Excited to share my beginner's journey through building an End to End Machine Learning Project!

To have a proper documentation of the codes used in this project, you may consider visiting my GitHub: [ Ссылка ]

Find me on LinkedIn: [ Ссылка ]

I am truly grateful to @krishnaik06 who guided me along the away. I wonder how much he is dedicated to teach AI. Consider watching his video for this project: [ Ссылка ]

Here's a quick walkthrough of the steps I followed:

Create a GitHub Repository:
- by creating a GitHub repository for my project to keep track of code changes and collaborate with others.

Initialize Git:
- Initialized Git in my current working directory to start version controlling my project.

Add Repository with Local Folder:
- Added the GitHub repository as a remote origin for my local folder to sync changes between local and remote repositories.

Create Virtual Environment (VENV):
- Set up a virtual environment in my working directory to isolate project dependencies.

Install Dependencies:
- Installed all project dependencies listed in the requirements file within the virtual environment to ensure a consistent environment across different systems.

Custom Exception and Logging:
- Created a file for custom exceptions and logging to handle errors and log messages effectively.

Data Collection:
- Gathered data for the project, which can be found on my GitHub repository.

Setup File:
- Developed a setup file for project management, facilitating easy installation and distribution of the project.

Notebook Folder:
- Created a 'notebook' folder containing Jupyter notebook files for exploratory data analysis and model training.

Source (src) Folder:
- Organized my project's source code into a 'src' folder, including data components, pipelines, and utility modules. Components include files for data ingestion, transformation, and model training, while the pipeline folder contains predict and train pipelines.

Application File:
- Developed an application file for a simple web interface using Flask, allowing users to interact with the model. The 'templates' folder contains HTML files for the frontend, with 'home.html' serving as a template.
Excited to continue this journey and share more updates soon! Stay tuned for more insights and progress updates. Feel free to explore my GitHub repository for more details and code snippets. Let's keep learning and building together! 🚀📊🔧

Happy Coding!

#MachineLearning
#datascienceprojects
#github
#projectdevelopment
#webdevelopment
#Flask
#BeginnersJourney
#student_performance_prediction
#niazroky

свернуть