def run(self, _model, _files):
R = {}
l = len(_files)
folds = 10
for y in range(l):
training = _files[y]
for x in range(l):
cfg = Configuration(training, _model, folds)
cfg.resultFolder = "results/" + self.id + "/"
cfg.tmpFolder = cfg.resultFolder + "tmp/"
test = _files[x]
csvA = CSV(training)
csvA.randomize(self.seed)
csvA.createFolds(folds, cfg.tmpFolder)
csvB = CSV(test)
csvB.randomize(self.seed)
csvB.createFolds(folds, cfg.tmpFolder)
cv = CrossValidation(cfg)
cv.model = _model
cv.folds = folds
cv.id = str(y) + "_" + str(x)
r = cv.run(csvA.id, csvB.id)
results = np.hstack([r.data.mean(0),
r.data.std(0)
]) # TUDO: mean only if size>1 !
# init the result matrices
if len(R) == 0:
for key in r.header:
R[key] = ResultMatrix([
FileHandler().generateId(file) for file in _files
], np.zeros((l, l)))
R[key + "_std"] = ResultMatrix([
FileHandler().generateId(file) for file in _files
], np.zeros((l, l)))
# update the result matrices
for i in range(len(r.header)):
R[r.header[i]].data[y][x] = results[i]
R[r.header[i] + "_std"].data[y][x] = results[i]
for key in R.keys():
R[key].save("results/" + self.id + "/" + key + ".csv")
def run(self, _models, _folds, _type):
if self.genDataSets:
csv = CSV()
csv.load(self.training)
csv.randomize(self.seed)
if _type == Type.REGRESSION:
csv.createFolds(_folds, self.resultFolder + "tmp/")
elif _type == Type.CLASSIFICATION:
classes = csv.stratify(_folds, self.resultFolder + "tmp/")
R = ResultMatrix()
for i in range(0, len(_models)):
model = _models[i]
model.modelType = _type
config = Configuration(self.training, model, _folds)
config.resultFolder = self.resultFolder
config.tmpFolder = self.resultFolder + "tmp/"
cv = CrossValidation(config, str(i))
r = cv.run(csv.id, csv.id)
results = np.hstack([r.data.mean(0),
r.data.std(0)]) # TUDO: mean only if size>1 !
R.add(r.header + [x + "_std" for x in r.header], results)
if self.verbose:
if i == 0:
r.printHeader()
r.printAggregated()
FileHandler().saveMatrix(R.header, R.data,
self.resultFolder + "results.csv")
if self.clear:
FileHandler().clearFolder(self.resultFolder + "tmp/")
return R.header, R.data