def build_model(training_data, config):
'''
Build model from the config and training data
'''
m_type = config[c.CLSFR_TYPE]
if m_type == c.DT_WITH_IG:
# for decision tree
# load thresholds
threshs = loader.load_arrays(config[c.THRESHS])
tree = Tree.Tree()
tree.build(utils.split_on_ig, training_data[0],
training_data[1], threshs, config[c.TERM_CON], int(config[c.TERM_THRESH]))
return tree
elif m_type == c.REGRESSION_TREE:
# for regression tree
# load thresholds
threshs = loader.load_arrays(config[c.THRESHS])
tree = Tree.Tree()
tree.build(utils.split_on_mse, training_data[0],
training_data[1], threshs, config[c.TERM_CON], float(config[c.TERM_THRESH]))
return tree
elif m_type == c.REGRESSION:
# for linear regression
reg_model = rmodel.Regression()
reg_model.build(training_data[0], training_data[1])
return reg_model
import EM as em import DataLoader as loader import numpy as np GAUSS2 = 'data/2gaussian.txt' GAUSS3 = 'data/3gaussian.txt' path = GAUSS3 k = 3 x = np.matrix(loader.load_arrays(path)) x = np.transpose(x) label, model, llh = em.em(x, k) print model
