def train(features, steps=10):
classifiers = []
#print len(features)
weights = [1 for n in features]
errors = []
bestStump = {}
featureList = features[0][0].keys()
for i in range(0, steps):
print "iteration: {0}".format(i)
minError = 99999999
for f in featureList:
#print "feature name={0}".format(f)
ds, matches = DecisionStump.train(features,f, weights)
error = ds.getErrorRate()
if error < minError:
minError = error
bestStump["stump"] = ds
bestStump["matches"] = matches
minError = minError / len(features)
alpha = float(0.5 * log((1.0-minError) / max(minError, 1e-16)))
bestStump["alpha"] = alpha
classifiers.append(bestStump)
AdaBoost2.setWeights(weights, bestStump["matches"], alpha)
errors.append(minError)
#aggErrorRate = sum(errors) / len(features)
print "error={0}".format(minError)
if minError == 0:
break
_max = max(errors)
votingWeights = [1 - e / sum(errors) for e in errors]
return AdaBoost2({'featureList':featureList, 'classifiers':classifiers, 'votingWeights':votingWeights})
def train(features, steps=10):
bestStumps = []
minError = 99999999
featureList = features[0][0].keys()
for i in range(steps):
classifiers = []
#print len(features)
weights = [5 for n in features]
errors = []
shuffle(featureList)
for f in featureList:
#print "feature name={0}".format(f)
ds, matches = DecisionStump.train(features,f, weights, 15)
#print len(features)
#print features[0][0]
AdaBoost.setWeights(weights, matches)
#AdaBoost.printWeights(weights)
errors.append(ds.getErrorRate())
classifiers.append(ds)
error = sum(errors)
print("error=",error)
if error < minError:
minError = error
bestStumps = list(classifiers)
_max = max(errors)
votingWeights = [1 - e / _max for e in errors]
print("minError=",minError)
return AdaBoost4({'featureList':featureList, 'classifiers':bestStumps, 'votingWeights':votingWeights})
def get_hypothesis(self, sampled_train_data):
"""
:param pandas.DataFrame sampled_train_data:
:return: self.best_stump
:type: DecisionStump
"""
self.stumps = []
self.max_gain = -float("inf") # negative infinity
self.best_stump = None # type: DecisionStump
for name in self.stump_names:
stump_temp = DecisionStump(name)
stump_temp.train(sampled_train_data)
self.stumps.append(stump_temp)
for stump in self.stumps:
gain_temp = stump.get_info_gain()
if gain_temp > self.max_gain:
self.max_gain = gain_temp
self.best_stump = stump
return self.best_stump
def train(features, steps=10):
classifiers = []
#print len(features)
weights = [10 for n in features]
errors = []
featureList = features[0][0].keys()
for f in featureList:
#print "feature name={0}".format(f)
ds, matches = DecisionStump.train(features,f, weights, steps)
#print len(features)
#print features[0][0]
AdaBoostAtCascade.setWeights(weights, matches)
#AdaBoost.printWeights(weights)
errors.append(ds.getErrorRate())
classifiers.append(ds)
_max = max(errors)
votingWeights = [1 - e / _max for e in errors]
return AdaBoostAtCascade({'featureList':featureList, 'classifiers':classifiers, 'votingWeights':votingWeights})