def test_frequency():
histogram = Listogram(fish_words)
# Verify frequency count of all words
assert histogram.frequency('one') == 1
assert histogram.frequency('two') == 1
assert histogram.frequency('red') == 1
assert histogram.frequency('blue') == 1
assert histogram.frequency('fish') == 4
def test_tokens(self):
histogram = Listogram(self.fish_words)
# Verify total count of all word tokens
assert len(self.fish_words) == 8
assert histogram.tokens == 8
# Adding words again should double total count of all word tokens
for word in self.fish_words:
histogram.add_count(word)
assert histogram.tokens == 8 * 2
def test_types(self):
histogram = Listogram(self.fish_words)
# Verify count of distinct word types
assert len(set(self.fish_words)) == 5
assert histogram.types == 5
# Adding words again should not change count of distinct word types
for word in self.fish_words:
histogram.add_count(word)
assert histogram.types == 5
def test_entries():
# NOTE: This test assumes Listogram is implemented as a list of tuples,
# but if you implement it as a list of lists (or a list of count-lists)
# you should modify the fish_list fixture above and/or this test (only)
listogram = Listogram(fish_words)
# Verify histogram as list of entries like [(word, count)]
assert len(listogram.list_histogram) == 5
assert len(listogram.list_histogram) == len(fish_list) # Ignore item order
def test_contains(self):
histogram = Listogram(self.fish_words)
# All of these words should be found
for word in self.fish_words:
assert word in histogram
# None of these words should be found
for word in ('fishy', 'food'):
assert word not in histogram
def test_contains(self):
histogram = Listogram(self.fish_words)
print(f"histogram in test: {histogram}")
# All of these words should be found
for word in self.fish_words:
assert word in histogram
# assert histogram.__contains__(word)
# None of these words should be found
for word in ('fishy', 'food'):
assert word not in histogram
def test_entries(self):
# NOTE: This test assumes Listogram is implemented as a list of tuples,
# but if you implement it as a list of lists (or a list of count-lists)
# you should modify the fish_list fixture above and/or this test (only)
listogram = Listogram(self.fish_words)
# Verify histogram as list of entries like [(word, count)]
dictogram = dict(listogram)
assert len(dictogram) == 5
self.assertCountEqual(dictogram, self.fish_dict) # Ignore item order
def test_contains(self):
histogram = Listogram(self.fish_words)
# All of these words should be found
print("\n", self.fish_words)
print(histogram)
for word in self.fish_words:
assert word in histogram
print([word])
# None of these words should be found
for word in ('fishy', 'food'):
assert word not in histogram
def test_contains(self):
histogram = Listogram(self.fish_words)
# All of these words should be found
for word in self.fish_list:
assert word in histogram
# None of these words should be found
isIn = False
for word in ('fishy', 'food'):
for item in histogram:
if word == item[0]:
isIn = True
assert isIn == False
def generate_words():
with open('words.txt', 'r') as f:
words = f.read().split(' ')
listo = Listogram(words).listogram_samples(10)
dicto = Dictogram(words).dictogram_samples(10)
histograms = {0: listo, 1: dicto}
# sentences = [sentence for (index, sentence) in histograms.items()]
# return sentences
return random_sentence(5, words)
def test_entries(self):
# NOTE: This test assumes Listogram is implemented as a list of tuples,
# but if you implement it as a list of lists (or a list of count-lists)
# you should modify the fish_list fixture above and/or this test (only)
listogram = Listogram(self.fish_words)
# reassign fish_list to be a list of lists
fish_list_lists = [list(tuple) for tuple in self.fish_list]
# Verify histogram as list of entries like [(word, count)]
assert len(listogram) == 5
self.assertCountEqual(listogram, fish_list_lists) # Ignore item order
# Verify histogram as dictionary of entries like {word: count}
dictogram = dict(listogram)
assert len(dictogram) == 5
self.assertCountEqual(dictogram, self.fish_dict) # Ignore item order
def test_frequency(self):
histogram = Listogram(self.fish_words)
# Verify frequency count of all words
assert histogram.frequency('one') == 1
assert histogram.frequency('two') == 1
assert histogram.frequency('red') == 1
assert histogram.frequency('blue') == 1
assert histogram.frequency('fish') == 4
# Verify frequency count of unseen words
assert histogram.frequency('food') == 0
def test_sample(self):
histogram = Listogram(self.fish_words)
# Create a list of 10,000 word samples from histogram
samples_list = [histogram.sample() for _ in range(10000)]
# Create a histogram to count frequency of each word
samples_hist = Listogram(samples_list)
# Check each word in original histogram
for word, count in histogram:
# Calculate word's observed frequency
observed_freq = count / histogram.tokens
# Calculate word's sampled frequency
samples = samples_hist.frequency(word)
sampled_freq = samples / samples_hist.tokens
# Verify word's sampled frequency is close to observed frequency
lower_bound = observed_freq * 0.9 # 10% below = 90% = 0.9
upper_bound = observed_freq * 1.1 # 10% above = 110% = 1.1
assert lower_bound <= sampled_freq <= upper_bound
def __init__(self, word_list, passed_text_list):
"""Initialize the class and create variables"""
self.passed_text_list = passed_text_list
if self.passed_text_list == True:
self.word_list = word_list
else:
self.word_list = create_list(word_list)
self.dictionary_histogram = Dictogram(self.word_list)
self.listogram = Listogram(self.word_list)
""" Creating the Markov Chain """
#Edit so as to get rid of length of list minus 1 and it doesnt run errors
for index in range(len(self.word_list) - 2):
word = self.word_list[index]
next_word = self.word_list[index + 1]
word_after_next = self.word_list[index + 2]
if (word, next_word) not in self:
small_dicto = Dictogram([(next_word, word_after_next)])
self[(word, next_word)] = small_dicto
else:
self[(word, next_word)].add_count((next_word, word_after_next))
from listogram import Listogram
# split the corpus into sentences
import re
corpus = "This is a sentence. And this is also a sentence. One fish two fish and all that."
sentences = re.split(r' *[\.\?!][\'"\)\]]* *', corpus)
print(sentences)
bag_of_words = []
# make a dictogram of each sentence
for sentence in sentences:
sentence = sentence.split(" ")
# put them all into a list
hist = Listogram(sentence)
print(hist)
bag_of_words.append(hist)
print(bag_of_words)
cume = 0
for word in histogram_in:
cume += histogram_in[word]
if (cume > value):
return word
def sample_list_O_stuff(histogram_in): # stuff means tuples or lists
cap = 0
i = 0
while i < len(histogram_in):
cap += histogram_in[i][1]
i += 1
value = random.randint(0, cap)
cume = 0
index = 0
while index < len(histogram_in):
cume += histogram_in[index][1]
if cume > value:
return histogram_in[index][0]
index += 1
if __name__ == "__main__":
text = clean_text('book_1.txt')
hist = Dictogram(text)
list_hist = Listogram(text)
print(sample_list_O_stuff(list_hist))
print(dictionary_sample(hist))
def test_add_count(self):
histogram = Listogram(self.fish_words)
# Add more words to update frequency counts
histogram.add_count('two', 2)
histogram.add_count('blue', 3)
histogram.add_count('fish', 4)
histogram.add_count('food', 5)
# Verify updated frequency count of all words
assert histogram.frequency('one') == 1
assert histogram.frequency('two') == 3
assert histogram.frequency('red') == 1
assert histogram.frequency('blue') == 4
assert histogram.frequency('fish') == 8
assert histogram.frequency('food') == 5
# Verify count of distinct word types
print(' *********************** ', histogram.types)
assert histogram.types == 6
# Verify total count of all word tokens
assert histogram.tokens == 8 + 14
def test_tokens():
listogram = Listogram(fish_words)
# Verify total count of all word tokens
assert len(fish_words) == 8
assert listogram.tokens == 8
def test_types():
listogram = Listogram(fish_words)
# Verify count of distinct word types
assert len(set(fish_words)) == 5
assert listogram.types == 5
def lists():
temp = Listogram("I DO AND YOU KNOW I DO AND YOU KNOW THAT I AM WITH YOU FOREVER".split())
return temp.generate_sentence(20)
def lists():
temp = Listogram('one fish two fish red fish blue fish'.split())
return temp.generate_sentence(10)
