def cross_vad(examples, num_folds = 10):
data = ut.dataCrossSplit(examples, num_folds, False)
errorRates = []
for i in range(num_folds):
egs = data[i]
dt = DTree(SelectAtt)
dt.training(egs[0], 1)
# calculate error rate
error = [0.] * 2
for j in range(2):
for x in egs[j]:
if dt.predict(x) != x[0]:
error[j] = error[j] + 1
error[j] = error[j] / len(egs[j])
print "Fold ", i, " trainingData errorRate: ", error[0], " testData errorRate:", error[1]
errorRates.append(error)
arr = np.array(errorRates)
print "Train Mean ErrorRate:", np.mean(arr[:,0]), " Test Mean ErrorRate:", np.mean(arr[:,1])
print "Train StdVar ErrorRate:", np.sqrt(np.var(arr[:,0])), " Test Mean ErrorRate:", np.sqrt(np.var(arr[:, 1]))
def getWeakLearner(w, egs):
"""
given:
a set of examples egs
a distribution on the examples w
return:
a decision stump y that minimize
J = \sum w_n I(y(x_n) \neq t_n)
"""
record = 0
error = 3171713.0
Nfeatures = len(egs[0]) - 1
for i in range(Nfeatures):
dt = DTree(lambda examples: i + 1)
dt.training(egs, 1)
tmp = weightedError(w, egs, dt)
if tmp < error:
error = tmp
record = dt
return record
def cross_vad(examples, num_folds = 10):
data = ut.dataCrossSplit(examples, num_folds, False)
errorRates = []
for i in range(num_folds):
egs = data[i]
dt = DTree(SelectAtt)
dt.training(egs[0], 1)
# calculate error rate
error = [0.] * 2
for j in range(2):
for x in egs[j]:
if dt.predict(x) != x[0]:
error[j] = error[j] + 1
error[j] = error[j] / len(egs[j])
print "Fold ", i, " trainingData errorRate: ", error[0], " testData errorRate:", error[1]
errorRates.append(error)
arr = np.array(errorRates)
print "Train Mean ErrorRate:", np.mean(arr[:,0]), " Test Mean ErrorRate:", np.mean(arr[:,1])
print "Train StdVar ErrorRate:", np.sqrt(np.var(arr[:,0])), " Test Mean ErrorRate:", np.sqrt(np.var(arr[:, 1]))
if __name__ == '__main__':
filename = sys.argv[1]
egs = ut.importRawData(filename)
egs = ut.preprocess(egs)
cross_vad(egs)
dt = DTree(SelectAtt)
dt.training(egs)
print "========= the decision tree ============"
dt.printTree()