def find_best_threshold(tree, method, input_file, output_file, n=4, idf_enabled=False):
if method in [knn_classifier, knn_classifier_xv]:
features = get_features(input_file, idf_enabled)
write_features("tmp.tab", features)
results = knn_classifier(None, outfile="tmp.tab")
else:
results = method(tree, output=output_file, n=n, idf_enabled=idf_enabled)
reference = parse_reference(input_file) # some speedup, read once
best_threshold = 0.01
best_accuracy = 0
threshold = 0.01
while(threshold <= 1):
threshold = round(threshold,2)
classification = classify_results(results, threshold)
#write(classification, output_file)
#find accuracy
acc = evaluate(input_file, output_file, pred_id2label=classification, ref_id2label=reference)
print "th:", threshold, "acc:",acc
if acc >= best_accuracy:
best_threshold = threshold
best_accuracy = acc
threshold += 0.01
print "best threshold was %.2f with %.4f accuracy" % (best_threshold,
best_accuracy)
def main(tree, output, method, threshold, find_best, n=4, idf_enabled=False):
#load xml and idf
if method in ["word", "lemma", "bleu"]:
print "Loading xmlfile"
tree = (load_xml.get_pairs(tree), tree)
print "done."
if idf_enabled:
generate_idf_score(tree[0])
elif method in ["print_ted", "ted"]:
print "Loading xmlfile"
tree = (create_tree.generate_syntax_tree(tree), tree)
print "done."
if idf_enabled:
generate_idf_score(load_xml.get_pairs(tree[1]))
elif method in ["features"]:
features = get_features(tree, idf_enabled)
write_features(output, features)
return
elif method in ["knn", "knn-xv"]:
tree = (tree, tree)
#run methods
if find_best:
find_best_threshold(tree[0], METHODS[method], tree[1],
output, n=n, idf_enabled=idf_enabled)
else:
if method in ["knn", "knn-xv"]:
features = get_features(tree[0], idf_enabled=idf_enabled)
write_features("features.tab", features)
results = METHODS[method](None, outfile="features.tab")
else:
results = METHODS[method](tree[0], n=n, idf_enabled=idf_enabled,
output=output)
if method == "print_ted":
return
classification = classify_results(results, threshold)
print "writing output"
write(classification, output)
print "Accuracy = %.4f" % evaluate(tree[1], output)
