def export(self, _training, _model, _out, _discretize=False):
FileHandler().createFolder("tmp")
tmpId = "_" + str(uuid.uuid1())
tmpFolder = "tmp/"
tmpTraining = "train" + tmpId + ".arff"
csv = CSV(_training)
csv.convertToARFF(tmpFolder + tmpTraining, False)
d = None
if _discretize:
d = csv.discretizeData()
attributes = csv.findAttributes(0)
weka = WEKA()
weka.folder = tmpFolder
weka.train(_model, tmpFolder + tmpTraining, tmpId)
data = "\n".join(FileHandler().read(tmpFolder + "raw" + tmpId + ".txt"))
FileHandler().checkFolder(_out)
weka.modelInterface.exportCode(data, csv, attributes, _out, _training, discretization=d)
FileHandler().deleteFiles([tmpFolder + tmpTraining, tmpFolder + "raw" + tmpId + ".txt"])
from models.randomforest.RandomForest import RandomForest
from experiment.Experiment import Experiment
from code.CodeGenerator import CodeGenerator
from code.CodeEvaluator import CodeEvaluator
from data.CSV import CSV
# define the training data set and set up the model
training = "../examples/mnoA.csv"
training = "../examples/vehicleClassification.csv"
csv = CSV(training)
attributes = csv.findAttributes(0)
d = csv.discretizeData()
model = RandomForest()
model.config.trees = 10
model.config.depth = 5
# perform a 10-fold cross validation
e = Experiment(training, "example_rf_disc")
e.classification([model], 10)
# export the C++ code
CodeGenerator().export(training, model, e.path("rf.cpp"), d)
#
ce = CodeEvaluator()
R, C = ce.crossValidation(model, training, attributes, e.tmp(), d)
R.printAggregated()