I am using LDA over a simple collection of documents. My goal is to extract topics, then use the extracted topics as features to evaluate my model.
I decided to use multinomial SVM as the evaluator.
import itertools
from gensim.models import ldamodel
from nltk.tokenize import RegexpTokenizer
from nltk.stem.porter import PorterStemmer
from gensim import corpora, models
from sklearn.naive_bayes import MultinomialNB
tokenizer = RegexpTokenizer(r'\w+')
# create English stop words list
en_stop = {'a'}
# Create p_stemmer of class PorterStemmer
p_stemmer = PorterStemmer()
# create sample documents
doc_a = "Brocolli is good to eat. My brother likes to eat good brocolli, but not my mother."
doc_b = "My mother spends a lot of time driving my brother around to baseball practice."
doc_c = "Some health experts suggest that driving may cause increased tension and blood pressure."
doc_d = "I often feel pressure to perform well at school, but my mother never seems to drive my brother to do better."
doc_e = "Health professionals say that brocolli is good for your health."
# compile sample documents into a list
doc_set = [doc_a, doc_b, doc_c, doc_d, doc_e]
# 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]
# stem tokens
stemmed_tokens = [p_stemmer.stem(i) for i in stopped_tokens]
# add tokens to list
texts.append(stemmed_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=2, id2word=dictionary, passes=20)
id2word = corpora.Dictionary(texts)
# Creates the Bag of Word corpus.
mm = [id2word.doc2bow(text) for text in texts]
# Trains the LDA models.
lda = ldamodel.LdaModel(corpus=mm, id2word=id2word, num_topics=4,
update_every=1, chunksize=10000, passes=1)
# Assigns the topics to the documents in corpus
a=[]
lda_corpus = lda[mm]
for i in range(len(doc_set)):
a.append(lda_corpus[i])
print(lda_corpus[i])
merged_list = list(itertools.chain(*lda_corpus))
print(a)
#my_list.append(my_list[i])
sv=MultinomialNB()
yvalues = [0,1,2,3]
sv.fit(a,yvalues)
predictclass = sv.predict(a)
testLables=[0,1,2,3]
from sklearn import metrics, tree
#yacc=metrics.accuracy_score(testLables,predictclass)
#print (yacc)
when I run this code it throws the error mentioned in the subject.
Also this is the output of LDA model(topic doc distribution) that I feed to SVM:
[[(0, 0.95533888404477663), (1, 0.014775921798986477), (2, 0.015161897773308793), (3, 0.014723296382928375)], [(0, 0.019079556242721694), (1, 0.017932434792585779), (2, 0.94498655991579728), (3, 0.018001449048895311)], [(0, 0.017957955483631164), (1, 0.017900184473362918), (2, 0.018133572636989413), (3, 0.9460082874060165)], [(0, 0.96554611572184923), (1, 0.011407838337200715), (2, 0.011537900721487016), (3, 0.011508145219463113)], [(0, 0.023306931039431281), (1, 0.022823706054846005), (2, 0.93072240824085961), (3, 0.023146954664863096)]]
my labels here are : 0,1,2,3
