NBA Fantasy Basketball Assistant

---

🏀 A full-stack AI application for fantasy basketball enthusiasts. 🏀

---

Overview

The NBA Fantasy Basketball Assistant is a full-stack AI application designed to provide in-depth analysis and actionable insights for fantasy basketball enthusiasts. Leveraging detailed NBA game statistics, this tool aims to enhance users' decision-making by predicting team performances, analyzing matchups, and offering personalized recommendations.

Core Features

📊 Team Performance Analysis

→ Historical Data Insights: Analyze historical data over the last nine seasons to predict future team performances.
→ Current Form: Calculate rolling averages of key statistics over recent games to determine current form and identify trends.

🏆 Matchup Analyzer

→ Historical Matchup Performance: Analyze historical matchups between teams to predict outcomes and evaluate matchup strengths and weaknesses.
→ Performance Trends Against Specific Opponents: Highlight performance trends against specific types of opponents (e.g., teams with strong defense or high-scoring offenses).

📝 Customizable Recommendations

→ User Criteria-Based Recommendations: Allow users to prioritize specific statistics and receive tailored recommendations.

---

Project Details

Development Progress:

This project is designed for continuous enhancement and improvement. Therefore, a chart has been added to track the development and completion progress of each project element, highlighting the future updates I plan to implement for improvement.

Component	Progress
App Interface (Full-Stack)	✅ Completed UI/UX Design Implementation ✅ Client successfully displays and interacts with server mock data ✅ Seamlessly implements dynamic internal page changes
Machine Learning Prediction Model	✅ Initial model complete with 63% accuracy ⚠️ Working to improve current accuracy
Integration of ML Results and Pandas Manipulation Data with Server	⚠️ In Progress

📅 Current Task 📅
Develop a JSON file that generates up-to-date performance and matchup analysis based on the mock data format.

Noteworthy Description Files:

ML-Model	ML-Model README.md file: Provides details and explanations behind the web scraping and predictor model training process
Client	Client README.md file: Provides details on navigating and utilizing the React App

Full Directory Tree:

nba-fantasy-assistant/
├── ML-model/
│   ├── README.md
│   ├── Create_NBADataset.ipynb   # Code for creating CSVs (Jupyter Notebook)
│   ├── Retrieve_NBAData.ipynb    # Web Scraping Code (Jupyter Notebook)
│   ├── NBA_PredictionModel1.ipynb # Base ML Model
│   ├── nba_data/
│   │   ├── .ipynb_checkpoints/
│   │   ├── scores/               # All individual box scores across seasons
│   │   ├── standings/            # All standings (by month) across seasons
│   │   ├── ...                   # Other miscellaneous csv files
├── client/
│   ├── public/
│   ├── src/
│   │   ├── components/
│   │   │   ├── Form.css
│   │   │   ├── Header.css
│   │   │   ├── Modal.css
│   │   │   ├── Modal.js
│   │   │   ├── NavButton.css
│   │   │   ├── NavButton.js
│   │   ├── images/               # All images used for app
│   │   ├── pages/
│   │   │   ├── Home.js           # Main (Home) Page
│   │   │   ├── Home.css
│   │   │   ├── TeamPerformanceAnalysis.js
│   │   │   ├── MatchupAnalyzer.js
│   │   │   ├── FantasyRecommendations.js
│   │   ├── App.js
│   │   ├── index.js
│   │   ├── index.css
│   ├── package.json
│   ├── README.md                # React App Explanation  
├── server/
│   ├── index.js
│   ├── package.json
├── README.md                    # Main Project File README
├── LICENSE

Tech Stack:

Other tools for ML Model: NumPy Pandas Scikit-learn BeautifulSoup

Running the Application:

Main Directory Command: cd NBA-Fantasy-Assistant

Front-End

1. Navigate to the client directory:

cd client

2. Install dependencies:

npm install

3. Start the React App:

npm start

Back-End

1. Navigate to the server directory:

cd server

2. Install dependencies:

npm install

2. Start the server:

node index.js

Open your browser and go to http://localhost:3000 to view the application.

---

This project is licensed under the MIT License.

Copyright (c) 2024 Naisha Sinha

---