Data Science Guide

Which data science concepts should I learn in order?

The biggest mistake that beginners do when studying data science is to start immediately on something too complex, like computer vision. This is the guide that has been outlined by Michelangiolo Mazzeschi. This list can be used as a syllabus for your study plan.

If you wish to get your hands dirty and start working on some projects, here is a list of projects with coding steps and examples that explain to you how to write ML.

1. Cross-sectional data

  1. Binary Classification and Monovariate Regression
  2. Data Transformations
  3. Multi-label classification and Multi-variate regression
  4. Clustering
  5. Dimensionality Reduction
  6. Rule Association Learning

2. Natural Language Processing

  1. Using API, parsing data, json files
  2. Web Scraping
  3. Data Cleaning, Lemmatization, Stemming
  4. Sentiment Analysis

3. Deep learning

  1. Multi-layer perceptron
  2. LSTM
  3. Predictive Maintenance

4. Vectors

  1. Start working with Big Data
  2. Word2Vec encoding
  3. BERT encoding
  4. Topic Modeling
  5. Recommendation System