Project Title: Crop Yield Prediction through Data Science
Objective:
This project aimed to analyze agricultural data and apply machine learning techniques to predict crop yields, with a particular focus on the agricultural dynamics of the Texas Panhandle. By identifying key factors influencing crop productivity, the project provided insights to optimize farming practices, mitigate risks, and support food security.
Overview:
The Data Science Workshop, hosted by the National Wind Institute at Texas Tech University and funded by the Texas Workforce Commission’s Wagner Peyser Grant, equipped participants with data-driven approaches to tackle regional challenges. The focus was on renewable energy, agriculture, and water resource management, with crop yield prediction as a critical component.
Crop yield prediction leverages advanced analytics to address agricultural challenges in the Texas Panhandle. This project trained high school participants to integrate datasets and use machine learning algorithms to gain actionable insights for improving farming practices in a sustainable way.
Key Activities:
- Data Integration: Merged datasets on crop yields, rainfall, temperature, and pesticide usage for a comprehensive analysis of factors affecting agricultural outcomes.
- Modeling Approach: Implemented machine learning algorithms, such as Decision Tree Regressor, to predict yields for crops like maize, potatoes, and cassava.
- Insights Gained: Identified key factors, including rainfall, temperature, and pesticide application, as critical determinants of crop productivity.
Impact:
- Farm Optimization: Helps farmers use predictive insights to allocate resources more efficiently and increase crop productivity.
- Risk Mitigation: Identifies and mitigates risks due to environmental factors, such as insufficient rainfall or excessive pesticide use.
- Educational Value: Engages students and stakeholders in using data science to solve pressing agricultural problems.
Why It Matters to Me:
This project highlights the power of interdisciplinary problem-solving in addressing critical regional challenges. By blending data science with agriculture, I aim to contribute to sustainable solutions for food security, ensuring the Texas Panhandle’s agricultural community thrives in the face of environmental and economic challenges.
Technology Stack:
- Machine Learning Models: Decision Tree Regressor for yield prediction.
- Programming Language: Python, leveraging libraries like Pandas, NumPy, and Scikit-learn for data analysis and modeling.
- Visualization Tools: Matplotlib and Seaborn for generating insights from data.
Project Title: Object-Oriented Programming Algorithm for Las Vegas Casino Games
Objective:
This project aimed to develop a Python-based algorithm using object-oriented programming principles to simulate two popular Las Vegas casino games—Blackjack and Quarter Slots. The algorithm allows users to choose their game, input their bet, and interact with a dynamic system that mimics real casino gameplay.
Overview:
As part of an Object-Oriented Programming class, this project focused on designing an interactive and engaging casino simulation. The system incorporates core programming concepts like encapsulation, inheritance, and polymorphism to create a modular and scalable codebase. By offering an immersive user experience, the algorithm allows users to explore probability, game rules, and betting strategies in a simulated environment.
The project highlights the versatility of object-oriented programming in creating practical, real-world applications while providing a fun and educational experience.
Key Activities:
- Game Selection and Betting: Designed an interactive menu that lets users choose between Blackjack and Quarter Slots and input their bets.
- Blackjack Implementation: Developed a Blackjack game using Python classes to represent cards, decks, players, and dealers. Integrated logic for card drawing, point calculation, and game rules such as “hit” or “stand.”
- Quarter Slots Implementation: Simulated slot machine gameplay with randomized reels and payouts. Included a dynamic betting system where users can adjust their stakes and receive winnings based on matching reel combinations.
- User Feedback and Results: Provided real-time feedback to users on wins, losses, and account balances after each round.
Impact:
This project demonstrates how object-oriented programming can be applied to real-world scenarios. By simulating casino games, the project introduces users to probability, strategic decision-making, and the structure of interactive software. It also enhances programming skills by emphasizing modular design and code reusability.
Applications:
- Educational Tool: Serves as a learning aid for understanding probability and game theory.
- Programming Practice: Offers a hands-on way to apply object-oriented principles to real-world problems.
- Entertainment: Provides a fun and engaging experience for users interested in casino games.
Why It Matters to Me:
As a student passionate about programming, this project allowed me to combine technical skills with creativity. It demonstrated how object-oriented programming could be used to build interactive applications while exploring the mathematical and strategic aspects of casino games.
Technology Stack:
- Programming Language: Python
- Core Concepts: Encapsulation, inheritance, and polymorphism in an object-oriented design.
- Libraries: Random module for simulating randomness in slots and card shuffling.