def test_sampler(histogram):
""" tests sampler by running it 10000 times, uncomment line 36 for this"""
test_words = []
for _ in range(10000):
test_words.append(sample(histogram))
test_hist = histogram_dictionary(test_words)
for item in test_hist.keys():
print(f"{item}: {test_hist[item]}")
def sentence_creator(histogram, num_words):
""" tests sampler by running it 10000 times, uncomment line 36 for this"""
words = []
sentence = []
for _ in range(0, num_words):
words.append(sample(histogram))
hist = histogram_dictionary(words)
for item in hist.keys():
sentence.append(item)
sentence_str = " ".join(sentence)
return sentence_str #sentence
word_list = words[word_index]
return word_list
def probability(histo):
""" equation for probability = (num of occurances) / sample total
Take the value of a word. Divide it by the total length of the histogram.
Mulitply by 100 to get percentage.
Be able to show all of the words and their percent in a list. """
total_count = len(histo.values(
)) # this is the total number of items in the histo. Should be 61.
# print(total_count) # yes, 61
word_percents = {}
for key in histo: # for the key in the histogram
word_percents[key] = str(
round(histo[key] / total_count * 100, 2)
) + "%" # divide it by the total items in the histogram and divide by 100
# round(_, which decimal point) <--- this will round the number to the second decimal point
return word_percents
# print(word_percents)
if __name__ == '__main__':
with open("sample.txt", "r") as data:
histo = histogram_dictionary(data)
random_word(histo)
probability(histo)
words.append(sample(histogram))
hist = histogram_dictionary(words)
for item in hist.keys():
sentence.append(item)
sentence_str = " ".join(sentence)
return sentence_str #sentence
def test_sampler(histogram):
""" tests sampler by running it 10000 times, uncomment line 36 for this"""
test_words = []
for _ in range(10000):
test_words.append(sample(histogram))
test_hist = histogram_dictionary(test_words)
for item in test_hist.keys():
print(f"{item}: {test_hist[item]}")
if __name__ == "__main__":
# file = sys.argv[:1]
# num_words = sys.argv[:1]
num_words = 8
f = open('harry_potterb1.txt')
words = f.read().split()
hist = histogram_dictionary(words)
print(sentence_creator(hist, num_words))
# Tests
# print(test_sampler(hist, num_words))
# print(word_sampler(hist))
return: a histogram
histogram creation function meant to check if words look like they are correctly sampled
"""
random_word_histogram = {}
for word in word_list:
if word in random_word_histogram:
random_word_histogram[word] += 1
else:
random_word_histogram[word] = 1
return random_word_histogram
if __name__ == "__main__":
text_document = sys.argv[1]
histo = histogram.histogram_dictionary(text_document)
random_words = [random_sampling(histo) for _ in range(10000)]
# print(random_check(random_words))
start = time.time()
random_freq_words = [weighted_dict_sampling(histo) for _ in range(100000)]
finish = time.time()
print(finish - start)
print(random_check(random_freq_words))
for _ in range(10):
print(weighted_dict_sampling(histo))
histogram_list[index + 1][1])
count += to_add
index += 1
type_index = random.randrange(len(histogram_list[index][1]))
return histogram_list[index][1][type_index]
if __name__ == "__main__":
file_name = "notess.txt"
#print(sample_lists_of_lists(file_name))
text = histogram.load_words(file_name)
text_length = len(text)
histogram_dict = histogram.histogram_dictionary(text)
print(get_probablities(histogram_dict, text_length))
'''current = time.time()
words = list()
print(time.time() - current)
samples = histogram.histogram_count_lists_try_catch(words)
print(samples)
#text = histogram.load_words(file_name)
histogram_list2 = histogram.histogram_dictionary(text)
current2 = time.time()
words = list()
for i in range(10000):
import histogram
import sys
import random
# Helper function for getting the total number of objects in the histogram
get_total(histogram):
# Take the token(total number of objects) and divide the frequency of the words by tokens to get a decimal. Then use that to select a random word based on frequency.
def sample_by_frequency(histogram):
# Get the "weight" of every letter together
token = len(histogram)
# Get the lucky index
random_index = random.randint(1, token)
# Iterate through all the words
for word in histogram:
# Subtract the words value from the histogram
random_index = random_index - word.values
if random_index <= 0:
return word
if __name__ == "__main__":
source_text = 'harry_potterb1.txt'
histogram = histogram.histogram_dictionary(source_text)
sample_by_frequency(histogram)
def main():
book = 'sherlock_no_title_chapters.txt'
word_list = histogram.generate_word_list(book)
histo = histogram.histogram_dictionary(word_list)
print(sample_by_frequency(histo))
