Course Introduction & Platform Onboarding

EA. Understanding the Ecosystem (Platform Implementation Training)

We are utilizing an accessible, scalable, and integrated technology stack to deliver a seamless learning experience, consistent with the project’s goal of reaching a geographically dispersed audience.

Component	Purpose & Access Point	Key Training Focus
Masterstudy LMS	The central hub for content delivery, tracking, quizzes, and submitting your GitHub links. https://doable.co.ke/.	LMS Navigation: Learn to use your Frontend Student Dashboard to track progress and view grades, supporting self-regulated learning. Utilize integrated Discussion Forums and Q&A for knowledge co-construction and peer collaboration.
Google Colab Notebooks	Your standardized, cloud-based coding environment, embedded directly within the LMS lesson pages. Access: Via the lesson links in Modules 1–5.	Eliminate Setup Barriers: Colab allows you to “get started with coding right away without getting frustrated” by eliminating the need to install or configure software. You will use Python and its libraries (NumPy, Pandas, etc.) here.
GitHub	The mandatory platform for project submission and portfolio management. This is where your completed `.ipynb` files will reside.	Professional Workflow: Exposes you to essential version control workflows used in industry. Your final portfolio will live here, demonstrating your proficiency to future employers.

B. Data Acquisition and Access Instructions

You will be working with the Agriculture And Farming Dataset, a complex, real-world dataset sourced from Kaggle.

Step	Instruction	Context/Placement
1. Data Location	The `agriculture_dataset` file is located in the `data` folder (Data Folder) within the main course Drive.	This folder contains the raw, “messy” data necessary for your hands-on experience.
2. Dataset Structure	Familiarize yourself with the 10 columns you will use, including `crop_type` (VARCHAR), `yield_tons` (DOUBLE), `fertilizer_used_tons` (DOUBLE), `soil_type` (VARCHAR), and `water_usage_cubic_meters` (DOUBLE).	The dataset has 50 rows and 10 columns.
3. Loading in Colab	When you open a project notebook (starting in Module 1), you must execute the initial code cell that either: A) Mounts Google Drive to access the `data` folder, or B) Loads the pre-staged file directly into the Colab environment.	This step mimics the professional practice of pulling data from cloud storage into your analysis environment.

C. GitHub Submission and Grading Workflow

This workflow is critical. Failure to follow these steps precisely will result in a non-submission or a failed grade.

The Projects are found in the Project Based Learning Assignment Section. After Every Module, Please proceed to the Projects Link and Solve the Project related to the module completed.

Step	Action	Objective
1. Repository Creation	Create a private GitHub repository (e.g., `ds-bootcamp-agriculture-projects`).	0. Course Introduction: This is where your professional portfolio will be built.
2. Complete Project	Complete the required analysis and code execution in your Google Colab Notebook.	Modules 1-5: Focus on satisfying all assignment requirements (e.g., proper data cleaning, model training).
3. Save and Upload	Download the notebook file to your local machine, saving it as a standard name (e.g., `M3_Pandas_Wrangling.ipynb`).	This is the artifact you generated in the cloud-based environment.
4. Commit and Push	Use the GitHub web interface or GitHub Desktop to add the `.ipynb` file to your repository, write a meaningful commit message (e.g., “M5: Final Capstone Model Trained”), and Push the changes live.	Professional Workflow: Demonstrates understanding of version control, which is essential for data practitioners.
5. Submit for Grading	Copy the direct URL link to your committed file (or the repository link, as specified per assignment) and paste it into the submission box on the Masterstudy LMS.	Your instructor will use this link to review and grade your work according to the rubric below.

D. Grading Rubric and Pass Threshold

To ensure you acquire the practical competencies demanded by industry, the passing threshold for every assignment is 70%. Scores below this point are a FAIL and require revision and resubmission.

Criterion Category	Weight (%)	Assessment Focus
I. Foundational Computing	30%	Correctness and efficiency of code, statistical application (Modules 1 & 2).
II. Data Wrangling & Quality	20%	Handling “messy” data, cleaning, imputation, and feature engineering (Module 3).
III. Capstone Synthesis & ML	25%	Problem formulation, model selection, training, and evaluation (Module 5).
IV. Communication & Connection	15%	Effective visualization and a non-technical executive summary (Modules 4 & 5).
V. Professional Workflow	10%	Consistent GitHub use, proper documentation, and code structure.
More To Learn On GitHub Use		GitHub Training Link
Google Colab With GitHub Use		Google Colab With GitHub