Output word frequencies.

corpus_analysis.py

from pattern.vector import *
import glob
from string import *
import operator
import json

words = ['sir', 'thank', 'love', 'god', 'life', 'night', 'shit', 'boy', 'girl', 'fuck', 'car', 'money', 'father', 'mother', 'hell', 'son', 'kill', 'dead', 'call', 'friend', 'stay', 'leave', 'baby', 'home', 'world']

documents = []
corpus = Corpus.load('years.corpus')

results = {}
for word in words:
  years = {}
	for year in range(1962, 2013):
		years[year] = 0
	results[word] = years

for document in corpus.documents:
	year = document.name
	for word in words:
		strength = document.tf(word)
		# results[word][year] = strength * 1000
		print year + ' - ' + word + ' - ' + str(strength)

# output = json.dumps(results)
# print output