Guide to self-study Data Science Part 1

Hello Everyone,

Being a data scientist, many people interested in getting into data science have contacted me for guidance on how to get into the field of data science. This article will discuss the recommended topics that one has to study to build essential skills in data science.

The topics presented here, if studied thoroughly, will provide the minimum background needed to start doing data science. This curriculum could also be used for designing an introductory college-level course in data science.

Keep in mind that knowledge acquired from courses alone will not make you a data scientist. Course work has to be accompanied by a capstone project or an internship. Kaggle competitions can be used for capstones, as they provide an opportunity to work on real-world data science projects.

The following list presents essential topics to learn introductory Data Science.

* Math Basics

(I) Multivariable Calculus

Most machine learning models are built with a dataset having several features or predictors. Hence familiarity with multivariable calculus is extremely important for building a machine learning model. Here are the topics you need to be familiar with:

  • Functions of several variables
  • Derivatives and gradients
  • Step function, Sigmoid function, Logit function, ReLU (Rectified Linear Unit) function
  • Cost function
  • Plotting of functions
  • Minimum and Maximum values of a function

(II) Linear Algebra

Linear algebra is the most important math skill in machine learning. A dataset is represented as a matrix. Linear algebra is used in data preprocessing, data transformation, and model evaluation. Here are the topics you need to be familiar with:

  • Vectors
  • Matrices
  • Transpose of a matrix
  • The inverse of a matrix
  • The determinant of a matrix
  • Dot product
  • Eigenvalues
  • Eigenvectors

(III) Optimization Methods

Most machine learning algorithms perform predictive modeling by minimizing an objective function, thereby learning the weights that must be applied to the testing data in order to obtain the predicted labels. Here are the topics you need to be familiar with:

  • Cost function/Objective function
  • Likelihood function
  • Error function
  • Gradient Descent Algorithm and its variants (e.g., Stochastic Gradient Descent Algorithm)

* Programming Basics

Python and R are considered the top programming languages for data science. You may decide to focus on just one language. Python is widely adopted by industries and academic training programs. As a beginner, it is recommended that you focus on one language only.

Here are some Python and R basics topics to master:

  • Basic R syntax
  • Foundational R programming concepts such as data types, vectors arithmetic, indexing, and data frames
  • How to perform operations in R including sorting, data wrangling using dplyr, and data visualization with ggplot2
  • R studio
  • Object-oriented programming aspects of Python
  • Jupyter notebooks
  • Be able to work with Python libraries such as NumPy, pylab, seaborn, matplotlib, pandas, scikit-learn, TensorFlow, PyTorch

* Data Basics

Learn how to manipulate data in various formats, for example, CSV file, pdf file, text file, etc. Learn how to clean data, impute data, scale data, import and export data, and scrap data from the internet. Some packages of interest are pandas, NumPy, pdf tools, stringr, etc. Additionally, R and Python contain several inbuilt datasets that can be used for practice. Learn data transformation and dimensionality reduction techniques such as covariance matrix plot, principal component analysis (PCA), and linear discriminant analysis (LDA).

* Probability and Statistics Basics

Statistics and Probability is used for visualization of features, data preprocessing, feature transformation, data imputation, dimensionality reduction, feature engineering, model evaluation, etc. Here are the topics you need to be familiar with:

  • Mean
  • Median
  • Mode
  • Standard deviation/variance
  • Correlation coefficient and the covariance matrix
  • Probability distributions (Binomial, Poisson, Normal)
  • p-value
  • Baye’s Theorem (Precision, Recall, Positive Predictive Value, Negative Predictive Value, Confusion Matrix, ROC Curve)
  • A/B Testing
  • Monte Carlo Simulation

* Data Visualization Basics

Learn essential components of a good data visualization. A good data visualization is made up of several components that have to be pieced up together to produce an end product:

a) Data Component : An important first step in deciding how to visualize data is to know what type of data it is, e.g., categorical data, discrete data, continuous data, time-series data, etc.

b) Geometric Component: Here is where you decide what kind of visualization is suitable for your data, e.g., scatter plot, line graphs, bar plots, histograms, Q-Q plots, smooth densities, boxplots, pair plots, heatmaps, etc.

c) Mapping Component: Here, you need to decide what variable to use as your x-variable and what to use as your y-variable. This is important, especially when your dataset is multi-dimensional with several features.

d) Scale Component: Here, you decide what kind of scales to use, e.g., linear scale, log scale, etc.

e) Labels Component: This includes things like axes labels, titles, legends, font size to use, etc.

f) Ethical Component : Here, you want to make sure your visualization tells the true story. You need to be aware of your actions when cleaning, summarizing, manipulating, and producing a data visualization and ensure you aren’t using your visualization to mislead or manipulate your audience.

Important data visualization tools include Python’s matplotlib and seaborn packages, and R’s ggplot2 package.

Continue to Part 2.
Link: Guide to self-study Data Science Part 2