Skip to content

Mini Project 1 submission #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
CBrooke47 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Mini Project 1 submission #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added Grubb_Markov_Analysis.pdf
View file
Open in desktop
Binary file not shown.
99 changes: 99 additions & 0 deletions Markov_Analysis
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
import sys
import string
import random
import pattern

suffix_map = {}
prefix = ()


from pattern.web import *
Alice = URL('http://www.gutenberg.org/files/11/11-h/11-h.htm').download()


"""
Opens the file
removes the header
processes them using markov analysis
"""
def process_file(filename, order=2):
fp = Alice
skip_header(fp)
fp = fp.split()

for word in fp:
process_word(word, order)


"""
Skips the header of Project Guttenburg page by looking for the ending phrase
"""
def skip_header(fp):
for line in fp:
if line.startswith('*END*THE SMALL PRINT!'):
break



"""
Processes each word in the imported file
Begins creating a dictonary of the words
"""
def process_word(word, order=2):
global prefix
if len(prefix) < order:
prefix += (word,)
return

try:
suffix_map[prefix].append(word)
except KeyError:
suffix_map[prefix] = [word]

prefix = shift(prefix, word)


"""
Generates a random prefix from the dictionary
Uses prefix to generate words to follow
"""
def random_text(n=100):
# Prefix generation
start = random.choice(suffix_map.keys())

for i in range(n):
suffixes = suffix_map.get(start, None)
if suffixes == None:

random_text(n-i)
return

# Suffix Generation
word = random.choice(suffixes)
print(word)
start = shift(start, word)

"""
Creates a tuple
Deletes the first word, and adds a new word to the end
"""
def shift(t, word):
return t[1:] + (word,)


def main(name, filename='', n=100, order=2, *args):
try:
n = int(n)
order = int(order)
except:
print('[# of words] [prefix length]')
else:
process_file(filename, order)
random_text(n)


if __name__ == '__main__':
main(*sys.argv)