def test_frequency():
dictogram = EasyDictogram(fish_words)
# Verify frequency count of all words
assert dictogram.frequency('one') == 1
assert dictogram.frequency('two') == 1
assert dictogram.frequency('red') == 1
assert dictogram.frequency('blue') == 1
assert dictogram.frequency('fish') == 4
def test_contains():
dictogram = EasyDictogram(fish_words).dictionary_histogram
# All of these words should be found
for word in fish_words:
assert word in dictogram
# None of these words should be found
for word in ('fishy', 'food'):
assert word not in dictogram
def build_markov(self, word_list):
markov_chain = {}
for i in range(len(word_list) - 1):
#get the current word and the word after
current_word = word_list[i]
next_word = word_list[i + 1]
if current_word in markov_chain.keys(): #already there
#get the histogram for that word in the chain
histogram = markov_chain[current_word]
#add to count
histogram.dictionary_histogram[
next_word] = histogram.dictionary_histogram.get(
next_word, 0) + 1
else: #first entry
markov_chain[current_word] = EasyDictogram([next_word])
return markov_chain
def test_sample():
dictogram = EasyDictogram(fish_words)
# Create a list of 10,000 word samples from histogram
samples_list = [dictogram.sample() for _ in range(10000)]
# Create a histogram to count frequency of each word
samples_hist = EasyDictogram(samples_list)
# Check each word in original histogram
for word, count in dictogram.dictionary_histogram.items():
# Calculate word's observed frequency
observed_freq = count / dictogram.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 test_entries():
dictogram = EasyDictogram(fish_words).dictionary_histogram
# Verify histogram as dictionary of entries like {word: count}
assert len(dictogram) == 5
assert len(dictogram) == len(fish_dict)
def test_types():
dictogram = EasyDictogram(fish_words)
# Verify count of distinct word types
assert len(set(fish_words)) == 5
assert dictogram.types == 5
def test_tokens():
dictogram = EasyDictogram(fish_words)
# Verify total count of all word tokens
assert len(fish_words) == 8
assert dictogram.tokens == 8