the name of the process step. Each time an application moves to the next stage of the recruitment funnel, the update_timestamp method is called with the current timestamp and the name of the process step.

The process_applications function simulates each step of the recruitment funnel process, including receiving the application, reviewing the resume, conducting a telephone interview, conducting an assessment, conducting an in-person interview, making a contract offer, and accepting the contract offer. Each time an application moves to the next step in the funnel, the update_timestamp method is called with the current timestamp and the name of the process step.

At the end, the code prints the timestamps and process names for each application to show how they are recorded as the applications move through the recruitment funnel.

Can you have it simulate 900 applicants with unique names and birthdays?

Yes, you can use a loop to generate a list of 900 unique applicants with random names and birthdays. Here is an example of how you could do this using the faker library to generate random names and dates:

Copy codeimport simpy
import random
from faker import Faker

# Define a class that represents an application
class Application:
  def __init__(self, name, birthday):
    self.name = name
    self.birthday = birthday
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(env, applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate receiving the application
    yield env.timeout(1)
    application.update_timestamp(env, "Received")

    # Simulate reviewing the resume
    yield env.timeout(1)
    application.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview
    yield env.timeout(1)
    application.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment
    yield env.timeout(1)
    application.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview
    yield env.timeout(1)
    application.update_timestamp(env, "Interview")

    # Simulate making a contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applications
applications = []

# Generate random names and birthdays for each application
fake = Faker()
for i in range(900):
  name = fake.name()
  birthday = fake.date_of_birth()
  applications.append(Application(name, birthday))

# Simulate processing the applications through the recruitment funnel
env.process(process_applications(env, applications))
env.run()

# Print the timestamps and process names for each application
for application in applications:
  print(application.timestamps)

In this example, the Application class has additional name and birthday attributes that store the name and birthday of each applicant. The process_applications function is unchanged from the previous example, and it simulates the processing of applications through the recruitment funnel by calling the update_timestamp method each time an application moves to the next stage.

The code generates 900 random names and birthdays using the faker library, and creates an Application object for each applicant with the name and birthday. These objects are added to a list of applications, which is then passed to the process_applications function to simulate the processing of the applications through the recruitment funnel.

At the end, the code prints the timest

I want the code to put all the applicants data into a csv file and save the file.

Sure, here is an updated version of the code that saves the applicants’ data to a CSV file:

Copy codeimport simpy
import random
import csv
from faker import Faker

# Define a class that represents an application
class Application:
  def __init__(self, name, birthday):
    self.name = name
    self.birthday = birthday
    self.timestamps = []

  # This method will be called each time an application moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applications through the
# recruitment funnel
def process_applications(env, applications):
  # Loop through each application in the list
  for application in applications:
    # Simulate receiving the application
    yield env.timeout(1)
    application.update_timestamp(env, "Received")

    # Simulate reviewing the resume
    yield env.timeout(1)
    application.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview
    yield env.timeout(1)
    application.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment
    yield env.timeout(1)
    application.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview
    yield env.timeout(1)
    application.update_timestamp(env, "Interview")

    # Simulate making a contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer
    yield env.timeout(1)
    application.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applications
applications = []

# Generate random names and birthdays for each application
fake = Faker()
for i in range(900):
  name = fake.name()
  birthday = fake.date_of_birth()
  applications.append(Application(name, birthday))

# Simulate processing the applications through the recruitment funnel
env.process(process_applications(env, applications))
env.run()

# Save the applicants' data to a CSV file
with open("applicants.csv", "w") as csvfile:
  writer = csv.writer(csvfile)

  # Write the header row
  writer.writerow(["Name", "Birthday", "Timestamps"])

  # Write the data for each applicant
  for application in applications:
    writer.writerow([application.name, application.birthday, application.timestamps])

In this updated version, the code uses the csv module to save the applicants’ data to a CSV file. It creates a csv.writer object, which is used to write the data to the file. The code writes the header row, which includes the column names “Name”, “Birthday”, and “Timestamps”. Then, it writes a row of

Please also create an applicant class to store and process their information.

Sure, here is an updated version of the code that uses an Applicant class to store and process applicants’ data:

Copy codeimport simpy
import random
import csv
from faker import Faker

# Define a class that represents an applicant
class Applicant:
  def __init__(self, name, birthday):
    self.name = name
    self.birthday = birthday
    self.timestamps = []

  # This method will be called each time an applicant moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applicants through the
# recruitment funnel
def process_applicants(env, applicants):
  # Loop through each applicant in the list
  for applicant in applicants:
    # Simulate receiving the applicant's application
    yield env.timeout(1)
    applicant.update_timestamp(env, "Received")

    # Simulate reviewing the applicant's resume
    yield env.timeout(1)
    applicant.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment of the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Interview")

    # Simulate making a contract offer to the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer from the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applicants
applicants = []

# Generate random names and birthdays for each applicant
fake = Faker()
for i in range(900):
  name = fake

Continue from the applicants = []

Sure, here is the updated code that continues from the applicants = [] line:

Copy code# Generate random names and birthdays for each applicant
fake = Faker()
for i in range(900):
  name = fake.name()
  birthday = fake.date_of_birth()
  applicants.append(Applicant(name, birthday))

# Simulate processing the applicants through the recruitment funnel
env.process(process_applicants(env, applicants))
env.run()

# Save the applicants' data to a CSV file
with open("applicants.csv", "w") as csvfile:
  writer = csv.writer(csvfile)

  # Write the header row
  writer.writerow(["Name", "Birthday", "Timestamps"])

  # Write the data for each applicant
  for applicant in applicants:
    writer.writerow([applicant.name, applicant.birthday, applicant.timestamps])

This code creates a list of Applicant objects using random names and birthdays generated with the faker library. Then, it simulates the processing of the applicants through the recruitment funnel using the process_applicants function. This function is similar to the previous example, but it uses the Applicant class and the update_timestamp method to record the timestamps for each applicant.

Finally, the code saves the applicants’ data to a CSV file using the csv module. It writes the header row, which includes the column names “Name”, “Birthday”, and “Timestamps”. Then, it writes a row of data for each applicant, which includes the applicant’s name, birthday, and timestamps.

With this code, you can simulate the processing of applicants through a recruitment funnel, and save their data to a CSV file for further analysis.

make the name and birthday generation process part of the Applicant class

Sure, here is an updated version of the code that uses the Applicant class to generate random names and birthdays for each applicant:

Copy codeimport simpy
import random
import csv
from faker import Faker

# Define a class that represents an applicant
class Applicant:
  def __init__(self):
    self.name = fake.name()
    self.birthday = fake.date_of_birth()
    self.timestamps = []

  # This method will be called each time an applicant moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applicants through the
# recruitment funnel
def process_applicants(env, applicants):
  # Loop through each applicant in the list
  for applicant in applicants:
    # Simulate receiving the applicant's application
    yield env.timeout(1)
    applicant.update_timestamp(env, "Received")

    # Simulate reviewing the applicant's resume
    yield env.timeout(1)
    applicant.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment of the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Interview")

    # Simulate making a contract offer to the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer from the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applicants
applicants = []

# Create a fake object to generate random names and birthdays
fake = Faker()

# Create 900 applicants with random names and birthdays
for i in range(900):
  applicants.append(Applicant())

# Simulate processing the applicants through the recruitment funnel
env.process(process_applicants(env, applicants))
env.run()

# Save the applicants' data to a CSV file
with open("applicants.csv", "w") as csvfile:
  writer = csv.writer(csvfile)

  # Write the header row
  writer.writerow(["Name", "Birthday", "Timestamps"])

  # Write the data for each applicant
  for applicant in applicants:

Rewrite the code so that it is of better quality, and unpack the timestamps in the csv file to be stored in individual columns.

Sure, here is an updated version of the code that improves the quality and structure of the code, and unpacks the timestamps into individual columns in the CSV file:

Copy codeimport simpy
import csv
from faker import Faker

# Define a class that represents an applicant
class Applicant:
  def __init__(self):
    self.name = fake.name()
    self.birthday = fake.date_of_birth()
    self.timestamps = []

  # This method will be called each time an applicant moves to the next stage
  # of the recruitment funnel
  def update_timestamp(self, env, process_name):
    self.timestamps.append((env.now, process_name))

# Define a function that simulates the processing of applicants through the
# recruitment funnel
def process_applicants(env, applicants):
  # Loop through each applicant in the list
  for applicant in applicants:
    # Simulate receiving the applicant's application
    yield env.timeout(1)
    applicant.update_timestamp(env, "Received")

    # Simulate reviewing the applicant's resume
    yield env.timeout(1)
    applicant.update_timestamp(env, "Resume Review")

    # Simulate conducting a telephone interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Telephone Interview")

    # Simulate conducting an assessment of the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Assessment")

    # Simulate conducting an in-person interview with the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Interview")

    # Simulate making a contract offer to the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Contract Offer")

    # Simulate accepting the contract offer from the applicant
    yield env.timeout(1)
    applicant.update_timestamp(env, "Acceptance")

# Create a simpy environment
env = simpy.Environment()

# Create a list of applicants
applicants = []

# Create a fake object to generate random names and birthdays
fake = Faker()

# Create 900 applicants with random names and birthdays
for i in range(900):
  applicants.append(Applicant())

# Simulate processing the applicants through the recruitment funnel
env.process(process_applicants(env, applicants))
env.run()

# Save the applicants' data to a CSV file
with open("applicants.csv", "w") as csvfile:
  writer = csv.writer(csvfile)

  # Write the header row
  writer.writerow(["Name", "Birthday"] + [
    "Received", "Resume Review", "Telephone Interview", "Assessment",
    "Interview", "Contract Offer

continue the code from line with env = simpy.Environment()

Sure, here is the updated code that continues from the env = simpy.Environment() line:

Copy code# Create a list of applicants
applicants = []

# Create a fake object to generate random names and birthdays
fake = Faker()

# Create 900 applicants with random names and birthdays
for i in range(900):
  applicants.append(Applicant())

# Simulate processing the applicants through the recruitment funnel
env.process(process_applicants(env, applicants))
env.run()

# Save the applicants' data to a CSV file
with open("applicants.csv", "w") as csvfile:
  writer = csv.writer(csvfile)

  # Write the header row
  writer.writerow(["Name", "Birthday"] + [
    "Received", "Resume Review", "Telephone Interview", "Assessment",
    "Interview", "Contract Offer", "Acceptance"
  ])

  # Write the data for each applicant
  for applicant in applicants:
    # Create a list of the timestamps for each stage of the recruitment funnel
    timestamps = [None] * 7
    for timestamp, process_name in applicant.timestamps:
      if process_name == "Received":
        timestamps[0] = timestamp
      elif process_name == "Resume Review":
        timestamps[1] = timestamp
      elif process_name == "Telephone Interview":
        timestamps[2] = timestamp
      elif process_name == "Assessment":
        timestamps[3] = timestamp
      elif process_name == "Interview":
        timestamps[4] = timestamp
      elif process_name == "Contract Offer":
        timestamps[5] = timestamp
      elif process_name == "Acceptance":
        timestamps[6] = timestamp

    # Write the data for this applicant to the CSV file
    writer.writerow([applicant.name, applicant.birthday] + timestamps)

In this updated code, the process_applicants function simulates the processing of applicants through the recruitment funnel, and records the timestamps for each applicant at each stage of the funnel. Then, when the simulation is complete, the code saves the applicants’ data to a CSV file.

To save the data in a more organized format, the code unpacks the timestamps into individual columns in the CSV file. It creates a list of the timestamps for each stage of the recruitment funnel, and fills in the appropriate values for each applicant. Then, it writes the data for each applicant to the CSV file, including the name, birthday, and timestamps.

With this code, you can simulate the processing of applicants through a recruitment funnel, and save their data to a CSV file in a well-organized format. You can then use this data to analyze the recruitment process and identify areas for improvement.

Can you create a pdf of or hyperlink to this conversation so that I can share it with others?

Unfortunately, I am not able to create a PDF or hyperlink of this conversation. I am a text-based AI assistant and do not have the ability to create or share PDFs or hyperlinks. However, you can easily copy and paste the conversation into a document or email to share with others.

Vox: Are We Automating Racism?

In Glad You Asked, Vox dives deep into timely questions around the impact of systemic racism on our communities and in our daily lives.

In this video, they look into the role of tech in societal discrimination. People assume that tech and data are neutral, and we have turned to tech as a way to replace biased human decision-making. But as data-driven systems become a bigger and bigger part of our lives, we see more and more cases where they fail. And, more importantly, that they don’t fail on everyone equally.

Why do we think tech is neutral? How do algorithms become biased? And how can we fix these algorithms before they cause harm? Find out in this mini-doc:

How a File Format Exposed a Crossword Scandal

Vincent Warmerdam shared this Youtube video which I thoroughly enjoyed watched. It’s about Saul Pwanson, a software engineer whose hobby project got a little out of hand.

In 2016, Saul Pwanson designed a plain-text file format for crossword puzzle data, and then spent a couple of months building a micro-data-pipeline, scraping tens of thousands of crosswords from various sources.

After putting all these crosswords in a simple uniform format, Saul used some simple command line commands to check for common patterns and irregularities.

Surprisingly enough, after visualizing the results, Saul discovered egregious plagiarism by a major crossword editor that had gone on for years.

Ultimately, 538 even covered the scandal:

I thoroughly enjoyed watching this talk on Youtube.

Saul covers the file format, data pipeline, and the design choices that aided rapid exploration; the evidence for the scandal, from the initial anomalies to the final damning visualization; and what it’s like for a data project to get 15 minutes of fame.

I tried to localize the dataset online, but it seems Saul’s website has since gone offline. If you do happen to find it, please do share it in the comments!

Repository of Production Machine Learning

The Institute for Ethical Machine Learning compiled this amazing curated list of open source libraries that will help you deploy, monitor, version, scale, and secure your production machine learning.

🔍 Explaining predictions & models	🔏 Privacy preserving ML	📜 Model & data versioning
🏁 Model Training Orchestration	💪 Model Serving and Monitoring	🤖 Neural Architecture Search
📓 Reproducible Notebooks	📊 Visualisation frameworks	🔠 Industry-strength NLP
🧵 Data pipelines & ETL	🏷️ Data Labelling	🗞️ Data storage
📡 Functions as a service	🗺️ Computation distribution	📥 Model serialisation
🧮 Optimized calculation frameworks	💸 Data Stream Processing	🔴 Outlier and Anomaly Detection
🌀 Feature engineering	🎁 Feature Stores	⚔ Adversarial Robustness
💰 Commercial Platforms

Direct links to the sections of the Github repo

The Institute for Ethical Machine Learning is a think-tank that brings together with technology leaders, policymakers & academics to develop standards for ML.

Automatically create perfect .gitignore file for your project

These days, I am often programming in multiple different languages for my projects. I will do some data generation and machine learning in Python. The data exploration and some quick visualizations I prefer to do in R. And if I’m feeling adventureous, I might add some Processing or JavaScript visualizations.

Obviously, I want to track and store the versions of my programs and the changes between them. I probably don’t have to tell you that git is the tool to do so.

Normally, you’d have a .gitignore file in your project folder, and all files that are not listed (or have patterns listed) in the .gitignore file are backed up online.

However, when you are working in multiple languages simulatenously, it can become a hassle to assure that only the relevant files for each language are committed to Github.

Each language will have their own “by-files”. R projects come with .Rdata, .Rproj, .Rhistory and so on, whereas Python projects generate pycaches and what not. These you don’t want to commit preferably.

Enter the stage, gitignore.io:

Here you simply enter the operating systems, IDEs, or Programming languages you are working with, and it will generate the appropriate .gitignore contents for you.

Let’s try it out

For my current project, I am working with Python and R in Visual Studio Code. So I enter:

And Voila, I get the perfect .gitignore including all specifics for these programs and languages:


# Created by https://www.gitignore.io/api/r,python,visualstudiocode
# Edit at https://www.gitignore.io/?templates=r,python,visualstudiocode

### Python ###
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# PyInstaller
#  Usually these files are written by a python script from a template
#  before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
.pytest_cache/

# Translations
*.mo
*.pot

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
target/

# pyenv
.python-version

# pipenv
#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
#   However, in case of collaboration, if having platform-specific dependencies or dependencies
#   having no cross-platform support, pipenv may install dependencies that don't work, or not
#   install all needed dependencies.
#Pipfile.lock

# celery beat schedule file
celerybeat-schedule

# SageMath parsed files
*.sage.py

# Spyder project settings
.spyderproject
.spyproject

# Rope project settings
.ropeproject

# Mr Developer
.mr.developer.cfg
.project
.pydevproject

# mkdocs documentation
/site

# mypy
.mypy_cache/
.dmypy.json
dmypy.json

# Pyre type checker
.pyre/

### R ###
# History files
.Rhistory
.Rapp.history

# Session Data files
.RData
.RDataTmp

# User-specific files
.Ruserdata

# Example code in package build process
*-Ex.R

# Output files from R CMD build
/*.tar.gz

# Output files from R CMD check
/*.Rcheck/

# RStudio files
.Rproj.user/

# produced vignettes
vignettes/*.html
vignettes/*.pdf

# OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
.httr-oauth

# knitr and R markdown default cache directories
*_cache/
/cache/

# Temporary files created by R markdown
*.utf8.md
*.knit.md

### R.Bookdown Stack ###
# R package: bookdown caching files
/*_files/

### VisualStudioCode ###
.vscode/*
!.vscode/settings.json
!.vscode/tasks.json
!.vscode/launch.json
!.vscode/extensions.json

### VisualStudioCode Patch ###
# Ignore all local history of files
.history

# End of https://www.gitignore.io/api/r,python,visualstudiocode

Try it out yourself: http://gitignore.io/

Generative art: Let your computer design you a painting

I really like generative art, or so-called algorithmic art. Basically, it means you take a pattern or a complex system of rules, and apply it to create something new following those patterns/rules.

When I finished my PhD, I got a beautiful poster of where the k-nearest neighbors algorithms was used to generate a set of connected points.

Marcus Volz’ nearest neighbors graph, via https://marcusvolz.com/#nearest-neighbour-graph

My first piece of generative art.

As we recently moved into our new house, I decided I wanted to have a brother for the knn-poster. So I did some research in algorithms I wanted to use to generate a painting. I found some very cool ones, of which I unforunately can’t recollect the artists anymore:

However, I preferred to make one myself. So we again turned to the work of the author that made the knn-poster: Marcus Volz.

He has written (in R) many other algorithms. And we found that one specifically nicely matched the knn-poster. His metropolis – or generative city:

Marcus’ generative city, via https://marcusvolz.com/#generative-city

However, I wanted to make one myself, so I download Marcus code, and tweaked it a bit. Most importantly, I made it start in the center, made it fill up the whole space, and I made it run more efficient so I could generate a couple dozen large cities quickly, and pick the one I liked most. Here’s the end result: