# -*- coding: utf-8 -*-
from hmm import Model
states = ("rainy", "sunny")
symbols = ("walk", "shop", "clean")
start_prob = {"rainy": 0.5, "sunny": 0.5}
trans_prob = {"rainy": {"rainy": 0.7, "sunny": 0.3}, "sunny": {"rainy": 0.4, "sunny": 0.6}}
emit_prob = {"rainy": {"walk": 0.1, "shop": 0.4, "clean": 0.5}, "sunny": {"walk": 0.6, "shop": 0.3, "clean": 0.1}}
sequence = ["walk", "shop", "clean", "clean", "walk", "walk", "walk", "clean"]
model = Model(states, symbols, start_prob, trans_prob, emit_prob)
print model.evaluate(sequence)
print model.decode(sequence)
phi = {'B':0.5,'E':0,'M':0,'S':0.5}
model = Model(S,observation,phi,trans_prob,conf_prob)
o_hstate = []
for obser in observations:
'''
Notice,if a setence is too long,when we use viterbi algorithm it may result in the beta = 0
There are two solution,one is split the setence into serval sub_setence,another is use log function for the viterbi
here we select the first method
'''
length = len(obser)
index,sub_obser,state= 0,[],[]
while index < length:
sub_obser.append(obser[index])
if obser[index] == '。' or obser[index]=='，':
sub_state = model.decode(sub_obser)
sub_obser = []
state += sub_state
elif index == length-1:
sub_state = model.decode(sub_obser)
sub_obser = []
state += sub_state
index += 1
o_hstate.append(state)
word_sequence = pro._word_sequence(observations,o_hstate)
print word_sequence[3]
trans_prob = {
'rainy': {
'rainy': 0.7,
'sunny': 0.3
},
'sunny': {
'rainy': 0.4,
'sunny': 0.6
}
}
emit_prob = {
'rainy': {
'walk': 0.1,
'shop': 0.4,
'clean': 0.5
},
'sunny': {
'walk': 0.6,
'shop': 0.3,
'clean': 0.1
}
}
sequence = ['walk', 'shop', 'clean', 'clean', 'walk', 'walk', 'walk', 'clean']
model = Model(states, symbols, start_prob, trans_prob, emit_prob)
print model.evaluate(sequence)
print model.decode(sequence)
trans_prob = {
'rainy': {
'rainy': 0.7,
'sunny': 0.3
},
'sunny': {
'rainy': 0.4,
'sunny': 0.6
}
}
emit_prob = {
'rainy': {
'walk': 0.1,
'shop': 0.4,
'clean': 0.5
},
'sunny': {
'walk': 0.6,
'shop': 0.3,
'clean': 0.1
}
}
sequence = ['walk', 'shop', 'clean', 'clean', 'walk', 'walk', 'walk', 'clean']
model = Model(states, symbols, start_prob, trans_prob, emit_prob)
print(model.evaluate(sequence))
print(model.decode(sequence))
#The hidden states
states = [1,2,3]
#The observation states
observation = [1,2]
#The intial probability for the hidden states
phi = {1:0.333,2:0.333,3:0.333}
#The trans prob for the hidden states
trans_prob = {
1:{1:0.333,2:0.333,3:0.333},
2:{1:0.333,2:0.333,3:0.333},
3:{1:0.333,2:0.333,3:0.333}
}
#The prob of observation in condition of a hidden state
conf_prob = {
1:{1:0.5,2:0.5},
2:{1:0.75,2:0.25},
3:{1:0.25,2:0.75}
}
observations =[1,1,1,1,2,1,2,2,2,2]
model = Model(states,observation,phi,trans_prob,conf_prob)
print model.evaluate(observations)
print model.decode(observations)
'''
observations = test
phi = {'B': 0.5, 'E': 0, 'M': 0, 'S': 0.5}
model = Model(S, observation, phi, trans_prob, conf_prob)
o_hstate = []
for obser in observations:
'''
Notice,if a setence is too long,when we use viterbi algorithm it may result in the beta = 0
There are two solution,one is split the setence into serval sub_setence,another is use log function for the viterbi
here we select the first method
'''
length = len(obser)
index, sub_obser, state = 0, [], []
while index < length:
sub_obser.append(obser[index])
if obser[index] == '。' or obser[index] == '，':
sub_state = model.decode(sub_obser)
sub_obser = []
state += sub_state
elif index == length - 1:
sub_state = model.decode(sub_obser)
sub_obser = []
state += sub_state
index += 1
o_hstate.append(state)
word_sequence = pro._word_sequence(observations, o_hstate)
print word_sequence[3]
#The prob of observation in condition of a hidden state
conf_prob = {
'rainy': {
'walk': 0.1,
'shop': 0.3,
'clean': 0.6
},
'sunny': {
'walk': 0.4,
'shop': 0.5,
'clean': 0.1
},
'cloudy': {
'walk': 0.6,
'shop': 0.25,
'clean': 0.15
}
}
observations = [
'walk', 'shop', 'clean', 'clean', 'walk', 'walk', 'walk', 'clean'
]
#The iter_num is the iteration number in the EM algorithm
iter_num = 50
model = Model(states, observation, phi, trans_prob, conf_prob, iter_num)
print model.evaluate(observations)
print model.decode(observations)
