def test(classif,
n=1,
train_size=500,
mode='k',
iterations=1,
dataset='',
extra_dataset=None,
limit=None,
binary=False,
idf=False,
negation=True):
(pos_dir, neg_dir) = select_dataset(dataset)
if extra_dataset:
mode = 'd'
iterations = 1
train_size = 1000
test_set = dataset
else:
test_set = None
print "TEST CONFIGURATION"
print "dataset: %(dataset)s, stars: %(extra_dataset)s \nn: %(n)s, limit: %(limit)s, binary: %(binary)s, \nmode: %(mode)s, iterations: %(iterations)s, idf: %(idf)s" % {
'n': n,
'train_size': train_size,
'mode': mode,
'iterations': iterations,
'dataset': dataset,
'extra_dataset': extra_dataset,
'limit': limit,
'binary': binary,
'idf': idf
}
ind = Indexes(mode=mode, iterations=iterations, train_size=train_size)
(pos_correct, neg_correct) = (0, 0)
for k in range(iterations):
ind.next()
m = TestConfiguration(classif,
n,
ind,
pos_dir,
neg_dir,
idf=idf,
test_set=test_set,
binary=binary,
limit=limit,
negation=negation)
m.train()
(pos, neg) = m.test()
pos_correct += pos
neg_correct += neg
print "Results:"
print "Positive:", round((pos_correct / iterations) * 100), "%"
print "Negative:", round((neg_correct / iterations) * 100), "%"
print "Total:", round(
(neg_correct + pos_correct) / (2 * iterations) * 100), "%"
def crossValidate(self, iterations, mode='k', train_size=500):
ind = Indexes(mode=mode, iterations=iterations, train_size=train_size)
pos_correct = 0
neg_correct = 0
for k in range(iterations):
ind.next()
self.set_index(ind)
self.train()
(pos, neg) = self.test()
pos_correct += pos
neg_correct += neg
print "Results:"
print "Positive:", round((pos_correct/iterations)*100), "%"
print "Negative:", round((neg_correct/iterations)*100), "%"
print "Total:", round((neg_correct + pos_correct)/(2*iterations)*100), "%"
def crossValidate(self, iterations, mode='k', train_size=500):
ind = Indexes(mode=mode, iterations=iterations, train_size=train_size)
pos_correct = 0
neg_correct = 0
for k in range(iterations):
ind.next()
self.set_index(ind)
self.train()
(pos, neg) = self.test()
pos_correct += pos
neg_correct += neg
print "Results:"
print "Positive:", round((pos_correct / iterations) * 100), "%"
print "Negative:", round((neg_correct / iterations) * 100), "%"
print "Total:", round(
(neg_correct + pos_correct) / (2 * iterations) * 100), "%"
def test(classif, n=1, train_size=500, mode='k', iterations=1, dataset='',
extra_dataset=None, limit=None, binary=False, idf=False, negation=True):
(pos_dir, neg_dir) = select_dataset(dataset)
if extra_dataset:
mode='d'
iterations=1
train_size = 1000
test_set = dataset
else:
test_set = None
print "TEST CONFIGURATION"
print "dataset: %(dataset)s, stars: %(extra_dataset)s \nn: %(n)s, limit: %(limit)s, binary: %(binary)s, \nmode: %(mode)s, iterations: %(iterations)s, idf: %(idf)s" % {'n':n,
'train_size':train_size,
'mode':mode,
'iterations':iterations,
'dataset':dataset,
'extra_dataset':extra_dataset,
'limit':limit,
'binary':binary,
'idf':idf}
ind = Indexes(mode=mode,iterations=iterations,train_size=train_size)
(pos_correct, neg_correct) = (0,0)
for k in range(iterations):
ind.next()
m = TestConfiguration(classif, n, ind, pos_dir, neg_dir, idf=idf,
test_set=test_set, binary=binary, limit=limit, negation=negation)
m.train()
(pos, neg) = m.test()
pos_correct += pos
neg_correct += neg
print "Results:"
print "Positive:", round((pos_correct/iterations)*100), "%"
print "Negative:", round((neg_correct/iterations)*100), "%"
print "Total:", round((neg_correct + pos_correct)/(2*iterations)*100), "%"
train_size = 800
mode = 'k'
iterations = 3
extra_dataset = None
# print "Bayes:"
# test(classifier.BayesClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations,
# dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation = negation)
print "MaxEnt:"
# test(classifier.MaximumEntropyClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations, dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation=negation)
# print "SVM:"
# test(classifier.LinearSVMClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations, dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation=negation)
mvc = MajorityVotingTester(negation)
ind = Indexes(mode='k', iterations=3, train_size=800)
ind.next()
print ind
(pos_dir, neg_dir) = select_dataset(dataset)
m1 = TestConfiguration(classifier.BayesClassifier,
n=n,
ind=ind,
pos_dir=pos_dir,
neg_dir=neg_dir,
binary=binary,
limit=limit,
idf=idf)
mvc.addClassifier(m1)
(pos_dir, neg_dir) = select_dataset(dataset)
m2 = TestConfiguration(classifier.MaximumEntropyClassifier,
train_size = 800
mode = 'k'
iterations = 3
extra_dataset=None
# print "Bayes:"
# test(classifier.BayesClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations,
# dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation = negation)
print "MaxEnt:"
# test(classifier.MaximumEntropyClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations, dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation=negation)
# print "SVM:"
# test(classifier.LinearSVMClassifier,n=n,train_size=train_size,mode=mode,iterations=iterations, dataset=dataset,extra_dataset=extra_dataset,limit=limit,binary=binary, idf=idf, negation=negation)
mvc = MajorityVotingTester(negation)
ind = Indexes(mode='k',iterations=3,train_size=800)
ind.next()
print ind
(pos_dir, neg_dir) = select_dataset(dataset)
m1 = TestConfiguration(classifier.BayesClassifier, n=n, ind=ind, pos_dir=pos_dir, neg_dir=neg_dir, binary=binary, limit=limit, idf=idf)
mvc.addClassifier(m1)
(pos_dir, neg_dir) = select_dataset(dataset)
m2 = TestConfiguration(classifier.MaximumEntropyClassifier, n=n, ind=ind, pos_dir=pos_dir, neg_dir=neg_dir, binary=binary, limit=limit, idf=idf)
mvc.addClassifier(m2)
(pos_dir, neg_dir) = select_dataset(dataset)
m3 = TestConfiguration(classifier.LinearSVMClassifier, n=n, ind=ind, pos_dir=pos_dir, neg_dir=neg_dir, binary=binary, limit=limit, idf=idf)
mvc.addClassifier(m3)
#!/usr/bin/python
import os
import ngrams
from Indexes import Indexes
import matplotlib.pyplot as plt
from classifier import MaximumEntropyClassifier
TRAIN_SIZE = 800
n = 1
print "Maximum Entropy"
pos = os.listdir("pos")
neg = os.listdir("neg")
ind = Indexes('r',1,TRAIN_SIZE)
print "> determined Indices"
ind.next()
pos_grams = [ngrams.ngrams(n, open("pos/"+pos[i]).read()) for i in ind.get_pos_train_ind()]
pos_collapsed_grams = ngrams.top_ngrams(ngrams.collapse_ngrams(pos_grams),16165)
neg_grams = [ngrams.ngrams(n, open("neg/"+neg[i]).read()) for i in ind.get_neg_train_ind()]
neg_collapsed_grams = ngrams.top_ngrams(ngrams.collapse_ngrams(neg_grams),16165)
print "> collapsed grams"
trainingset = [([k],'pos',v) for (k,v) in pos_collapsed_grams.iteritems()]
trainingset.extend([([k],'neg',v) for (k,v) in neg_collapsed_grams.iteritems()])
m = MaximumEntropyClassifier(trainingset)
print "> created model"
pos_res = []
#!/usr/bin/python
import os
import ngrams
from Indexes import Indexes
import matplotlib.pyplot as plt
from classifier import MaximumEntropyClassifier
TRAIN_SIZE = 800
n = 1
print "Maximum Entropy"
pos = os.listdir("pos")
neg = os.listdir("neg")
ind = Indexes('r', 1, TRAIN_SIZE)
print "> determined Indices"
ind.next()
pos_grams = [
ngrams.ngrams(n,
open("pos/" + pos[i]).read())
for i in ind.get_pos_train_ind()
]
pos_collapsed_grams = ngrams.top_ngrams(ngrams.collapse_ngrams(pos_grams),
16165)
neg_grams = [
ngrams.ngrams(n,
open("neg/" + neg[i]).read())
for i in ind.get_neg_train_ind()
]
