def _update_training_data_with_new_features( light_curve_data: DataBase, next_day_data: DataBase, metadata_value: int, id_key_name: str) -> DataBase: """ Updates new features of the training with new metadata value Parameters ---------- light_curve_data light curve data next_day_data next day light curve data id_key_name object identification key name metadata_value metadata object value """ next_day_pool_data_flag = ( next_day_data.pool_metadata[id_key_name].values == metadata_value) light_curve_data.train_metadata = pd.concat( [light_curve_data.train_metadata, next_day_data.pool_metadata[next_day_pool_data_flag]], axis=0, ignore_index=True) light_curve_data.train_features = np.append( light_curve_data.train_features, next_day_data.pool_features[next_day_pool_data_flag], axis=0) light_curve_data.train_labels = np.append( light_curve_data.train_labels, next_day_data.pool_labels[next_day_pool_data_flag], axis=0) return light_curve_data
def _save_metrics_and_queried_sample( database_class: DataBase, current_loop: int, output_metric_file_name: str, output_queried_file_name: str, batch: int, epoch: int, is_save_full_query: bool): """ Saves metrics and queried sample data Parameters ---------- database_class An instance of DataBase class current_loop Number of learning loops finished at this stage. output_metric_file_name Full path to file to store metrics results. output_queried_file_name batch Number of queries in each loop. epoch Days since the beginning of the survey. is_save_full_query If true, write down a complete queried sample stored in property 'queried_sample'. Otherwise append 1 line per loop to 'queried_sample_file'. Default is False. """ database_class.save_metrics( loop=current_loop, output_metrics_file=output_metric_file_name, batch=batch, epoch=epoch) if is_save_full_query: output_queried_file_name = (output_queried_file_name[:-4] + '_' + str(current_loop) + '.dat') database_class.save_queried_sample( output_queried_file_name, loop=current_loop, full_sample=is_save_full_query, epoch=epoch)
def test_load_bazin_features(): """Test loading Bazin features.""" # test full light curve case fname1 = testing.download_data("tests/Bazin_SNPCC1.dat") data1 = DataBase() data1.load_bazin_features(path_to_bazin_file=fname1, screen=True, survey='DES', sample=None) # read data independently data_temp1 = pd.read_csv(fname1, sep=" ") sizes1 = len(data_temp1.keys()) == \ len(data1.features_names) - 1 + len(data1.metadata_names) queryable1 = 'queryable' in data1.metadata_names # test time domain case fname2 = testing.download_data('tests/day_20.dat') data2 = DataBase() data2.load_bazin_features(path_to_bazin_file=fname2, screen=True, survey='DES', sample=None) data_temp2 = pd.read_csv(fname2) sizes2 = len(data_temp2.keys()) == len(data2.features_names) + \ len(data2.metadata_names) queryable2 = 'queryable' in data2.metadata_names assert (sizes1 and queryable1) assert (sizes2 and queryable2)
def run_evaluation(database_class: DataBase, metric_label: str): """ Evaluates the active learning model Parameters ---------- database_class An instance of DataBase class metric_label Choice of metric. Currently only "snpcc", "cosmo" or "snpcc_cosmo" are accepted. Default is "snpcc". """ database_class.evaluate_classification(metric_label=metric_label)
def run_make_query(database_class: DataBase, strategy: str, batch_size: int, is_queryable: bool): """ Run active learning query process Parameters ---------- database_class An instance of DataBase class strategy Strategy used to choose the most informative object. Current implementation accepts 'UncSampling' and 'RandomSampling', 'UncSamplingEntropy', 'UncSamplingLeastConfident', 'UncSamplingMargin', 'QBDMI', 'QBDEntropy', . Default is `UncSampling`. batch_size Number of objects to be chosen in each batch query. Default is 1 is_queryable If True, consider only queryable objects. Default is False. """ return database_class.make_query(strategy=strategy, batch=batch_size, queryable=is_queryable)
def run_classification(database_class: DataBase, classifier: str, is_classifier_bootstrap: bool, prediction_dir: str, is_save_prediction: bool, iteration_step: int, **kwargs: dict) -> DataBase: """ Run active learning classification model Parameters ---------- database_class An instance of DataBase class classifier Machine Learning algorithm. Currently implemented options are 'RandomForest', 'GradientBoostedTrees', 'KNNclassifier','MLPclassifier','SVMclassifier' and 'NBclassifier'. Default is 'RandomForest'. is_classifier_bootstrap if tp apply a machine learning classifier by bootstrapping prediction_dir Output directory to store prediction file for each loop. Only used if `save_predictions==True is_save_prediction if predictions should be saved iteration_step active learning iteration number kwargs All keywords required by the classifier function. ------- """ if is_classifier_bootstrap: database_class.classify_bootstrap(method=classifier, loop=iteration_step, pred_dir=prediction_dir, save_predictions=is_save_prediction, **kwargs) else: database_class.classify(method=classifier, pred_dir=prediction_dir, loop=iteration_step, save_predictions=is_save_prediction, **kwargs) return database_class
def _update_next_day_pool_data(next_day_data: DataBase, next_day_pool_metadata_indices) -> DataBase: """ Removes metadata value data from next day pool sample Parameters ---------- next_day_data next day light curve data next_day_pool_metadata_indices indices of metadata value in next day light curve data """ # remove obj from pool sample next_day_data.pool_metadata = next_day_data.pool_metadata.drop( next_day_data.pool_metadata.index[next_day_pool_metadata_indices]) next_day_data.pool_labels = np.delete( next_day_data.pool_labels, next_day_pool_metadata_indices, axis=0) next_day_data.pool_features = np.delete( next_day_data.pool_features, next_day_pool_metadata_indices, axis=0) return next_day_data
def _update_samples_with_object_indices( database_class: DataBase, object_indices: list, is_queryable: bool, epoch: int) -> DataBase: """ Runs database class update_samples methods with object indices Parameters ---------- database_class An instance of DataBase class object_indices List of indexes identifying objects to be moved. is_queryable If True, consider queryable flag. Default is False. epoch Day since beginning of survey. Default is 20. """ database_class.update_samples( object_indices, queryable=is_queryable, epoch=epoch) return database_class
def _save_metrics_and_queried_samples(database_class: DataBase, metrics_file_name: str, queried_file_name: str, iteration_step: int, batch: int, full_sample: bool, file_name_suffix: str = None): """ Save metrics and queried samples details Parameters ---------- database_class An instance of DataBase class metrics_file_name Full path to file to store metrics results. queried_file_name Complete path to output file. iteration_step active learning iteration number batch Number of queries in each loop. full_sample If true, write down a complete queried sample stored in property 'queried_sample'. Otherwise append 1 line per loop to 'queried_sample_file'. Default is False. file_name_suffix suffix string for save file name with file extension """ if file_name_suffix is not None: metrics_file_name = metrics_file_name.replace('.dat', file_name_suffix) queried_file_name = queried_file_name.replace('.dat', file_name_suffix) database_class.save_metrics(loop=iteration_step, output_metrics_file=metrics_file_name, batch=batch, epoch=iteration_step) database_class.save_queried_sample(queried_file_name, loop=iteration_step, full_sample=full_sample, epoch=iteration_step, batch=batch)
def save_photo_ids(database_class: DataBase, is_save_photoids_to_file: bool, is_save_snana_types: bool, metadata_fname: str, photo_class_threshold: float, iteration_step: int, file_name_prefix: str = None, file_name_suffix: str = None): """ Function to save photo IDs to a file Parameters ---------- database_class An instance of DataBase class is_save_photoids_to_file If true, populate the photo_Ia_list attribute. Otherwise write to file. Default is False. is_save_snana_types if True, translate type to SNANA codes and add column with original values. Default is False. metadata_fname Full path to PLAsTiCC zenodo test metadata file. photo_class_threshold Probability threshold above which an object is considered Ia. iteration_step active learning iteration number file_name_suffix suffix string for save file name with file extension file_name_prefix prefix string for save file name """ if is_save_photoids_to_file or is_save_snana_types: file_name = file_name_prefix + '_' + str( iteration_step) + file_name_suffix database_class.output_photo_Ia(photo_class_threshold, to_file=is_save_photoids_to_file, filename=file_name, SNANA_types=is_save_snana_types, metadata_fname=metadata_fname)
def _update_data_by_remove_repeated_ids(first_loop_data: DataBase, light_curve_data: DataBase, id_key_name: str, pool_labels_class: str = 'Ia') -> Tuple[ DataBase, DataBase]: """ Updates first loop and initial data by removing repetitive id indices Parameters ---------- first_loop_data first loop light curve data light_curve_data initial light curve training data id_key_name object identification key name pool_labels_class pool labels class name """ repeated_id_flags = np.in1d( first_loop_data.pool_metadata[id_key_name].values, light_curve_data.train_metadata[id_key_name].values) first_loop_data.pool_metadata = first_loop_data.pool_metadata[ ~repeated_id_flags] first_loop_data.pool_features = first_loop_data.pool_features[ ~repeated_id_flags] pool_labels = ( first_loop_data.pool_metadata['type'].values == pool_labels_class) first_loop_data.pool_labels = pool_labels.astype(int) light_curve_data.pool_features = first_loop_data.pool_features light_curve_data.pool_metadata = first_loop_data.pool_metadata light_curve_data.pool_labels = first_loop_data.pool_labels return first_loop_data, light_curve_data
def _run_classification_and_evaluation( database_class: DataBase, classifier: str, is_classifier_bootstrap: bool, **kwargs: dict) -> DataBase: """ Runs active learning classification and evaluation methods Parameters ---------- database_class An instance of DataBase class classifier Machine Learning algorithm. Currently 'RandomForest', 'GradientBoostedTrees', 'KNN', 'MLP', 'SVM' and 'NB' are implemented. Default is 'RandomForest'. is_classifier_bootstrap if tp apply a machine learning classifier by bootstrapping kwargs All keywords required by the classifier function. """ if is_classifier_bootstrap: database_class.classify_bootstrap(method=classifier, **kwargs) else: database_class.classify(method=classifier, **kwargs) database_class.evaluate_classification() return database_class
def _update_canonical_ids(light_curve_data: DataBase, canonical_file_name: str, is_restrict_canonical: bool) -> Tuple[ DataBase, DataBase]: """ Updates canonical ids Parameters ---------- light_curve_data initial light curve training data canonical_file_name Path to canonical sample features files. It is only used if "strategy==canonical". is_restrict_canonical If True, restrict the search to the canonical sample. """ database_class = None if is_restrict_canonical: database_class = DataBase() database_class.load_features(path_to_file=canonical_file_name) light_curve_data.queryable_ids = database_class.queryable_ids return light_curve_data, database_class
def _update_queryable_ids(light_curve_data: DataBase, id_key_name: str, is_queryable: bool) -> DataBase: """ Updates queryable ids Parameters ---------- light_curve_data initial light curve training data id_key_name object identification key name is_queryable If True, allow queries only on objects flagged as queryable. Default is True. """ if is_queryable: queryable_flags = light_curve_data.pool_metadata['queryable'].values light_curve_data.queryable_ids = light_curve_data.pool_metadata[ id_key_name].values[queryable_flags] else: light_curve_data.queryable_ids = light_curve_data.pool_metadata[ id_key_name].values return light_curve_data
def _get_indices_of_objects_to_be_queried( database_class: DataBase, strategy: str, budgets: tuple, is_queryable: bool, query_threshold: float, batch: int) -> list: """ Finds indices of objects to be queried Parameters ---------- database_class An instance of DataBase class strategy Query strategy. Options are (all can be run with budget): "UncSampling", "UncSamplingEntropy", "UncSamplingLeastConfident", "UncSamplingMargin", "QBDMI", "QBDEntropy", "RandomSampling", budgets Budgets for each of the telescopes is_queryable If True, allow queries only on objects flagged as queryable. Default is True. query_threshold Percentile threshold for query. Default is 1. batch Size of batch to be queried in each loop. Default is 1. """ if budgets: object_indices = database_class.make_query_budget( budgets=budgets, strategy=strategy) else: object_indices = database_class.make_query( strategy=strategy, batch=batch, queryable=is_queryable, query_thre=query_threshold) return list(object_indices)
def _remove_old_training_features( light_curve_data: DataBase, light_curve_metadata: np.ndarray, metadata_value: int): """ Removes old training features Parameters ---------- light_curve_data light curve training data light_curve_metadata light curve meta data metadata_value metadata object value """ current_day_object_index = list(light_curve_metadata).index( metadata_value) light_curve_data.train_metadata = light_curve_data.train_metadata.drop( light_curve_data.train_metadata.index[current_day_object_index]) light_curve_data.train_labels = np.delete( light_curve_data.train_labels, current_day_object_index, axis=0) light_curve_data.train_features = np.delete( light_curve_data.train_features, current_day_object_index, axis=0) return light_curve_data
def _update_light_curve_data_val_and_test_data( light_curve_data: DataBase, first_loop_data: DataBase, is_separate_files: bool = False, initial_training: Union[str, int] = 'original', is_queryable: bool = False, number_of_classes: int = 2) -> DataBase: """ Updates initial light curve validation and test data Parameters ---------- light_curve_data initial light curve training data first_loop_data first loop light curve data is_queryable If True, allow queries only on objects flagged as queryable. Default is True. is_separate_files If True, consider samples separately read from independent files. Default is False. initial_training Choice of initial training sample. If 'original': begin from the train sample flagged in the file eilf 'previous': read training and queried from previous run. If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is 'original'. number_of_classes Number of classes to consider in the classification Currently only number_of_classes == 2 is implemented. """ if is_separate_files: light_curve_data.build_samples( nclass=number_of_classes, queryable=is_queryable, sep_files=is_separate_files, initial_training=initial_training) else: light_curve_data.test_features = first_loop_data.pool_features light_curve_data.test_metadata = first_loop_data.pool_metadata light_curve_data.test_labels = first_loop_data.pool_labels light_curve_data.validation_features = first_loop_data.pool_features light_curve_data.validation_metadata = first_loop_data.pool_metadata light_curve_data.validation_labels = first_loop_data.pool_labels return light_curve_data
def _update_queried_sample(light_curve_data: DataBase, next_day_data: DataBase, id_key_name: str, metadata_value: int) -> DataBase: """ Updates queried sample in light curve data Parameters ---------- light_curve_data light curve data next_day_data next day light curve data id_key_name object identification key name metadata_value metadata object value """ # build query data frame full_header_name = (['epoch'] + light_curve_data.metadata_names + light_curve_data.features_names) queried_sample = pd.DataFrame(light_curve_data.queried_sample, columns=full_header_name) # get object index in the queried sample queried_index = list( queried_sample[id_key_name].values).index(metadata_value) # get flag to isolate object in question queried_values_flag = queried_sample[id_key_name].values == metadata_value # get object epoch in the queried sample metadata_value_epoch = queried_sample['epoch'].values[queried_values_flag] # remove old features from queried queried_sample = queried_sample.drop(queried_sample.index[queried_index]) next_day_pool_data_flag = ( next_day_data.pool_metadata[id_key_name].values == metadata_value) new_query_pool_metadata = list(next_day_data.pool_metadata[ next_day_pool_data_flag].values[0]) new_query_pool_features = list(next_day_data.pool_features[ next_day_pool_data_flag][0]) new_query = ([metadata_value_epoch[0]] + new_query_pool_metadata + new_query_pool_features) new_query = pd.DataFrame([new_query], columns=full_header_name) queried_sample = pd.concat([queried_sample, new_query], axis=0, ignore_index=True) # update queried sample light_curve_data.queried_sample = list(queried_sample.values) return light_curve_data
def _update_initial_train_meta_data_header( first_loop_data: DataBase, light_curve_data: DataBase) -> DataBase: """ Updates if all headers in test not exist in train Parameters ---------- first_loop_data first loop light curve data light_curve_data light curve learning data """ for each_name in first_loop_data.metadata_names: if each_name not in light_curve_data.metadata_names: light_curve_data.metadata_names.append(each_name) light_curve_data.metadata[each_name] = None light_curve_data.train_metadata.insert( len(light_curve_data.metadata_names) - 1, each_name, None, True) return light_curve_data
def _update_next_day_val_and_test_data( next_day_data: DataBase, metadata_value: int, id_key_name: str) -> DataBase: """ Removes metadata value data from next day validation and test samples Parameters ---------- next_day_data next day light curve data metadata_value metadata object value id_key_name object identification key name """ if (len(next_day_data.validation_metadata) > 0 and metadata_value in next_day_data.validation_metadata[id_key_name].values): val_indices = list(next_day_data.validation_metadata[ id_key_name].values).index(metadata_value) next_day_data.validation_metadata = ( next_day_data.validation_metadata.drop( next_day_data.validation_metadata.index[val_indices])) next_day_data.validation_labels = np.delete( next_day_data.validation_labels, val_indices, axis=0) next_day_data.validation_features = np.delete( next_day_data.validation_features, val_indices, axis=0) if (len(next_day_data.test_metadata) > 0 and metadata_value in next_day_data.test_metadata[id_key_name].values): test_indices = list(next_day_data.test_metadata[ id_key_name].values).index(metadata_value) next_day_data.test_metadata = ( next_day_data.test_metadata.drop( next_day_data.test_metadata.index[test_indices])) next_day_data.test_labels = np.delete( next_day_data.test_labels, test_indices, axis=0) next_day_data.test_features = np.delete( next_day_data.test_features, test_indices, axis=0) return next_day_data
def learn_loop(nloops: int, strategy: str, path_to_features: str, output_diag_file: str, output_queried_file: str, features_method='Bazin', classifier='RandomForest', training='original', batch=1, screen=True, survey='DES', perc=0.1, nclass=2): """Perform the active learning loop. All results are saved to file. Parameters ---------- nloops: int Number of active learning loops to run. strategy: str Query strategy. Options are 'UncSampling' and 'RandomSampling'. path_to_features: str or dict Complete path to input features file. if dict, keywords should be 'train' and 'test', and values must contain the path for separate train and test sample files. output_diag_file: str Full path to output file to store diagnostics of each loop. output_queried_file: str Full path to output file to store the queried sample. features_method: str (optional) Feature extraction method. Currently only 'Bazin' is implemented. classifier: str (optional) Machine Learning algorithm. Currently only 'RandomForest' is implemented. training: str or int (optional) Choice of initial training sample. If 'original': begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is 'original'. batch: int (optional) Size of batch to be queried in each loop. Default is 1. screen: bool (optional) If True, print on screen number of light curves processed. survey: str (optional) 'DES' or 'LSST'. Default is 'DES'. Name of the survey which characterizes filter set. perc: float in [0,1] (optioal) Percentile chosen to identify the new query. Only used for PercentileSampling. Default is 0.1. nclass: int (optional) Number of classes to consider in the classification Currently only nclass == 2 is implemented. """ ## This module will need to be expanded for RESSPECT # initiate object data = DataBase() # load features if isinstance(path_to_features, str): data.load_features(path_to_features, method=features_method, screen=screen, survey=survey) # separate training and test samples data.build_samples(initial_training=training, nclass=nclass) else: data.load_features(path_to_features['train'], method=features_method, screen=screen, survey=survey, sample='train') data.load_features(path_to_features['test'], method=features_method, screen=screen, survey=survey, sample='test') data.build_samples(initial_training=training, nclass=nclass, screen=screen, sep_files=True) for loop in range(nloops): if screen: print('Processing... ', loop) # classify data.classify(method=classifier) # calculate metrics data.evaluate_classification() # choose object to query indx = data.make_query(strategy=strategy, batch=batch, perc=perc) # update training and test samples data.update_samples(indx, loop=loop) # save diagnostics for current state data.save_metrics(loop=loop, output_metrics_file=output_diag_file, batch=batch, epoch=loop) # save query sample to file data.save_queried_sample(output_queried_file, loop=loop, full_sample=False)
def learn_loop(nloops: int, strategy: str, path_to_features: str, output_metrics_file: str, output_queried_file: str, features_method: str = 'Bazin', classifier: str = 'RandomForest', training: str = 'original', batch: int = 1, survey: str = 'DES', nclass: int = 2, photo_class_thr: float = 0.5, photo_ids_to_file: bool = False, photo_ids_froot: str = ' ', classifier_bootstrap: bool = False, save_predictions: bool = False, sep_files=False, pred_dir: str = None, queryable: bool = False, metric_label: str = 'snpcc', save_alt_class: bool = False, SNANA_types: bool = False, metadata_fname: str = None, bar: bool = True, **kwargs): """ Perform the active learning loop. All results are saved to file. Parameters ---------- nloops: int Number of active learning loops to run. strategy: str Query strategy. Options are 'UncSampling', 'RandomSampling', 'UncSamplingEntropy', 'UncSamplingLeastConfident', 'UncSamplingMargin', 'QBDMI' and 'QBDEntropy'. path_to_features: str or dict Complete path to input features file. if dict, keywords should be 'train' and 'test', and values must contain the path for separate train and test sample files. output_metrics_file: str Full path to output file to store metric values of each loop. output_queried_file: str Full path to output file to store the queried sample. features_method: str (optional) Feature extraction method. Currently only 'Bazin' is implemented. classifier: str (optional) Machine Learning algorithm. Currently implemented options are 'RandomForest', 'GradientBoostedTrees', 'K-NNclassifier','MLPclassifier','SVMclassifier' and 'NBclassifier'. Default is 'RandomForest'. sep_files: bool (optional) If True, consider train and test samples separately read from independent files. Default is False. batch: int (optional) Size of batch to be queried in each loop. Default is 1. classifier_bootstrap: bool (optional) Flag for bootstrapping on the classifier Must be true if using disagreement based strategy. metadata_fname: str (optional) Complete path to PLAsTiCC zenodo test metadata. Only used it SNANA_types == True. Default is None. metric_label: str (optional) Choice of metric. Currently only "snpcc", "cosmo" or "snpcc_cosmo" are accepted. Default is "snpcc". nclass: int (optional) Number of classes to consider in the classification Currently only nclass == 2 is implemented. photo_class_thr: float (optional) Threshold for photometric classification. Default is 0.5. Only used if photo_ids is True. photo_ids_to_file: bool (optional) If True, save photometric ids to file. Default is False. photo_ids_froot: str (optional) Output root of file name to store photo ids. Only used if photo_ids is True. pred_dir: str (optional) Output diretory to store prediction file for each loop. Only used if `save_predictions==True`. queryable: bool (optional) If True, check if randomly chosen object is queryable. Default is False. save_alt_class: bool (optional) If True, train the model and save classifications for alternative query label (this is necessary to calculate impact on cosmology). Default is False. save_predictions: bool (optional) If True, save classification predictions to file in each loop. Default is False. SNANA_types: bool (optional) If True, translate zenodo types to SNANA codes. Default is False. survey: str (optional) 'DES' or 'LSST'. Default is 'DES'. Name of the survey which characterizes filter set. training: str or int (optional) Choice of initial training sample. If 'original': begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is 'original'. bar: bool (optional) If True, display progress bar. kwargs: extra parameters All keywords required by the classifier function. """ if 'QBD' in strategy and not classifier_bootstrap: raise ValueError( 'Bootstrap must be true when using disagreement strategy') # initiate object database_class = DataBase() logging.info('Loading features') database_class = load_features(database_class, path_to_features, survey, features_method, nclass, training, queryable, sep_files) logging.info('Running active learning loop') if bar: ensemble = progressbar.progressbar(range(nloops)) else: ensemble = range(nloops) for iteration_step in ensemble: if not bar: print(iteration_step) database_class = run_classification(database_class, classifier, classifier_bootstrap, pred_dir, save_predictions, iteration_step, **kwargs) run_evaluation(database_class, metric_label) save_photo_ids(database_class, photo_ids_to_file, SNANA_types, metadata_fname, photo_class_thr, iteration_step, photo_ids_froot, '.dat') indices_to_query = run_make_query(database_class, strategy, batch, queryable) if save_alt_class and batch == 1: database_class_alternative = copy.deepcopy(database_class) database_class_alternative = update_alternative_label( database_class_alternative, indices_to_query, iteration_step, classifier, pred_dir, save_predictions, metric_label, SNANA_types, photo_ids_to_file, metadata_fname, photo_class_thr, photo_ids_froot, **kwargs) _save_metrics_and_queried_samples(database_class_alternative, output_metrics_file, output_queried_file, iteration_step, batch, False, '_alt_label.dat') elif save_alt_class and batch > 1: raise ValueError('Alternative label only works with batch=1!') database_class.update_samples(indices_to_query, epoch=iteration_step, queryable=queryable, alternative_label=False) _save_metrics_and_queried_samples(database_class, output_metrics_file, output_queried_file, iteration_step, batch, False) return database_class
def load_features(database_class: DataBase, path_to_features: Union[str, dict], survey: str, features_method: str, number_of_classes: int, training_method: str, is_queryable: bool, separate_files: bool = False, save_samples: bool = False) -> DataBase: """ Load features according to feature extraction method Parameters ---------- database_class An instance of DataBase class path_to_features Complete path to input features file. if dict, keywords should be 'train' and 'test', and values must contain the path for separate train and test sample files. survey 'DES' or 'LSST'. Default is 'DES'. Name of the survey which characterizes filter set. features_method Feature extraction method. Currently only 'Bazin' is implemented. number_of_classes Number of classes to consider in the classification Currently only nclass == 2 is implemented. training_method Choice of initial training sample. If 'original': begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is 'original'. is_queryable If True, check if randomly chosen object is queryable. Default is False. separate_files: bool (optional) If True, consider train and test samples separately read from independent files. Default is False. save_samples: bool (optional) If True, save training and test samples to file. Default is False. """ if isinstance(path_to_features, str): database_class.load_features(path_to_file=path_to_features, method=features_method, survey=survey) else: features_set_names = ['train', 'test', 'validation', 'pool'] for sample_name in features_set_names: if sample_name in path_to_features.keys(): database_class.load_features(path_to_features[sample_name], method=features_method, survey=survey, sample=sample_name) else: logging.warning(f'Path to {sample_name} not given.' f' Proceeding without this sample') database_class.build_samples(initial_training=training_method, nclass=number_of_classes, queryable=is_queryable, sep_files=separate_files, save_samples=save_samples) return database_class
def update_alternative_label( database_class_alternative: DataBase, indices_to_query: list, iteration_step: int, classifier: str, pred_dir: str, is_save_prediction: bool, metric_label: str, is_save_snana_types: bool, is_save_photoids_to_file: bool, meta_data_fname: str, photo_class_threshold: float, photo_ids_froot: str, **kwargs: dict): """ Function to update active learning training with alternative label Parameters ---------- database_class_alternative An instance of DataBase class for alternative label indices_to_query List of indexes identifying objects to be moved. iteration_step active learning iteration number classifier Machine Learning algorithm. Currently implemented options are 'RandomForest', 'GradientBoostedTrees', 'K-NNclassifier','MLPclassifier','SVMclassifier' and 'NBclassifier'. Default is 'RandomForest'. pred_dir Output diretory to store prediction file for each loop. Only used if `save_predictions==True`. is_save_prediction if predictions should be saved metric_label Choice of metric. Currently only "snpcc", "cosmo" or "snpcc_cosmo" are accepted. Default is "snpcc". is_save_snana_types if True, translate type to SNANA codes and add column with original values. Default is False. is_save_photoids_to_file If true, populate the photo_Ia_list attribute. Otherwise write to file. Default is False. meta_data_fname Full path to PLAsTiCC zenodo test metadata file. photo_class_threshold Probability threshold above which an object is considered Ia. photo_ids_froot Output root of file name to store photo ids. Only used if photo_ids is True. kwargs additional arguments """ database_class_alternative.update_samples(indices_to_query, epoch=iteration_step, alternative_label=True) database_class_alternative = run_classification(database_class_alternative, classifier, False, pred_dir, is_save_prediction, iteration_step, **kwargs) run_evaluation(database_class_alternative, metric_label) save_photo_ids(database_class_alternative, is_save_photoids_to_file, is_save_snana_types, meta_data_fname, photo_class_threshold, iteration_step, photo_ids_froot, '_alt_label.dat') return database_class_alternative
def load_dataset(file_names_dict: dict, survey_name: str = 'DES', initial_training: Union[str, int] = 'original', ia_training_fraction: float = 0.5, is_queryable: bool = False, is_separate_files: bool = False, samples_list: list = [None], is_load_build_samples: bool = True, number_of_classes: int = 2, feature_extraction_method: str = 'Bazin', is_save_samples: bool = False) -> DataBase: """ Reads a data sample from file. Parameters ---------- file_names_dict: dict Path to light curve features file. #if "sep_files == True", dictionary keywords must contain identify #different samples: ['train', 'test','validation', 'pool', None] ia_training_fraction: float in [0,1] (optional) Fraction of Ia required in initial training sample. Only used if "initial_training" is a number. Default is 0.5. initial_training: str or int (optional) Choice of initial training sample. If 'original': begin from the train sample flagged in the file elif int: choose the required number of samples at random, ensuring that at least "ia_frac" are SN Ia. Default is 'original'. is_queryable: bool (optional) If True, allow queries only on objects flagged as queryable. Default is True. is_separate_files: bool (optional) If True, consider samples separately read from independent files. Default is False. survey_name: str (optional) Name of survey to be analyzed. Accepts 'DES' or 'LSST'. Default is DES. samples_list: list (optional) If None, sample is given by a column within the given file. else, read independent files for 'train' and 'test'. Default is None. number_of_classes Number of classes to consider in the classification Currently only nclass == 2 is implemented. feature_extraction_method: str (optional) Feature extraction method. The current implementation only accepts method=='Bazin' or 'photometry'. Default is 'Bazin'. is_save_samples: bool (optional) If True, save training and test samples to file. Default is False. is_load_build_samples if database.build_samples method should be called """ # initiate object database_class = DataBase() for sample in samples_list: database_class.load_features( file_names_dict[sample], survey=survey_name, sample=sample, method=feature_extraction_method) if is_load_build_samples: database_class.build_samples( initial_training=initial_training, nclass=number_of_classes, Ia_frac=ia_training_fraction, queryable=is_queryable, save_samples=is_save_samples, sep_files=is_separate_files, survey=survey_name) return database_class
def _update_light_curve_data_for_next_epoch( light_curve_data: DataBase, next_day_data: DataBase, canonical_data: DataBase, is_queryable: bool, strategy: str, is_separate_files: bool) -> DataBase: """ Updates samples for next epoch Parameters ---------- light_curve_data light curve learning data next_day_data next day light curve data canonical_data canonical strategy light curve data is_queryable If True, allow queries only on objects flagged as queryable. Default is True. strategy Query strategy. Options are (all can be run with budget): "UncSampling", "UncSamplingEntropy", "UncSamplingLeastConfident", "UncSamplingMargin", "QBDMI", "QBDEntropy", "RandomSampling", is_separate_files If True, consider samples separately read from independent files. Default is False. """ light_curve_data.pool_metadata = next_day_data.pool_metadata light_curve_data.pool_features = next_day_data.pool_features light_curve_data.pool_labels = next_day_data.pool_labels if not is_separate_files: light_curve_data.test_metadata = next_day_data.test_metadata light_curve_data.test_features = next_day_data.test_features light_curve_data.test_labels = next_day_data.test_labels light_curve_data.validation_metadata = next_day_data.validation_metadata light_curve_data.validation_features = next_day_data.validation_features light_curve_data.validation_labels = next_day_data.validation_labels if strategy == 'canonical': light_curve_data.queryable_ids = canonical_data.queryable_ids if is_queryable: queryable_flag = light_curve_data.pool_metadata['queryable'].values light_curve_data.queryable_ids = light_curve_data.pool_metadata[ 'id'].values[queryable_flag] else: light_curve_data.queryable_ids = light_curve_data.pool_metadata[ 'id'].values return light_curve_data
def time_domain_loop(days: list, output_diag_file: str, output_queried_file: str, path_to_features_dir: str, strategy: str, batch=1, canonical = False, classifier='RandomForest', features_method='Bazin', path_to_canonical="", path_to_full_lc_features="", screen=True, training='original'): """Perform the active learning loop. All results are saved to file. Parameters ---------- days: list List of 2 elements. First and last day of observations since the beginning of the survey. output_diag_file: str Full path to output file to store diagnostics of each loop. output_queried_file: str Full path to output file to store the queried sample. path_to_features_dir: str Complete path to directory holding features files for all days. strategy: str Query strategy. Options are 'UncSampling' and 'RandomSampling'. batch: int (optional) Size of batch to be queried in each loop. Default is 1. canonical: bool (optional) If True, restrict the search to the canonical sample. classifier: str (optional) Machine Learning algorithm. Currently only 'RandomForest' is implemented. features_method: str (optional) Feature extraction method. Currently only 'Bazin' is implemented. path_to_canonical: str (optional) Path to canonical sample features files. It is only used if "strategy==canonical". path_to_full_lc_features: str (optional) Path to full light curve features file. Only used if training is a number. screen: bool (optional) If True, print on screen number of light curves processed. training: str or int (optional) Choice of initial training sample. If 'original': begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia Default is 'original'. """ ## This will need to change for RESSPECT # initiate object data = DataBase() # load features for the first day path_to_features = path_to_features_dir + 'day_' + str(int(days[0])) + '.dat' data.load_features(path_to_features, method=features_method, screen=screen) # change training if training == 'original': data.build_samples(initial_training='original') full_lc_features = get_original_training(path_to_features=path_to_full_lc_features) data.train_metadata = full_lc_features.train_metadata data.train_labels = full_lc_features.train_labels data.train_features = full_lc_features.train_features else: data.build_samples(initial_training=int(training)) # get list of canonical ids if canonical: canonical = DataBase() canonical.load_features(path_to_file=path_to_canonical) data.queryable_ids = canonical.queryable_ids for night in range(int(days[0]), int(days[-1]) - 1): if screen: print('Processing night: ', night) # cont loop loop = night - int(days[0]) # classify data.classify(method=classifier) # calculate metrics data.evaluate_classification() # choose object to query indx = data.make_query(strategy=strategy, batch=batch) # update training and test samples data.update_samples(indx, loop=loop) # save diagnostics for current state data.save_metrics(loop=loop, output_metrics_file=output_diag_file, batch=batch, epoch=night) # save query sample to file data.save_queried_sample(output_queried_file, loop=loop, full_sample=False) # load features for next day path_to_features2 = path_to_features_dir + 'day_' + str(night + 1) + '.dat' data_tomorrow = DataBase() data_tomorrow.load_features(path_to_features2, method=features_method, screen=False) # identify objects in the new day which must be in training train_flag = np.array([item in data.train_metadata['id'].values for item in data_tomorrow.metadata['id'].values]) # use new data data.train_metadata = data_tomorrow.metadata[train_flag] data.train_features = data_tomorrow.features.values[train_flag] data.test_metadata = data_tomorrow.metadata[~train_flag] data.test_features = data_tomorrow.features.values[~train_flag] # new labels data.train_labels = np.array([int(item == 'Ia') for item in data.train_metadata['type'].values]) data.test_labels = np.array([int(item == 'Ia') for item in data.test_metadata['type'].values]) if strategy == 'canonical': data.queryable_ids = canonical.queryable_ids if queryable: queryable_flag = data_tomorrow.metadata['queryable'].values queryable_test_flag = np.logical_and(~train_flag, queryable_flag) data.queryable_ids = data_tomorrow.metadata['id'].values[queryable_test_flag] else: data.queryable_ids = data_tomorrow.metadata['id'].values[~train_flag] if screen: print('Training set size: ', data.train_metadata.shape[0]) print('Test set size: ', data.test_metadata.shape[0])