Maria Mouschoutzi, Author at Towards Data Science https://towardsdatascience.com Publish AI, ML & data-science insights to a global community of data professionals. Fri, 11 Jul 2025 17:57:06 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.1 https://towardsdatascience.com/wp-content/uploads/2025/02/cropped-Favicon-32x32.png Maria Mouschoutzi, Author at Towards Data Science https://towardsdatascience.com 32 32 Hitchhiker’s Guide to RAG: From Tiny Files to Tolstoy with OpenAI’s API and LangChain https://towardsdatascience.com/hitchhikers-guide-to-rag-from-tiny-files-to-tolstoy-with-openais-api-and-langchain/ Fri, 11 Jul 2025 17:56:46 +0000 https://towardsdatascience.com/?p=606560 Scaling a simple RAG pipeline from simple notes to full books

The post Hitchhiker’s Guide to RAG: From Tiny Files to Tolstoy with OpenAI’s API and LangChain appeared first on Towards Data Science.

]]> Hitchhiker’s Guide to RAG with ChatGPT API and LangChain https://towardsdatascience.com/hitchhikers-guide-to-rag-with-chatgpt-api-and-langchain/ Thu, 26 Jun 2025 18:18:26 +0000 https://towardsdatascience.com/?p=606432 Build a simple Python RAG pipeline using your local files as context

The post Hitchhiker’s Guide to RAG with ChatGPT API and LangChain appeared first on Towards Data Science.

]]> Water Cooler Small Talk, Ep 7: Anscombe’s Quartet and the Datasaurus https://towardsdatascience.com/water-cooler-small-talk-ep-7-anscombes-quartet-and-the-datasaurus-09a143400320/ Mon, 27 Jan 2025 17:52:11 +0000 https://towardsdatascience.com/water-cooler-small-talk-ep-7-anscombes-quartet-and-the-datasaurus-09a143400320/ Why descriptive statistics aren't enough and plotting your data is always essential

The post Water Cooler Small Talk, Ep 7: Anscombe’s Quartet and the Datasaurus appeared first on Towards Data Science.

]]> Water Cooler Small Talk, Ep 6: Benford’s Law https://towardsdatascience.com/water-cooler-small-talk-benfords-law-a1c12419e773/ Wed, 15 Jan 2025 19:02:01 +0000 https://towardsdatascience.com/water-cooler-small-talk-benfords-law-a1c12419e773/ A look into the strange first digit distribution of naturally occurring datasets

The post Water Cooler Small Talk, Ep 6: Benford’s Law appeared first on Towards Data Science.

]]> Water Cooler Small Talk: Simpson’s Paradox https://towardsdatascience.com/water-cooler-small-talk-simpsons-paradox-caf98151db0e/ Fri, 29 Nov 2024 16:02:09 +0000 https://towardsdatascience.com/water-cooler-small-talk-simpsons-paradox-caf98151db0e/ Is your data tricking you? What can you do about it?

The post Water Cooler Small Talk: Simpson’s Paradox appeared first on Towards Data Science.

]]> Water Cooler Small Talk: Why Does the Monty Hall Problem Still Bother Us? 🐐🚗 https://towardsdatascience.com/water-cooler-small-talk-why-does-the-monty-hall-problem-still-bother-us-cc50d906522c/ Wed, 20 Nov 2024 13:02:12 +0000 https://towardsdatascience.com/water-cooler-small-talk-why-does-the-monty-hall-problem-still-bother-us-cc50d906522c/ A look at the counterintuitive mathematics of game show puzzles

The post Water Cooler Small Talk: Why Does the Monty Hall Problem Still Bother Us? 🐐🚗 appeared first on Towards Data Science.

]]> Les Miserables Social Network Analysis Using Marimo Notebooks and the NetworkX Python library🕊️⚔️ https://towardsdatascience.com/les-miserables-social-network-analysis-using-marimo-notebooks-and-the-networkx-python-library-%ef%b8%8f-%ef%b8%8f-3f433216412f/ Thu, 31 Oct 2024 07:02:24 +0000 https://towardsdatascience.com/les-miserables-social-network-analysis-using-marimo-notebooks-and-the-networkx-python-library-%ef%b8%8f-%ef%b8%8f-3f433216412f/ Build a Marimo notebook using NetworkX Python library, uncovering the hidden structures in Victor Hugo's masterpiece

The post Les Miserables Social Network Analysis Using Marimo Notebooks and the NetworkX Python library🕊️⚔️ appeared first on Towards Data Science.

]]> Water Cooler Small Talk: The Birthday Paradox 🎂🎉 https://towardsdatascience.com/water-cooler-small-talk-the-birthday-paradox-94ea294502c7/ Wed, 25 Sep 2024 05:09:11 +0000 https://towardsdatascience.com/water-cooler-small-talk-the-birthday-paradox-94ea294502c7/ A look at the counterintuitive mathematics of shared birthdays

The post Water Cooler Small Talk: The Birthday Paradox 🎂🎉 appeared first on Towards Data Science.

]]> Water Cooler Small Talk: Gambler’s Fallacy and Ruin https://towardsdatascience.com/water-cooler-small-talk-gamblers-fallacy-and-ruin-3f882707fd19/ Thu, 12 Sep 2024 17:46:33 +0000 https://towardsdatascience.com/water-cooler-small-talk-gamblers-fallacy-and-ruin-3f882707fd19/ An intuitive and thorough explanation of gambling, luck, and risk to keep you from looking foolish

The post Water Cooler Small Talk: Gambler’s Fallacy and Ruin appeared first on Towards Data Science.

]]> The Price of Gold: Is Olympic Success Reserved for the Wealthy?🥇 https://towardsdatascience.com/the-price-of-gold-is-olympic-success-reserved-for-the-wealthy-adade0233d61/ Sat, 07 Sep 2024 05:36:22 +0000 https://towardsdatascience.com/the-price-of-gold-is-olympic-success-reserved-for-the-wealthy-adade0233d61/ Analyzing 30 years of Olympic Games medals distribution and national wealth indicators

The post The Price of Gold: Is Olympic Success Reserved for the Wealthy?🥇 appeared first on Towards Data Science.

]]> Was Michael Scott the World’s Best Boss? https://towardsdatascience.com/was-michael-scott-the-worlds-best-boss-e5fd26074061/ Mon, 29 Jul 2024 09:13:13 +0000 https://towardsdatascience.com/was-michael-scott-the-worlds-best-boss-e5fd26074061/ Sentiment analysis of 'The Office' TV series using SchrutePy, NLTK and Hugging Face Transformers 🤗

The post Was Michael Scott the World’s Best Boss? appeared first on Towards Data Science.

]]> How Many Pokemon Fit? https://towardsdatascience.com/how-many-pokemon-fit-84f812c0387e/ Wed, 12 Jun 2024 17:35:40 +0000 https://towardsdatascience.com/how-many-pokemon-fit-84f812c0387e/ Finding the best Pokemon team by modeling and solving a knapsack problem with PokeAPI and PuLP optimization Python library

The post How Many Pokemon Fit? appeared first on Towards Data Science.

]]> From Data to Dashboard: Visualizing the Ancient Maritime Silk Road with Dash Leaflet and SeaRoute… https://towardsdatascience.com/from-data-to-dashboard-visualizing-the-ancient-maritime-silk-road-with-dash-leaflet-and-searoute-ac8a521ac4e9/ Wed, 22 May 2024 16:56:44 +0000 https://towardsdatascience.com/from-data-to-dashboard-visualizing-the-ancient-maritime-silk-road-with-dash-leaflet-and-searoute-ac8a521ac4e9/ Build an interactive map visualization displaying the shortest path between two points at sea within the Python Dash Framework

The post From Data to Dashboard: Visualizing the Ancient Maritime Silk Road with Dash Leaflet and SeaRoute… appeared first on Towards Data Science.

]]>