def get_algos_config(cfg_dir):
r"""Read the algorithms configuration file.
Parameters
----------
cfg_dir : str
The directory where the configuration file ``algos.yml``
is stored.
Returns
-------
specs : dict
The specifications for determining which algorithms to run.
"""
logger.info("Algorithm Configuration")
# Read the configuration file
full_path = SSEP.join([cfg_dir, 'algos.yml'])
with open(full_path, 'r') as ymlfile:
specs = yaml.load(ymlfile, Loader=yaml.FullLoader)
# Find optional packages
find_optional_packages()
# Ensure each algorithm has required keys
minimum_keys = ['model_type', 'params', 'grid']
required_keys_keras = minimum_keys + ['layers', 'compiler']
for algo in specs:
if 'KERAS' in algo:
required_keys = required_keys_keras
else:
required_keys = minimum_keys
algo_keys = list(specs[algo].keys())
if set(algo_keys) != set(required_keys):
logger.warning("Algorithm %s has the wrong keys %s",
algo, required_keys)
logger.warning("Keys found instead: %s", algo_keys)
else:
# determine whether or not model type is valid
model_types = {x.name: x.value for x in ModelType}
model_type = specs[algo]['model_type']
if model_type in model_types:
specs[algo]['model_type'] = ModelType(model_types[model_type])
else:
raise ValueError("algos.yml model:type %s unrecognized" % model_type)
# Algorithm Specifications
return specs
def get_model_config():
r"""Read in the configuration file for AlphaPy.
Parameters
----------
None : None
Returns
-------
specs : dict
The parameters for controlling AlphaPy.
Raises
------
ValueError
Unrecognized value of a ``model.yml`` field.
"""
logger.info("Model Configuration")
# Read the configuration file
full_path = SSEP.join([PSEP, 'config', 'model.yml'])
with open(full_path, 'r') as ymlfile:
cfg = yaml.load(ymlfile, Loader=yaml.FullLoader)
# Store configuration parameters in dictionary
specs = {}
# Section: project [this section must be first]
specs['directory'] = cfg['project']['directory']
specs['extension'] = cfg['project']['file_extension']
specs['submission_file'] = cfg['project']['submission_file']
specs['submit_probas'] = cfg['project']['submit_probas']
# Section: data
specs['drop'] = cfg['data']['drop']
specs['features'] = cfg['data']['features']
specs['sentinel'] = cfg['data']['sentinel']
specs['separator'] = cfg['data']['separator']
specs['shuffle'] = cfg['data']['shuffle']
specs['split'] = cfg['data']['split']
specs['target'] = cfg['data']['target']
specs['target_value'] = cfg['data']['target_value']
# sampling
specs['sampling'] = cfg['data']['sampling']['option']
# determine whether or not sampling method is valid
samplers = {x.name: x.value for x in SamplingMethod}
sampling_method = cfg['data']['sampling']['method']
if sampling_method in samplers:
specs['sampling_method'] = SamplingMethod(samplers[sampling_method])
else:
raise ValueError("model.yml data:sampling:method %s unrecognized" %
sampling_method)
# end of sampling method
specs['sampling_ratio'] = cfg['data']['sampling']['ratio']
# Section: features
# clustering
specs['clustering'] = cfg['features']['clustering']['option']
specs['cluster_min'] = cfg['features']['clustering']['minimum']
specs['cluster_max'] = cfg['features']['clustering']['maximum']
specs['cluster_inc'] = cfg['features']['clustering']['increment']
# counts
specs['counts'] = cfg['features']['counts']['option']
# encoding
specs['rounding'] = cfg['features']['encoding']['rounding']
# determine whether or not encoder is valid
encoders = {x.name: x.value for x in Encoders}
encoder = cfg['features']['encoding']['type']
if encoder in encoders:
specs['encoder'] = Encoders(encoders[encoder])
else:
raise ValueError("model.yml features:encoding:type %s unrecognized" %
encoder)
# factors
specs['factors'] = cfg['features']['factors']
# interactions
specs['interactions'] = cfg['features']['interactions']['option']
specs['isample_pct'] = cfg['features']['interactions']['sampling_pct']
specs['poly_degree'] = cfg['features']['interactions']['poly_degree']
# isomap
specs['isomap'] = cfg['features']['isomap']['option']
specs['iso_components'] = cfg['features']['isomap']['components']
specs['iso_neighbors'] = cfg['features']['isomap']['neighbors']
# log transformation
specs['logtransform'] = cfg['features']['logtransform']['option']
# low-variance features
specs['lv_remove'] = cfg['features']['variance']['option']
specs['lv_threshold'] = cfg['features']['variance']['threshold']
# NumPy
specs['numpy'] = cfg['features']['numpy']['option']
# pca
specs['pca'] = cfg['features']['pca']['option']
specs['pca_min'] = cfg['features']['pca']['minimum']
specs['pca_max'] = cfg['features']['pca']['maximum']
specs['pca_inc'] = cfg['features']['pca']['increment']
specs['pca_whiten'] = cfg['features']['pca']['whiten']
# Scaling
specs['scaler_option'] = cfg['features']['scaling']['option']
# determine whether or not scaling type is valid
scaler_types = {x.name: x.value for x in Scalers}
scaler_type = cfg['features']['scaling']['type']
if scaler_type in scaler_types:
specs['scaler_type'] = Scalers(scaler_types[scaler_type])
else:
raise ValueError("model.yml features:scaling:type %s unrecognized" %
scaler_type)
# SciPy
specs['scipy'] = cfg['features']['scipy']['option']
# text
specs['ngrams_max'] = cfg['features']['text']['ngrams']
specs['vectorize'] = cfg['features']['text']['vectorize']
# t-sne
specs['tsne'] = cfg['features']['tsne']['option']
specs['tsne_components'] = cfg['features']['tsne']['components']
specs['tsne_learn_rate'] = cfg['features']['tsne']['learning_rate']
specs['tsne_perplexity'] = cfg['features']['tsne']['perplexity']
# Section: model
specs['algorithms'] = cfg['model']['algorithms']
specs['cv_folds'] = cfg['model']['cv_folds']
# determine whether or not model type is valid
model_types = {x.name: x.value for x in ModelType}
model_type = cfg['model']['type']
if model_type in model_types:
specs['model_type'] = ModelType(model_types[model_type])
else:
raise ValueError("model.yml model:type %s unrecognized" % model_type)
# end of model type
specs['n_estimators'] = cfg['model']['estimators']
specs['pvalue_level'] = cfg['model']['pvalue_level']
specs['scorer'] = cfg['model']['scoring_function']
# calibration
specs['calibration'] = cfg['model']['calibration']['option']
specs['cal_type'] = cfg['model']['calibration']['type']
# feature selection
specs['feature_selection'] = cfg['model']['feature_selection']['option']
specs['fs_percentage'] = cfg['model']['feature_selection']['percentage']
specs['fs_uni_grid'] = cfg['model']['feature_selection']['uni_grid']
score_func = cfg['model']['feature_selection']['score_func']
if score_func in feature_scorers:
specs['fs_score_func'] = feature_scorers[score_func]
else:
raise ValueError(
"model.yml model:feature_selection:score_func %s unrecognized" %
score_func)
# grid search
specs['grid_search'] = cfg['model']['grid_search']['option']
specs['gs_iters'] = cfg['model']['grid_search']['iterations']
specs['gs_random'] = cfg['model']['grid_search']['random']
specs['gs_sample'] = cfg['model']['grid_search']['subsample']
specs['gs_sample_pct'] = cfg['model']['grid_search']['sampling_pct']
# rfe
specs['rfe'] = cfg['model']['rfe']['option']
specs['rfe_step'] = cfg['model']['rfe']['step']
# Section: pipeline
specs['n_jobs'] = cfg['pipeline']['number_jobs']
specs['seed'] = cfg['pipeline']['seed']
specs['verbosity'] = cfg['pipeline']['verbosity']
# Section: plots
specs['calibration_plot'] = cfg['plots']['calibration']
specs['confusion_matrix'] = cfg['plots']['confusion_matrix']
specs['importances'] = cfg['plots']['importances']
specs['learning_curve'] = cfg['plots']['learning_curve']
specs['roc_curve'] = cfg['plots']['roc_curve']
# Section: treatments
try:
specs['treatments'] = cfg['treatments']
except:
specs['treatments'] = None
logger.info("No Treatments Found")
# Section: xgboost
specs['esr'] = cfg['xgboost']['stopping_rounds']
# Log the configuration parameters
logger.info('MODEL PARAMETERS:')
logger.info('algorithms = %s', specs['algorithms'])
logger.info('calibration = %r', specs['calibration'])
logger.info('cal_type = %s', specs['cal_type'])
logger.info('calibration_plot = %r', specs['calibration'])
logger.info('clustering = %r', specs['clustering'])
logger.info('cluster_inc = %d', specs['cluster_inc'])
logger.info('cluster_max = %d', specs['cluster_max'])
logger.info('cluster_min = %d', specs['cluster_min'])
logger.info('confusion_matrix = %r', specs['confusion_matrix'])
logger.info('counts = %r', specs['counts'])
logger.info('cv_folds = %d', specs['cv_folds'])
logger.info('directory = %s', specs['directory'])
logger.info('extension = %s', specs['extension'])
logger.info('drop = %s', specs['drop'])
logger.info('encoder = %r', specs['encoder'])
logger.info('esr = %d', specs['esr'])
logger.info('factors = %s', specs['factors'])
logger.info('features [X] = %s', specs['features'])
logger.info('feature_selection = %r', specs['feature_selection'])
logger.info('fs_percentage = %d', specs['fs_percentage'])
logger.info('fs_score_func = %s', specs['fs_score_func'])
logger.info('fs_uni_grid = %s', specs['fs_uni_grid'])
logger.info('grid_search = %r', specs['grid_search'])
logger.info('gs_iters = %d', specs['gs_iters'])
logger.info('gs_random = %r', specs['gs_random'])
logger.info('gs_sample = %r', specs['gs_sample'])
logger.info('gs_sample_pct = %f', specs['gs_sample_pct'])
logger.info('importances = %r', specs['importances'])
logger.info('interactions = %r', specs['interactions'])
logger.info('isomap = %r', specs['isomap'])
logger.info('iso_components = %d', specs['iso_components'])
logger.info('iso_neighbors = %d', specs['iso_neighbors'])
logger.info('isample_pct = %d', specs['isample_pct'])
logger.info('learning_curve = %r', specs['learning_curve'])
logger.info('logtransform = %r', specs['logtransform'])
logger.info('lv_remove = %r', specs['lv_remove'])
logger.info('lv_threshold = %f', specs['lv_threshold'])
logger.info('model_type = %r', specs['model_type'])
logger.info('n_estimators = %d', specs['n_estimators'])
logger.info('n_jobs = %d', specs['n_jobs'])
logger.info('ngrams_max = %d', specs['ngrams_max'])
logger.info('numpy = %r', specs['numpy'])
logger.info('pca = %r', specs['pca'])
logger.info('pca_inc = %d', specs['pca_inc'])
logger.info('pca_max = %d', specs['pca_max'])
logger.info('pca_min = %d', specs['pca_min'])
logger.info('pca_whiten = %r', specs['pca_whiten'])
logger.info('poly_degree = %d', specs['poly_degree'])
logger.info('pvalue_level = %f', specs['pvalue_level'])
logger.info('rfe = %r', specs['rfe'])
logger.info('rfe_step = %d', specs['rfe_step'])
logger.info('roc_curve = %r', specs['roc_curve'])
logger.info('rounding = %d', specs['rounding'])
logger.info('sampling = %r', specs['sampling'])
logger.info('sampling_method = %r', specs['sampling_method'])
logger.info('sampling_ratio = %f', specs['sampling_ratio'])
logger.info('scaler_option = %r', specs['scaler_option'])
logger.info('scaler_type = %r', specs['scaler_type'])
logger.info('scipy = %r', specs['scipy'])
logger.info('scorer = %s', specs['scorer'])
logger.info('seed = %d', specs['seed'])
logger.info('sentinel = %d', specs['sentinel'])
logger.info('separator = %s', specs['separator'])
logger.info('shuffle = %r', specs['shuffle'])
logger.info('split = %f', specs['split'])
logger.info('submission_file = %s', specs['submission_file'])
logger.info('submit_probas = %r', specs['submit_probas'])
logger.info('target [y] = %s', specs['target'])
logger.info('target_value = %d', specs['target_value'])
logger.info('treatments = %s', specs['treatments'])
logger.info('tsne = %r', specs['tsne'])
logger.info('tsne_components = %d', specs['tsne_components'])
logger.info('tsne_learn_rate = %f', specs['tsne_learn_rate'])
logger.info('tsne_perplexity = %f', specs['tsne_perplexity'])
logger.info('vectorize = %r', specs['vectorize'])
logger.info('verbosity = %d', specs['verbosity'])
# Specifications to create the model
return specs