import dataprocessing
import numpy as np
import HMM
import nltk
import poetrytools
X, conv_words = dataprocessing.parse_words_lines()
n_states = 5
n_observations = len(conv_words)
hmm = HMM.unsupervised_HMM(X, n_states, n_iters=300)
emission = hmm.generate_emission(M=10)
# i-1 because the observations are 1-indexed
translated_emission = [conv_words[i] for i in emission]
line = ''
for word in translated_emission:
line += word + ' '
print(line)
print(emission)
# Print transition matrix.
A_vis = np.around(np.array(hmm.A), 4)
print(A_vis)
# Obtain the top 10 words for each state.
O = np.array(hmm.O)
for i in range(len(O)):
state_emissions = O[i, :]
top_emissions = state_emissions.argsort()[-10:][::-1]
import dataprocessing
import numpy as np
import HMM
import pickle
import copy
X_raw, conversion_list = dataprocessing.parse_words_lines()
print(X_raw)
# REVERSE X
X = copy.deepcopy(X_raw)
for i in range(len(X_raw)):
X[i].reverse()
print(X)
n_states = 50
lines = []
emissions = []
n_observations = len(conversion_list)
hmm = HMM.unsupervised_HMM(X, n_states, n_iters=10)
for _ in range(10):
emission = hmm.generate_emission(M=10)
# i-1 because the observations are 1-indexed
translated_emission = [conversion_list[i] for i in emission]
line = ''
for word in translated_emission:
line += word + ' '
import dataprocessing
import numpy as np
import pickle
import copy
import HMM
# Label the state with the part of speech.
X, word_conv = dataprocessing.parse_words_lines()
word_lists = dataprocessing.get_word_lists()
print(X)
for i in range(len(X)):
X[i].reverse()
print(X)
print(word_lists)
for i in range(len(word_lists)):
word_lists[i].reverse()
print(word_lists)
# Load up saved pos
with open('pos.txt', 'rb') as file:
pos = pickle.load(file)
flattened_pos = []
for i in range(len(pos)):
for j in range(len(pos[i])):
flattened_pos.append(pos[i][j])
unique_pos, counts = np.unique(flattened_pos, return_counts=True)
pos_dict = {}
for i in range(len(unique_pos)):