def gbjjInnerLoop(learner):
"""
@param learner:
@return: cv score of the learner
"""
global trainX, trainY, lf, n_jobs, cvObj
l = clone(learner)
scores = jjcross_val_score(l, trainX, trainY, score_func=lf, n_jobs=n_jobs, cv=cvObj)
return scores.mean()
def _fit_stage(self, X, y, rmTolerance):
"""
fits one stage of gradient boosting
@param X:
@param y:
@param rmTolerance: tolerance for 1D optimization
@return: nothing
"""
residuals = self.lossFunction.negative_gradient(y, self._currentPrediction)
trainX, trainY, _, _ = splitTrainTest(X, residuals, 1-self.subsample) # stochastic boosting. train only on a portion of the data
if len(np.unique(trainY))==1:
hm = MajorityPredictor().fit(trainY)
else:
cvObj = KFold(n=len(trainX), n_folds=self.cvNumFolds, indices=False, shuffle=True, random_state=self.randomState)
# find the h that best mimics the negative gradient
if self.n_jobs > 1: # parallel
n_jobs = max(1, self.n_jobs/len(self.learners), self.cvNumFolds)
# n_jobs = 1
pool = MyPool(processes=self.n_jobs, initializer=gbjjInit, initargs=(trainX, trainY, self.lossFunction, n_jobs, cvObj))
temp = pool.map_async(gbjjInnerLoop, self.learners)
temp.wait()
h_res = temp.get()
pool.close()
pool.join()
else: # single thread
h_res = []
for learner in self.learners:
if self.verbosity >= 2:
print 'Fitting learner:', learner
l = clone(learner)
scores = jjcross_val_score(l, trainX, trainY, score_func=self.lossFunction, n_jobs=1, cv=cvObj)
h_res.append(scores.mean())
hm = clone(self.learners[np.argsort(h_res)[0]])
if self.verbosity>=1:
print "The best classifier is", hm.__class__
# find rm
hm.fit(trainX, trainY)
hmx = hm.predict(X)
rm = minimize_scalar(lambda r: self.lossFunction(y, self._currentPrediction + r*hmx), tol=rmTolerance).x
# append estimator and weight
self._estimators.append((hm, rm))
