How dasuna/its-2140---machine-learning works
This repository is a collection of machine-learning lab sessions, not a packaged runtime application. The principal user workflow is for a learner to work through notebook-based exercises, from regression and classification fundamentals to clustering, model inference, deployment, and experiment tracking. Notebook titles identify these capabilities, but no notebook source was available to confirm execution order, dataset usage, or internal calls; the graph therefore shows learner access rather than inferred runtime flows.
Main entry points: advertising_sales_prediction.ipynb Advertising Regression · multiple_linear_regression_SGD.ipynb Multiple Regression SGD · logistic_regression_new.ipynb Logistic Regression · softmax_regression.ipynb Softmax Regression
Components 15
Modeling Fundamentals
- Advertising Regression
Week 2/advertising_sales_prediction.ipynb - Multiple Regression SGD
Week 3/multiple_linear_regression_SGD.ipynb - Logistic Regression
Week 4/logistic_regression_new.ipynb - Softmax Regression
Week 6/softmax_regression.ipynb
Unsupervised Learning
- K-Means Clustering
Week 5/k-means-clustering.ipynb
Model Lifecycle
- Model Inference
Week 7/get_inferences.ipynb - Training and Artifacts
Week 7/model_training_and_artifacts_saving.ipynb - Sentiment Deployment
Week 8/sentiment-analysis_sklearn-pipeline_deployment.ipynb
Experimentation
- Hyperparameter Tuning
Week 9/hyperparameter_tuning_experiment.ipynb - Logistic Tracking
Week 9/logistic_regression_tracking.ipynb - MLflow Tracking
Week 9/ml_flow_tracking.ipynb
Other components
- Learner
- Advertising Data
Week 2/advertising.csv - Clothing Reviews Data
Week 4/womens_clothing_ecommerce_reviews.csv - Clothing Reviews Data
Week 7/womens_clothing_ecommerce_reviews.csv
Connections 11
- Learner → Advertising Regression: studies
- Learner → Multiple Regression SGD: studies
- Learner → Logistic Regression: studies
- Learner → Softmax Regression: studies
- Learner → K-Means Clustering: studies
- Learner → Model Inference: studies
- Learner → Training and Artifacts: studies
- Learner → Sentiment Deployment: studies
- Learner → Hyperparameter Tuning: studies
- Learner → Logistic Tracking: studies
- Learner → MLflow Tracking: studies