def main():
doc = open("fingerprintGender.txt",'r')
wordsDict = getwords(doc.read())
genericClassifier = classifier.classifier(wordsDict)
genericClassifier.setdb("generic.db")
sampletrain(genericClassifier)
print "---genericClassifier---"
print genericClassifier.weightedprob('quick rabbit','good', genericClassifier.fprob)
print "---Naive Bayes---"
bayesClassifier = naivebayes.naivebayes(wordsDict)
bayesClassifier.setdb("bayes.db")
sampletrain(bayesClassifier)
print bayesClassifier.prob('quick rabbit','good')
bayesClassifier.classify('quick money',default='unknown')
for i in range(10): sampletrain(bayesClassifier)
print bayesClassifier.classify('quick money',default='unknown')
print "---FISHER CLASSIFIER---"
fisher = fisherclassifier.fisherclassifier(wordsDict)
fisher.setdb("fisher.db")
sampletrain(fisher)
print fisher.fisherprob('quick rabbit','good')
print fisher.weightedprob('money','bad', fisher.cprob)
def main():
trainingparams = [0.01, 0.02, 0.03, 0.125, 0.625, 1]
iterations = 5
eta = 0.001
epsilon = 0.001
valuerange = 10
params = []
data = utils.getdata('breast-cancer-wisconsin.data.txt')
nb = naivebayes.naivebayes(data, trainingparams, iterations, valuerange)
nb['label'] = 'Naive Bayes'
lr = logisticregression.logisticregression(data, trainingparams,
iterations, eta, epsilon)
lr['label'] = 'Logistic Regression'
params.append(lr)
params.append(nb)
plot = graph.plot(params, 'Training Set', 'Accuracy')
plot.show()
return
data_test = r.readfile("Text_Data_for_Project1_test_data.txt")
alabel_train, clabel_train, adata_train, cdata_train = p.p_traindata(
data_train)
alabel_test, adata_test = p.p_testdata(data_test)
atraintestmix = np.vstack((adata_train, adata_test))
att_num = np.shape(adata_train)[1]
dat_num = np.shape(adata_train)[0]
adata_traintest_dummy, a_label = p.indexing(atraintestmix,
att_num,
dat_num,
key="test")
adata_train_dummy = adata_traintest_dummy[:-1, :]
adata_test_dummy = np.array([adata_traintest_dummy[-1, :]])
cdata_train_dummy, c_label = p.indexing(cdata_train, 1, dat_num, key="test")
m, p = 0, 0
prior_probability = cd.cal_prior(adata_train_dummy, cdata_train_dummy, a_label,
c_label, dat_num, m, p)
a_probability = cd.cal_prob(adata_train_dummy, dat_num)
c_probability = cd.cal_prob(cdata_train_dummy, dat_num)
result = nb.naivebayes(adata_test_dummy, prior_probability, a_probability,
c_probability, a_label, c_label)
print(result)
# print cl.prob('quick money', 'bad')
# for i in range(10):
# docclass.sampletrain(cl)
# print cl.classify('quick money', defalt='unknow')
# print cl.prob('quick money', 'good')
# print cl.prob('quick money', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.cprob('quick', 'good')
# print cl.cprob('money', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.cprob('quick', 'good')
# print cl.fisherprob('quick rabbit', 'good')
# print cl.fisherprob('quick rabbit', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.classify('quick rabbit')
# print cl.classify("quick money")
# cl.setminimum('bad', 0.8)
# print cl.classify("quick money")
cl = fisherClassifier.FisherClassifier(docclass.getwords)
cl.setdb("test1.db")
docclass.sampletrain(cl)
cl2 = naivebayes.naivebayes(docclass.getwords)
cl2.setdb("test1.db")
print cl2.classify('quick money')
from whoareyou import whoareyou from genTrainFeatures import genTrainFeatures from naivebayesCL import naivebayesCL xTr, yTr = genTrainFeatures() w, b = naivebayesCL(xTr, yTr) #whoareyou(w,b) from naivebayes import naivebayes x1 = xTr[:, 1] print(x1.shape) log = naivebayes(xTr, yTr, x1) print(log)
def example_tests():
# =============================================================================
# function [r, ok, s]=example_tests()
#
# Tests the functions from homework assignment 0
# Please make sure that the error statements are instructive.
#
# Output:
# r= The number of tests that failed
# ok= The number of tests that passed
# s= statement describing the failed test (s={} if all succeed)
# =============================================================================
# Put in any seed below
random.seed(31415926535)
# initial outputs
r = 0
ok = 0
s = [] #used to be matlab cell array
# load in name data
xTr, yTr = genTrainFeatures()
print('---------Starting Test 1---------')
try:
# Test 1: check if probabilities sum to 1
pos, neg = naivebayesPY(xTr, yTr)
failtest = (np.linalg.norm(pos + neg - 1) > 1e-8)
addon = ''
except:
failtest = True
addon = traceback.format_exc()
if failtest:
r = r + 1
s += 'Failed Test 1 naivebayesPY: Probabilities of P(Y) do not sum to 1.\n' + addon + '\n'
print("failed")
else:
ok = ok + 1
print('---------Completed Test 1---------')
y = np.matrix([-1, 1])
x = np.matrix([[0, 1], [1, 0]])
failtest = False
print('---------Starting Test 2---------')
try:
# Test 2: Test the Naive Bayes function on a simple matrix
pos, neg = naivebayesPY(x, y)
pos0 = 0.5
neg0 = 0.5
if (pos != pos0) or (neg != neg0):
failtest = True
addon = ''
except:
failtest = True
addon = traceback.format_exc()
if failtest:
r = r + 1
s += 'Failed Test 2 naivebayesPXY: The calculation of P(Y) seems incorrect.\n' + addon + '\n'
print("failed")
else:
ok = ok + 1
print('---------Completed Test 2---------')
failtest = False
print('---------Starting Test 3---------')
pospossi0 = np.matrix([[0.66667], [0.33333]])
negpossi0 = np.matrix([[0.33333], [0.66667]])
try:
# Test 3 calculate conditional probabilities
pospossi, negpossi = naivebayesPXY(x, y)
print(pospossi)
print(negpossi)
addon = ''
if (np.linalg.norm(pospossi - pospossi0) >
1e-3) or (np.linalg.norm(negpossi - negpossi0) > 1e-3):
failtest = True
except:
failtest = True
addon = traceback.format_exc()
if failtest:
r = r + 1
s += 'Failed Test 3: The calculation of P(X|Y) seems incorrect.\n' + addon + '\n'
print("failed")
else:
ok = ok + 1
print('---------Finished Test 3---------')
# Tests 4~8 are testing about the naivebayesPXY function.
# Some are sanity tests that the function is returning reasonable answers.
# Some are making sure they are correct on small cases
print('---------Starting Test 4---------')
xTr, yTr = genTrainFeatures()
posprob, negprob = naivebayesPXY(xTr, yTr)
print(posprob.shape)
print(negprob.shape)
print('---------Finished Test 4---------')
# Tests 9 is on naivebayes
print('---------Starting Test 9---------')
logratio = naivebayes(x, y, np.array([[1], [1]]))
print(logratio)
print("---------------------------------")
logratio = naivebayes(x, y, np.array([[0], [0]]))
print(logratio)
print('---------Finished Test 9---------')
# Tests 10-11 is on naivebayesCL
print('---------Starting Test 10-11---------')
w, b = naivebayesCL(xTr, yTr)
print(w.shape)
print(b)
w, b = naivebayesCL(x, y)
print(w.shape)
print(b)
print('---------Finished Test 10-11---------')
percentage = ok / (r + ok) * 100
print("Passing percentage: " + str(percentage))
return r, ok, s
# print cl.prob('quick money', 'bad')
# for i in range(10):
# docclass.sampletrain(cl)
# print cl.classify('quick money', defalt='unknow')
# print cl.prob('quick money', 'good')
# print cl.prob('quick money', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.cprob('quick', 'good')
# print cl.cprob('money', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.cprob('quick', 'good')
# print cl.fisherprob('quick rabbit', 'good')
# print cl.fisherprob('quick rabbit', 'bad')
# cl=fisherClassifier.FisherClassifier(docclass.getwords)
# docclass.sampletrain(cl)
# print cl.classify('quick rabbit')
# print cl.classify("quick money")
# cl.setminimum('bad', 0.8)
# print cl.classify("quick money")
cl=fisherClassifier.FisherClassifier(docclass.getwords)
cl.setdb("test1.db")
docclass.sampletrain(cl)
cl2=naivebayes.naivebayes(docclass.getwords)
cl2.setdb("test1.db")
print cl2.classify('quick money')
