Causal Incrementality Engine in Python: 3 Methods Compared

A clean HMM.py utility for market regime detection with Hidden Markov Models. This module: - Trains a Gaussian HMM on the most recent 900 trading days - Accepts a DataFrame + configurable feature columns - Validates inputs and handles missing data - Returns both the fitted model and labeled output with: - hidden_state - per-state probabilities (state_prob_k) Designed it to be practical for quant workflows: reproducible (random_state), configurable (n_states, covariance_type, n_iter), and ready to plug into signal pipelines. #Python #QuantFinance #AlgorithmicTrading #SoftwareEngineering

Standard LLM chains are great for straight lines, but real-world problems are messy. They need loops, second guesses, and human check-ins. LangGraph solves that problem. It’s the "pro mode" for LangChain. I just put together a quick post on how to get started with this framework with a simple code example. Here’s the TL;DR: ✅ Define State Early: Use TypedDict to give your agent a reliable memory. ✅ Conditional Edges: Let the LLM decide when to pivot or retry. ✅ Persistence: Never lose progress again with built-in checkpointers. ✅ Human-in-the-Loop: Add "pause" buttons for high-stakes actions. ✅ Keep Nodes Pure: Small, focused functions make debugging a breeze. Check out the full breakdown below! 👇 https://lnkd.in/e_T-bCaG #AI #DataScience #Python #LangChain #LangGraph #MachineLearning #LLM

Master Figures, Lines & Arrows in Matplotlib! The matplotlib module can plot geometric figures such as rectangles, circles, and triangles. These figures can then illustrate mathematical, technical, and physical relationships. This blog post demonstrates the creative options of matplotlib through three examples by illustrating the Pythagorean theorem: a gear representation, a pointer diagram, and a current-carrying conductor in a homogeneous magnetic field. #Python #DataViz #Matplotlib #CodeMagic #RheinwerkComputingBlog Dive in now and transform your graphs! https://hubs.la/Q04byPg90

Day 22/100 – DSA Journey Problem: Find Mode in Binary Search Tree (BST) Today’s problem focused on understanding how Binary Search Trees (BST) behave and how we can efficiently extract useful insights from them. Understanding the BST A Binary Search Tree follows a structured property: Left subtree → values ≤ root Right subtree → values ≥ root Because of this, when we perform an Inorder Traversal (Left → Root → Right), the values are visited in sorted order. Why Inorder Traversal? Since duplicates appear consecutively in a sorted sequence, inorder traversal allows us to: Track frequency without using extra space Compare current value with previous value Efficiently determine the most frequent element (mode) Approach Used Traverse the BST using inorder traversal Maintain: Previous value Current count Maximum frequency Update result list whenever a new maximum frequency is found Key Learning This problem highlights how leveraging tree properties can help optimize solutions. Instead of using extra space (like hashmaps), we used traversal behavior to achieve an efficient solution. Conclusion Understanding the underlying structure of data (like BST properties) is often more powerful than brute-force approaches. Smart traversal choices can significantly reduce space complexity and improve performance. #Day22 #100DaysOfCode #DSA #BinarySearchTree #Python #CodingJourney #LeetCode #ProblemSolving

ABTalks (Season-1) | AI Engineering – Day 54 Building the Document Processing Pipeline Today I worked on the first core component of the system — handling documents. ⚙️ What I implemented: - Uploading documents (PDF/Text) - Chunking data into smaller pieces - Generating embeddings for each chunk 🧠 Key Insight: Large documents can’t be processed directly by LLMs — breaking them into meaningful chunks is crucial for accurate retrieval. 📌 Tools explored: Python, LangChain, Vector Embeddings #ABTalks #Day54 #RAG #LangChain #AIProjects #FullStackAI ABTalksOnAI

The second batch of my new course "ML for the mountain cryosphere" is available! By the example of predicting rock glacier activity and permafrost occurrence using naïve Bayes and logistic regression, we learn about • The ML modelling framework with test-train-validation split and generalisation capability • The implementation of a simple gradient descent optimizer • Using directed acyclic graphs (DAGs) to talk about causal structure • The performance metrics of binary classifiers Link to material in the comment. Next topic is Bayesian inference, stay tuned. #MachineLearning #GeoAI #Cryosphere #Permafrost #RockGlaciers #UniInnsbruck #Python #PyMC #ScikitLearn

In the past years, foundation models have been extensively utilized in time series forecasting, with models like TimeGPT and TimesFM gaining significant attention. Kairos is a flexible and efficient foundation model designed to handle the dynamic and heterogeneous nature of real world data. The model was trained on the PreSTS corpus comprising of 300 billion time points from various domains. Kairos achieves excellent forecasting performance on the GIFT-Eval benchmark, while having significantly fewer parameters compared to other models. Check the link for more information and follow me for regular data science content! 𝗞𝗮𝗶𝗿𝗼𝘀 𝗼𝗳𝗳𝗶𝗰𝗮𝗹 𝘄𝗲𝗯𝘀𝗶𝘁𝗲: https://lnkd.in/dtxjtQvK 𝗟𝗲𝗮𝗿𝗻 𝗠𝗟 𝗮𝗻𝗱 𝗙𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴: https://lnkd.in/dyByK4F #datascience #python #deeplearning #forecasting

Day 243 of #365DaysOfCode Solved Minimum Distance Between Three Equal Elements I using a hashmap-based indexing approach. Grouped indices of identical elements and evaluated triplets by scanning index lists to compute the minimum distance. This approach efficiently reduces redundant comparisons by leveraging value-based grouping. The solution runs in O(n) time with additional space for index storage. Continuing to refine problem solving through pattern recognition and efficient data organization. #365DaysOfCode #Day243 #DSA #LeetCode #Python #Algorithms #HashMap #ProblemSolving #Consistency

A handwritten digit classifier built from scratch using NumPy. The project focuses on understanding the core mechanics of a neural network by implementing the full pipeline directly, including forward propagation, ReLU, softmax, backpropagation, and gradient descent. It also includes training reports, experiments, inference, Docker, CI, and a small demo to make the workflow easier to run and inspect. Latest MNIST run reached 95.78% test accuracy. GitHub: https://lnkd.in/gMS7a99g #machinelearning #numpy #neuralnetwork #python #mlengineering

🚗 Built an Automatic Number Plate Recognition (ANPR) System! Excited to share my recent project where I developed a real-time ANPR system using YOLOv8 and EasyOCR. 🔍 Key Features: • Real-time number plate detection • OCR-based text extraction • Custom dataset creation This project helped me strengthen my skills in Computer Vision and Machine Learning. 🔗 GitHub Repository: https://lnkd.in/g_5r5wcW #MachineLearning #ComputerVision #YOLO #Python #DataScience