How carolinapercina62/ml_dsaa_practicals works
This repository is a set of DSAA machine-learning practicals: students work through weekly Jupyter notebooks, with separately released solutions. The learning path moves from supervised-learning foundations and an ML process through data-quality exploration, feature work, performance measures and model selection; classification and regression are taught in parallel where indicated. Week 3 cleans raw datasets and records decisions for later weeks, which use the supplied interim data and logs. The graph reflects README-described capabilities; notebook internals beyond the sampled helper and preprocessing code are not inferred.
Main entry points: week_03_deepen_exploration.ipynb Data exploration · week_03_deepen_exploration_regression.ipynb Price regression · logs Cleaning logs · week_05_model_selection.ipynb Model selection
Components 22
Course materials
- Cleaning log tools
notebooks/week_03/course_helpers.py - Preprocessing tools
notebooks/week_05/preprocessing.py - Course project
project
Practical notebooks
- Supervised ML
notebooks/week_01/week_01_supervised_ml_and_environment.ipynb - ML process
notebooks/week_02/week_02_ml_pipeline.ipynb - Data exploration
notebooks/week_03/week_03_deepen_exploration.ipynb - Price regression
notebooks/week_03/week_03_deepen_exploration_regression.ipynb - Feature work
notebooks/week_04/week_04_feature_work_classification.ipynb - Regression features
notebooks/week_04/week_04_feature_work_regression.ipynb - Performance measures
notebooks/week_05/week_05_performance_measures.ipynb - Model selection
notebooks/week_05/week_05_model_selection.ipynb
Datasets and logs
- Raw cars data
data/raw/cars4you_raw.csv - Raw champions data
data/raw/champions_raw.csv - Cleaned cars data
data/interim/cars4you.csv - Cleaned champions data
data/interim/champions.csv - Cleaning logs
logs - Feature logs
logs
Released solutions
- Week 1 solution
solutions/week_01/week_01_supervised_ml_and_environment_solution.ipynb - Week 2 solution
solutions/week_02/week_02_ml_pipeline_solution.ipynb - Exploration solution
solutions/week_03/week_03_deepen_exploration_solution.ipynb - Regression solution
solutions/week_03/week_03_deepen_exploration_regression_solution.ipynb
Other components
- Student
Connections 37
- Student → Supervised ML: opens
- Student → ML process: opens
- Student → Data exploration: opens
- Student → Price regression: opens
- Student → Feature work: opens
- Student → Regression features: opens
- Student → Performance measures: opens
- Student → Model selection: opens
- Student → Week 1 solution: reviews
- Student → Week 2 solution: reviews
- Student → Exploration solution: reviews
- Student → Regression solution: reviews
- Data exploration → Raw champions data: cleans
- Price regression → Raw cars data: cleans
- Data exploration → Cleaned champions data: writes
- Price regression → Cleaned cars data: writes
- Data exploration → Cleaning logs: writes
- Price regression → Cleaning logs: writes
- Data exploration → Cleaning log tools: uses
- Price regression → Cleaning log tools: uses
- Feature work → Cleaned champions data: reads
- Feature work → Cleaning logs: reads
- Regression features → Cleaned cars data: reads
- Regression features → Cleaning logs: reads
- Performance measures → Cleaned cars data: reads
- Performance measures → Cleaned champions data: reads
- Performance measures → Cleaning logs: reads
- Model selection → Cleaned cars data: reads
- Model selection → Cleaned champions data: reads
- Model selection → Cleaning logs: reads
- Model selection → Preprocessing tools: uses
- Feature work → Feature logs: writes
- Regression features → Feature logs: writes
- Supervised ML → Week 1 solution: answered by
- ML process → Week 2 solution: answered by
- Data exploration → Exploration solution: answered by
- Price regression → Regression solution: answered by