def train(self, graphs):
"""
Trains a C{NaiveBayesClassifier} using the edges present in
graphs list as positive examples, the edges not present as
negative examples. Uses a feature vector of head-word,
head-tag, child-word, and child-tag.
@type graphs: A list of C{DependencyGraph}
@param graphs: A list of dependency graphs to train the scorer.
"""
# Create training labeled training examples
labeled_examples = []
for graph in graphs:
for head_node in graph.nodelist:
for child_index in range(len(graph.nodelist)):
child_node = graph.get_by_address(child_index)
if child_index in head_node['deps']:
label = "T"
else:
label = "F"
features = [head_node['word'], head_node['tag'], child_node['word'], child_node['tag']]
labeled_examples.append((dict(a=head_node['word'],b=head_node['tag'],c=child_node['word'],d=child_node['tag']), label))
# Train the classifier
import nltk
nltk.usage(nltk.ClassifierI)
self.classifier = nltk.classify.NaiveBayesClassifier.train(labeled_examples)
def train(self, graphs):
"""
Trains a C{NaiveBayesClassifier} using the edges present in
graphs list as positive examples, the edges not present as
negative examples. Uses a feature vector of head-word,
head-tag, child-word, and child-tag.
@type graphs: A list of C{DependencyGraph}
@param graphs: A list of dependency graphs to train the scorer.
"""
# Create training labeled training examples
labeled_examples = []
for graph in graphs:
for head_node in graph.nodelist:
for child_index in range(len(graph.nodelist)):
child_node = graph.get_by_address(child_index)
if child_index in head_node['deps']:
label = "T"
else:
label = "F"
features = [
head_node['word'], head_node['tag'],
child_node['word'], child_node['tag']
]
labeled_examples.append((dict(a=head_node['word'],
b=head_node['tag'],
c=child_node['word'],
d=child_node['tag']), label))
# Train the classifier
import nltk
nltk.usage(nltk.ClassifierI)
self.classifier = nltk.classify.NaiveBayesClassifier.train(
labeled_examples)
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.
# This file is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with GNU Emacs; see the file COPYING. If not, write to
# the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
# Boston, MA 02110-1301 USA,
import nltk
nltk.usage(nltk.classify.ClassifierI)
from pprint import pprint
train = [
(dict(a=1, b=1, c=1), 'y'),
(dict(a=1, b=1, c=1), 'x'),
(dict(a=1, b=1, c=0), 'y'),
(dict(a=0, b=1, c=1), 'x'),
(dict(a=0, b=1, c=1), 'y'),
(dict(a=0, b=0, c=1), 'y'),
(dict(a=0, b=1, c=0), 'x'),
(dict(a=0, b=0, c=0), 'x'),
(dict(a=0, b=1, c=1), 'y'),
]
test = [
(dict(a=1, b=0, c=1)), # unseen
import nltk
#from nltk.classify.naivebayes import NaiveBayesClassifier
nltk.usage(nltk.classify.ClassifierI)
l = ['NP','VGF','BLK','CCP','JJP','VGNN']
f=open('small_train')
for i in f:
line = i.split()
if line:
l.append(line[1])
l1=[]
f.close()
d={}
f1=open('small_train')
for i in f1:
line=i.split()
d={}
# for j in l:
# d[j]=0
if line:
line1=line[0].split('-')
d['a']=line[1]
l1.append((d,line1[0]))
f1.close()
f2=open('small_train')
l2=[]
for i in f2:
line=i.split()
d={}
# for j in l:
# d[j]=0
if line:
globalWords[str(j[0])] += j[1]
else:
globalWords[str(j[0])] = j[1]
print globalWords"""
# Classifier tester
import numpy
import scipy
import nltk
print 'NumPy Version: ', numpy.__version__
print 'SciPy Version: ', scipy.__version__
print 'NLTK Version: ', nltk.__version__
print nltk.usage(nltk.ClassifierI)
# Training & test data
arch = sys.argv[1]
fi = open(arch, 'r')
content = fi.readlines()
globalWords = {}
countINF, countNAV, countRES = 0.0, 0.0, 0.0
querys, category = [], []
for i in content:
data = i.split('\t')
if data[0] == "INF":
countINF += 1
elif data[0] == "NAV":
globalWords[str(j[0])] += j[1]
else:
globalWords[str(j[0])] = j[1]
print globalWords"""
# Classifier tester
import numpy;
import scipy;
import nltk;
print 'NumPy Version: ', numpy.__version__
print 'SciPy Version: ', scipy.__version__
print 'NLTK Version: ', nltk.__version__
print nltk.usage(nltk.ClassifierI)
# Training & test data
arch = sys.argv[1]
fi = open(arch, 'r')
content = fi.readlines()
globalWords = {}
countINF, countNAV, countRES = 0.0, 0.0, 0.0
querys, category = [], []
for i in content:
data = i.split('\t')
if data[0] == "INF":
countINF += 1
elif data[0] == "NAV":