def analyse_comments(analysed_at=None):
classifier = None
if CURRENT_MODEL == MODEL_LOGISITIC_REGRESSION:
classifier = analyse_with_logistic_regression()
if classifier is None:
print("Classifier is not set up. Set up classifier first.")
return
print("Model is ready. Starting analysis...")
suspected = 0
adder = DBModelAdder()
adder.start()
comments_for_analysis = SiteComment.comments_for_analysis(analysed_at)
for comment in comments_for_analysis:
comment.analysed = datetime.datetime.now()
comment.looks_rude = classifier.classify_rude(comment)
adder.add(comment)
if comment.looks_rude:
suspected += 1
adder.done()
print("Analysis was done for %s comments, %s suspected to be rude." %
(str(len(comments_for_analysis)), str(suspected)))
def analyse_with_cosine():
stats = DocsStats()
rude_comments = SiteComment.rude_comments()
rude_docs = list()
for comment in rude_comments:
rude_docs.append(
Document(stats, comment.id, comment.body, comment.processed_body))
unverified_comments = SiteComment.comments_for_analysis()
unverified_docs = list()
for comment in unverified_comments:
unverified_docs.append(
Document(stats, comment.id, comment.body, comment.processed_body))
stats.calculate_idfs()
stats.vectorise_documents()
cosine = CosineSimilarity(rude_docs)
rude_cluster = cosine.biggest_cluster()
for item in rude_cluster:
print("- ", item.body, "\r\n")