SYMBOL INDEX (125 symbols across 11 files)

FILE: scripts/reproducibility/afd/create_afd_resources.py
  function afd_train_model_demo (line 32) | def afd_train_model_demo(config):

FILE: scripts/reproducibility/afd/score_afd_model.py
  function create_outcomes (line 31) | def create_outcomes(outcomes):
  function create_rules (line 40) | def create_rules(score_cuts, outcomes):
  function ast_with_nan (line 88) | def ast_with_nan(x):
  function afd_train_model_demo (line 95) | def afd_train_model_demo():

FILE: scripts/reproducibility/autogluon/benchmark_ag.py
  function run_ag (line 29) | def run_ag(dataset, base_path, time_limit=3600, presets=None, hyperparam...

FILE: scripts/reproducibility/autosklearn/benchmark_autosklearn.py
  function load_data (line 77) | def load_data(dataset_path):
  function get_recall (line 101) | def get_recall(fpr, tpr, fpr_target=0.01):
  function run_autosklearn (line 105) | def run_autosklearn(dataset_path):

FILE: scripts/reproducibility/benchmark_utils.py
  function load_data (line 22) | def load_data(dataset, base_path):
  function get_recall (line 45) | def get_recall(fpr, tpr, fpr_target=0.01):

FILE: scripts/reproducibility/h2o/benchmark_h2o.py
  function run_h2o (line 29) | def run_h2o(dataset, base_path, connect_url=None, time_limit=None, inclu...

FILE: scripts/reproducibility/label-noise/load_fdb_datasets.py
  function noise_amount (line 20) | def noise_amount(df):
  function noise_rate (line 23) | def noise_rate(df):
  function type_1_noise_amount (line 29) | def type_1_noise_amount(df):
  function type_2_noise_amount (line 34) | def type_2_noise_amount(df):
  function actual_legit_amount (line 39) | def actual_legit_amount(df):
  function observed_legit_amount (line 42) | def observed_legit_amount(df):
  function actual_fraud_amount (line 45) | def actual_fraud_amount(df):
  function observed_fraud_amount (line 48) | def observed_fraud_amount(df):
  function actual_fraud_rate (line 51) | def actual_fraud_rate(df):
  function observed_fraud_rate (line 57) | def observed_fraud_rate(df):
  function type_1_noise_rate (line 63) | def type_1_noise_rate(df):
  function type_2_noise_rate (line 69) | def type_2_noise_rate(df):
  function prepare_data_fdb (line 75) | def prepare_data_fdb(key, drop_text_enr_features=True):
  function add_noise (line 212) | def add_noise(df, noise_type, noise_amount, *, time_index=None, features...
  function train_valid_split (line 273) | def train_valid_split(df, split=0.7, shuffle=True, sort_key='creation_da...
  function prepare_noisy_dataset (line 285) | def prepare_noisy_dataset(key, noise_type, noise_amount, split=0.7, shuf...
  function dataset_stats (line 345) | def dataset_stats(dataset):

FILE: scripts/reproducibility/label-noise/micro_models.py
  class MicroModelError (line 6) | class MicroModelError(Exception):
    method __init__ (line 10) | def __init__(self, error_message):
  class MicroModel (line 14) | class MicroModel:
    method __init__ (line 20) | def __init__(self, ModelClass, *args, **kwargs):
    method set_thresh (line 28) | def set_thresh(self, thresh):
    method fit (line 32) | def fit(self, x, y, *args, **kwargs):
    method predict_proba (line 36) | def predict_proba(self, x, *args, **kwargs):
    method predict (line 43) | def predict(self, x):
  class MicroModelEnsemble (line 54) | class MicroModelEnsemble:
    method __init__ (line 59) | def __init__(self, ModelClass, num_clfs=16, score_type='preds_avg', *a...
    method fit (line 85) | def fit(self, x, y, *args, **kwargs):
    method predict_proba (line 103) | def predict_proba(self, x, *args, **kwargs):
    method predict (line 117) | def predict(self, x, threshold=0.5, *args, **kwargs):
    method filter_noise (line 123) | def filter_noise(self, x, y, pulearning=True, threshold=0.5):
    method clean_noise (line 136) | def clean_noise(self, x, y, pulearning=True, threshold=0.5):
  class MicroModelCleaner (line 155) | class MicroModelCleaner:
    method __init__ (line 161) | def __init__(self, ModelClass, strategy='filter', pulearning=True, num...
    method fit (line 181) | def fit(self, x, y, *args, **kwargs):
    method predict (line 192) | def predict(self, x, *args, **kwargs):
    method predict_proba (line 195) | def predict_proba(self, x, *args, **kwargs):

FILE: src/fdb/datasets.py
  class FraudDatasetBenchmark (line 6) | class FraudDatasetBenchmark(ABC):
    method __init__ (line 7) | def __init__(
    method train (line 23) | def train(self):
    method test (line 27) | def test(self):
    method test_labels (line 31) | def test_labels(self):
    method eval (line 34) | def eval(self, y_pred):

FILE: src/fdb/preprocessing.py
  class BasePreProcessor (line 51) | class BasePreProcessor(ABC):
    method __init__ (line 52) | def __init__(
    method _download_kaggle_data_from_competetions (line 93) | def _download_kaggle_data_from_competetions(self):
    method _download_kaggle_data_from_datasets_with_given_filename (line 101) | def _download_kaggle_data_from_datasets_with_given_filename(self):
    method _download_kaggle_data_from_datasets_containing_single_file (line 114) | def _download_kaggle_data_from_datasets_containing_single_file(self):
    method download_kaggle_data (line 122) | def download_kaggle_data(self):
    method load_data (line 150) | def load_data(self):
    method timestamp_col (line 156) | def timestamp_col(self):
    method label_col (line 160) | def label_col(self):
    method event_id_col (line 167) | def event_id_col(self):
    method entity_id_col (line 171) | def entity_id_col(self):
    method standardize_timestamp_col (line 174) | def standardize_timestamp_col(self):
    method standardize_label_col (line 191) | def standardize_label_col(self):
    method standardize_event_id_col (line 195) | def standardize_event_id_col(self):
    method standardize_entity_id_col (line 204) | def standardize_entity_id_col(self):
    method rename_features (line 211) | def rename_features(self):
    method subset_features (line 215) | def subset_features(self):
    method drop_features (line 219) | def drop_features(self):
    method add_meta_data (line 222) | def add_meta_data(self):
    method sort_by_timestamp (line 226) | def sort_by_timestamp(self):
    method lower_case_col_names (line 229) | def lower_case_col_names(self):
    method preprocess (line 232) | def preprocess(self):
    method train_test_split (line 245) | def train_test_split(self):
  class FakejobPreProcessor (line 264) | class FakejobPreProcessor(BasePreProcessor):
    method __init__ (line 265) | def __init__(self, **kw):
  class VehicleloanPreProcessor (line 269) | class VehicleloanPreProcessor(BasePreProcessor):
    method __init__ (line 270) | def __init__(self, **kw):
  class MalurlPreProcessor (line 274) | class MalurlPreProcessor(BasePreProcessor):
    method __init__ (line 280) | def __init__(self, **kw):
    method standardize_label_col (line 283) | def standardize_label_col(self):
    method add_dummy_col (line 294) | def add_dummy_col(self):
    method preprocess (line 297) | def preprocess(self):
  class IEEEPreProcessor (line 301) | class IEEEPreProcessor(BasePreProcessor):
    method __init__ (line 312) | def __init__(self, **kw):
    method _dtypes_cols (line 316) | def _dtypes_cols():
    method load_data (line 372) | def load_data(self):
    method normalization (line 396) | def normalization(self):
    method standardize_entity_id_col (line 402) | def standardize_entity_id_col(self):
    method _add_seconds (line 412) | def _add_seconds(x):
    method standardize_timestamp_col (line 419) | def standardize_timestamp_col(self):
    method subset_features (line 425) | def subset_features(self):
    method preprocess (line 436) | def preprocess(self):
  class CCFraudPreProcessor (line 450) | class CCFraudPreProcessor(BasePreProcessor):
    method __init__ (line 451) | def __init__(self, **kw):
    method _add_minutes (line 455) | def _add_minutes(x):
    method standardize_timestamp_col (line 461) | def standardize_timestamp_col(self):
  class FraudecomPreProcessor (line 467) | class FraudecomPreProcessor(BasePreProcessor):
    method __init__ (line 468) | def __init__(self, ip_address_col, signup_time_col, **kw):
    method _add_years (line 474) | def _add_years(init_time):
    method standardize_timestamp_col (line 481) | def standardize_timestamp_col(self):
    method process_ip (line 490) | def process_ip(self):
    method create_time_since_signup (line 497) | def create_time_since_signup(self):
    method preprocess (line 502) | def preprocess(self):
  class SparknovPreProcessor (line 517) | class SparknovPreProcessor(BasePreProcessor):
    method __init__ (line 518) | def __init__(self, **kw):
    method load_data (line 521) | def load_data(self):
    method _add_months (line 538) | def _add_months(x):
    method standardize_timestamp_col (line 545) | def standardize_timestamp_col(self):
    method standardize_entity_id_col (line 551) | def standardize_entity_id_col(self):
    method train_test_split (line 558) | def train_test_split(self):
  class TwitterbotPreProcessor (line 574) | class TwitterbotPreProcessor(BasePreProcessor):
    method __init__ (line 575) | def __init__(self, **kw):
    method standardize_label_col (line 578) | def standardize_label_col(self):
  class IPBlocklistPreProcessor (line 588) | class IPBlocklistPreProcessor(BasePreProcessor):
    method __init__ (line 598) | def __init__(self, version, **kw):
    method load_data (line 602) | def load_data(self):
    method add_dummy_col (line 628) | def add_dummy_col(self):
    method train_test_split (line 631) | def train_test_split(self):
    method preprocess (line 635) | def preprocess(self):

FILE: src/fdb/preprocessing_objects.py
  function load_data (line 4) | def load_data(key, load_pre_downloaded, delete_downloaded, add_random_va...