def buildManyModels(self):
'''
Uses every combination of the parameters specified below to create a
MaximumEntropyClassifier, train it, and evaluate it
'''
all_filesubsets = [2000, 4000, 6000]
all_min_occurences = [3, 5, 7]
max_iter = 4
all_grams = [[1], [1, 2]]
for filesubset in all_filesubsets:
for min_occurence in all_min_occurences:
for grams in all_grams:
self.maxent_args = {
'filesubset': filesubset,
'min_occurences': min_occurence,
'max_iter': max_iter,
'grams': grams
}
ent = MaximumEntropyClassifier(self.rawfname,
**self.maxent_args)
print 'About to train with', self.maxent_args
ent.trainClassifier()
self.evaluate(ent)
def run(self):
'''
Trains a MaximumEntropyClassifier using <self.maxent_args> and evaluates
the trained model
'''
ent = MaximumEntropyClassifier(self.rawfname, **self.maxent_args)
print 'Initialized classifier, about to train...'
ent.trainClassifier()
self.evaluate(ent)
def run(self):
'''
Trains a MaximumEntropyClassifier using <self.maxent_args> and evaluates
the trained model
'''
ent = MaximumEntropyClassifier(self.rawfname, **self.maxent_args)
print 'Initialized classifier, about to train...'
ent.trainClassifier()
self.evaluate(ent)
def buildManyModels(self):
all_filesubsets = [2000, 4000, 6000]
all_min_occurences = [3, 5, 7]
max_iter = 4
all_grams = [[1], [1, 2]]
for filesubset in all_filesubsets:
for min_occurence in all_min_occurences:
for grams in all_grams:
self.maxent_args = {
'filesubset': filesubset,
'min_occurences': min_occurence,
'max_iter': max_iter,
'grams': grams
}
ent = MaximumEntropyClassifier(self.rawfname,
**self.maxent_args)
ent.trainClassifier()
self.evaluate(ent)
def buildManyModels(self):
'''
Uses every combination of the parameters specified below to create a
MaximumEntropyClassifier, train it, and evaluate it
'''
all_filesubsets = [2000, 4000, 6000]
all_min_occurences = [3, 5, 7]
max_iter = 4
all_grams = [[1], [1,2]]
for filesubset in all_filesubsets:
for min_occurence in all_min_occurences:
for grams in all_grams:
self.maxent_args = {
'filesubset' : filesubset,
'min_occurences' : min_occurence,
'max_iter' : max_iter,
'grams' : grams
}
ent = MaximumEntropyClassifier(self.rawfname, **self.maxent_args)
print 'About to train with', self.maxent_args
ent.trainClassifier()
self.evaluate(ent)
from maxentclassifier import MaximumEntropyClassifier
from naivebayesclassifier import NaiveBayesClassifier
import random
import csv
fname = 'training.csv'
nb = NaiveBayesClassifier(fname, grams=[1, 2])
nb.setThresholds(neg=1.0, pos=20.0)
nb.setWeight(0.000000000005)
nb.trainClassifier()
ment = MaximumEntropyClassifier(fname)
ment.trainClassifier()
classifiers = [nb, ment]
def csvdata_to_list(data):
d=[]
for row in data:
d.append(row)
return d
def search(text,data):
output = []
i=0
for d in data:
if d[0].lower().find(text) != -1:
output.append([])
output[i].append(d[0])
import os
from maxentclassifier import MaximumEntropyClassifier
from naivebayesclassifier import NaiveBayesClassifier
# name of training set file
fname = 'trainingandtestdata/training.csv'
# train classifiers here first
nb = NaiveBayesClassifier(fname, grams=[1,2])
nb.setThresholds(neg=1.0, pos=20.0)
nb.setWeight(0.000000000005)
nb.trainClassifier()
ment = MaximumEntropyClassifier(fname)
ment.trainClassifier()
classifiers = [nb, ment]
class MainHandler(tornado.web.RequestHandler):
'''
Handles request to main page
'''
def get(self):
query = self.get_argument("query", "").strip()
cchosen = int(self.get_argument("classifier-type", 0))
auth = tweepy.OAuthHandler ("Yd1EFIv3psmpXdhR3lPVjUXva","WcmeKDjoaD3suYMQbgIyXTTtKcaDvws4h5cFwmlBy7jgDMxO9E")
auth.set_access_token ("797867203-pm0v4oRKAe6EThRKeAq2H8tPruUUHepzhrTuXdbB", "0HpeNMR6P00UFqMwHvadZxvhXGzIonDxW1LdMHSH5AOQR")
api = tweepy.API(auth)
def run(self):
ent = MaximumEntropyClassifier(self.rawfname, **self.maxent_args)
ent.trainClassifier()
self.evaluate(ent)