save_location = '../../experiment_data/experiment_12'
k_list = [25, 50, 75, 100, 150, 200, 250, 300]
kernel_list = ["custom", "linear", "poly_2", "poly_3", "rbf"]
# results -> k -> kernal
results = []
limit_1 = 400 #training set
limit_2 = 400 #validation set
for k in k_list:
print "Running experiment for k=" + str(k) + "..."
ab = ABClassifier()
ab.download_cursors(limit_unlabeled=5000, limit_labeled=5000)
#ab.download_tweet_cursors(limit_unlabeled = 800, limit_labeled = 1000)
ab.run_lsa(k=k)
#pos_cursor_training = ab.labeled_collection.find({"bullying_label":"1"},timeout=False).limit(400)
#neg_cursor_training = ab.labeled_collection.find({"bullying_label":"0"},timeout=False).limit(400)
pos_cursor_training = ab.labeled_collection.find({
"bully": True
},
timeout=False).limit(400)
neg_cursor_training = ab.labeled_collection.find({
"bully": False
},
timeout=False).limit(400)
results_obj['true_pos'] = 0
results_obj['true_neg'] = 0
results_obj['true_pos_rate'] = 0
results_obj['true_neg_rate'] = 0
results_obj['accuracy'] = 0
results_obj['num_iterations'] = 0
results[k] = results_obj
for i in xrange(0,20):
for k in k_list:
print "Running experiment for k = " + str(k)
ab = ABClassifier()
ab.download_cursors(limit_unlabeled = limit_1, limit_labeled = limit_1)
ab.run_lsa(k=k)
print "Starting classification..."
unlabeled_cursor = ab.db.tweets.find({"bullying_label" : {'$exists' :True}}, timeout = False)
pos_cursor = ab.labeled_collection.find({"bully":True},timeout=False).limit(unlabeled_cursor.count())
neg_cursor = ab.labeled_collection.find({"bully":False},timeout=False).limit(unlabeled_cursor.count())
unl = []
pos = []
neg = []
for u,p,n in zip(unlabeled_cursor, pos_cursor, neg_cursor):
u_obj = {}
k_list = [25, 50, 75, 100, 150, 200, 250, 300]
kernel_list = ["custom", "linear", "poly_2","poly_3", "rbf"]
# results -> k -> kernal
results = []
limit_1 = 400 #training set
limit_2 = 400 #validation set
for k in k_list:
print "Running experiment for k=" + str(k) + "..."
ab = ABClassifier()
ab.download_cursors(limit_unlabeled = 5000, limit_labeled = 5000)
#ab.download_tweet_cursors(limit_unlabeled = 800, limit_labeled = 1000)
ab.run_lsa(k=k)
#pos_cursor_training = ab.labeled_collection.find({"bullying_label":"1"},timeout=False).limit(400)
#neg_cursor_training = ab.labeled_collection.find({"bullying_label":"0"},timeout=False).limit(400)
pos_cursor_training = ab.labeled_collection.find({"bully":True},timeout=False).limit(400)
neg_cursor_training = ab.labeled_collection.find({"bully":False},timeout=False).limit(400)
training = []
tlabels = []
pos_validation = []
pos_vlabels = []
neg_validation = []
results = {}
for t in thresholds:
results_obj = {}
results_obj['t'] = t
results_obj['pos_list_size'] = 0
results_obj['neg_list_size'] = 0
results_obj['true_pos'] = 0
results_obj['true_neg'] = 0
results_obj['true_pos_rate'] = 0
results_obj['true_neg_rate'] = 0
results_obj['accuracy'] = 0
results_obj['num_iterations'] = 0
results[int(t * 100)] = results_obj
ab = ABClassifier()
ab.download_cursors(limit_unlabeled=limit_1, limit_labeled=limit_1)
ab.run_lsa(k=k)
context_tweets = [
"Literally go f**k yourself, because you're honestly pathetic.",
"f**k you f****n w***e go f**k yourself stupid bitch",
"but this bad I want to kick her ass cuz she thinks she's a hard chola like sit ur fat ass down lol",
"course he did he's a whipped bitch that will say anything to make u happy, unlike ur mum who called u fat",
"Fat pig. You're disgusting.",
"From some illiterate online keyboard warrior? Go back to sucking your butt buddy's fat junk.",
"God Says; Evil Don't Know The Way. You are gay with AIDS & your sin cost you your anointing! This is why you use DUST!"
"f**k you stupid f****t f*g"
]
tweet_cvs = []
for c in context_tweets:
tweet_cvs.append(ab.get_context_vector(c))