def handle(self, *args, **options):
wb = Workbook()
ws = wb.active
ws.title = 'first sheet'
for time in range(1, 346, 5):
# reset data
Document.objects.update(sentiment=None, predicted_sentiment=None)
relevant_docs = Document.objects.filter(published__gte=ShareValue.objects.first().time,
published__lte=ShareValue.objects.last().time - timedelta(
minutes=time), similar__isnull=True)
for document in relevant_docs:
sharevalue_before = ShareValue.objects.filter(share=document.share, time__lte=document.published,
time__gte=document.published - timedelta(
minutes=5)).last()
# first share value in the interval [d.published + time, d.published + time * 2]
sharevalue_after = ShareValue.objects.filter(share=document.share,
time__gte=document.published + timedelta(minutes=time),
time__lte=document.published + timedelta(
minutes=time * 2)).first()
if sharevalue_after and sharevalue_before:
price_before = sharevalue_before.price
price_after = sharevalue_after.price
if price_after > price_before:
impact = 'pos'
elif price_before > price_after:
impact = 'neg'
else:
impact = 'neu'
document.sentiment = impact
document.save()
known_feats = []
for doc in Document.objects.filter(sentiment__isnull=False, similar__isnull=True):
text = get_nltktext(doc.text)
known_feats.append((word_feats(text), doc.sentiment))
if known_feats:
known_data_count = len(known_feats)
# 2/3 training data
num_training_data = int(round(2 * known_data_count / 3))
training_feats = known_feats[:num_training_data]
classifier = NaiveBayesClassifier.train(training_feats)
classifier.show_most_informative_features()
# 1/3 test_data
num_testing_data = int(round(known_data_count / 3))
testing_feats = known_feats[::-1][:num_testing_data]
accuracy = nltk.classify.util.accuracy(classifier, testing_feats)
ws.append([time, accuracy])
wb.save(settings.FILE)
def handle(self, *args, **options):
wb = Workbook()
ws = wb.active
ws.title = 'first sheet'
time = 21
# reset data
Document.objects.update(sentiment=None, predicted_sentiment=None)
relevant_docs = Document.objects.filter(published__gte=ShareValue.objects.first().time,
published__lte=ShareValue.objects.last().time - timedelta(
minutes=time))
for d in relevant_docs:
# last sharevalue in interval [d.published - time, d.published]
sharevalue_before = ShareValue.objects.filter(share=d.share, time__lte=d.published,
time__gte=d.published - timedelta(minutes=time)).last()
# first share value in the interval [d.published + time, d.published + time * 2]
sharevalue_after = ShareValue.objects.filter(share=d.share,
time__gte=d.published + timedelta(minutes=time),
time__lte=d.published + timedelta(
minutes=time * 2)).first()
if sharevalue_after and sharevalue_before:
price_before = sharevalue_before.price
price_after = sharevalue_after.price
if price_after > price_before:
impact = 'pos'
elif price_before > price_after:
impact = 'neg'
else:
impact = 'neu'
d.sentiment = impact
d.save()
relevant_docs = Document.objects.filter(published__gte=ShareValue.objects.first().time,
published__lte=ShareValue.objects.last().time - timedelta(
minutes=time))
for document in relevant_docs:
known_feats = []
for training_docs in relevant_docs.filter(published__lt=document.published - timedelta(minutes=time)):
text = get_nltktext(training_docs.text)
known_feats.append((word_feats(text), training_docs.sentiment))
print('ja')
if known_feats:
classifier = NaiveBayesClassifier.train(known_feats)
classifier.show_most_informative_features()
# classify current document
text = get_nltktext(document.text)
result = classifier.classify(word_feats(text))
document.predicted_sentiment = result
document.save()
calculate_credibility()
prediction = 0
for doc in Document.objects.filter(share=document.share,
published__gte=document.published - timedelta(minutes=time),
predicted_sentiment__isnull=False):
if doc.predicted_sentiment == 'pos':
prediction += 1 * doc.credibility
elif doc.predicted_sentiment == 'neg':
prediction += -1 * doc.credibility
if prediction > 0:
result = 'pos'
elif prediction < 0:
result = 'neg'
else:
result = 'neu'
ws.append([result, document.sentiment, result == document.sentiment])
wb.save(settings.FILE)