MarkovChainz - A learning algorithm that just wants to rap

deeplearning.py

import numpy as np
 
def nonlin(x,deriv=False):
	if(deriv==True):
		return x*(1-x)
	return 1/(1+np.exp(-x))
 
X = np.array([[0,0,1],
			[0,1,1],
			[1,0,1],
			[1,1,1]])
 
y = np.array([[0],
			[1],
			[1],
			[0]])
 
np.random.seed(1)
 
# randomly initialize our weights with mean 0
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1
 
for j in xrange(60000):
 
	# Feed forward through layers 0, 1, and 2
	l0 = X
	l1 = nonlin(np.dot(l0,syn0))
	l2 = nonlin(np.dot(l1,syn1))
	 
	# how much did we miss the target value?
	l2_error = y - l2
	 
	if (j% 10000) == 0:
		print "Error:" + str(np.mean(np.abs(l2_error)))
	 
	# in what direction is the target value?
	# were we really sure? if so, don't change too much.
	l2_delta = l2_error*nonlin(l2,deriv=True)
	 
	# how much did each l1 value contribute to the l2 error (according to the weights)?
	l1_error = l2_delta.dot(syn1.T)
	 
	# in what direction is the target l1?
	# were we really sure? if so, don't change too much.
	l1_delta = l1_error * nonlin(l1,deriv=True)
	 
	syn1 += l1.T.dot(l2_delta)
	syn0 += l0.T.dot(l1_delta)
	

markov.py

import sys
from random import choice
from glob import glob

nonword = "\n" # Since we split on whitespace, this can never be a word
w1 = nonword
w2 = nonword

# GENERATE TABLE
table = {}


for file in glob("*.txt"):
	f = open(file, 'r')
	for line in f:
		# print line
		for word in line.split():
			table.setdefault( (w1, w2), [] ).append(word)
			w1, w2 = w2, word
	f.close()
table.setdefault( (w1, w2), [] ).append(nonword) # Mark the end of the file

# GENERATE OUTPUT
w1 = nonword
w2 = nonword

maxwords = 1000

o = open('out.mkc', 'w')
for i in xrange(maxwords):
	newword = choice(table[(w1, w2)])
	if newword == nonword:
		sys.exit()
	print newword
	o.write(newword + " ")
	w1, w2 = w2, newword
o.close()