def markov():
"""Forming sentence with markov chain"""
clean_text_list = clean_file('corpus.txt')
markov_word = markov_chain(clean_text_list)
# higher_order_markov_chain = nth_order_markov_model(2, clean_text_list)
sentence = generate_sentence(10, markov_word)
return sentence
def tests():
texts = ['rumpelstiltskin.txt', 'tom_thumb.txt']
story_list = cleanup.clean_file(texts[0])
result = tuples_histogram(story_list)
# print(result)
print(unique_words_lists_tuples_dictionary(result))
print(frequency_tuples_and_lists("Killer", result))
print(frequency_tuples_and_lists("to", result))
# print(sort_tuples_and_lists(result))
result = lists_histogram(story_list)
# print(result)
print(unique_words_lists_tuples_dictionary(result))
print(frequency_tuples_and_lists("Killer", result))
print(frequency_tuples_and_lists("to", result))
# print(sort_tuples_and_lists(result))
result = dictionary_histogram(story_list)
# print(result)
print(unique_words_lists_tuples_dictionary(result))
print(frequency_dictionary("Killer", result))
print(frequency_dictionary("to", result))
result = counts_histogram(story_list)
# print(result)
print(unique_words_counts(result))
def tests():
import sys
arguments = sys.argv[1:] # Exclude script name in first argument
if len(arguments) >= 1:
# Test histogram on given arguments
print_histogram(arguments)
else:
# # Test histogram on letters in a word
word = 'abracadabra'
print_histogram(list(word))
# Test histogram on words in a classic book title
fish_text = 'one fish two fish red fish blue fish'
print_histogram(fish_text.split())
# # Test histogram on words in a long repetitive sentence
woodchuck_text = ('how much wood would a wood chuck chuck'
' if a wood chuck could chuck wood')
print_histogram(woodchuck_text.split())
contents = cleanup.clean_file('ghosts_on_coruscant.txt')
narkie = Narkovogram(4, contents)
print(narkie.random_walk(10))
def home():
# Get cleaned data
file_name = 'SiliconValley.txt'
cleaned_file = cleanup.clean_file(file_name)
# Create data structure
data_structure = markov.make_higher_order_markov_model(3, cleaned_file)
# Pass data structure to get random setence with 140 chars
random_sentence = markov.generate_random_sentence_n(140, data_structure)
# Get a random actor to say the quote
random_actor = word_frequency.random_actor()
random_actor_cleaned = random_actor.replace(' ', '_')
random_actor_cleaned = random_actor_cleaned.replace('\'', '')
print('random actor = ', random_actor)
print('random actor cleaned ', random_actor_cleaned)
print('random sentence ', random_sentence)
# Render website <3
return render_template('layout.html',
sentence=random_sentence,
actor=random_actor,
actor_image=random_actor_cleaned)
sentence_count += 1
current_window = generate_random_start(markov_model)
sentence = [current_window[0]]
elif sentence_count == 0 and new_tweet_len >= length:
# forget the sentence and generate a new one :P
current_window = generate_random_start(markov_model)
sentence = [current_window[0]]
elif sentence_count > 0 and new_tweet_len < length:
# More than one sentence. and length is still less max
# Get another new sentence
tweet += sentence_string
sentence_string = ' '.join(sentence)
sentence_count += 1
current_window = generate_random_start(markov_model)
sentence = [current_window[0]]
else:
# Return this good good tweet
return tweet
if __name__ == '__main__':
clean_text_list = clean_file('corpus.txt')
# print(clean_text_list)
# print(markov_chain(clean_text_list))
# markov_chain = markov_chain(clean_text_list)
# # higher_order_markov_chain = nth_order_markov_model(2, clean_text_list)
# print(markov_chain)
# sentence = generate_sentence(10, markov_chain)
# # sentence = generate_sentence_with_higher_order(10, higher_order_markov_chain)
# print(sentence)
def main():
texts = ['rumpelstiltskin.txt', 'tom_thumb.txt']
contents = cleanup.clean_file(texts[0])
print(random_walk(contents, 10))
def tests():
texts = ['rumpelstiltskin.txt', 'tom_thumb.txt']
contents = cleanup.clean_file(texts[0])
generate_sentence(10, contents)
ten_thousand_words = list_of_words(10000)
hundred_hgram = Dictogram(hundred_words)
ten_thousand_hgram = Dictogram(ten_thousand_words)
hundred_search = hundred_words[-1]
ten_thousand_search = ten_thousand_words[-1]
stmt = "ten_thousand_hgram.count('{}')".format(ten_thousand_search)
setup = "from __main__ import ten_thousand_hgram"
timer = timeit.Timer(stmt, setup=setup)
iterations = 10000
result = timer.timeit(number=iterations)
print("count time for 100-word histogram: " + str(result))
# '*********** CREATING DATA STRUCTURES ***********'
words_list = cleanup.clean_file('SiliconValley_Actors.txt')
print 'Start creating Dictogram'
dictogram = Dictogram(words_list)
print 'Time to create Dictogram: ', 'seconds'
stmt_dictogram = "dictogram.return_weighted_random_word()"
setup_dictogram = "from __main__ import dictogram"
timer_dictogram = timeit.Timer(stmt_dictogram, setup=setup_dictogram)
result_dictogram = timer_dictogram.timeit(number=iterations)
print("count time for finding " + str(iterations) + " random weighted words " + str(result_dictogram))
listogram = Listogram(words_list)
print 'Time to create Listogram: ', 'seconds'
from flask import Flask, request, render_template
import re
import random
import os
import sample
import cleanup
import narkovogram
import sentence
app = Flask(__name__)
contents = cleanup.clean_file('ghosts_on_coruscant.txt')
last_order = 5
# def get_words():
# f = open("./text/ghosts_on_coruscant.txt", "r")
# contents = f.read()
# f.close()
# return contents
@app.route('/', methods=['GET'])
def generate_sentence():
narkie = narkovogram.Narkovogram(5, contents)
number = request.args.get('num')
order = request.args.get('order')
if number is None:
number = 10
else:
number = int(number)