Refactor time_domain_loop with new TimeDomainConfiguration #74
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
maxwest-uw
changed the title
Click here to view all benchmarks. |
drewoldag
approved these changes
Nov 6, 2024
Comment on lines
112
to
146
| def __post_init__(self): | ||
| # file checking | ||
| if not path.isdir(self.path_to_features_dir): | ||
| raise ValueError("`path_to_features` must be an existing directory.") | ||
|
|
||
| # check strategy | ||
| if self.strategy not in VALID_STRATEGIES: | ||
| raise ValueError(f"{self.strategy} is not a valid strategy.") | ||
| if "QBD" in self.strategy and not self.clf_bootstrap: | ||
| raise ValueError("Bootstrap must be true when using disagreement strategy") | ||
|
|
||
| for key in self.path_to_ini_files.keys(): | ||
| if not path.isfile(self.path_to_ini_files[key]): | ||
| raise ValueError(f"{key} does not point to existing file.") | ||
|
|
||
| def to_dict(self): | ||
| """converts configurations elements into a dict.""" | ||
| return asdict(self) | ||
|
|
||
| @classmethod | ||
| def from_dict(cls, lc_dict): | ||
| """creates a `LoopConfiguration` instance from a dict.""" | ||
| return cls(**lc_dict) | ||
|
|
||
| def to_json(self, file_path): | ||
| """write out the `LoopConfiguration` as a json file.""" | ||
| with open(file_path, 'w') as fp: | ||
| json.dump(self.to_dict(), fp) | ||
|
|
||
| @classmethod | ||
| def from_json(cls, file_path): | ||
| """read a `LoopConfiguration` generated json file and instantiate.""" | ||
| with open(file_path) as fp: | ||
| lc_dict = json.load(fp) | ||
| return cls(**lc_dict) |
There was a problem hiding this comment.
These methods seem fairly similar to the ones in the LoopConfiguration data class. I can't recall the details of inheritance for Python dataclasses, but would it be possible/worth pushing these up into a parent class?
Comment on lines
671
to
+711
| for metadata_value in light_curve_data.train_metadata[id_key_name].values: | ||
| next_day_pool_metadata = next_day_data.pool_metadata[id_key_name].values | ||
| if metadata_value in next_day_pool_metadata: | ||
| next_day_pool_metadata_indices = list( | ||
| next_day_pool_metadata).index(metadata_value) | ||
| next_day_pool_metadata_indices = list(next_day_pool_metadata).index(metadata_value) | ||
| if metadata_value not in light_curve_train_ids: | ||
| light_curve_train_metadata = light_curve_data.train_metadata[ | ||
| id_key_name].values | ||
| light_curve_train_metadata = light_curve_data.train_metadata[id_key_name].values | ||
| light_curve_data = _remove_old_training_features( | ||
| light_curve_data, light_curve_train_metadata, | ||
| metadata_value) | ||
| light_curve_data, | ||
| light_curve_train_metadata, | ||
| metadata_value | ||
| ) | ||
| if light_curve_data.queryable_ids.shape[0] > 0: | ||
| light_curve_data = _update_queried_sample( | ||
| light_curve_data, next_day_data, id_key_name, | ||
| metadata_value) | ||
| light_curve_data, | ||
| next_day_data, | ||
| id_key_name, | ||
| metadata_value | ||
| ) | ||
| light_curve_data = _update_training_data_with_new_features( | ||
| light_curve_data, next_day_data, metadata_value, id_key_name) | ||
| light_curve_data, | ||
| next_day_data, | ||
| metadata_value, | ||
| id_key_name | ||
| ) | ||
| next_day_data = _update_next_day_pool_data( | ||
| next_day_data, next_day_pool_metadata_indices) | ||
| next_day_data, | ||
| next_day_pool_metadata_indices | ||
| ) | ||
| next_day_data = _update_next_day_val_and_test_data( | ||
| next_day_data, metadata_value, id_key_name) | ||
| next_day_data, | ||
| metadata_value, | ||
| id_key_name | ||
| ) | ||
| light_curve_data = _update_light_curve_data_for_next_epoch( | ||
| light_curve_data, next_day_data, canonical_data, is_queryable, strategy, | ||
| is_separate_files) | ||
| light_curve_data, | ||
| next_day_data, | ||
| canonical_data, | ||
| config.queryable, | ||
| config.strategy, | ||
| config.sep_files | ||
| ) |
There was a problem hiding this comment.
I know that you didn't introduce this, but oh my, this looks like a place where lots of bugs can hide. 😬
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.
Change Description
A refactor of
time_domain_loop, with the creation of a newTimeDomainConfigurationdataclass. This functions very similar toLoopConfigurationin #36 .Solution Description
Created a separate dataclass for time domain to keep simplicity of use.
Code Quality