/ds-task

Pre-interview task for Data Scientist candidates

Primary LanguageJupyter Notebook

Data Positions at SCFHS

Requirements

Before you run the import sell make the following is installed in your enviroment:

- Numpy
- Pandas
- Matplot
- Selenium Driver
- GekioDriver (For the Firefox Selenium web driver
- Ummaqra (For dealing with Hijri dates): `pip3 install ummalqura`

Data Scientist

Thank you for your interest in our Data Scientist positions. Before we have a chat about SCFHS's fit to your career path, let's have a look at what you can do in 72 hours as a Data Scientist.

Question

A friend once told me some in the Muslim community think people tend to die more (often) in the month of Shaban. As a data scientist, what do you think?

Approach

Please make use of (but not limited to) the data by the Medina Municipality

Structure your analysis with the following components:

  1. Refine your objective
  2. Collect the data (save the data in the directory data/)
  3. Data Exploration and Data Cleaning
  4. Modeling
  5. Summarize your results
  6. List any resource you used

You may code in python or R in a jupyter notebook environment.

Submission

There are 3 steps:

  1. To accept this task, clone this repo.
  2. When you are done, push it to your own github repo and make your repo public
  3. Fill this form

Tips

  1. Make sure your notebook is properly rendered before push.
  2. Include a proper .gitignore to reduce clutter in your repo.
  3. This is about showcasing your skills and thinking. Please comment along the way and share your thought process. Commit Often, Perfect Later.
  4. If you have relevant past projects (with code and/or visualization showcases) that you would like to share, feel free to add the repos and/or Tableau public links in the section below.
  5. If you have any questions, please raise an issue on this repo.

Past projects

I have done the following data science project as part of Udacity's Data Scientist Nanodegree, which I currently taking: