def main(training_data, test_data, output_file):
if test_data:
training_features = get_features(training_data)
test_features = get_features(test_data)
write_f("train.tab", training_features)
write_f("test.tab", test_features)
results = tweaked_on_testdata("train.tab", "test.tab")
classification = classify_results(results, 0.5)
print "witing output"
write(classification, output_file)
else:
training_features = get_features(training_data)
write_f("train.tab", training_features)
results = tweaked("train.tab") # cross-validation
print "classifying"
classification = classify_results(results, 0.5)
print "writing output"
write(classification, output_file)
print "Accuracy = %.4f" % evaluate(training_data, output_file)
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)