galiquisSentiment Analysis Module
This section brings all the detail together to create a module that can be used to monitor twitter sentiment.
The code for this is seperated into two blocks.
The first pickles most of the heavy training to save time in future iteration:-.
import nltk
import random
#from nltk.corpus import movie_reviews
from nltk.classify.scikitlearn import SklearnClassifier
import pickle
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC
from nltk.classify import ClassifierI
from statistics import mode
from nltk.tokenize import word_tokenize
#from unidecode import unidecode
class VoteClassifier(ClassifierI):
def __init__(self, *classifiers):
self._classifiers = classifiers
def classify(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
return mode(votes)
def confidence(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
choice_votes = votes.count(mode(votes))
conf = choice_votes / len(votes)
return conf
short_pos = open("positive.txt","r", encoding='utf-8', errors='replace').read() ## had to add a line to tell the open function to use utf-8
short_neg = open("negative.txt","r", encoding='utf-8', errors='replace').read()
# move this up here
all_words = []
documents = []
# j is adject, r is adverb, and v is verb
#allowed_word_types = ["J","R","V"]
allowed_word_types = ["J"]
for p in short_pos.split('\n'):
documents.append( (p, "pos") )
words = word_tokenize(p)
pos = nltk.pos_tag(words)
for w in pos:
if w[1][0] in allowed_word_types:
all_words.append(w[0].lower())
for p in short_neg.split('\n'):
documents.append( (p, "neg") )
words = word_tokenize(p)
pos = nltk.pos_tag(words)
for w in pos:
if w[1][0] in allowed_word_types:
all_words.append(w[0].lower())
save_documents = open("pickled_algos/documents.pickle","wb")
pickle.dump(documents, save_documents)
save_documents.close()
all_words = nltk.FreqDist(all_words)
word_features = list(all_words.keys())[:5000]
save_word_features = open("pickled_algos/word_features5k.pickle","wb")
pickle.dump(word_features, save_word_features)
save_word_features.close()
def find_features(document):
words = word_tokenize(document)
features = {}
for w in word_features:
features[w] = (w in words)
return features
featuresets = [(find_features(rev), category) for (rev, category) in documents]
random.shuffle(featuresets)
print(len(featuresets))
testing_set = featuresets[7400:] # memory limitations on the Pi meant this needed reducing from 10,000
training_set = featuresets[:7400]
save_featuresets = open("pickled_algos/featuresets.pickle","wb") ## added code to pickle featuresets
pickle.dump(featuresets, save_featuresets)
save_featuresets.close()
classifier = nltk.NaiveBayesClassifier.train(training_set)
print("Original Naive Bayes Algo accuracy percent:", (nltk.classify.accuracy(classifier, testing_set))*100)
classifier.show_most_informative_features(15)
###############
save_classifier = open("pickled_algos/originalnaivebayes5k.pickle","wb")
pickle.dump(classifier, save_classifier)
save_classifier.close()
MNB_classifier = SklearnClassifier(MultinomialNB())
MNB_classifier.train(training_set)
print("MNB_classifier accuracy percent:", (nltk.classify.accuracy(MNB_classifier, testing_set))*100)
save_classifier = open("pickled_algos/MNB_classifier5k.pickle","wb")
pickle.dump(MNB_classifier, save_classifier)
save_classifier.close()
BernoulliNB_classifier = SklearnClassifier(BernoulliNB())
BernoulliNB_classifier.train(training_set)
print("BernoulliNB_classifier accuracy percent:", (nltk.classify.accuracy(BernoulliNB_classifier, testing_set))*100)
save_classifier = open("pickled_algos/BernoulliNB_classifier5k.pickle","wb")
pickle.dump(BernoulliNB_classifier, save_classifier)
save_classifier.close()
LogisticRegression_classifier = SklearnClassifier(LogisticRegression())
LogisticRegression_classifier.train(training_set)
print("LogisticRegression_classifier accuracy percent:", (nltk.classify.accuracy(LogisticRegression_classifier, testing_set))*100)
save_classifier = open("pickled_algos/LogisticRegression_classifier5k.pickle","wb")
pickle.dump(LogisticRegression_classifier, save_classifier)
save_classifier.close()
LinearSVC_classifier = SklearnClassifier(LinearSVC())
LinearSVC_classifier.train(training_set)
print("LinearSVC_classifier accuracy percent:", (nltk.classify.accuracy(LinearSVC_classifier, testing_set))*100)
save_classifier = open("pickled_algos/LinearSVC_classifier5k.pickle","wb")
pickle.dump(LinearSVC_classifier, save_classifier)
save_classifier.close()
##NuSVC_classifier = SklearnClassifier(NuSVC())
##NuSVC_classifier.train(training_set)
##print("NuSVC_classifier accuracy percent:", (nltk.classify.accuracy(NuSVC_classifier, testing_set))*100)
SGDC_classifier = SklearnClassifier(SGDClassifier())
SGDC_classifier.train(training_set)
print("SGDClassifier accuracy percent:",nltk.classify.accuracy(SGDC_classifier, testing_set)*100)
save_classifier = open("pickled_algos/SGDC_classifier5k.pickle","wb")
pickle.dump(SGDC_classifier, save_classifier)
save_classifier.close()
I had to drop the size of the learning set given the memory restrictions on the Pi not sure there was another way around this and it probably means that to start doing some of this stuff seriously….I’m going to need a bigger/better server.
Also I added a section to pickle the featuresets:-
save_featuresets = open("pickled_algos/featuresets.pickle","wb") ## added code to pickle featuresets
pickle.dump(featuresets, save_featuresets)
save_featuresets.close()
One option might be clustering the Pi or putting together a low power server – which then leads into building a full home server farm.
The next section is then the sentiment module:-
#File: sentiment_mod.py
import nltk
import random
#from nltk.corpus import movie_reviews
from nltk.classify.scikitlearn import SklearnClassifier
import pickle
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.svm import SVC, LinearSVC, NuSVC
from nltk.classify import ClassifierI
from statistics import mode
from nltk.tokenize import word_tokenize
class VoteClassifier(ClassifierI):
def __init__(self, *classifiers):
self._classifiers = classifiers
def classify(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
return mode(votes)
def confidence(self, features):
votes = []
for c in self._classifiers:
v = c.classify(features)
votes.append(v)
choice_votes = votes.count(mode(votes))
conf = choice_votes / len(votes)
return conf
documents_f = open("pickled_algos/documents.pickle", "rb")
documents = pickle.load(documents_f)
documents_f.close()
word_features5k_f = open("pickled_algos/word_features5k.pickle", "rb")
word_features = pickle.load(word_features5k_f)
word_features5k_f.close()
def find_features(document):
words = word_tokenize(document)
features = {}
for w in word_features:
features[w] = (w in words)
return features
featuresets_f = open("pickled_algos/featuresets.pickle", "rb")
featuresets = pickle.load(featuresets_f)
featuresets_f.close()
random.shuffle(featuresets)
print(len(featuresets))
testing_set = featuresets[10000:]
training_set = featuresets[:10000]
open_file = open("pickled_algos/originalnaivebayes5k.pickle", "rb")
classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/MNB_classifier5k.pickle", "rb")
MNB_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/BernoulliNB_classifier5k.pickle", "rb")
BernoulliNB_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/LogisticRegression_classifier5k.pickle", "rb")
LogisticRegression_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/LinearSVC_classifier5k.pickle", "rb")
LinearSVC_classifier = pickle.load(open_file)
open_file.close()
open_file = open("pickled_algos/SGDC_classifier5k.pickle", "rb")
SGDC_classifier = pickle.load(open_file)
open_file.close()
voted_classifier = VoteClassifier(
classifier,
LinearSVC_classifier,
MNB_classifier,
BernoulliNB_classifier,
LogisticRegression_classifier)
def sentiment(text):
feats = find_features(text)
return voted_classifier.classify(feats),voted_classifier.confidence(feats)