import os,re
import math
from math import log10
import nltk.corpus
from nltk.tokenize import RegexpTokenizer
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from collections import defaultdict
python_file_root = './presidential_debates'
def getidf(token):
document_occurance = 0
for filename in os.listdir(python_file_root):
file = open(os.path.join(python_file_root, filename), "r")
for line in file:
if re.search(r'\b' +token+ r'\b', line):
document_occurance = document_occurance + 1
break
if (document_occurance != 0):
idf = log10(30 / document_occurance)
return idf
return -1
def normalize(filename,token):
file = open(os.path.join(python_file_root, filename), "r")
counts = dict()
square = []
count1 = 0
for line in file:
count1 = count1 + 1
if line in counts:
counts[line] += 1
else:
counts[line] = 1
for key,value in counts.items():
tf = 1 +log10(value)
idf = getidf(key.rstrip())
square.append((tf * idf)*(tf * idf))
summ = sum(square)
sqroot = math.sqrt(summ)
return sqroot
def getweight(filename,token):
hit_count1 = 0
final = 0
file = open(os.path.join(python_file_root, filename), "r")
idft = getidf(token)
for line in file:
if re.search(r'\b' +token+ r'\b', line):
hit_count1 = hit_count1 + 1
if (hit_count1 == 0):
return 0
else:
tf = 1 + log10(hit_count1)
initial = idft * tf
if(initial <= 0):
final = 0
return final
else:
normalize_fact = normalize(filename,token)
final = initial / normalize_fact
return final
for filename in os.listdir(python_file_root):
file = open(os.path.join(python_file_root, filename), "r")
doc = file.read()
doc = doc.lower()
stemmed = []
tokenizer = RegexpTokenizer(r'[a-zA-Z]+')
tokens = tokenizer.tokenize(doc)
stoplist = stopwords.words('english')
stop_removed = [word for word in tokens if word not in stoplist]
with open(os.path.join(python_file_root, filename), "w") as f:
for item in stop_removed:
stemmer = PorterStemmer()
stemmed = [stemmer.stem(item)]
for items in stemmed:
f.write("%s\n" % items)
print("\nIDF\n")
print("%.12f" % getidf("health"))
print("%.12f" % getidf("agenda"))
print("%.12f" % getidf("vector"))
print("%.12f" % getidf("reason"))
print("%.12f" % getidf("hispan"))
print("%.12f" % getidf("hispanic"))
print("\n")
print("%.12f" % getweight("2012-10-03.txt","health"))
print("%.12f" % getweight("1960-10-21.txt","reason"))
print("%.12f" % getweight("1976-10-22.txt","agenda"))
print("%.12f" % getweight("2012-10-16.txt","hispan"))
print("%.12f" % getweight("2012-10-16.txt","hispanic"))
我有30个txt文件,并且我已经开发了一个程序来查找idf和标准化的tf-idf向量。我得到了正确的值,但函数getweight花费了超过15分钟的时间来生成输出。谁能建议我一些优化方法。 我不想使用任何其他非标准的Python包。
答案 0 :(得分:0)
为什么要为每个单词创建一个 new PorterStemmer?
除了这个显而易见的事情之外,请尝试对代码进行性能分析。 NLTI的名声很慢-因此,这可能不是您的错。如果您进行了简介,那么您就会知道。