👋 Hi, I’m Fari @DataEden

😄 Pronouns: He/Him

---

👀 Interests

I’m deeply passionate about science, technology, and innovation! Here are a few fields I’m actively exploring and contributing to:

• 🌐 Artificial Intelligence & Machine Learning
• 🖥️ Software Development
• 📊 Data Science & Analytics
• ☁️ Cloud Computing
• 🔐 Cybersecurity
• 🌍 Full-Stack Web Development
• 📈 Statistics & Mathematics

---

🌱 Currently Learning

• C Programming Language
• Java Programming
• AI Programming with Python

---

😎 About This Repository

• This repository reflects my journey in data science and machine learning.
• It includes projects, learning resources, and hands-on experiences.
• I aim to share valuable insights while pushing boundaries in tech.

---

💞️ Looking to Collaborate On

• AI/ML Projects
• Cloud-Based Solutions (soon to achieve AWS Solutions Architect Associate Certification 🎉)
• Cutting-edge software development and advanced training in AI/ML

---

📫 Contact Me

• Email: datainsidedata[at]gmail[dot]com

---

🤩 Fun Facts & Goals

• I'm on a continuous journey of lifelong learning and discovery.
• Favorite motto: "Be curious. Be persistent. Build amazing things."
• Favorite word, Assiduous...
• Happy coding and learning! 🚀

---

Machine Learning Project

Part of the AWS/Udacity AI Programming with Python Nanodegree

Overview:

• This project is part of the AWS/Udacity AI Programming with Python Nanodegree, initially designed by Computer Scientist Jenner Staab. The main focus is to develop an image classification pipeline that identifies whether or not images are of dogs, classifies their breed, and evaluates the performance of three CNN models: ResNet, AlexNet, and VGG.
• While the focus is on image classification, the lessons learned and skills gained provide practical insights that extend and or apply to fields like Marketing Analytics and Data Science, enabling AI/ML to enhance decision-making and generate actionable insights.

---

Objectives:

1. Classify Images: Determine whether the provided images are of dogs and, if so, classify their breed.
2. Model Evaluation: Compare and assess the performance of the ResNet, AlexNet, and VGG models.
3. Resource Optimization: Evaluate time and resource requirements for each model and determine if alternative solutions could yield similar results efficiently.
4. Extend Learning: Apply insights from classification techniques to projects in data-driven marketing and analytics.

---

Project Features :

• Programming Languages: Python, SQL.
• Tools Used:
  • Visual Studio Code with Anaconda.
  • scikit-learn for machine learning workflows.
  • Jupyter Notebooks for interactive analysis
• Learning Outcomes:
  • Gained hands-on experience in image classification.
  • Explored generative AI and predictive modeling techniques for broader analytics goals.
  • Improved understanding of time-efficient algorithms for large-scale data handling.

---

Program Breakdown:

Key Tasks:

1. Timing Code: Measure program runtime and resource usage.
2. Command Line Arguments: Retrieve inputs dynamically using argparse.
3. Pet Image Labels: Use filenames to generate accurate image labels.
4. Classifying Images: Run CNN models to classify images and compare results.
5. Result Analysis: Calculate accuracy and evaluate model performances.

---

Highlights

• Building an image classification pipeline using CNN models like ResNet, AlexNet, and VGG.
• Analyzing model performance to identify areas for optimization.
• Exploring the applications of generative AI in marketing and predictive modeling.

---

Learning Goals

Technical Goals

• Master machine learning workflows for classification and prediction.
• Gain expertise with tools like Python, scikit-learn, and Jupyter.

Marketing Analytics Goals

• Explore how data science methodologies can enhance marketing strategies.
• Apply lessons from this classification project to domains like customer segmentation and predictive analytics.

---

How to Use

---

Project Workflow:

1. Prepare Environment:

   git clone https://github.com/DataEden/DataScience.git

   • Set up your environment by following the instructions provided in the Readme.md file to install all required dependencies.
2. Run the project:
   • Execute the classification pipeline scripts with python check_images.py.
   • There is a FAQ section along with other resources provided in notes.
   • Use provided CNN models: ResNet, AlexNet, and VGG.
3. Analyze Results:
   • Use Jupyter Notebooks to visualize and evaluate performance metrics.
   • Compare accuracy and runtime for each model.
4. Iterate and Improve:
   • Adjust algorithms and refine processes to improve performance.

Contribute

This project is open for collaboration! Here’s how you can contribute:

• Fork this repository to suggest improvements or extend its features.
• Open issues to report bugs or request enhancements.
• Submit pull requests with your contributions.

Acknowledgments

• This project was designed by Computer Scientist Jenner S. as part of the AWS/Udacity AI Programming with Python Nanodegree.
• Grateful for the opportunity to learn cutting-edge technologies and contribute to real-world problem-solving.

Future Directions:

This project is just the beginning of an exciting journey in AI, ML, and Data Science: I’m exploring ways to extend this project to marketing data science, including:

• Marketing Analytics:
  • Apply classification techniques for customer segmentation.
  • Build predictive models for campaign optimization.
  • Incorporating and leveraging generative AI tools for innovative marketing analytics and insights.
• Advanced ML Applications:
  • Explore transfer learning to improve model accuracy.
  • Incorporate real-time classification pipelines in broader applications.