def __init__(self, memory_size=4):
"""Initialize Dialog Manager, Trainer Classes, Reading Training Data.
Args:
memory_size: Past Length of Conversation to be considered as History of the
conversation.
"""
self.conversation_count = 0
# Initialize a queue with the required memory of past conversations
self.history = deque("", memory_size)
# Load the training sets for both states
self.training_set_state1 = rdr.trainer_reader("training_data.csv").load()
self.training_set_state2 = rdr.trainer_reader("training_data_2.csv").load()
self.training_map_1 = dict({0: 1})
self.training_map_2 = dict({0: 1})
self.training_set_state1 = self._map_multiple_response(self.training_set_state1, self.training_map_1)
self.training_set_state2 = self._map_multiple_response(self.training_set_state2, self.training_map_2)
lambda_pi_1 = [
0.2395105181493061,
0.0006173868035890566,
0.03237275574954535,
0.0006901882640402509,
0.44723785605466126,
0.2795712949788579,
]
lambda_pi_2 = [
0.0015018046263117243,
0.001374250681872707,
0.12433409846344812,
0.002426809340382256,
0.663739481446308,
0.06767643891963208,
]
# Use the training sets to train two classifiers
self.trn_1 = tr.trainer(0.002166020551556791, lambda_pi_1, self.training_set_state1)
self.trn_2 = tr.trainer(0.006249742180327811, lambda_pi_2, self.training_set_state2)
self.trn_1.train()
self.trn_2.train()
# Set threshold for dialogue generation
self.threshold_1 = float("-0.000428095769801")
self.threshold_2 = float("-0.00154795755273")
def __init__(self, memory_size = 4):
self.conversation_count = 0
# Initialize a queue with the required memory of past conversations
self.history = deque('', memory_size)
# Load the training sets for both states
self.training_set_state1 = rdr.trainer_reader('Data/training_ML.csv').load()
self.training_map_1 = dict({0:1})
self.training_set_state1 = self._map_multiple_response(self.training_set_state1, self.training_map_1)
#lambda_pi_1 = [0.022637184564677337, 0.0006614527936524828, 0.8151936922826796, 0.009768802605860376, 0.9977721108143799, 0.9676503420836119]
#self.lambda_pi_1 = [0.5089104109775326, 0.5432925251421259, 0.02218191679541291, 0.8877708494421628, 0.8206554620659708, 0.6351178059195106]
self.lambda_pi_1 = [0.2517703455341973, 0.024354405309287175, 0.3108059389694587, 0.6223442089112752, 0.28378859405365237, 0.41789353929407375]
self.lambda_pi_1 = map(lambda x: x/sum(self.lambda_pi_1), self.lambda_pi_1 )
#0.5340087189383883 #0.7204150300022019
# Use the training sets to train two classifiers
#self.trn_1 = tr.trainer(0.007672586062919887, lambda_pi_1 , self.training_set_state1)
self.trn_1 = tr.trainer(self.lambda_pi_1 , self.training_set_state1)
self.trn_1.train()
# Set threshold for dialogue generation
self.threshold_1 = float('0.06')#-0.0015
def __init__(self, memory_size=4):
self.conversation_count = 0
# Initialize a queue with the required memory of past conversations
self.history = deque('', memory_size)
# Load the training sets for both states
self.training_set_state1 = rdr.trainer_reader(
'Data/training_ML.csv').load()
self.training_map_1 = dict({0: 1})
self.training_set_state1 = self._map_multiple_response(
self.training_set_state1, self.training_map_1)
#lambda_pi_1 = [0.022637184564677337, 0.0006614527936524828, 0.8151936922826796, 0.009768802605860376, 0.9977721108143799, 0.9676503420836119]
#self.lambda_pi_1 = [0.5089104109775326, 0.5432925251421259, 0.02218191679541291, 0.8877708494421628, 0.8206554620659708, 0.6351178059195106]
self.lambda_pi_1 = [
0.2517703455341973, 0.024354405309287175, 0.3108059389694587,
0.6223442089112752, 0.28378859405365237, 0.41789353929407375
]
self.lambda_pi_1 = map(lambda x: x / sum(self.lambda_pi_1),
self.lambda_pi_1)
#0.5340087189383883 #0.7204150300022019
# Use the training sets to train two classifiers
#self.trn_1 = tr.trainer(0.007672586062919887, lambda_pi_1 , self.training_set_state1)
self.trn_1 = tr.trainer(self.lambda_pi_1, self.training_set_state1)
self.trn_1.train()
# Set threshold for dialogue generation
self.threshold_1 = float('0.06') #-0.0015
import trainer_main as tr
import utility as ut
import numpy as np
import ACOR
import trainer_reader as rdr
def map_multiple_response(training_set, tmap):
training_map = dict()
for (ques, ans) in training_set:
training_map[ques] = training_map.get(ques, []) + [ans]
mtrs = []
for ques, answers in training_map.iteritems():
tmap[answers[0]] = answers
mtrs.append((ques, answers[0]))
return mtrs
tmap = dict()
reader = rdr.trainer_reader('Data/training_ML.csv')
training_set = reader.load()
training_set = map_multiple_response(training_set, tmap)
print np.sort(training_set),'\n'
CM = tr.OptimizeLambda(training_set)
Optimization = ACOR.ACO(cFunc = CM.costFunction, nDim = 6, nAnt = 50, m = 20, q = 2.14, e = 3.5, limit = CM.getLimits())
Optimization.optimizeMin(500)
import trainer_main as tr
import utility as ut
import numpy as np
import ACOR
import trainer_reader as rdr
def map_multiple_response(training_set, tmap):
training_map = dict()
for (ques, ans) in training_set:
training_map[ques] = training_map.get(ques, []) + [ans]
mtrs = []
for ques, answers in training_map.iteritems():
tmap[answers[0]] = answers
mtrs.append((ques, answers[0]))
return mtrs
tmap = dict()
reader = rdr.trainer_reader('training_ML.csv')
training_set = reader.load()
training_set = map_multiple_response(training_set, tmap)
print np.sort(training_set),'\n'
CM = tr.OptimizeLambda(training_set)
Optimization = ACOR.ACO(cFunc = CM.costFunction, nDim = 6, nAnt = 50, m = 20, q = 2.14, e = 3.5, limit = CM.getLimits())
Optimization.optimizeMin(500)
import trainer_reader as rdr
def map_multiple_response(training_set, tmap):
training_map = dict()
for (ques, ans) in training_set:
training_map[ques] = training_map.get(ques, []) + [ans]
mtrs = []
for ques, answers in training_map.iteritems():
tmap[answers[0]] = answers
mtrs.append((ques, answers[0]))
return mtrs
tmap = dict()
reader = rdr.trainer_reader('Data/training_ML.csv')
training_set = reader.load()
training_set = map_multiple_response(training_set, tmap)
print np.sort(training_set), '\n'
CM = tr.OptimizeLambda(training_set)
Optimization = ACOR.ACO(cFunc=CM.costFunction,
nDim=6,
nAnt=50,
m=20,
q=2.14,
e=3.5,
limit=CM.getLimits())
.
.
.
]
.
"""
training_map = dict()
for (ques, ans) in training_set:
training_map[ques] = training_map.get(ques, []) + [ans]
mtrs = []
for ques, answers in training_map.iteritems():
tmap[answers[0]] = answers
mtrs.append((ques, answers[0]))
return mtrs
tmap = dict()
reader = rdr.trainer_reader('training_data_2.csv')
training_set = reader.load()
training_set = map_multiple_response(training_set, tmap)
print np.sort(training_set)
CM = tr.OptimizeLambda(training_set)
Optimization = ACOR.ACO(cFunc = CM.costFunction, nDim = 7, nAnt = 50, m = 20, q = 2.14, e = 3.5, limit = CM.getLimits())
Optimization.optimizeMin(500)