def test_chain_traversal():
word_list = get_words("fish.txt")
markov_chain = MarkovChain(word_list)
pprint(markov_chain)
from dictionary_words import get_words
from dictionary_histogram import dict_histogram
wordList = get_words('animals.txt')
def histogram_tuple(list):
dictionary = dict_histogram(list)
tuple_histogram = []
for i in dictionary:
tuple_histogram.append((i, dictionary[i]))
return tuple_histogram
if __name__ == "__main__":
print(histogram_tuple(wordList))
num = 0
random_num = uniform(0, total_hist_count(hist))
for word in hist:
count = hist[word]
num += count
if num > random_num:
return word
def sample_sentence(num, hist):
""" using the sample function, this function creates a sentence,
the length depending on what is passed into num """
sentence = []
for _ in range(0, num):
sentence.append(sample(hist))
return ' '.join(sentence)
def test_probability(word_hist, num):
probability = []
for _ in range(0, num):
probability.append(sample(word_hist))
pprint(dict_histogram(probability))
if __name__ == "__main__":
word_list = get_words('fish.txt')
word_hist = dict_histogram(word_list)
test_probability(word_hist, 1000)
import dictionary_words
import rearrange
import sys
import itertools
dic_words = dictionary_words.get_words()
def get_all_anagrams(word):
output_anagrams = []
word_chars = list(word)
for n in range(len(word_chars) - 1):
for permutation in itertools.permutations(word_chars, len(word_chars)):
current_str = set_to_string(permutation).lower()
output_anagrams.append(current_str)
return remove_duplicates(output_anagrams)
def get_anagrams_from_dictionary(word):
output_anagrams = []
for dic_word in dic_words:
# Only look if length matches
if len(dic_word) == len(word):
original_dic_word = dic_word
word_chars = list(word.lower())
dic_word_chars = list(dic_word.lower().strip())
from dictionary_words import get_words
def dict_histogram(lists):
"""Count occurences in the given list
and return that data structure"""
dictionary = {}
for i in lists:
if i in dictionary:
dictionary[i] += 1
else:
dictionary[i] = 1
return dictionary
def total_hist_count(hist):
total_count = 0
for word in hist:
total_count += hist[word]
return total_count
if __name__ == "__main__":
print(dict_histogram(get_words('1984.txt')))
def tweet():
word_list = get_words('1984.txt')
markov_chain = MarkovChain(word_list)
sentence = markov_chain.chain_traversal(30)
return render_template("index.html", sentence = sentence)