Shawn McMichael’s Post

Start strong: XGBoost 3.2.0 delivers major categorical re-coder improvements and ARM CUDA support, scaling predictive modeling efficiently. Release: https://lnkd.in/gWiAbMEc In ML tasks, these expand hardware compatibility. Noticing XGBoost 3.2.0 changes? Views? #XGBoost #MachineLearning #Python #DataScience #AIProgress

Start strong: XGBoost 3.2.0 (Feb 2026) delivers major categorical re-coder updates and hardware compatibility, scaling predictive modeling effectively. Release: https://lnkd.in/gWiAbMEc In ML tasks, these broaden efficient training options. Following XGBoost 3.2.0? What stands out? #XGBoost #MachineLearning #Python #DataScience #AIProgress

Start strong: XGBoost 3.2.0 refines categorical handling and ARM CUDA, boosting scalable predictions. Changes: https://lnkd.in/gK4A79-H In ML tasks, these expand efficiency. XGBoost 3.2.0 wins? Views? #XGBoost #MachineLearning #Python #DataScience #AIProgress

Longest Common Span with Equal Sum in Two Binary Arrays: Reduced the problem using a difference array + prefix sum + hashmap, converting it into a longest zero-sum subarray pattern. Time Complexity: O(n) Small optimizations. Stronger fundamentals. Consistency compounds. #geekstreak60 #npci #DataStructures #Algorithms #ProblemSolving #Python #CodingJourney

Edge-Quantum Inference. Goal-oriented agents managing real-time prediction fixes on federated multi-QPU edge nodes. Skills: Python, scikit-learn. https://lnkd.in/dR837zSA #EdgeAI #QuantumInference #DataScience

Before working on the AI employee, spent time learning the core: 𝘀𝘂𝗯𝗽𝗿𝗼𝗰𝗲𝘀𝘀 𝗶𝗻 𝗣𝘆𝘁𝗵𝗼𝗻. Understanding how Python can execute external commands, capture stdout and stderr, control execution with timeouts, and work with clean string outputs instead of raw bytes. Also looked into managing return codes and controlling how external tools run from inside a Python program. Small piece, but it’s the bridge between Python and the outside world. #Python #Subprocess #Learning

🌟 Day 40 | Strengthening data structure fundamentals 🌿 Today, I learned about the Morris Traversal Algorithm, an efficient way to traverse a binary tree without using recursion or a stack. Explored how temporary links are created to perform inorder traversal with O(1) space complexity, making the approach both clever and memory-efficient✨ #DSA #BinaryTree #Python #ProblemSolving #ComputerScience #Coding #BTech

“Better features = better predictions. Here’s how I realized it.” I spent hours transforming and selecting features in my dataset. The impact was huge: • Improved model accuracy • Reduced overfitting • Revealed hidden patterns in data This taught me that algorithms matter less than meaningful features. 💬 What’s your go-to feature engineering trick? #DataScience #MachineLearning #FeatureEngineering #Python #Projects

Exploring KNN Imputation in Machine Learning 🤖 Built a Kaggle notebook to learn how KNN Imputer can handle missing values by using patterns from similar data points. A simple yet powerful technique for smarter missing value handling. Kaggle notebook 👇 [https://lnkd.in/gvpirkKn] #MachineLearning #DataScience #Kaggle #Python

Machine Learning models require numerical input. So before training a model we must Convert categorical values -> Numerical values. e.g: Value Convert to Yes 1 No 0 True 1 False 0 #DataScience #python #machinelearning