{"id":24696744,"url":"https://github.com/ercodex/predicting-new-medicines-with-sgd-classifier","last_synced_at":"2026-04-14T01:30:55.217Z","repository":{"id":274316410,"uuid":"922534390","full_name":"ercodex/Predicting-New-Medicines-with-SGD-Classifier","owner":"ercodex","description":"\"Shittiest Model of the Competition\" award winner!","archived":false,"fork":false,"pushed_at":"2025-01-26T14:31:37.000Z","size":32,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-03T02:06:00.858Z","etag":null,"topics":["classifier-model","dask","kaggle-competition","machine-learning","numpy","python","scikit-learn"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ercodex.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-26T13:29:20.000Z","updated_at":"2025-01-26T14:33:44.000Z","dependencies_parsed_at":"2025-01-26T15:20:55.799Z","dependency_job_id":"32d5c0b8-dae5-49b1-8b15-bf99b2f6afd3","html_url":"https://github.com/ercodex/Predicting-New-Medicines-with-SGD-Classifier","commit_stats":null,"previous_names":["ercodex/predicting-new-medicines-with-random-forest-classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ercodex%2FPredicting-New-Medicines-with-SGD-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ercodex%2FPredicting-New-Medicines-with-SGD-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ercodex%2FPredicting-New-Medicines-with-SGD-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ercodex%2FPredicting-New-Medicines-with-SGD-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ercodex","download_url":"https://codeload.github.com/ercodex/Predicting-New-Medicines-with-SGD-Classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244901102,"owners_count":20528858,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["classifier-model","dask","kaggle-competition","machine-learning","numpy","python","scikit-learn"],"created_at":"2025-01-27T02:03:05.637Z","updated_at":"2026-04-14T01:30:55.171Z","avatar_url":"https://github.com/ercodex.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# *If you’re looking for a story of triumph, you’re in the wrong place. If you want to see how grit and curiosity can turn failures into lessons, welcome aboard!*\n\n# \"Shittiest Model of the Competition\" Award Winner!\n- This model was my submission for the Kaggle competition **\"NeurIPS 2024 - Predict New Medicines with BELKA\"**.\n\n## Story\n- Fresh off completing a machine learning course on Udemy, I thought, \"Why not test my skills?\" So I jumped into this competition... solo. Spoiler alert: the DL veterans crushed me.  \n- Here's what I had: 8 GB of DDR4 RAM, a trusty GTX 1650 GPU, minimal ML experience, zero knowledge of neural networks, and, of course, my unmatched stubbornness.\n\n## What I Did\n1. **Understanding the Data**  \n   - The dataset was biological and massive: 3 protein targets, millions of molecule sequences generated by ~300 molecules. The task? Predict which molecules are likely to bind to these targets. Cool concept, overwhelming data.  \n\n2. **The 50 GB Challenge**  \n   - Yep, 50 GB of data. My RAM said, \"Nope.\" I tried compressing, transforming, mapping... eventually shrunk it to 35 GB. Still not enough.  \n   - A college instructor gave me a golden tip: \"If they can zip the download file to 5 GB for competitors, you can figure something out.\" Inspired, I spent **2 months** creating mapping tables, using the less-space-consuming data types , and trimming down data to a manageable 15 GB. Turns out, others in the discussion forum were struggling too.\n\n3. **Building the Model**  \n   - With the clock ticking, I went for the two most practical option for me: **Random Forest Classifier**, or **Stochastic Gradient Descent Classifier**. No fancy hyperparameter tuning, there was barely any time.\n   - Training posed another hustle. The dataset was too large for my setup, and NumPy just didn’t cut it. Enter **Dask library**, the lifesaver! It handled chunked training like a charm, and I managed to train, predict, and submit just before the deadline.\n   - Each training session nearly took 8 hours. My laptop was working like a full-time employee.\n\n4. **The Results**  \n   - Final ranking: **1925/1952**. Sure, I wasn’t at the top, but the journey taught me invaluable lessons in data handling, persistence, and problem-solving. Plus, it was hilarious!\n\n5. **Special Thanks**\n   - A shoutout to my instructor who guide the way to the model. **Not turning away an eager student can change many things.**  \n   - A shoutout to **ChatGPT**, which sped up my problem-solving process. While I didn’t use it to code the model, it served as a trusted guide whenever I got stuck.\n\n## What I Learned\n- Learned techniques to handle **large datasets**.  \n- Discovered the **Dask** library.\n- Learned about **SGD Classifier**\n- Gained hands-on experience with .csv and .parquet formats.\n- SMILES format for representing biological data.\n- Gained practical experience in **data visualization** and **feature engineering**.  \n- Realized I need to start training myself in **Deep Learning**.  \n- Built connections with instructors by showcasing my efforts.  \n- Most importantly, I had fun and grew as a Computer Engineering student.\n\n**There is a picture about what the name of training data looked like at the end. It's pretty funny! Check it out.** \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fercodex%2Fpredicting-new-medicines-with-sgd-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fercodex%2Fpredicting-new-medicines-with-sgd-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fercodex%2Fpredicting-new-medicines-with-sgd-classifier/lists"}