Data Science Interview Cheat Sheet

Biron's Job Interview Cheat Sheet is some of the best actionable advice out there and will help you feel confident in your next interview. The Do's and Don'ts are all things that I personally have used to qualify (and disqualify!) candidates, so take note. About This Resource. When I was applying to Data Science jobs, I noticed that there was a need for a comprehensive statistics and probability cheat sheet that goes beyond the very fundamentals of statistics (like mean/median/mode).

Mac pro 5 1 mojave wifi. On November 5, 2010, Apple introduced the Mac Pro Server, which officially replaced the Xserve line of Apple servers as of January 31, 2011. The Mac Pro Server includes an unlimited Mac OS X Server license and an Intel Xeon 2.8 GHz Quad-Core processor, with 8 GB of DDR3 RAM. MP 1,1-5,1 Mac Pro 5,1 Strange. OS upgrade is an option for the awesome but aging 5,1 natively. What a lot of other users are doing macOS 10.14.6 Mojave - can.

Data Science Cheatsheet 2.0


BY Aaron Wang

A helpful 4-page data science cheat sheet that can be used for exam analyses, interview training, and everything in between. This resource is not intended to be a detailed, in-depth exploration of any particular model, but rather a basic, condensed introduction to some of the most fundamental machine learning algorithms. This cheat sheet is intended for those who have a clear understanding of statistics and linear algebra, but someone with even a novice understanding of those subjects will also find it very helpful

opics covered (some more in-depth than others) include:

Python Data Science Interview Cheat Sheet

  • Common Distributions
  • Linear and Logistic Regression
  • Decision Trees and Random Forest
  • SVM
  • KNN
  • Clustering
  • Boosting
  • Dimension Reduction (PCA, LDA, Factor Analysis)
  • NLP
  • Neural Networks
  • Recommender Systems
  • Reinforcement Learning
  • Anomaly Detection


Get Link

Data Science Cheatsheet 2.0 PDF

Enter your email address to receive a download link.

Python data science interview cheat sheet

This is a straight-to-the-point, distilled list of technical interview Do's and Don'ts, mainly for algorithmic interviews. Some of these may apply to only phone screens or whiteboard interviews, but most will apply to both. I revise this list before each of my interviews to remind myself of them and eventually internalized all of them to the point I do not have to rely on it anymore.


  • ✅ = Do
  • ❌ = Don't
  • ⚠️ = Situational

Before interview#

Prepare pen, paper and earphones/headphones.
Find a quiet environment with good Internet connection.
Ensure webcam and audio are working. There were times I had to restart Chrome to get Hangouts to work again.
Request for the option to interview over Hangouts/Skype instead of a phone call; it is easier to send links or text across.
Decide on and be familiar with a programming language.
Familiarize yourself with the coding environment (CoderPad/CodePen). Set up the coding shortcuts, turn on autocompletion, tab spacing, etc.
Prepare answers to the frequently-asked behavioral questions in an interview.
Prepare some questions to ask at the end of the interview.
Dress comfortably. Usually you do not need to wear smart clothes, casual should be fine. T-shirts and jeans are acceptable at most places.
Stay calm and composed.
⚠️Turn off the webcam if possible. Most remote interviews will not require video chat and leaving it on only serves as a distraction.

Science Cheat Sheet Pdf


Introduce yourself in a few sentences under a minute or two.
Mention interesting points that are relevant to the role you are applying for.
Sound enthusiastic! Speak with a smile and you will naturally sound more engaging.
Spend too long introducing yourself. The more time you spend talking the less time you have to code.

Upon receiving the question#

Repeat the question back at the interviewer.
Clarify any assumptions you made subconsciously. Many questions are under-specified on purpose. E.g. a tree-like diagram could very well be a graph that allows for cycles and a naive recursive solution would not work.
Clarify input format and range. Ask whether input can be assumed to be well-formed and non-null.
Work through a small example to ensure you understood the question.
Explain a high level approach even if it is a brute force one.
Improve upon the approach and optimize. Reduce duplicated work and cache repeated computations.
Think carefully, then state and explain the time and space complexity of your approaches.
If stuck, think about related problems you have seen before and how they were solved. Check out the tips in this section.
Ignore information given to you. Every piece is important.
Jump into coding straightaway.
Start coding without interviewer's green light.
Appear too unsure about your approach or analysis.

During coding#

Explain what you are coding/typing to the interviewer, what you are trying to achieve.
Practice good coding style. Clear variable names, consistent operator spacing, proper indentation, etc.
Type/write at a reasonable speed.
As much as possible, write actual compilable code, not pseudocode.
Write in a modular fashion. Extract out chunks of repeated code into functions.
Ask for permission to use trivial functions without having to implement them; saves you some time.
Use the hints given by the interviewer.
Demonstrate mastery of your chosen programming language.
Demonstrate technical knowledge in data structures and algorithms.
If you are cutting corners in your code, state that out loud to your interviewer and say what you would do in a non-interview setting (no time constraints). E.g., 'Under non-interview settings, I would write a regex to parse this string rather than using split() which may not cover all cases.'
Practice whiteboard space-management skills.
⚠️Reasonable defensive coding. Check for nulls, empty collections, etc. Can omit if input validity has been clarified with the interviewer.
Remain quiet the whole time.
Spend too much time writing comments.
Use extremely verbose or single-character (unless they're common like i, n) variable names.
Copy and paste code without checking (e.g. variables need to be renamed).
Interrupt your interviewer when they are talking. Usually if they speak, they are trying to give you hints or steer you in the right direction.
Write too big (takes up too much space) or too small (illegible) if on a whiteboard.

After coding#

Scan through your code for mistakes as if it was your first time seeing code written by someone else.
Check for off-by-one errors.
Come up with more test cases. Try extreme test cases.
Step through your code with those test cases.
Look out for places where you can refactor.
Reiterate the time and space complexity of your code.
Explain trade-offs and how the code/approach can be improved if given more time.
Immediately announce that you are done coding. Do the above first!
Argue with the interviewer. They may be wrong but that is very unlikely given that they are familiar with the question.

Wrap up#

Ask questions. More importantly, ask good and engaging questions that are tailored to the company! Pick some questions from this list.
Thank the interviewer.
⚠️Ask about your interview performance. It can get awkward.
End the interview without asking any questions.

Data Science Interview Cheat Sheets

Post interview#

Science Cheat Sheet

Record the interview questions and answers down as these can be useful for future reference.
⚠️Send a follow up email to your interviewer(s) thanking them for their time and the opportunity to interview with them.