A well structured and detailed guide to financial concepts and their underlying mathematical tools. Impressively comprehensive and featuring numerous templates of clean code.
An extensive and well written compendium that covers a range of methods for dimensionality reduction and outlier detection. Expertly designed; with great visuals and explanations.
This work is a great example of image data cleaning and quality checks with the help of the annoy library. It emphasises the importance of understanding your training data.
Exceptionally well structured and narrated, this musical experimentation learns from Chopin to write its own piano melodies using LSTMs. Note the stylish gifs and playable audio files.
"Mapping poverty around the world" by Ruta Sakalauskaite:
A geospatial exploration of poverty indices and the metrics that contribute to them. The well-designed folium maps gradually increase in information to paint a comprehensive picture.
"Starting point: Big Query and London Crime" by @WCanniford:
A narrated introduction to Google's Big Query powering the exploration of a crime dataset. The tools & SQL are well explained; beyond that the visuals help to understand the quirks of the data.
"Deep Sea Dive into Top 10% - Survival Guide" by @agodwin_p:
The famous Titanic starter challenge is always worth a look for creative content, such as this well illustrated and narrated end-to-end analysis featuring helpful infographics and references.
"Analyzing Editors Descriptions | Hidden Gems" by Thomas Konstantin:
Time to get meta: This work explores the Hidden Gems series, specifically the text and sentiment of my reviews, with great ideas, narration, and structure. And now it contains itself.
"Evolution of social complexity: A data analysis" by Muskan Jain:
This Notebook studies the changes in social complexity over time. It applies external diagrams to great effect, and features detailed interpretations of its findings.
"COVID-19 World Vaccination Progress" by Ivanna Chovhan:
A well organised Notebook which demonstrates how readability is drastically improved through section headers, compact code, and nuggets of interpretation and narration that accompany visuals.
"Forecast with N-BEATS || Interpretable model" by Gaétan Dubuc:
This work presents a detailed introduction on a neural network time series forecasting method, complete with applied examples. Note the clean structure and helpful visuals.
I'm well on track for my 500 @Kaggle hours. Got a bit carried away in March, with a few free weekends. Some of this work isn't public yet, but will be soon.
Competition wise, things are going less well. I've joined a few comps late, but my results aren't anything to write home (or write tweets) about, so far. No teaming up yet, either.
I've learnt a few new tricks, though; especially for imaging data. Hoping to build on those.
"RANZCR 1st Place Soluiton Cls Model (small ver.)" by Qishen Ha:
Another underrated 1st place competition notebook: this well-structured work demonstrates a part of the 2-stage segmentation + classification approach that won the recent imaging challenge.
A narrated introduction to using the Biopython library on a genome dataset. Note the way in which the code is enriched with detailed explanations and interpretations.