mlsanigeria / ai-hacktober-mlsa Goto Github PK

👋 Hello Contributors!

To maintain the quality of our documentation and resources, we need your help to spot and correct errors in our Contribution Guidelines. This will ensure that our guidelines are clear, concise, and accurate for all contributors.

How You Can Help:

1. Review the Contribution Guidelines: Take a close look at the Contribution Guidelines document in the repository.
2. Identify Errors: Carefully identify any spelling errors, grammatical mistakes, or inaccuracies within the document.
3. Propose Corrections: Suggest corrections for the errors you find. You can use inline comments or submit a pull request with the changes.

Example:

If you find a sentence like this:

"We welcoming all contributions."

Please suggest/make the correction:

"We welcome all contributions."

Create a Pull Request: Once you've identified and corrected the errors, create a pull request with your changes. Follow our guidelines for submitting pull requests, as outlined in the Contribution Guidelines.

Happy error-spotting and correcting! 📝🚀

📊 Data Collection for Project 3 - Nigerian Student's Year One Performance Prediction

Project Overview

In Project 3, we are working on building a Tabular Machine Learning model that predicts the Year One GPA (Grade Point Average) of Nigerian students. This model will rely on various features, including Jamb scores, Waec grades, experiences during the first-year session, reading patterns, consistency of class attendance, and more.

Our goal is to create a predictive tool that helps Nigerian students anticipate their Year One GPA and make informed decisions about their education.

What's Needed

We need your valuable input to collect the necessary data for this project. Your contribution involves filling out a survey form that captures essential information. Please note that:

• Authentic Information: It's crucial to provide authentic and accurate information as this will contribute to creating a reliable and useful predictive model.

• Data Anonymity: Rest assured that the survey form collects data anonymously and does not record any personal information. Your privacy is our priority.

How You Can Contribute

1. Survey Form: Access the survey form using the following link: Survey Form Link.

2. Complete the Survey: Fill out the survey form by providing the requested information honestly and accurately.

3. Contribution Acknowledgment: Your participation in this data collection process is a valuable contribution to our project, even though it can't be recorded as a merged pull request on GitHub. This is a significant part of open-source contribution.

Let's Build a Predictive Tool Together!

By participating in this data collection process, you are helping us gather the data needed to train and test our predictive model. Your contribution plays a pivotal role in the success of our project.

Note: If you have any questions or need assistance with the survey form, please feel free to ask in the comments. Your engagement is greatly appreciated.

There is a slight issue with the ordinal encoding for the WAEC grades.
This is what is found in the file.

# Ordinal encoding map
ordinal_encoding_map = {'A': 5, 'B': 4, 'C': 3, 'D': 2, 'E': 1, 'F': 6}

The value for 'F" is inputted as 6 instead of 0

If you agree with me, I would love to solve the issue.

Issue Overview

Our project documentation is the gateway for newcomers to understand, contribute, and make the most of our projects. To ensure it's informative, user-friendly, and up-to-date, we need your expertise!

What's Needed

We're looking for contributors to help us enhance our project documentation in the following ways:

1. Content Review: Review the existing documentation for accuracy, clarity, and completeness.

2. Updating: Identify outdated information and update it to reflect the current state of the project.

3. Clarity: Simplify complex topics and ensure that even beginners can understand our documentation.

4. Organization: Suggest improvements in the structure and organization of the documentation.

How You Can Contribute

1. Fork the Repository: Fork our project repository to work on the documentation enhancements.

2. Make Your Changes: Make the necessary updates and improvements to the documentation.

3. Create a Pull Request: Submit a pull request with your changes. Ensure that you follow our Contribution Guidelines for detailed instructions.

4. Review and Collaboration: We'll review your pull request and collaborate to finalize the documentation enhancements.

Let's Make Learning and Contributing Easier!

By contributing to our documentation, you're helping us create a better experience for everyone in our community. Your input will be invaluable for both newcomers and seasoned contributors.

Thank you for making our project even better! 🙌

Note: If you have any questions or need assistance, feel free to ask in the comments.

Can we create a model folder for the image classification model where we can store all the models trained.

Issue Overview

Our project aims to break down language barriers and enable seamless communication in local dialects. To achieve this, we need to implement a robust translation workflow that can translate English text to Yoruba, Igbo, and Hausa dialects. We're counting on your expertise to make it happen!

What's Needed

Your task will be to implement the translation workflow that can accurately convert English text to the chosen dialects.

Specific Tasks:

1. Language Integration: Integrate language translation using the accurate ISO 639-1 code for each dialect.

2. Text Translation: Develop the logic to translate English text to the selected dialects.

3. Workflow Testing: Thoroughly test the translation workflow to ensure high-quality results.

How You Can Contribute

1. Fork the Repository: Fork our project repository to start working on the translation workflow.

2. Coding: Write the necessary code to implement text translation from English to the specified dialect.

3. Testing: Rigorously test the translation workflow and make adjustments as needed.

4. Create a Pull Request: Submit a pull request with your changes once you've completed the development. Be sure to follow our Contribution Guidelines.

5. Review and Collaboration: We'll review your pull request, provide feedback, and collaborate to finalize the translation workflow.

Let's Bridge Language Barriers Together!

By contributing to the translation workflow, you're helping us create a more inclusive and accessible service that can connect people across languages. Your efforts will make a significant impact on our project's success!

Thank you for your dedication to our mission! 🌐📝

Note: If you have any questions or need assistance, feel free to ask in the comments.

Project Overview

In Project 1, we are working on creating a robust image classification system that can accurately identify different types of buildings, including:

• Bungalows
• Storey Buildings
• High-rise buildings (including skyscrapers)

Our goal is to build a machine learning model that excels at classifying these buildings based on images contributed by our community of contributors.

What's Needed

We need your help in collecting images of these building types to train and test our classification model. Specifically, we are looking for images that meet the following criteria:

• Aspect Ratio: Images should have an aspect ratio of 3:4 (portrait format).
• Size: Don't worry about image size; we have a workflow in place to resize images to a size of 300 by 400 pixels that would be used for modelling.

How You Can Contribute

1. Capture Images: Take clear photos of the building types (bungalows, storey buildings, and high-rise buildings) in portrait format.

2. Image Naming: Please name your images uniquely. You can also choose to indicate the type of building and any relevant information about the image location if available.

3. Contribution: Navigate to the data folder for project 1 and upload your images under the folder with the right building type. A minimum of 10 images in total is what will be required of you.

4. Quality Check: Ensure that the images are of good quality and clearly depict the building type.

Example Image Names:

• bungalow_01.jpg
• storey_building_night.jpg
• highrise_skyscraper_02.png
• 20123907183_23.jpeg

Let's Build an Accurate Building Classifier Together!

Your contributions will play a crucial role in training our machine learning model to accurately classify buildings. By sharing images of these building types, you're helping us create a more inclusive and effective solution.

Thank you for your valuable contributions! 🏙️📸

Note: If you have any questions or need assistance with image uploads, feel free to ask in the comments. Let's make this project a success!

🚀 Speech Translation - Streamlit Script Contribution

Project Overview

In Project 2, we are working towards creating a powerful translation service for local dialects, including Yoruba, Igbo, and Hausa, using Microsoft AI services.

What's Needed

We are looking for contributors to help us create a Streamlit script that interacts with our translation workflow. The script should allow users to input either audio or text in English and receive translations to Yoruba, Igbo, or Hausa.

How You Can Contribute

1. Familiarize Yourself: Take some time to explore our project's repository and understand the existing code and documentation.

2. Create a Streamlit Script: Develop a Streamlit script that integrates with our translation workflow. Users should be able to input either audio or text in English, and the script should provide translations to the selected local dialect (Yoruba, Igbo, or Hausa).

3. Test Your Script: Ensure that your Streamlit script functions correctly by testing it with sample inputs.

4. Create a Pull Request: Submit a pull request to our repository with your Streamlit script and any necessary documentation.

5. Participate in Discussions: Engage with the community by participating in discussions related to your contribution.

Getting Started

To get started, please review our Contribution Guidelines for detailed instructions on how to contribute effectively.

Happy Hacking!🎉

Context:
I would like to add an additional link (YouTube video) to the resources under the contributing file.

Has the feature been requested before?
No it hasn't

Describe the solution you'd like
Looking at the resources for project two, I wasn't quite sure where to start because I was new to Azure services. I believe adding a link to the session conducted for project 2 will give a new contributor (who is new to Microsoft Azure services) and idea on how to start and will serve as a proper support to the previous links on documentation.

If the feature request is approved, would you be willing to work on it and submit a PR?
Yes

👋 Hello Contributors!

We believe that documentations should not only be informative but also visually engaging. To add a touch of fun and expressiveness, we'd like to incorporate emojis into our documentation subtitles.

How You Can Help:

1. Review the Documentation: Take a look at the documentation files in the repository.
2. Identify Subtitles: Locate subtitles within the documentation where adding emojis could enhance the visual appeal and provide context.
3. Propose Emojis: Suggest emojis that you think would be suitable for each subtitle. Feel free to be creative and choose emojis that align with the content.
4. Create a Pull Request: Once you've made your suggestions, create a pull request with your changes. Please follow our Contribution Guidelines for detailed instructions.

Example:

Subtitle: "How to Contact Us"

Suggested Emoji: 📞

Subtitle with Emoji: "📞 How to Contact Us"

Happy emoji-adding! 🎉

Issue Overview

We're on a mission to build a powerful translation service that can handle both text and speech inputs. One crucial piece of the puzzle is the speech-to-text functionality. We need your help to make this feature come to life!

What's Needed

We're looking for contributors to help us develop the speech-to-text functionality for our translation service leveraging Azure AI Services. Links to resources on getting started with Azure's Speech service and Translator service have been included in the Contribution Guidelines.

Specific Tasks:

1. Speech Recognition Integration: Integrate a speech recognition engine into our project.

2. Audio Input Handling: Implement the ability to accept audio inputs from users.

3. Transcription: Convert spoken words from audio into text.

How You Can Contribute

1. Fork the Repository: Fork our project repository to start working on the speech-to-text feature.

2. Coding: Write the necessary code to implement speech recognition and transcription functionality.

3. Testing: Thoroughly test the feature to ensure accurate transcription.

4. Create a Pull Request: Submit a pull request with your changes once you've completed the development. Be sure to follow our Contribution Guidelines.

5. Review and Collaboration: We'll review your pull request, provide feedback, and collaborate to finalize the feature.

Let's Make Speech-to-Text Magic Happen!

By contributing to the development of speech-to-text functionality, you're helping us create a more versatile and user-friendly translation service. This feature will enable users to communicate seamlessly across language barriers.

Thank you for lending your expertise to our project! 🗣️📝

Note: If you have any questions or need assistance, feel free to ask in the comments.

Description:

Welcome, contributors! It's time to dive into the modeling phase of our Image Classification Project. We're excited to see our AI model in action and make it capable of classifying different types of buildings from images.

Project Overview:

• Objective: To create a robust image classification model.
• Classes: Bungalow, Storey-building, High-rise (including skyscrapers).
• Dataset: Dataset Link
• Starter Notebook: Starter Notebook Link

Tasks for Modeling Phase:

1. Data Preprocessing: Ensure the dataset is cleaned, and images are appropriately formatted for training.

2. Model Selection: Choose a suitable image classification algorithm or neural network architecture (e.g., CNNs).

3. Training: Train the model on the provided dataset. Experiment with different hyperparameters to improve accuracy.

4. Evaluation: Assess the model's performance using appropriate evaluation metrics. Focus on accuracy, precision, recall, and F1-score.

5. Fine-tuning: Optimize the model for better results. Explore techniques like data augmentation and transfer learning.

6. Documentation: Create documentation within your working folder with detailed information on the chosen model, training process, and evaluation results.

Contribution Guidelines:

• Please fork this repository and create a new branch for your modelling work.
• (Optional) Reference this issue in your pull request (PR) to link it with the modelling phase.
• Provide clear and concise commit messages.
• Collaborate with fellow contributors and maintain an open line of communication.

Let's work together to build a powerful image classification model. Remember, every contribution matters.

If you have any questions or need assistance, feel free to ask in the comments. Happy modelling! 📸🤖