import sys
sys.path.append('..')
from ABClassifier.ABClassifier import ABClassifier
import numpy as np
ab = ABClassifier()
ab.download_cursors(limit_unlabeled = 1000, limit_labeled = 1000)
ab.run_lsa(k=100)
ab.compute_context_vectors()
pos_labeled_pws = ab.pairwise_similarity(ab.pos_labeled_cv_list)
neg_labeled_pws = ab.pairwise_similarity(ab.neg_labeled_cv_list)
unlabeled_pws = ab.pairwise_similarity(ab.unlabeled_cv_list)
print "done getting pws"
x = np.array(pos_labeled_pws.values())
a = np.asarray(x)
np.savetxt('pos_labeled.csv', a, delimiter=",")
y = np.array(neg_labeled_pws.values())
b = np.asarray(y)
np.savetxt('neg_labeled.csv', b, delimiter=",")
z = np.array(unlabeled_pws.values())
c = np.asarray(z)
np.savetxt('unlabeled.csv', c, delimiter=",")
import sys
sys.path.append('../..')
from ABClassifier.ABClassifier import ABClassifier
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
save_location = '../../experiment_data/experiment_2'
k_list = [5, 10, 25, 50, 100, 150, 250, 500]
for k in k_list:
ab = ABClassifier()
ab.download_cursors(limit_unlabeled=1000, limit_labeled=1000)
ab.run_lsa(k=k)
ab.compute_context_vectors(save_location=save_location)
print "Performing pairwise similarity measures..."
pos_labeled_pws = cosine_similarity(ab.pos_labeled_cv_list).flatten()
neg_labeled_pws = cosine_similarity(ab.neg_labeled_cv_list).flatten()
unlabeled_pws = cosine_similarity(ab.unlabeled_cv_list).flatten()
print "Done."
print "Saving..."
np.savetxt(save_location + '/pw_pos_' + str(k) + '.csv',
pos_labeled_pws,
delimiter=",")
np.savetxt(save_location + '/pw_neg_' + str(k) + '.csv',
import sys
sys.path.append('..')
from ABClassifier.ABClassifier import ABClassifier
import numpy as np
ab = ABClassifier()
ab.download_cursors(limit_unlabeled=10000, limit_labeled=10000)
ab.run_lsa(k=100)
ab.compute_context_vectors()
pos_labeled_pws = ab.pairwise_similarity(ab.pos_labeled_cv_list)
neg_labeled_pws = ab.pairwise_similarity(ab.neg_labeled_cv_list)
unlabeled_pws = ab.pairwise_similarity(ab.unlabeled_cv_list)
print "done getting pws"
x = np.array(pos_labeled_pws.values())
a = np.asarray(x)
np.savetxt('pos_labeled.csv', a, delimiter=",")
y = np.array(neg_labeled_pws.values())
b = np.asarray(y)
np.savetxt('neg_labeled.csv', b, delimiter=",")
z = np.array(unlabeled_pws.values())
c = np.asarray(z)
np.savetxt('unlabeled.csv', c, delimiter=",")
-Vary the number of input tweets to the Co-Occurrence Matrix
"""
import sys
sys.path.append('../..')
from ABClassifier.ABClassifier import ABClassifier
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
save_location = '../../experiment_data/experiment_1b'
ab = ABClassifier()
ab.download_cursors(limit_unlabeled = 2500, limit_labeled = 2500)
ab.run_lsa(k=100)
ab.compute_context_vectors(save_location = save_location)
print "Performing pairwise similarity measures..."
pos_labeled_pws = ab.pairwise_similarity(ab.pos_labeled_cv_list)
neg_labeled_pws = ab.pairwise_similarity(ab.neg_labeled_cv_list)
unlabeled_pws = ab.pairwise_similarity(ab.unlabeled_cv_list)
#pos_neg_pws = cosine_similarity(ab.pos_labeled_cv_list, ab.neg_labeled_cv_list)
#pos_unl_pws = cosine_similarity(ab.pos_labeled_cv_list, ab.unlabeled_cv_list)
#neg_unl_pws = cosine_similarity(ab.neg_labeled_cv_list, ab.unlabeled_labeled_cv_list)
print "Done."
print "Saving..."