Tech Tips, Tricks & Trivia

The Maven Analytics course on " Data Prep & Exploratory Data Analysis " by Alice Zhao is a beginner-friendly introduction to machine learning with Python. It covers the key steps of the data science workflow, including: Gathering Data Scoping a Project Modeling Data Sharing Insights Cleaning Data Exploring Data Modeling Data  Sharing Insights The presentation deck which is available as a download crisply summarizes the essential details and is a great reference to keep going back to. The course is well-suited for aspiring data scientists looking to get hands-on experience with the data prep and EDA stages of the machine learning workflow using Python and Jupyter Notebook. 

This Week I Learned -  * Claude.ai, Replit.com, Bolt.new, V0.dev, Pythagora.ai and a few other tools write and deploy code just based on a prompt.   * "We ( Thoughtworks ) see some antipatterns starting to appear in the hyperactive AI space, including the mistaken notion that humans can fully replace pair programming with AI as the companion, overreliance on coding assistance suggestions, code quality issues with generated code and faster growth rates of codebases. AI tends to solve problems via brute force rather than use abstractions, such as using dozens of stacked conditionals rather than the Strategy design pattern. The code quality issues in particular highlight an area of continued diligence by developers and architects to make sure they don’t drown in "working-but-terrible" code. Thus, team members should double down on good engineering practices — such as unit testing, architectural fitness functions and other proven governance and validation techniques — to ma...

See more of my AI co-creations

There is a wealth of free learning resources, including self-paced courses mostly with video content, available for anyone interested in Generative AI. In addition to the companies that develop AI tools, there are many individual experts you can follow to stay up to date. Here’s a list: DeepLearning.AI Google - Qwiklabs / Cloud Skills Boost Microsoft - Learn platform , Github AWS -  AWS Skill Builder   Oracle University nVIDIA Self-Paced Courses   Claude - Educational courses Llama - Github IBM - CognitiveClass.ai Code.org   DataBricks Weights & Biases AI Academy Project Management Institute (PMI)   Janakiram MSV Andrej Karpathy W.I.P

I attended a session on Agentic Frameworks by Koundinya N V S S, Senior Data Scientist, at the Swecha DevDays Hyderabad event held at the Swecha office in Gachibowli on 21st September 2024. The presenter kept the session interactive and live coded a sample. I learned about new Gen AI topics and picked up some coding tips. Notes - Agentic frameworks are software tools and libraries that provide:  • A structured approach for designing and implementing agents  • Pre-built components for handling perception, reasoning, action, and learning  • Abstractions and interfaces to simplify the development process  Examples of Agentic Frameworks:  Microsoft Autogen   CrewAI   LangGraph   huginn   MetaGPT   AgentGPT   BabyAGI Below is a deck shared by Swecha -

As extreme weather events become more frequent and unpredictable, nowcasts are becoming more crucial than traditional forecasts, especially with phenomena like urban heat islands. These days, even the best-laid plans can fall apart if weather isn't factored in. Zomato is offering real-time weather data from 60 Indian cities through a free public API called Weather Union , gathered via a crowd-supported weather infrastructure. I've extracted the latitude and longitude of the weather stations that Zomato has provided in PDF format and shared the CSV file on GitHub . About half of these locations use an Automated Weather System, while the rest have Rain Gauge Systems that only track rainfall.  For stations with rain gauges, the API provides data only on rainfall, and fields like temperature, humidity, and wind speed return null values. I’ve created a simple code sample using Zomato's public API, which you can check on GitHub .  The sample also includes an external link that d...

This Week I Learned -  *  Cloud native applications use DevOps automations features and enable continuous delivery and deployment of software changes that get released on a regular basis. Additionally, developers can use methodologies like blue-green and canary deployments to make improvements to the apps without any disruption to the user experience.  Source - Oracle *  LLM Pricing Calculator * Two new models from Mistral: Ministral 3B and Ministral 8B have joined Mixtral, Pixtral, Codestral and Mathstral as weird naming variants on the Mistral theme. -via Simon Willison * Google’s Gemini 1.5 model large context window can process up to 2 million tokens at once vs. the typical 32k - 128k tokens. * AI Assistance in Chrome Dev Tools is out now in Chrome Canary. * The Visual Studio Code extension Live Preview can run your site on a local web server and auto-refresh as you change it. Google's IDX.dev has an in-built live preview. These reminded me of Microsoft's F...

This Week I Learned -  * Llama 3.2 90B and 11B accept images as well as text and generate text output (image processing is not available in the European Union). Llama 3.2 1B and 3B accept and generate text. All four models can process 131,072 tokens of input context and generate 2,048 tokens of output. Llama 3.2’s vision-language capabilities now drive the company’s Meta AI chatbot. For example, users can upload a photo of a flower and ask the chatbot to identify it or post a picture of food and request a recipe. - The Batch * Llama Stack is a set of APIs for customizing Llama models and building Llama-based agentic applications. By offering tools to build agentic workflows, Llama Stack takes Llama 3.2 well beyond the models themselves. The short course “ Introducing Multimodal Llama 3.2 ” by Amit Sangani, Senior Director of AI Partner Engineering at Meta, shows how to put these models to use. * Gemini Nano is the smallest version of the Gemini model family. * Adobe integ...

Gross domestic product, or GDP for short, is like the financial scoreboard of a country's economic game.  It tallies up the total market value of all the final goods and services made during a particular time period.  The formula to figure out this mega number:  GDP = Consumption + Investment + Government Spending + (Exports - Imports).  Courtesy: The Economist Courtesy: Visual Capitalist Top 15 Countries By GDP (1600-2019) - RankingCharts

This Week I Learned -  *  Gemini Code Assist can support you across key stages of the Software Development Life Cycle (SDLC) like design, build & test and deploy. * Similar to the original GitHub Copilot "AI pair programmer," Google's AI-powered code completion tool, Gemini Code Assist, will be available for free in Microsoft's Visual Studio Code editor until November 8, 2024. The Gemini Code Assist + Google Cloud Code extension can be found in the VS Code Marketplace .  * With over 7,000 languages and countless cultural differences, AI has the potential to foster global understanding. The latest Kaggle competition invites Gen AI practitioners to fine-tune Gemma 2 for a specific language or cultural context . * Fail fast, and learn faster to thrive in an AI-augmented world - The chances of failure are very high in AI projects. You don't want to play it safe, because you can't. * "If you're in an organization with 500+ employees and you don't ...

Mirabelle is a customized version of the powerful Datasette tool, specifically tailored for exploring the Open Food Facts database —a collaborative, free, and open resource of food products from around the globe. Originally created by Simon Wilson, Datasette allows users to discover patterns in data and share their findings effortlessly through interactive websites. It's built on top of SQLite, a lightweight database engine used in popular applications like Google Chrome, Firefox, iPhones, Android devices, and more. With Mirabelle, you can query the food product database through a form - If you have basic knowledge of SQL, you can easily dive into the Open Food Facts database via an intuitive, user-friendly interface and customize the queries -  Plus, it offers built-in features to generate simple line, bar, and scatter plot charts, making it a versatile tool for both data exploration and visualization. By using appropriate queries, the data can be refined to generate meaningful ...