def simpleTest():
vocabularyList, pWordsSpamicity, pWordsHealthy, pSpam, DS = \
naiveBayes.getTrainedModelInfo()
fileFolder = './test/'
smsWords, classLables = naiveBayes.loadMailData(fileFolder)
smsType = naiveBayes.classify(vocabularyList, pWordsSpamicity,
pWordsHealthy, pSpam, smsWords[0])
print(smsType)
def testClassifyErrorRateByIndex():
fileFolder = './public/'
smsWords, classLables = naiveBayes.loadMailDataTest(fileFolder)
test_index = [
2, 6, 7, 8, 13, 16, 19, 29, 35, 37, 40, 42, 43, 45, 46, 49, 51, 52, 64,
65, 71, 72, 78, 79, 80, 84, 85, 90, 91, 98, 103, 109, 111, 117, 123,
129, 135, 138, 142, 149, 169, 188, 191, 192, 203, 221, 225, 226, 229,
232, 236, 243, 250, 254, 257, 258, 259, 264, 268, 281, 298, 300, 308,
319, 322, 329, 333, 335, 338, 339, 340, 344, 347, 358, 359, 362, 382,
385, 391, 394, 402, 410, 415, 417, 418, 422, 423, 424, 425, 428, 437,
441, 456, 461, 462, 470, 472, 477, 480, 481
]
testWords = [smsWords[i] for i in test_index]
testWordsType = [classLables[i] for i in test_index]
# testCount = 200
# for i in range(testCount):
# randomIndex = int(random.uniform(0, len(classLables)))
# testWordsType.append(classLables[randomIndex])
# testWords.append(smsWords[randomIndex])
# del (smsWords[randomIndex])
# del (classLables[randomIndex])
vocabularyList, pWordsSpamicity, pWordsHealthy, pSpam, DS = \
naiveBayes.getTrainedModelInfo()
errorCount = 0.0
tp, tn, fp, fn = 0, 0, 0, 0
for i in range(len(test_index)):
smsType = naiveBayes.classify(vocabularyList, pWordsSpamicity,
pWordsHealthy, pSpam, testWords[i])
print('predicted:', smsType, ' actual:', testWordsType[i])
if smsType != testWordsType[i]:
if (smsType == 1):
fp += 1
else:
fn += 1
else:
if (smsType == 1):
tp += 1
else:
tn += 1
print("""
Predicted: | SPAM | HAM
----------------------------
Ground Truth: | |
SPAM | %4d | %4d
HAM | %4d | %4d
""" % (tp, fn, fp, tn))
acc = (tp + tn) / (fp + fn + tp + tn)
print("acc->", acc)
def testClassifyErrorRateMSE():
fileFolder = './public/'
mailWords, classLables = naiveBayes.loadMailData(fileFolder)
test_index = [
2, 6, 7, 8, 13, 16, 19, 29, 35, 37, 40, 42, 43, 45, 46, 49, 51, 52, 64,
65, 71, 72, 78, 79, 80, 84, 85, 90, 91, 98, 103, 109, 111, 117, 123,
129, 135, 138, 142, 149, 169, 188, 191, 192, 203, 221, 225, 226, 229,
232, 236, 243, 250, 254, 257, 258, 259, 264, 268, 281, 298, 300, 308,
319, 322, 329, 333, 335, 338, 339, 340, 344, 347, 358, 359, 362, 382,
385, 391, 394, 402, 410, 415, 417, 418, 422, 423, 424, 425, 428, 437,
441, 456, 461, 462, 470, 472, 477, 480, 481
]
testWords = [mailWords[i] for i in test_index]
testWordsType = [classLables[i] for i in test_index]
# testCount = 200
# for i in range(testCount):
# randomIndex = int(random.uniform(0, len(classLables)))
# testWordsType.append(classLables[randomIndex])
# testWords.append(smsWords[randomIndex])
# del (smsWords[randomIndex])
# del (classLables[randomIndex])
vocabularyList, pWordsSpamicity, pWordsHealthy, pSpam, DS = \
naiveBayes.getTrainedModelInfo()
errorCount = 0.0
tp, tn, fp, fn = 0, 0, 0, 0
se = 0
for i in range(len(test_index)):
testWordsCount = naiveBayes.setOfWordsToVecTor(vocabularyList,
testWords[i])
trainMarkedWords = np.array(testWordsCount)
p1, p0, type = naiveBayes.adaboostClassify(vocabularyList,
pWordsSpamicity,
pWordsHealthy, DS, pSpam,
trainMarkedWords)
autual = testWordsType[i]
if autual == 1:
se += (pow((p1 / 20000 - 1), 2) + pow((p0 / 20000), 2)) / 2
else:
se += (pow((p1 / 20000), 2) + pow((p0 / 20000 - 1), 2)) / 2
print("mse->", se / len(test_index))
def testClassifyErrorRate():
fileFolder = './public/'
smsWords, classLables = naiveBayes.loadMailDataTest(fileFolder)
#smsWords, classLables = naiveBayes.loadMailData(fileFolder)
testWords = smsWords
testWordsType = classLables
vocabularyList, pWordsSpamicity, pWordsHealthy, pSpam, DS = \
naiveBayes.getTrainedModelInfo()
errorCount = 0.0
tp, tn, fp, fn = 0, 0, 0, 0
for i in range(len(classLables)):
# smsType = naiveBayes.adaboostClassifyForPredict(vocabularyList, pWordsSpamicity,
# pWordsHealthy, DS, pSpam, testWords[i])
smsType = naiveBayes.classify(vocabularyList, pWordsSpamicity,
pWordsHealthy, pSpam, testWords[i])
#print('predicted:', smsType, ' actual:', testWordsType[i])
if smsType != testWordsType[i]:
print(i)
if (smsType == 1):
fp += 1
else:
fn += 1
else:
if (smsType == 1):
tp += 1
else:
tn += 1
print("""
Predicted: | SPAM | HAM
----------------------------
Ground Truth: | |
SPAM | %4d | %4d
HAM | %4d | %4d
""" % (tp, fn, fp, tn))
acc = 100.0 * (tp + tn) / (fp + fn + tp + tn)
print("acc->", acc)