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()
for k in range(1, len(crossData[i][1]) + 1):
for x in crossData[i][1][k]:
totNum = totNum + 1
if cl.classify(x) != k:
totError = totError + 1
return (totError + 0.) / totNum
# check input
if len(sys.argv) != 3:
print "input error"
exit()
fileName = sys.argv[1]
if fileName == "Iris.csv":
subDim = 3
else:
subDim = 9
num_cross = int(sys.argv[2])
# import data
# since the date in the file are in order
# need to make it random to run cross validation
rawData = ut.makeDataRandom(ut.importRawData(fileName))
rawData = ut.importRawData(fileName)
trainData = ut.dataCrossSplit(rawData, num_cross)
#print tmp[1]
print "Data: ", fileName
print "Error rate for cross_validation:", cross_validation(trainData, subDim)
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 20 22:55:53 2013
@author: jiecaoc
"""
import utilities as ut
import classes as cls
egs = ut.importRawData('Ionosphere.csv')
raw = ut.dataCrossSplit(egs, 2, False)
dt = cls.DTree(cls.SelectAtt)
dt.training(raw[0][0])
c = 0
for eg in raw[0][1]:
if eg[0] != dt.predict(eg):
# print eg[0], dt.predict(eg)
c = c + 1
print (c + .0) / len(egs)
w1 = ut.ls2Vec([0.5] * phi.shape[1])
delta = 1
while delta > 0.5:
w0 = w1
pi = Pi(w0, phi)
R = calcR(pi)
tmp = reduce(np.dot, [phi.transpose(), R, phi])
z = np.dot(phi, w0) - np.dot(np.linalg.inv(R), (pi - y))
w1 = reduce(np.dot, [np.linalg.inv(tmp), phi.transpose(), R, z])
delta = np.linalg.norm(np.dot(phi.transpose(), (y - pi)))
print delta
return w1
# import data
data = ut.importRawData('Pima.csv')
k = 100
y = ut.ls2Vec(map(lambda x: x[0] - 1 , data[1:k]))
phi = np.array(map(lambda x: x[1:], data[1:k]))
#print phi
w = calculateW(phi, y)
#print calcR(Pi(w, phi))
#pi = Pi(w, phi)
#print np.linalg.det(np.dot(phi.transpose(), phi))
# w = reduce(np.dot, [np.linalg.inv(np.dot(phi.transpose(), phi)) , phi.transpose(), y])
print w
for x in data[1:k]:
print x[0] - 1, sigma( np.dot(w.transpose(), ut.ls2Vec(x[1:])))
#print np.dot(phi.transpose(), (y - pi))
