Last active
January 23, 2017 06:02
-
-
Save rinchik/cac5a3fe0f58dba1764ee87f7c3b3d43 to your computer and use it in GitHub Desktop.
Text generator class. Analyzes and generates quotes of the random length.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from collections import Counter | |
from random import randint | |
import sys | |
class TextGenerator: | |
text_file = 'example_bible.txt' | |
raw_data = None | |
word_map = None | |
words = None | |
steps = 30 | |
def __init__(self): | |
self.prepare_data() | |
self.analyze() | |
self.generate() | |
def prepare_data(self): | |
with open(self.text_file, 'r') as example: | |
self.raw_data=example.read().replace('\n', ' ').replace('.', ' . ').replace(',', ' , ').replace(';', ' ').replace(':', ' ') | |
example.close() | |
def analyze(self): | |
self.words = self.raw_data.split() | |
word_pairs = [[self.words[i],self.words[i+1]] for i in range(len(self.words)-1)] | |
self.word_map = dict() | |
for word in list(set(self.words)): | |
for pair in word_pairs: | |
if word == pair[0]: | |
self.word_map.setdefault(word, []).append(pair[1]) | |
self.word_map[word] = Counter(self.word_map[word]).most_common(11) | |
def generate(self, state = None): | |
self.steps -= 1 | |
if state is None: | |
state = self.words[randint(0, len(self.words))] | |
if self.word_map[state]: | |
next = self.word_map[state][randint(0, len(self.word_map[state])-1)] | |
sys.stdout.write(next+' ') | |
if self.steps > 0: | |
self.generate(next) | |
TextGenerator() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment