def train(self):
pos_train = [{} for f in self.pos_train_data]
neg_train = [{} for f in self.neg_train_data]
# Reading files
for (j, lim) in zip(self.n, self.limit):
all_grams = [
ngrams.ngrams(j, f, self.negation) for f in self.pos_train_data
]
for i in range(len(self.pos_train_data)):
pos_train[i].update(all_grams[i])
featureslist = all_grams
all_grams = [
ngrams.ngrams(j, f, self.negation) for f in self.neg_train_data
]
for i in range(len(self.neg_train_data)):
neg_train[i].update(all_grams[i])
featureslist.extend(all_grams)
# Collapsing, limiting ngrams
self.features.update(
ngrams.top_ngrams(ngrams.collapse_ngrams(featureslist), lim))
# Creating Index
self.classifier = self.clsf(restrictFeatures=self.features)
print "# features: %s" % self.classifier.nfeatures
if self.idf:
print "Using TF-IDF"
idf = ngrams.ngrams_to_idf(pos_train + neg_train)
for i in range(len(pos_train)):
for j in pos_train[i]:
pos_train[i][j] = pos_train[i][j] * idf[j]
for i in range(len(neg_train)):
for j in neg_train[i]:
neg_train[i][j] = neg_train[i][j] * idf[j]
# Making classifier
for i in pos_train:
self.count += 1
self.classifier.addFeatureVector(i, 1, binary=self.binary)
for i in neg_train:
self.classifier.addFeatureVector(i, -1, binary=self.binary)
self.classifier.compile()
def train(self):
pos_train = [{} for f in self.pos_train_data]
neg_train = [{} for f in self.neg_train_data]
# Reading files
for (j,lim) in zip(self.n,self.limit):
all_grams = [ngrams.ngrams(j, f, self.negation) for f in self.pos_train_data]
for i in range(len(self.pos_train_data)):
pos_train[i].update(all_grams[i])
featureslist = all_grams
all_grams = [ngrams.ngrams(j, f, self.negation) for f in self.neg_train_data]
for i in range(len(self.neg_train_data)):
neg_train[i].update(all_grams[i])
featureslist.extend(all_grams)
# Collapsing, limiting ngrams
self.features.update(ngrams.top_ngrams(ngrams.collapse_ngrams(
featureslist),lim))
# Creating Index
self.classifier = self.clsf(restrictFeatures = self.features)
print "# features: %s" % self.classifier.nfeatures
if self.idf:
print "Using TF-IDF"
idf = ngrams.ngrams_to_idf(pos_train + neg_train)
for i in range(len(pos_train)):
for j in pos_train[i]:
pos_train[i][j] = pos_train[i][j] * idf[j]
for i in range(len(neg_train)):
for j in neg_train[i]:
neg_train[i][j] = neg_train[i][j] * idf[j]
# Making classifier
for i in pos_train:
self.count += 1
self.classifier.addFeatureVector(i, 1, binary=self.binary)
for i in neg_train:
self.classifier.addFeatureVector(i, -1, binary=self.binary)
self.classifier.compile()
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 = []
neg_res = []
pos_tests = [ngrams.ngrams(n, open("pos/"+pos[i]).read()) for i in ind.get_pos_test_ind()]
pos_results = [m.classify(test) for test in pos_tests]
pos_correct = len([i for i in pos_results if i >= 0.5])
print "Positive: %s of %s, %s accuracy" % (pos_correct,len(pos_tests),(float(pos_correct)/len(pos_tests)))
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"
