{"id":23582438,"url":"https://github.com/parag000/gpu-accelerated-ml-for-big-data-processing","last_synced_at":"2026-05-03T12:35:22.493Z","repository":{"id":261277473,"uuid":"883828467","full_name":"Parag000/GPU-Accelerated-ML-For-Big-Data-Processing","owner":"Parag000","description":"This project predicts the \"Scariest Monster\" using a dataset of 12 million entries and 106 features. Utilizing GPU-accelerated processing and the Random Forest Regressor using the Nvidia Rapids API. The goal is to minimize RMSE for accurate predictions","archived":false,"fork":false,"pushed_at":"2024-11-05T17:50:11.000Z","size":303,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-18T02:44:14.035Z","etag":null,"topics":["cudf","cuml","python3","rapidsai","sklearn"],"latest_commit_sha":null,"homepage":"https://colab.research.google.com/drive/1N9I19hw8kbnNC2j3QmP5nTD5GbgGF5qW?usp=sharing","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Parag000.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-11-05T16:37:10.000Z","updated_at":"2025-01-18T19:33:09.000Z","dependencies_parsed_at":"2024-11-05T17:45:03.471Z","dependency_job_id":"3b71618c-0574-4529-94ad-5600996691d9","html_url":"https://github.com/Parag000/GPU-Accelerated-ML-For-Big-Data-Processing","commit_stats":null,"previous_names":["parag000/nvidia-data-science-competition","parag000/gpu-accelerated-ml-for-big-data-processing"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Parag000%2FGPU-Accelerated-ML-For-Big-Data-Processing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Parag000%2FGPU-Accelerated-ML-For-Big-Data-Processing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Parag000%2FGPU-Accelerated-ML-For-Big-Data-Processing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Parag000%2FGPU-Accelerated-ML-For-Big-Data-Processing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Parag000","download_url":"https://codeload.github.com/Parag000/GPU-Accelerated-ML-For-Big-Data-Processing/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239399808,"owners_count":19632021,"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":["cudf","cuml","python3","rapidsai","sklearn"],"created_at":"2024-12-27T01:09:27.533Z","updated_at":"2026-05-03T12:35:22.426Z","avatar_url":"https://github.com/Parag000.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 👻 Predicting the Scariest Monster - Nvidia Hackathon\n\n## Link to Colab Notebook:\n[Open this notebook in Google Colab](https://colab.research.google.com/drive/1N9I19hw8kbnNC2j3QmP5nTD5GbgGF5qW?usp=sharing)\n\n## Our Submission Scores\n![Submission Score](https://github.com/Parag000/Nvidia-Data-Science-Competition/blob/main/submisssion-score.png?raw=true)\n\n## Project Overview\n\nThis project presents a solution for the **ODSC 2024 NVIDIA Hackathon**, where data scientists are challenged to predict the \"Scariest Monster\" using a massive dataset filled with 12 million entries, each described by 106 anonymous features. The ultimate goal is to forecast the number of votes each monster received in a global terror poll, utilizing GPU-accelerated data processing and machine learning techniques.\n\n## Dataset\n\nThe competition dataset includes:\n\n- **12 million monster entries**\n- **106 anonymous features** (a mix of categorical and numerical)\n- **Target variable 'y'**: Number of votes each monster received in the global terror poll\n- **Dataset size**: Approximately **8-10GB**\n\n## Approach\n\nOur approach to tackling this challenge involves the following steps:\n\n1. **Data Loading and Preprocessing**: \n   - Loading the data using **cuDF** (RAPIDS NVIDIA API) for GPU-accelerated processing.\n   - Performing basic **Exploratory Data Analysis (EDA)** to understand the dataset.\n   - Dropping categorical columns to avoid creating sparse matrices.\n   - Applying **mean imputation** for numerical columns.\n   - Removing outliers and performing **robust normalization** for stability.\n\n2. **Memory-Efficient Train-Test Split**:\n   - Creating a custom train-test split method to handle memory constraints effectively.\n   - Using a random shuffled column for efficient data shuffling and splitting.\n\n3. **Model Training**:\n   - Implementing a **Random Forest Regressor** using the RAPIDS **cuML** library for GPU-accelerated processing.\n\n4. **Post-processing**:\n   - Applying **inverse robust scaling** to calculate the final RMSE value.\n\n5. **Prediction and Submission**:\n   - Generating predictions on the test set.\n   - Preparing the submission file in accordance with the competition guidelines.\n\n## Technologies Used\n\n- **Used A100 hardware acceleration**\n- **Python 3.x**\n- **RAPIDS cuDF** for GPU-accelerated data processing\n- **RAPIDS cuML** for GPU-accelerated machine learning\n- **Scikit-learn** for preprocessing and metrics\n- **Google Colab Notebook** for interactive development\n\n## Results\n\nThe model's performance is evaluated based on **Root Mean Squared Error (RMSE)**, with lower scores indicating better performance.\n\n\n## Getting Started\n\n1. **Clone this repository**:\n   ```bash\n   https://github.com/Parag000/Nvidia-Data-Science-Competition.git\n\n\n## Leaderboard\n![Leaderboard](https://github.com/Parag000/Nvidia-Data-Science-Competition/blob/main/leaderboard.png)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparag000%2Fgpu-accelerated-ml-for-big-data-processing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fparag000%2Fgpu-accelerated-ml-for-big-data-processing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparag000%2Fgpu-accelerated-ml-for-big-data-processing/lists"}