{"id":25193819,"url":"https://github.com/angchekar28/valorant-gameplay-analysis","last_synced_at":"2026-04-12T22:05:27.777Z","repository":{"id":275821528,"uuid":"927301292","full_name":"angchekar28/Valorant-Gameplay-Analysis","owner":"angchekar28","description":"This project analyzes Valorant gameplay data to understand key factors affecting match outcomes. It compares various machine learning models to predict player performance, rank classification, and match success.","archived":false,"fork":false,"pushed_at":"2025-02-25T06:03:03.000Z","size":467,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-25T06:30:39.890Z","etag":null,"topics":["data-analysis","data-science","data-visualization","exploratory-data-analysis","jupyter-notebook","machine-learning","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/angchekar28.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":"2025-02-04T18:26:05.000Z","updated_at":"2025-02-25T06:03:06.000Z","dependencies_parsed_at":"2025-02-04T19:35:13.542Z","dependency_job_id":"72c60a4b-5eeb-4c63-aadc-67764a610e5b","html_url":"https://github.com/angchekar28/Valorant-Gameplay-Analysis","commit_stats":null,"previous_names":["angchekar28/valorant-gameplay-analysis"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FValorant-Gameplay-Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FValorant-Gameplay-Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FValorant-Gameplay-Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angchekar28%2FValorant-Gameplay-Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/angchekar28","download_url":"https://codeload.github.com/angchekar28/Valorant-Gameplay-Analysis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247187861,"owners_count":20898391,"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":["data-analysis","data-science","data-visualization","exploratory-data-analysis","jupyter-notebook","machine-learning","python"],"created_at":"2025-02-09T23:22:40.604Z","updated_at":"2025-10-30T05:46:24.329Z","avatar_url":"https://github.com/angchekar28.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📌 Valorant Gameplay Analysis \u0026 Model Comparison\n\n## 📝 Project Overview\nThis project analyzes Valorant gameplay data and evaluates different machine learning models to predict player performance. The goal is to understand key factors that influence match outcomes.\n\n## 🎮 Dataset\n- **Source:** Valorant match statistics  \n- **Columns:**  \n  - `Player ID`, `Agent`, `KDA`, `Win/Loss`, `Map`, `Rank`, `Headshot %`, `Damage per Round`  \n  - `Rounds Won`, `Rounds Lost`, `Economy`, `Spike Plants`, `Spike Defuses`  \n\n## ⚙️ Methodology\n1. **Data Preprocessing**  \n   - Handling missing values  \n   - Label encoding the output  \n   - Encoding categorical data (e.g., Agents, Maps)  \n\n2. **Exploratory Data Analysis (EDA)**  \n   - Distribution of player statistics  \n   - Impact of different agents on performance  \n   - Correlation between rank and gameplay metrics  \n   - Implemented for loops to streamline the plotting of Countplots, Histplots, and Barplots across multiple features instead of using separate blocks  \n\n3. **Model Implementation**  \n   - Compared XGBoost, Random Forest, and CatBoost using a for loop for efficiency  \n   - Performed hyperparameter tuning and k-fold cross-validation for better model performance  \n\n4. **Model Evaluation**  \n   - Accuracy and precision metrics  \n   - Classification Study \n   - Feature Importance analysis (Not Updated in Code. Basic Fearure Engineering Was Done)\n   - Previously, Random Forest had the best accuracy at 78 percent, but after optimization, CatBoost achieved 85 percent accuracy.  \n\n5. **Dimensionality Reduction**  \n   - Attempted dimensionality reduction using LDA, but it did not provide significant improvements. Hence, it was not included in the final project scope.\n\n## 🏆 Conclusion\n- CatBoost demonstrated the highest accuracy and is the most suitable model for this dataset  \n- Hyperparameter tuning played a crucial role in enhancing performance, highlighting the importance of fine-tuning machine learning models  \n- Dimensionality reduction methods like LDA may not always be beneficial, and their effectiveness depends on the dataset and feature distribution (Removed from code)  \n- Using for loops for visualization and model comparisons increased efficiency and improved code readability  \n- Future improvements could include testing additional models, feature engineering, and exploring alternative dimensionality reduction techniques  \n\n## 🚀 Feature Scaling \u0026 Deep Learning Experiment\nI have performed feature scaling and deep learning separately in a Google Colab notebook. However, the results did not show a significant improvement nor outperformed CatBoost's accuracy of 85 percent.  \nI would love to hear your suggestions on improving the model performance.  \n\n## 🛠️ Installation \u0026 Usage\n```bash\n# Install dependencies\npip install pandas numpy matplotlib seaborn scikit-learn\n\n# Clone the repository\ngit clone \u003crepo_url\u003e\ncd \u003crepo_folder\u003e\n\n# Open Jupyter Notebook\njupyter notebook valorant-analysis-models-comparison.ipynb\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangchekar28%2Fvalorant-gameplay-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fangchekar28%2Fvalorant-gameplay-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangchekar28%2Fvalorant-gameplay-analysis/lists"}