One data, three models, detailed calculations made easy — Decision Tree is a simple model and easy to interpret. However, it is unstable because small variations in the data might result in a completely different tree being generated. It tends to overfit train data, thus has a high variance and poorly generalizes on unseen test data. This problem is…

With hands-on case study walkthroughs — There are 2 major kinds of machine learning models: supervised and unsupervised. In supervised learning, you have input data X and output data y, then the model finds a map from X to y. In unsupervised learning, you only have input data X. The goal of unsupervised learning varies: clustering…

With hands-on case study walkthroughs — Unlike linear models and SVM (see Part 1), some machine learning models are really complex to learn from their mathematical formulation. Fortunately, they can be understood by following a step-by-step process they execute on a small dummy dataset. …

How does linear regression relate to logistic regression and Support Vector Machine? — Table of contents · So, how does machine learning work? · Linear Models ∘ Linear regression ∘ Ridge ∘ Lasso ∘ Elastic-Net · Logistic Regression · Support Vector Machine (SVM) ∘ Classification ∘ Regression ∘ Kernel functions · A note on preprocessing · Conclusion Machine learning modeling is a data…

And how to match LaTeX syntax using recursive regex — Table of Contents · Preprocessing · Split Dataset · Modeling ∘ Random Prediction ∘ Rule-based Prediction ∘ Machine Learning ∘ Stacking Models · Wrapping Up In this story, you will do baseline modeling for a dataset as a multilabel classification task. Throughout the way, you will learn how to: Preprocess…

Label your data programmatically! — Table of Contents: · Exploratory Data Analysis · Keyword Labeling Functions · Heuristic Labeling Functions · Labeling Functions with spaCy · Combining Labeling Function Outputs · Training a Classifier · Wrapping Up There was a radical idea to entirely eliminate hand-labeling any training data in machine learning projects. It birthed…

A smarter way of human labeling with doccano and modAL — Table of Contents · Human Labeling · Active Learning ∘ Performance with all observations ∘ Performance with active learning · Wrapping Up Okay, let’s talk about the one thing which doesn’t gain that much traction in the data science realm: labeling your data. It’s a painful process, and that may…

Utilizing Streamlit secret and session state to fully interact with your users — Table of Contents Motivation 🔥 Step 1: Firestore Basics ∘ What is Firestore? ∘ Setting-up Firestore ∘ Generate Private Key 👑 Step 2: Upgrade Your Streamlit Functionality ∘ Resketch! ∘ Database Structure 👨‍💻 Step 3: Backend Code ∘ Install Libraries ∘ Build the Footer ∘ Session State 🔗 Step 4…

And its implementation for solving a nonlinear control theory problem — Table of Contents 🐦 An Inspiration from Nature ✍️ Problem Statement 💻 Building the PSO Algorithm 🧪 Testing the Algorithm by Running Once 📉 Analyzing Performance ∘ Case 1: N = 3 and scaling = 0.10 ∘ Case 2: N = 6 and scaling = 0.03 ∘ Case…