def main():
# Load configuration from file
config = Configuration(config_file='/home/huma/Downloads/irlib-0.1.1/irlib/classify.conf')
try:
config.load_configuration()
config_data = config.get_configuration()
except:
print("Error loading configuration file.")
print("Classifier aborting.")
raise
# config.display_configuration()
print(config)
# sys.exit()
myfolds = config.get_folds()
correctness = 0
# Preporcessor: tokenizer, stemmer, etc.
prep_lower = config_data['lower']
prep_stem = config_data['stem']
prep_pos = config_data['pos']
prep_ngram = config_data['ngram']
prep = Preprocessor(pattern='\W+', lower=prep_lower, stem=prep_stem, pos=prep_pos, ngram=prep_ngram)
for myfold in myfolds:
ev = Evaluation(config=config, fold=myfold)
if config_data['classifier'] == 'rocchio':
ml = Rocchio(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
elif config_data['classifier'] == 'knn':
ml = KNN(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
else:
ml = NaiveBayes(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
training(config, myfold, ml, prep)
ml.do_padding()
ml.calculate_training_data()
# r.display_idx()
ml.diagnose()
testing(config, myfold, ml, ev, prep)
k = config_data['k']
results = ev.calculate(review_spam=True, k=k)
print('Accuracy for fold %d: %s' % (myfold, results))
correctness += results
print("Average accuracy for all folds:", correctness / len(myfolds))
