コード例 #1
0
def main():
    words = cleanup.text_list('text/dickens.txt')
    m_chain = markov.order_mchain(2, words)
    c_start = markov.start_token(m_chain)
    walk_the_dog = markov.walk(c_start, m_chain)
    almost = markov.finalize(walk_the_dog)
    home = str(almost)
    return render_template("main.html", sentence=home)
コード例 #2
0
ファイル: app.py プロジェクト: capt-alien/tweet
def main():
    #process and import file
    words = cleanup.text_list('text/dickens.txt')
    m_chain = markov.order_mchain(2, words)
    c_start = markov.start_token(m_chain)
    walk_the_dog = markov.walk(c_start, m_chain)
    almost = markov.finalize(walk_the_dog)
    home = str(almost)
    # # #create resulting object
    # return home
    return render_template("main.html", sentence=home)
コード例 #3
0
from sys import argv
import cleanup
import tokenize
import wordcount
import sample


def sentance(histogram, total, loop):
    looper = int(loop)
    sentance1 = []
    word_string = " "
    # loop
    for i in range(0, looper):
        weight_word = sample.weighted_random(histogram, total)
        sentance1.append(weight_word)
    #turn list into a string
    word_string = word_string.join(word for word in sentance1)
    return word_string


if __name__ == '__main__':
    file1 = argv[1]  #file to analyze
    looper = int(argv[2])  # number of times that loop will run
    hist1 = wordcount.dict_words((cleanup.text_list(file1)))
    total = wordcount.sum_value(hist1)
    #runs sentance function
    print(sentance(hist1, total, looper))
コード例 #4
0
    # walks the markov
    sentence = ['START', start_token[1]]
    #while the last entry in the list sentence is not "STOP"
    while sentence[len(sentence)-1] != 'STOP': #or len(sentence) < 19:
        window = (sentence[len(sentence) - 2], sentence[len(sentence)-1])
        hist = dictionary[tuple(window)]
        next_word = sample.weighted_random(hist, sample.sum_value(hist))
        sentence.append(next_word)
    return(sentence)

def finalize(sentence):
    # remove start_token and capatlize the second word of the listself.
    sentence.pop(0)
    sentence.pop()
    sentence[0] = sentence[0].capitalize()
    word_string = ''
    word_string = word_string.join(' '+ word for word in sentence) + '.'
    return word_string



if __name__ == '__main__':
    file1 = argv[1]  #file to analyze
    words = cleanup.text_list(file1)
    # m_chain = order_mchain(2, words)
    m_chain = m_chain_one(words)
    print(m_chain)
    # c_start = start_token(m_chain)
    # walk_the_dog = walk(c_start, m_chain)
    # print(finalize(walk_the_dog))
コード例 #5
0
ファイル: tokenize2.py プロジェクト: capt-alien/tweet
# Creates a list of unique values
from sys import argv
import cleanup


def unique_list(words):
    unique_words = []
    for word in words:
        if word not in unique_words:
            unique_words.append(word)
    # return unique words lists
    return unique_words


if __name__ == '__main__':
    file1 = argv[1]
    list = unique_list(cleanup.text_list(file1))
    print(list)
コード例 #6
0
ファイル: wordcount.py プロジェクト: capt-alien/tweet
    #takes a list argument and returns a word count
    tuple_list = []
    for word in words:
        if (word, words.count(word)) not in tuple_list:
            tuple_list.append((word, words.count(word)))
    return tuple_list

#sums dictionary in histo
def sum_value(histogram):
    total = (sum(histogram.values()))
    return total

#opens file_name
if __name__ == '__main__':
    file1 = argv[1]
    print_list = cleanup.text_list(file1)
    #promts user for method
    print("==================================")
    print("Welcome to Hist-o-grama-rama!!!!!")
    print("=======>INSTRUCTIONS<============")
    print("Press 1 for a Dictionary")
    print("Press 2 for a List of Lists")
    print("Press 3 for a Tuple")
    input1 = input("Which method would you like returned? ")
    #dictionary
    if input1 == "1":
        dict_list = dict_words(print_list)
        tots = sum_value(dict_list)
        print(dict_list)
        print(tots)
コード例 #7
0
ファイル: markov.py プロジェクト: capt-alien/what_the_dickens
def main():
        file1 = argv[1]
        words = cleanup.text_list(file1)
        m_chain = order_mchain(2, words)
        print(m_chain)