def test():
with closing(connect_db()) as db:
svm = SVM(C=1)
fill_negative_votes()
X, Y = get_feature_vecs(db)
# Divide up X into S chunks
N = len(X)
S = N
# Cross validation, and get the averate number of misclassified
count = 0
total_incorrect = 0
for s in range(S):
print "iter:", count
size_of_fold = math.ceil(1.0*N/S)
start = s*size_of_fold
end = start + size_of_fold
if end > N:
print "end > N"
end = N
print "range:", start, end
holdoutX = X[start:end,:]
trainingX = np.concatenate( (X[0:start], X[end:N]) )
holdoutY = Y[start:end]
trainingY = np.concatenate( (Y[0:start], Y[end:N]) )
print "len holdoutX:", len(holdoutX)
print "len trainingX;", len(trainingX)
print "len holdoutY:", len(holdoutY)
print "len trainingY;", len(trainingY)
svm.train_dual(trainingX, trainingY)
num_misclass = svm.num_incorrect(holdoutX, holdoutY)
total_incorrect += num_misclass
print "Num incorrect:", num_misclass
count +=1
print "Total misclassified with SVM:", 1.0 * total_incorrect
# Now use keyword classification
votes = get_all_votes()
num_incorrect = 0
for vote, event, doc in votes:
classify = keyword_classify(event, doc)
if classify != vote:
print "Classified as:", classify, "actual:", vote
num_incorrect += 1
else:
print "Classified as:", classify, "actual:", vote
print "Total misclassified with keyword approach:", num_incorrect