def __init__( self, change_params, lab_panel, num_episodes, use_cache=None, random_state=None, build_raw_only=False, ): SupervisedLearningPipeline.__init__(self, lab_panel, num_episodes, use_cache, random_state) self._change_params = change_params self._change_params[ 'feature_old'] = self._lookup_previous_measurement_feature( self._var) log.debug('change_params: %s' % self._change_params) if build_raw_only: self._build_raw_feature_matrix() return else: self._build_raw_feature_matrix() self._build_processed_feature_matrix() self._train_and_analyze_predictors()
def __init__(self, lab_panel, microcultures, num_episodes, use_cache=None, random_state=None): SupervisedLearningPipeline.__init__(self, lab_panel, num_episodes, use_cache, random_state) self.panel = microcultures self._build_raw_feature_matrix() self._build_processed_feature_matrix() self._train_and_analyze_predictors()
def __init__(self, lab_panel, num_episodes, use_cache=None, random_state=None, isLabPanel=True, notUsePatIds=[], pat_batch_ind=None): self.notUsePatIds = notUsePatIds self.pat_batch_ind = pat_batch_ind self.usedPatIds = [] SupervisedLearningPipeline.__init__(self, lab_panel, num_episodes, use_cache, random_state, isLabPanel) self._factory = FeatureMatrixFactory() self._build_raw_feature_matrix()
def __init__(self, lab_panel, num_episodes, use_cache=None, random_state=None, isLabPanel=True, timeLimit=None, notUsePatIds=None, holdOut=False, pat_batch_ind=None): self.notUsePatIds = notUsePatIds self.pat_batch_ind = pat_batch_ind self.usedPatIds = [] SupervisedLearningPipeline.__init__( self, lab_panel, num_episodes, use_cache, random_state, isLabPanel, timeLimit, holdOut, isLabNormalityPredictionPipeline=True) # TODO: naming of lab_panel self._factory = FeatureMatrixFactory() self._build_raw_feature_matrix() data_lab_folder = self._fetch_data_dir_path( inspect.getfile(inspect.currentframe())) feat2imputed_dict_path = data_lab_folder + '/feat2imputed_dict.pkl' if holdOut: ''' For holdOut evaluation data, produce the raw matrix, pick features according to the saved feat2imputed_dict. ''' self.feat2imputed_dict = pickle.load( open(feat2imputed_dict_path, 'r')) self._build_processed_feature_matrix_holdout() self._analyze_predictors_on_holdout() else: ''' For training/validation data, record the pat_ids, selected features and their imputed value correspondingly. ''' pickle.dump(self.usedPatIds, open('data/used_patient_set_%s.pkl' % self._var, 'w'), pickle.HIGHEST_PROTOCOL) self._build_processed_feature_matrix() self._build_baseline_results() # TODO: prototype in SLPP return # TODO: find better place to put the dict.pkl pickle.dump(self.feat2imputed_dict, open(feat2imputed_dict_path, 'w'), pickle.HIGHEST_PROTOCOL) self._train_and_analyze_predictors()
def __init__(self, lab_panel, num_episodes, use_cache=None, random_state=None, timeLimit=None, notUsePatIds=None, holdOut=False, pat_batch_ind=None, includeLastNormality=True): # self.notUsePatIds = notUsePatIds self.pat_batch_ind = pat_batch_ind self._holdOut = holdOut self.usedPatIds = [] SupervisedLearningPipeline.__init__(self, lab_panel, num_episodes, use_cache, random_state, timeLimit, notUsePatIds) # TODO: naming of lab_panel self._factory = FeatureMatrixFactory() self._build_raw_feature_matrix() if LAB_TYPE == 'panel': self.ylabel = 'all_components_normal' else: self.ylabel = 'component_normal' self.includeLastNormality = includeLastNormality if self.includeLastNormality: fm_io = FeatureMatrixIO() df = fm_io.read_file_to_data_frame('data/'+lab_panel+'/%s-normality-matrix-raw.tab'%lab_panel) df = df.sort_values(['pat_id', 'order_time']).reset_index(drop=True) df['last_normality'] = df['order_proc_id'].apply(lambda x:float('nan')) for i in range(1,df.shape[0]): if df.ix[i, 'pat_id'] == df.ix[i-1, 'pat_id']: df.ix[i, 'last_normality'] = df.ix[i-1, self.ylabel] df.to_csv('data/'+lab_panel+'/%s-normality-matrix-raw.tab'%lab_panel, index=False, sep='\t') data_lab_folder = self._fetch_data_dir_path(inspect.getfile(inspect.currentframe())) feat2imputed_dict_path = data_lab_folder + '/feat2imputed_dict.pkl' if holdOut: ''' For holdOut evaluation data, produce the raw matrix, pick features according to the saved feat2imputed_dict. ''' self.feat2imputed_dict = pickle.load(open(feat2imputed_dict_path, 'r')) self._build_processed_feature_matrix_holdout() self._analyze_predictors_on_holdout() else: ''' For training/validation data, record the pat_ids, selected features and their imputed value correspondingly. ''' pickle.dump(self.usedPatIds, open('data/used_patient_set_%s.pkl'%self._var, 'w'), pickle.HIGHEST_PROTOCOL) self._build_processed_feature_matrix() self._build_baseline_results() # TODO: prototype in SLPP # return # TODO: find better place to put the dict.pkl pickle.dump(self.feat2imputed_dict, open(feat2imputed_dict_path, 'w'), pickle.HIGHEST_PROTOCOL) self._train_and_analyze_predictors()