python - n-grams with Naive Bayes classifier Error -


i experimenting python nltk text classification. here code example practicing: http://www.laurentluce.com/posts/twitter-sentiment-analysis-using-python-and-nltk/

here code:

from nltk import bigrams nltk.probability import eleprobdist, freqdist nltk import naivebayesclassifier collections import defaultdict  train_samples = {}  file ('data/positive.txt', 'rt') f:    line in f.readlines():        train_samples[line] = 'pos'  file ('data/negative.txt', 'rt') d:    line in d.readlines():        train_samples[line] = 'neg'  f = open("data/test.txt", "r") test_samples = f.readlines()  # error in code # def bigramreturner(text): #    tweetstring = text.lower() #    bigramfeaturevector = {} #    item in bigrams(tweetstring.split()): #        bigramfeaturevector.append(' '.join(item)) #    return bigramfeaturevector  # updated code stack overflow comment  def bigramreturner (tweetstring):     tweetstring = tweetstring.lower()     #comment line since function not defined     #tweetstring = removepunctuation (tweetstring)     bigramfeaturevector = []     item in nltk.unigrams(tweetstring.split()):         bigramfeaturevector.append(' '.join(item))     return bigramfeaturevector  def get_labeled_features(samples):     word_freqs = {}     text, label in train_samples.items():         tokens = text.split()         token in tokens:             if token not in word_freqs:                 word_freqs[token] = {'pos': 0, 'neg': 0}             word_freqs[token][label] += 1     return word_freqs   def get_label_probdist(labeled_features):     label_fd = freqdist()     item, counts in labeled_features.items():         label in ['neg', 'pos']:             if counts[label] > 0:                 label_fd.inc(label)     label_probdist = eleprobdist(label_fd)     return label_probdist   def get_feature_probdist(labeled_features):     feature_freqdist = defaultdict(freqdist)     feature_values = defaultdict(set)     num_samples = len(train_samples) / 2     token, counts in labeled_features.items():         label in ['neg', 'pos']:             feature_freqdist[label, token].inc(true, count=counts[label])             feature_freqdist[label, token].inc(none, num_samples - counts[label])             feature_values[token].add(none)             feature_values[token].add(true)     item in feature_freqdist.items():         print item[0], item[1]     feature_probdist = {}     ((label, fname), freqdist) in feature_freqdist.items():         probdist = eleprobdist(freqdist, bins=len(feature_values[fname]))         feature_probdist[label, fname] = probdist     return feature_probdist    labeled_features = get_labeled_features(train_samples)  label_probdist = get_label_probdist(labeled_features)  feature_probdist = get_feature_probdist(labeled_features)  classifier = naivebayesclassifier(label_probdist, feature_probdist)   sample in test_samples:     print "%s | %s" % (sample, classifier.classify(bigramreturner(sample)))

but when run code following error:

traceback (most recent call last):   file "naive_bigram_1.py", line 87, in <module>     print "%s | %s" % (sample, classifier.classify(bigramreturner(sample)))   file "naive_bigram_1.py", line 30, in bigramreturner     tweetstring = removepunctuation (tweetstring) nameerror: global name 'removepunctuation' not defined

i saw similar question other error, here updated n-grams naive bayes classifier

you're calling function removepunctuation hasn't been defined previously:

def bigramreturner (tweetstring):     tweetstring = tweetstring.lower()     tweetstring = removepunctuation (tweetstring)     ....

i noticed put spaces between functions' names , parameters list. avoid it's not idiomatic python , cause problems (like function being evaluated object instead of being called).


Comments

Post a Comment

Popular posts from this blog

java.util.scanner - How to read and add only numbers to array from a text file -

i'm learning java , have question regarding reading file want read numbers file contains strings well. here example of file: 66.56 "3 java 3-43 5-42 2.1 1 and here coding: public class test { public static void main (string [] args){ if (0 < args.length) { file x = new file(args[0]); try{ scanner in = new scanner( new fileinputstream(x)); arraylist<double> test = new arraylist<>(); while(in.hasnext()){ if(in.hasnextdouble()){ double f=in.nextdouble(); test.add(f);} else {in.next();} } catch(ioexception e) { system.err.println("exception during reading: " + e); } } my problem add 66.56,2.1 , 1 doesn't add 3 after "3 or ignores 3-43 , 5-42 can tell me how skip strings , add doubles here? thanks all said 3 ie; "3, 3-43 , 4-42 strings either u read string , split , check number @ " , - or put in space between characters , integers. jvm after compilation tre...
Read more

rewrite - Trouble with Wordpress multiple custom querystrings -

i'm working on adding multiple querystring , doesn't seem work. i've found codes seems work others might i'm missing something. i want like: http://mydomain.com/board/?getyear=2013&getsometext2=sometext to http://mydomain.com/board/2013/sometext/ i added code below functions.php file. doesn't seem work should though. this works. echoing querystring gets both variable without problem. http://mydomain.com/board/2013/sometext/ but doesn't. tested querystring vis isset() seems nothing being set/get http://mydomain.com/board/2013/ function add_query_vars($vars) { $vars[] = "getyear"; $vars[] = "getsometext2"; return $vars; } add_filter('query_vars', 'add_query_vars'); function add_rewrite_rules($arules) { $anewrules = array('board/([^/]+)/([^/]+)/?$' => 'index.php?pagename=board&getyear=$matches[1]&getsometext2=$matches[2]'); $arules = $a...
Read more