Last active
December 17, 2015 05:28
-
-
Save boblannon/5557702 to your computer and use it in GitHub Desktop.
quick and dirty method of using residual IDF to find keywords in a corpus. implementation of chruch and gale 1991
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 defaultdict | |
from math import log | |
from math import exp | |
import pandas as pd | |
# this is based on data in the form released here: http://corpora.uni-leipzig.de/ | |
# inv_w.txt is a table of (word_id, sentence_id, offset), which lets us create an inverted | |
# index with offset information | |
inv_w = defaultdict(lambda:defaultdict(list)) | |
for line in open('inv_w.txt'): | |
wid,sid,offset = line.strip().split('\t') | |
inv_w[int(wid)][int(sid)].append(int(offset)) | |
# words.txt is a table of (word_id, word, corpus_frequency), which allows us to make a master | |
# dictionary of corpus-wide counts | |
words = {} | |
for line in open('words.txt'): | |
wid,word,cf = line.strip().split('\t') | |
words[word] = {'wid':wid,'cf':cf} | |
id_lookup = {v['wid']:k for k,v in words.iteritems()} | |
# N - total number of documents in a corpus | |
# cf - corpus frequency, or the number of times the word occurs in across a corpus | |
# df - document frequency, or the number of documents that contain at least one occurrence of the word | |
# IDF - inverse document frequency | |
def smooth_cf(cf): | |
#TODO: write a smoothing fct | |
return float(cf) | |
def smooth_df(df): | |
#TODO: write a smoothing fct | |
return float(df) | |
def poisson(cf,N): | |
p = exp(-(smooth_cf(cf)/float(N))) # may want to include some smoothing, here | |
return log(1-p,2) | |
def IDF(df,N): | |
idf = float(N)/smooth_df(df) | |
return log(idf,2) | |
def RIDF(s): | |
w = words[s] | |
cf = w['cf'] | |
wid = w['wid'] | |
df = len(inv_w[wid]) | |
if cf == 0: | |
return 0 | |
else: | |
return IDF(df,300000) + poisson(cf,300000) | |
ridf_records = [(v['wid'],k,RIDF(k)) for k,v in words.iteritems()] | |
df = pd.DataFrame(rows) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment