def main(model_file):
''' Run visualizations for the provided model. '''
# Load the model.
print('Visulaizations for the model ' + model_file)
model = load(model_file)
# Visualize the transition and observation matrices.
visualize_sparsities(model, O_max_cols=10000, O_vmax=0.003)
# Get the most common output words from each state.
_, detoken, _ = get_corpus("data/shakespeare.txt", split_by_line=False)
for state in range(model.L):
print(f'state {state} -> ', end='')
print_common_words(model.O[state], detoken, nwords=10)
# Make word cloud for each state.
obs, obs_map = parse_observations(
open(os.path.join(os.getcwd(), 'data/shakespeare.txt')).read())
wordclouds = states_to_wordclouds(model, obs_map)
# Make an animation.
anim = animate_emission(model, obs_map, M=8)
plt.show()
from HMM import unsupervised_HMM
from HMM_helper import (
parse_observations,
sample_sentence,
visualize_sparsities,
)
from Utility import Utility
# Print the transition matrix.
if __name__ == '__main__':
train = False
n_states = 10
N_iters = 50
text = open(os.path.join(os.getcwd(), '../data/shakespeare.txt')).read()
obs, obs_map, stress_dic = parse_observations(text)
#print(obs)
# Train the HMM.
if train:
HMM = unsupervised_HMM(obs, n_states, N_iters)
file = open('hmm_10.txt', 'wb')
pickle.dump(HMM, file)
file.close()
else:
file = open("hmm_10.txt", "rb")
HMM = pickle.load(file)
#######
dic = open(os.path.join(os.getcwd(),
'../data/Syllable_dictionary.txt')).read()
lines = [line.split() for line in dic.split('\n') if line.split()]
# ## Visualization of the dataset # We will be using the Constitution as our dataset. First, we visualize the entirety of the Constitution as a wordcloud: # In[7]: text = open(os.path.join(os.getcwd(), 'data/constitution.txt')).read() wordcloud = text_to_wordcloud(text, title='Constitution') # ## Training an HMM # Now we train an HMM on our dataset. We use 10 hidden states and train over 100 iterations: # In[8]: obs, obs_map = parse_observations(text) hmm8 = unsupervised_HMM(obs, 10, 100) # ## Part G: Visualization of the sparsities of A and O # We can visualize the sparsities of the A and O matrices by treating the matrix entries as intensity values and showing them as images. What patterns do you notice? # In[9]: visualize_sparsities(hmm8, O_max_cols=50) # ## Generating a sample sentence # As you have already seen, an HMM can be used to generate sample sequences based on the given dataset. Run the cell below to show a sample sentence based on the Constitution. # In[5]: