LR with priors initial implementation #66
Merged
Conversation
This file contains 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
Wiz Scan Summary
|
SkBlaz
reviewed
Mar 19, 2024
| @@ -57,17 +59,22 @@ def sklearn_surrogate( | |||
| unique_values, counts = np.unique(vector_second, return_counts=True) | |||
|
|
|||
| # Establish min support for this type of ranking. | |||
| if counts[0] < len(unique_values) * (2**5): | |||
| estimate_feature_importance = 0 | |||
| # if counts[0] < len(unique_values) * (2**5): | |||
There was a problem hiding this comment.
Let's remove such comments
| estimate_feature_importance = 1 + \ | ||
| np.median(estimate_feature_importance_list) | ||
| else: | ||
| X = np.concatenate((X,vector_first.reshape(-1, 1)), axis=1) |
There was a problem hiding this comment.
There is a space missing after X, wondering why lint didn't catch that. @miha-jenko maybe some idea?
| X = np.concatenate((X,vector_first.reshape(-1, 1)), axis=1) | ||
| X = transf.fit_transform(X) | ||
| estimate_feature_importance_list = cross_val_score( | ||
| clf, X, vector_second, scoring='neg_log_loss', cv=4, |
There was a problem hiding this comment.
Let's put the num. of folds to top of the file as a constant for now
outrank/core_ranking.py
Outdated
| @@ -130,9 +130,13 @@ def mixed_rank_graph( | |||
| # Map the scoring calls to the worker pool | |||
| pbar.set_description('Allocating thread pool') | |||
|
|
|||
| reference_model_features = {} | |||
| if 'prior' in args.heuristic: | |||
There was a problem hiding this comment.
you check for -prior at some point, but prior at some other point. Consider creating a helper function is_prior_heuristic or something, that unifies this behavior (and centralizes it)
bmramor
commented
Mar 22, 2024
SkBlaz
requested changes
Mar 22, 2024
outrank/core_ranking.py
Outdated
| ) | ||
| if args.reference_model_JSON != '': | ||
| model_combinations = extract_features_from_reference_JSON(args.reference_model_JSON, combined_features_only = True) | ||
| model_combinations = [tuple(sorted(combination.split(','))) for combination in model_combinations] |
There was a problem hiding this comment.
combination delimiter could be a const, as it repeats
outrank/core_ranking.py
Outdated
| random.shuffle(full_combination_space) | ||
| full_combination_space = full_combination_space[ | ||
| : args.combination_number_upper_bound | ||
| ] | ||
| if is_prior_heuristic(args): | ||
| full_combination_space = full_combination_space + [tuple for tuple in model_combinations if tuple not in full_combination_space] |
There was a problem hiding this comment.
Isn't this second part list(set(model_combinations).difference(set(full_combination_space)))
outrank/core_ranking.py
Outdated
| @@ -225,7 +244,7 @@ def compute_combined_features( | |||
| pbar.set_description('Concatenating into final frame ..') | |||
| input_dataframe = pd.concat([input_dataframe, tmp_df], axis=1) | |||
| del tmp_df | |||
|
|
|||
outrank/core_utils.py
Outdated
| """Given a model's JSON, extract unique features""" | ||
|
|
||
| with open(json_path) as jp: | ||
| content = json.load(jp) | ||
|
|
||
| unique_features = set() | ||
| feature_space = content['desc'].get('features', []) | ||
| if full_feature_space: |
There was a problem hiding this comment.
full_feature_space sounds somewhat odd for a flag that computes a set
outrank/core_utils.py
Outdated
| @@ -641,3 +644,10 @@ def summarize_rare_counts( | |||
| final_df.to_csv( | |||
| f'{args.output_folder}/feature_sparsity_summary.tsv', index=False, sep='\t', | |||
| ) | |||
|
|
|||
|
|
|||
| def is_prior_heuristic(args: Any): | |||
miha-jenko
reviewed
Mar 27, 2024
miha-jenko
approved these changes
Apr 2, 2024
SkBlaz
approved these changes
Apr 2, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.