How jitamb/get-started-with-ml works
Main components
• Data Input & Preprocessing: Even if the notebooks contain hardcoded or simulated data, include a block that represents data sourcing or preprocessing. In a typical ML project, this would cover data import, cleaning, and feature engineering.
• Experiment Modules: Create separate components for the two experiments:
• K-Means Clustering: Representing the unsupervised learning workflow.
• Logistic Regression: Representing the supervised learning workflow.
• Model Evaluation & Visualization: Since ML experiments typically include performance metrics and plots, include a block for evaluating results (e.g., cluster validity or classification accuracy) and for visualizing outputs.
Relationships and interactions
• That each module independently takes the preprocessed data, applies its algorithm, and produces evaluation outputs.
• If there is any common library or configuration (e.g., use of Scikit-learn, NumPy, or Pandas in both notebooks), you might include an “Environment/Dependencies” block to represent these common components.