def forest_config(config, n_jobs=[-1], settings=None):
"""
forest_config: obj -> obj
---------------------------------------------------------------
Sets the defaults for a custom forest configuration object
from configobj.
The defaults are only set if the setting does not exist (thus,
it is implied that the user needs a default).
Required Parameters
-------------------
* config: obj
The configobj instance object to scan if defaults
have been customized.
Optional Parameters
-------------------
* settings: None
The global settings to use if it exists, otherwise
use the defaults.
Returns
-------
* config: obj
The configobj instance after defaults have been set
if applicable.
---------------------------------------------------------------
"""
config = _global_config(config, settings, RandomForestClassifier._get_param_names())
config['n_estimators'] = [10, 64, 96, 128] if 'n_estimators' not in config else config['n_estimators']
config['criterion'] = ['entropy'] if 'criterion' not in config else config['criterion']
config['oob_score'] = [True] if 'oob_score' not in config else [True]
config['class_weight'] = ['balanced'] if 'class_weight' not in config else config['class_weight']
config['n_jobs'] = [n_jobs] if 'n_jobs' not in config else config['n_jobs']
return config
except ImportError:
import draw
import feature as fea
import metrics as mt
BASE_PATH = Path(__file__).parent
RAA_DB = BASE_PATH / 'nr_raa_data.db'
NAA = ['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K',
'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y']
svm_params = SVC._get_param_names()
knn_params = KNeighborsClassifier._get_param_names()
rf_params = RandomForestClassifier._get_param_names()
clf_param_names = {'svm': svm_params, 'knn': knn_params, 'rf': rf_params}
clf_dic = {'svm': SVC, 'knn': KNeighborsClassifier, 'rf': RandomForestClassifier}
def check_aa(aa):
if aa[0] == "-" or aa[-1] == "-":
raise ValueError("amino acid cluster is wrong!")
if "-" not in aa:
raise ValueError("need an amino acid cluster!")
aa = aa.strip().upper()
cls_ls = list(aa.replace("-", "")).sort()
if NAA.sort() != cls_ls:
raise ValueError("amino acid cluster is wrong!")
# TODO - query optimization