Learning Python Data Structures for AI

Day 14 of My AI Journey 🚀 Today I focused on working with real data using file handling in Python. Covered: 👉 Reading and writing files 👉 Processing data from text/CSV files 👉 Combining file data with lists and dictionaries What I worked on: 👉 Built small scripts to read data, process it, and generate outputs 👉 Practiced handling real input instead of hardcoded values Key takeaway: 👉 Working with real data introduces new challenges and requires more structured thinking This step is helping me transition from practice problems to real-world data processing, which is essential for AI systems. #Python #AI #LearningInPublic #BuildInPublic

Used my weekends to upskill in AI (RAG, embeddings, LLMs) and built a chatbot. It lets you ask questions and get instant, context-based answers instead of manually searching through documents. Tech: Python | Streamlit | LangChain | ChromaDB | HuggingFace | Llama 3.3 via Groq 🎥 Demo: https://lnkd.in/gA_Cnv2y 💻 GitHub: https://lnkd.in/g7kcx53b #AI #RAG #LLM #Python #GenerativeAI

✨ A New Beginning in My AI/ML Journey As part of the Industry Immersion Program by MeetMux, Day 3 marked my transition from setup to execution. 🔹 What I tackled today: Built a basic data pipeline using Python, NumPy, and Pandas — focusing on how data is processed, structured, and analyzed. 🔹 What I learned : The concept of vectorization in NumPy — instead of using loops, operations can be applied to entire datasets at once, making computations significantly faster. This is a core technique used in real-world AI systems. 🔹 My goal: To continue building a strong foundation in data handling and move towards implementing real-world machine learning models by the end of this week. 🔗 My Work (GitHub): https://lnkd.in/gQNYJ8ce #AI #MachineLearning #Python #NumPy #Pandas #IndustryImmersion #LearningInPublic #MeetMux

🚀 Day 25 of My Generative & Agentic AI Journey! Today’s focus was on advanced concepts of Generators in Python — going deeper into how they work internally. Here’s what I learned: ⏭️ next() Method: • Used to manually get the next value from a generator • Helps control iteration step by step ♾️ Infinite Generators: • Generators can run indefinitely and produce values endlessly • Useful for streams or continuous data generation 📩 Sending Values to Generators: • We can send values into a generator using special methods • This allows dynamic interaction with the generator while it’s running 🔗 yield from: • Used to delegate part of a generator’s operations to another generator • Makes code cleaner when working with multiple generators ⛔ Closing Generators: • Generators can be stopped manually using close() • Helps in releasing resources and stopping execution when needed 💡 Key takeaway: Generators are not just for iteration — they can be controlled, extended, and optimized for handling complex data flows. Diving deeper into advanced Python concepts 🚀 #Day25 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Most ML time isn’t spent on modeling — it’s data cleaning. Tried skrub, and it genuinely simplifies the pipeline. You can go from raw data to a working model in minutes, especially for real-world tabular data. Worth checking out 👇 #skrub #MachineLearning #Python #DataScience #AI #MLOps #DataEngineering #ScikitLearn

One rogue data point can completely skew your machine learning model. Check out this quick, visual guide breaking down the mechanics of Outlier Detection (IQR vs. Z-Score) and when you should cap vs. drop your data! #Part1 #DataScience #MachineLearning #DataCleaning #Python #DataEngineering #AI #TechEducation

Built a conversational AI agent from scratch today 🤖 •It can understand what a user actually wants, pull answers from a knowledge base in real time, and trigger actions only when the right conditions are met , no premature tool calls, no hallucinated responses. •Tech stack: Python, LangGraph, Groq (Llama 3.1), RAG pipeline with local JSON knowledge base •What I found interesting is how much cleaner state management gets when you treat a conversation like a flowchart rather than a simple back-and-forth. -Every turn, the agent knows exactly where it is and what it still needs. Still a lot to explore with multi-agent setups and proper vector databases but solid foundation built 🔧 #Python #LangChain #LangGraph #GenerativeAI #MachineLearning #RAG #BuildInPublic

🚀 Day 8 of My Generative & Agentic AI Journey! Today’s focus was on Sets in Python and how they help in handling unique data and performing operations. Here’s what I learned: 🧩 Sets in Python: • Sets are collections of unique elements • Created using {} brackets • Automatically remove duplicate values Example: {1, 2, 2, 3} → {1, 2, 3} ⚙️ Set Operations: Let: A = {1, 2, 3} B = {3, 4, 5} • Union ( | ) → Combines all unique elements A | B → {1, 2, 3, 4, 5} • Intersection ( & ) → Common elements A & B → {3} • Difference ( - ) → Elements in A but not in B A - B → {1, 2} ❄️ Frozenset: • Frozenset is an immutable version of a set — it cannot be changed after creation 👉 Key takeaway: Sets are super useful for handling unique data and performing fast operations like union and intersection. Another step forward in strengthening Python fundamentals 💪 #Day8 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Built an AI Object Detector using Python! Feed any image → AI finds all objects,  draws boxes and shows confidence scores. Tested on a messy room image and detected: - Bed, couch, books, potted plant - All with 65-82% confidence Tech stack: - Python - HuggingFace Transformers - Facebook DETR model - Pillow + Matplotlib GitHub: https://lnkd.in/dj4PVi2D #Python #AI #ComputerVision #DeepLearning #Portfolio

Most people learn plotting. Few learn how to tell stories with data. Today I built an interactive visualization of Pakistan’s major cities using Plotly. Instead of static graphs: → Each city becomes a data point → Size represents magnitude → Color represents intensity → Hover reveals insights This is where data visualization becomes decision-making. Next step: integrating real-time datasets. #DataScience #Python #Visualization #AI #LearningInPublic