Published inLevel Up Coding·PinnedMember-onlyWanna Break into Data Science in 2024? Think Twice!It won’t be smooth sailing for you — I am a refugee. I didn’t come from a background in data science, computer science, math, or statistics. But I’ve successfully transitioned into a data science job. Some friends wanted to do the same and asked me for advice. I’ve always begun with “Are you sure?”. Table of Contents · What…Data Science11 min readData Science11 min read
Published inLevel Up Coding·Oct 9Member-onlyHow to Write Documentation for Your Data Science Projects Using MkDocsFrom logging, typing, and docstring, to beautiful documentation within minutes — Imagine you wanted to work on an interesting project online only to find yourself confused about where to start. Or worse, you revisited an old project of yours but had no idea what you’d done. A new intern asked you about an ongoing team project but you needed to explain…Data Science15 min readData Science15 min read
Published inTowards Data Science·Jun 4Member-onlyOkay, You’ve Trained the Best Machine Learning Model. What’s Next?An MLOps project beyond modeling in Jupyter Notebook — Table of Contents · Initialize a Repository · Migrate Your Codebase ∘ config/config.py ∘ config/args.json ∘ tagolym/utils.py ∘ tagolym/data.py ∘ tagolym/train.py ∘ tagolym/predict.py ∘ tagolym/evaluate.py ∘ tagolym/main.py …Data Science18 min readData Science18 min read
Published inLevel Up Coding·Apr 3Member-only4 Simple Steps to Quickly Create an Interactive Dashboard for Network Graph Data VisualizationA mini project to deploy your data insight using “dash” and “visdcc” — Table of Contents · What is Graph Data? · Step 1. Define the Project Background 1. Search 2. Peek 3. Play · Step 2. Choose the Tech Stack ∘ Data wrangling ∘ Graph visualization ∘ Web hosting · Step 3. Coding Time! ∘ To start off, let’s…Data Science10 min readData Science10 min read
Published inLevel Up Coding·Feb 14Member-onlyWhat are the Most Popular Medium Tags Right Now? I Built a Dashboard to Find OutYou’ll never find outdated answers again — Table of Contents · Exploring Medium · Building the Dashboard 1. Search 2. Peek 3. Play · Now, It's Your Turn The year 2023 began. I wanted to write a fresh story on Medium, you know, the next big thing and whatnot. …Medium6 min readMedium6 min read
Published inTowards Data Science·Nov 30, 2022Member-onlyA Real-World Case Study of Using Git Commands as a Data ScientistComplete with Branch Illustration — You’re a data scientist. As data science is becoming more and more mature every day, software engineering practices begin creeping in. You are forced to venture out of your local jupyter notebooks and meet other data scientists in the wild to build a great product. To help you out with…Data Science11 min readData Science11 min read
Published inTowards Data Science·Oct 11, 2022Member-onlyBeautifully Illustrated: NLP Models from RNN to TransformerExplaining their complex mathematical formula with working diagrams — Table of Contents · Recurrent Neural Networks (RNN) ∘ Vanilla RNN ∘ Long Short-term Memory (LSTM) ∘ Gated Recurrent Unit (GRU) · RNN Architectures · Attention ∘ Seq2seq with Attention ∘ Self-attention ∘ Multi-head Attention · Transformer ∘ Step 1. Adding Positional Encoding to Word Embeddings ∘ Step…Data Science12 min readData Science12 min read
Published inLevel Up Coding·Sep 12, 2022Member-onlyGloVe and fastText Clearly Explained: Extracting Features from Text DataHow are they better than Word2Vec? — Table of Contents 🧤 GloVe ⚙️ The Basics 🧮 Cost Function Derivation 🔮 Final Prediction 🪙 Advantages & Limitations ⏩ fastText 📚 Skip-gram reviewed 📈 Improving Skip-gram 🆚 fastText vs Word2Vec 🚀 Summary In most cases, Word2Vec embedding is better than the bag of words representation of texts by allowing…Machine Learning11 min readMachine Learning11 min read
Published inTowards Data Science·Aug 30, 2022Member-onlyAll You Need to Know About Bag of Words and Word2Vec — Text Feature ExtractionWhy Word2Vec is better, and why it’s not good enough — While image data is straightforward to be used by deep learning models (RGB value as the input), this is not the case for text data. Deep learning models only work on numbers, not sequences of symbols like texts. So, you need a way to somehow extract meaningful numerical feature vectors…Data Science9 min readData Science9 min read
Published inTowards Data Science·Aug 22, 2022Member-only5 Popular CNN Architectures Clearly Explained and VisualizedAnd why the heck does Inception look like a trident?! — Table of Contents · Fully Connected Layer and Activation Function · Convolution and Pooling Layer · Normalization Layer ∘ Local Response Normalization ∘ Batch Normalization · 5 Most Well-Known CNN Architectures Visualized ∘ LeNet-5 ∘ AlexNet ∘ VGG-16 ∘ Inception-v1 ∘ ResNet-50 · Wrapping Up The introduction of LeNet in…Machine Learning13 min readMachine Learning13 min read
