Conversation
- prep minimal dataset - compare models using plot - updated MADCAP plot taken from commit b966d5e on model-evaluation branch
- create notebook identifying minimal data items - script to compare and plot model performance - modify viz functions to receive models
- plot scripts default to model_group_name of 'admissions' - modify notebooks 4a and 4e
- prep minimal dataset - compare models using plot - updated MADCAP plot taken from commit b966d5e on model-evaluation branch
- create notebook identifying minimal data items - script to compare and plot model performance - modify viz functions to receive models
- plot scripts default to model_group_name of 'admissions' - modify notebooks 4a and 4e
- update README - add minimal syntethic dataset - edit writing in notebooks 1, 2, 3a-c - reinstate thumbnails for webinars - modify train_all_models to return models Multi-line description of commit, feel free to be detailed. [Ticket: X]
- Allow calling function to pass home_patgh to load.load_data - Make model saving and real-time inference optional in train_all_models - Modify viz.qq_plot and viz.prob_dist_plot to return fig
- additional fields in ed_visits_minimal syntethic data - add calibration option when training emergency demand model - modify viz.calibration_plot to add model name suffix - edit notebook 4a to examine poor calibration
- return calibrated pipeline within the best_model object - use calibrated pipeline for real-time prediction if available - use calibrated pipeline for calibration, distribution, madcap plots if available - rewrite minimum demand notebook - updates to notebook 4a [Ticket: X]
- reinstate evaluate.py from branch model-evalution - reisntate evaluation_plots from branch model-evalution - update evaluation notebook - clarify use model_name; model_key refers to model_name plus prediction_time - plot five qq plots side by side
- Add dataclasses for model metrics - Return TrainedModel and nested TrainingResults when training model - Pass a tuple of three models to create_predictions() - Enforce types of TrainedModel, SequencPredictor, WeightedPoisson - Update tests
- Remove references to admissions where models can be used for any purpose - Rename TrainedModel dataclass to TrainedClassifier - Rename train_single_model() to train_classifier() - Rename train_admissions_models() to train_multiple_models() - Make train_single_model() accept any classifier with args - Add validation of input types when generating demand predictions - Add tests of input type validation On branch simplify-training-args
- move classifiers, sequence predictor and weighted poisson training to own scripts - move save models to train.utils [Ticket: X]
- make the naming of objects saved with trained models more intuitive - rename metrics.py to model_artifacts.py - rename metrics in TrainedClassifier class to training_results - rename metadata saved in TrainingResults to training_info - remove saving of valid_logloss (already in cv_results) - create cv_trials data class - use new hyperparameter results class in visualisation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.