How mprodriguezj/previomachinelearning works
Project type and purpose
• This is an interactive Machine-Learning evaluation tool built with Streamlit.
• It focuses on data ingestion, exploratory data analysis (EDA), training decision-tree and ensemble classifiers, and visualizing metrics (confusion matrix, ROC/AUC, etc.).
File structure
• Top‐level files:
• app.py – Streamlit entry point (UI layer)
• requirements.txt – Python dependencies (pandas, scikit-learn, streamlit, matplotlib/seaborn, etc.)
• data/ – folder holding CSV datasets
• modules/ – core processing layer, subdivided into:
• data_loader.py – data ingestion and validation
• eda.py – exploratory data analysis functions
• decision_tree.py – training/evaluation of decision-tree classifiers
• ensemble_models.py – training/evaluation of RandomForest, AdaBoost, GradientBoosting, Bagging
README for insights
• Confirms technology stack: Python ≥3.10, Streamlit UI, scikit-learn models, pandas for data, Matplotlib/Seaborn for plots.
• Workflow: user uploads or selects a dataset → EDA → model selection (decision tree or ensemble variants) → training & metrics → plots and tables in the browser.