計算語料庫中每個LDA主題的權重

Question

我計算了我的LDA模型，檢索了我的主題，現在我正在尋找計算語料庫上每個主題的權重/百分比的方法。令人驚訝的我找不到這樣做的方法，到目前爲止我的代碼看起來像：

## Libraries to download 
from nltk.tokenize import RegexpTokenizer 
from nltk.corpus import stopwords 
from nltk.stem.porter import PorterStemmer 
from gensim import corpora, models 
import gensim 

## Tokenizing 
tokenizer = RegexpTokenizer(r'\w+') 

# create English stop words list 
en_stop = stopwords.words('english') 

# Create p_stemmer of class PorterStemmer 
p_stemmer = PorterStemmer() 

import json 
import nltk 
import re 
import pandas 

appended_data = [] 

#for i in range(20014,2016): 
# df0 = pandas.DataFrame([json.loads(l) for l in open('SDM_%d.json' % i)]) 
# appended_data.append(df0) 

for i in range(2005,2016): 
    if i > 2013: 
     df0 = pandas.DataFrame([json.loads(l) for l in open('SDM_%d.json' % i)]) 
     appended_data.append(df0) 
    df1 = pandas.DataFrame([json.loads(l) for l in open('Scot_%d.json' % i)]) 
    df2 = pandas.DataFrame([json.loads(l) for l in open('APJ_%d.json' % i)]) 
    df3 = pandas.DataFrame([json.loads(l) for l in open('TH500_%d.json' % i)]) 
    df4 = pandas.DataFrame([json.loads(l) for l in open('DRSM_%d.json' % i)]) 
    appended_data.append(df1) 
    appended_data.append(df2) 
    appended_data.append(df3) 
    appended_data.append(df4) 


appended_data = pandas.concat(appended_data) 
# doc_set = df1.body 

doc_set = appended_data.body 

# list for tokenized documents in loop 
texts = [] 

# loop through document list 
for i in doc_set: 

    # clean and tokenize document string 
    raw = i.lower() 
    tokens = tokenizer.tokenize(raw) 

    # remove stop words from tokens 
    stopped_tokens = [i for i in tokens if not i in en_stop] 

    # add tokens to list 
    texts.append(stopped_tokens) 

# turn our tokenized documents into a id <-> term dictionary 
dictionary = corpora.Dictionary(texts) 

# convert tokenized documents into a document-term matrix 
corpus = [dictionary.doc2bow(text) for text in texts] 

# generate LDA model 
ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=15, id2word = dictionary, passes=50) 
ldamodel.save("model.lda0") 

到目前爲止，我在別的論壇看到的是做到以下幾點：

from itertools import chain 
print(type(doc_set)) 
print(len(doc_set)) 

for top in ldamodel.print_topics(): 
    print(top) 
print 

# Assinging the topics to the document in corpus 
lda_corpus = ldamodel[corpus] 
#print(lda_corpus) 

# Find the threshold, let's set the threshold to be 1/#clusters, 
# To prove that the threshold is sane, we average the sum of all probabilities: 
scores = list(chain(*[[score for topic_id,score in topic] \ 
        for topic in [doc for doc in lda_corpus]])) 
print(sum(scores)) 
print(len(scores)) 
threshold = sum(scores)/len(scores) 
print(threshold) 

cluster1 = [j for i,j in zip(lda_corpus,doc_set) if i[0][1] > threshold] 
cluster2 = [j for i,j in zip(lda_corpus,doc_set) if i[1][1] > threshold] 
cluster3 = [j for i,j in zip(lda_corpus,doc_set) if i[2][1] > threshold] 

但是我得到集羣2中的錯誤：IndexError: list index out of range。任何想法爲什麼？

Answer 1

你需要一個最小概率在LDA功能狀態爲零：此外

ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=15, id2word = dictionary, passes=50, minimum_probability=0) 

，你可以得到由主題分佈於所有的文章：

for i in range(len(doc_set)): 
    print(ldamodel[corpus[i]])