def testExample1(self):
dataset = pd.read_csv('allelectronics.csv')
self.model = NaiveBayes(dataset)
self.model.train()
datatuple = {'age':'youth','income':'medium','student':'yes','credit_rating':'fair'}
print(self.model.predict(datatuple))
self.assertEqual(self.model.predict(datatuple),'yes')
def test_nb_using_iris(self):
iris = load_iris()
data = iris['data']
target = iris['target']
nb = NaiveBayes()
nb.fit(data, target)
preds = nb.predict(data)
assert accuracy_score(preds, target) > 0.9
def test_naive_bayes(self):
data = array([
[1, 'S'],
[1, 'M'],
[1, 'M'],
[1, 'S'],
[1, 'S'],
[2, 'S'],
[2, 'M'],
[2, 'M'],
[2, 'L'],
[2, 'L'],
[3, 'L'],
[3, 'M'],
[3, 'M'],
[3, 'L'],
[3, 'L'],
])
labels = array([-1, -1, 1, 1, -1, -1, -1, 1, 1, 1, 1, 1, 1, 1, -1])
nb = NaiveBayes()
nb.fit(data, labels)
preds = nb.predict(data)
assert accuracy_score(preds, labels) > 0.7
def __init__(self, categories, path):
self.naive_bayes = NaiveBayes(categories)
self.path = path
self.classified_examples = dict()
from dataset_parser import parse_dataset from bayes import NaiveBayes from test_train_split import dataset_split dataset = parse_dataset() (train, test) = dataset_split(dataset, 0.2) naive_bayes = NaiveBayes(train, 'class') score = naive_bayes.evaluate(test) print(score)
+##+ +#+
### +#+
+##+ +##+
+## +##+
+#+ +##+
+#+ +##
+#+ +#+
+##+ +##+
###+ +##+
+####++###++
+#########
++#######
+###+++
"""
digitPercep = PerceptronNetwork(digitWidth * digitHeight, digitY)
digitPercep.train(digitWidth, digitHeight, digitTrainingImagesPath,
digitTrainingLabelsPath)
print "Perceptron guess:"
print digitPercep.test_one(digitWidth, digitHeight, digit)
digitBayes = NaiveBayes(digitWidth * digitHeight, 10, 2)
digitBayes.train(digitWidth, digitHeight, digitTrainingImagesPath,
digitTrainingLabelsPath)
print "Naive Bayes guess:"
print digitBayes.test_one(digitWidth, digitHeight, digit)
from bayes import NaiveBayes
from util import FileOperate
from util import train_test_split
from metrics import accuracy_score
# 运行这部分代码的时候，要将 playML 这个文件夹设置为源代码的根文件夹
if __name__ == '__main__':
# 1、加载数据，spam 表示垃圾短信（1），ham 表示非垃圾短信（0）
data_path = '../input/SMSSpamCollection'
label = '\t'
fo = FileOperate(data_path, label)
X, y = fo.load_data()
# 2、分割数据集，得到训练数据集与测试数据集
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=.25,
random_state=666)
# 开始训练
nb = NaiveBayes()
nb.fit(X_train, y_train)
# 开始预测
y_pred = nb.predict(X_test)
# 计算得分
score = accuracy_score(y_test, y_pred)
print('准确率：', score)
from backends import RedisBackend
from bayes import NaiveBayes
from classifiers import FMClassifier
from optparse import OptionParser
parser = OptionParser(conflict_handler='resolve')
parser.add_option('-h', dest='host')
parser.add_option('-p', '--port', dest='port')
options, args = parser.parse_args()
clsfr = FMClassifier(
pickle.load(
open(
'/Users/georgecourtsunis/projects/disqus/disqus/analytics/hadoop/thread_views/var/cmap.b',
'rb')))
backend = RedisBackend(host=options.host, port=options.port)
bayes = NaiveBayes(backend=backend)
_start = time.time()
for file_name in args:
print 'Training file %s' % file_name
fd = open(file_name, 'r')
_counter = 0
for line in fd:
_counter += 1
if _counter % 100000 == 0:
print _counter, (time.time() - _start)
# if _counter % 1000000 == 0:
# break
# grab args
vector, count = line.split('\t')
vector = json.loads(vector)
# -*- coding:utf-8 -*-
from bayes import NaiveBayes
def loadDataSet():
train_samples = [
['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
['my', 'dalmation', 'is', 'so', 'cute', ' and', 'I', 'love', 'him'],
['stop', 'posting', 'stupid', 'worthless', 'garbage'],
['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']
]
test_samples = [['love', 'my', 'girl', 'friend'], ['stupid', 'garbage'],
['Haha', 'I', 'really', "Love", "You"],
['This', 'is', "my", "dog"]]
train_classes = [0, 1, 0, 1, 0, 1] # 0：good; 1:bad
return train_samples, train_classes, test_samples
if __name__ == "__main__":
train_samples, train_classes, test_samples = loadDataSet()
clf = NaiveBayes()
clf.train(train_samples, train_classes)
# test:
for item in test_samples:
clf.classify(item)
print "times: {}".format(digitPercepTimes)
print "means: {}".format(digitPercepAvgs)
print "stds: {}".format(digitPercepStds)
# naive bayes classification
#print "---------- Naive Bayes ----------"
digitBayesAvgs = []
digitBayesStds = []
digitBayesTimes = []
for percent in percents:
p = percent / 10.0
x = 5
res = []
times = []
for i in range(0, 5):
digitBayes = NaiveBayes(digitWidth * digitHeight, 10, 2)
t1 = time.time()
digitBayes.train(digitWidth, digitHeight, digitTrainingImagesPath,
digitTrainingLabelsPath, p)
dt = time.time() - t1
percentageCorrect = digitBayes.test(digitWidth, digitHeight,
digitTestImagesPath,
digitTestLabelsPath)
res.append(percentageCorrect)
times.append(dt)
avgTime = mean(times)
avgAcc = mean(res)
stdAcc = stddev(res)
digitBayesAvgs.append(avgAcc)
digitBayesStds.append(stdAcc)
digitBayesTimes.append(avgTime)
