Data Analytics Lab (CS-605) - Unit 3 Short Notes

How unit 3 is examined

This unit has one topic, MATLAB as a data analytics tool; no past question has been asked on it, so learn the definition and the key points below.

Introduction to MATLAB as a data analytics tool

<span style="display:inline-block;padding:.16em .6em;border:1.5px solid currentColor;border-radius:999px;font-size:.68em;font-weight:700;letter-spacing:.06em;text-transform:uppercase;opacity:.75">Not asked since 2022</span>

Definition. <mark>MATLAB (Matrix Laboratory) is a proprietary MathWorks environment and language for numerical computing, data analysis and visualization, built around matrices.</mark>

Key points.

1. Every variable is a matrix or array, so vectorised statistics such as mean, std, corrcoef and polyfit run on whole datasets without loops.
2. Data is imported from CSV, Excel and databases with readtable, and cleaned with functions such as fillmissing and rmoutliers.
3. Toolboxes (Statistics and Machine Learning, Curve Fitting, Deep Learning) add regression, classification and clustering.
4. Built-in plotting (plot, histogram, scatter) gives quick visualization, and the Live Editor combines code, output and text.

Last-minute revision

• MATLAB stands for Matrix Laboratory and is a commercial product of MathWorks.
• The matrix is the basic data type; a scalar is a 1x1 matrix.
• readtable imports tabular data such as CSV and Excel files.
• mean, median, std and var give descriptive statistics.
• corrcoef gives correlation and polyfit fits a regression line.
• fillmissing handles missing values and rmoutliers removes outliers.
• plot, histogram and scatter draw the basic charts.
• Toolboxes extend MATLAB for statistics, machine learning and deep learning.
• MATLAB is licensed and paid, unlike the free tools R and Python.

Memory hooks

• MAT-LAB: MATrix LABoratory, everything is a matrix.
• Read, Clean, Analyse, Plot: readtable, fillmissing, corrcoef, plot.
• Toolbox means extra power: pay for each specialised box.

Coverage checklist

• Introduction to MATLAB as a data analytics tool: definition, matrix basis, import and cleaning, toolboxes, plotting (no past questions).