print "moving to a sparse representation..." train_feat = sparsify(train_feat) test_feat = sparsify(test_feat) train_labl = [s.labels for s in train_sequences] train_labl = [item for sublist in train_labl for item in sublist] obsr_labl = [s.labels for s in test_sequences] test_seq = [" ".join(x) for x in obsr_labl] test_tok = [item for sublist in obsr_labl for item in sublist] obsr_list = get_observations(test_feat, test_sequences) memm = MEMM(10, 0.0001) memm.fit(train_feat, train_labl, fe.num_feats) pred_tok, pred_seq = memm.predict_sequences(obsr_list) # Structured Perceptron using viterbi in the inference step """percep = StructuredPerceptron(10, fe, 0.1) percep.fit(train_sequences) pred_tok, pred_seq = percep.predict_sequences(test_sequences) obsr_labl = [s.labels for s in test_sequences] test_seq = [" ".join(x) for x in obsr_labl] test_tok = [item for sublist in obsr_labl for item in sublist]""" # print results print metrics.classification_report(test_tok, pred_tok)
print "moving to a sparse representation..." train_feat = sparsify(train_feat) test_feat = sparsify(test_feat) train_labl = [s.labels for s in train_sequences] train_labl = [item for sublist in train_labl for item in sublist] obsr_labl = [s.labels for s in test_sequences] test_seq = [" ".join(x) for x in obsr_labl] test_tok = [item for sublist in obsr_labl for item in sublist] obsr_list = get_observations(test_feat, test_sequences) memm = MEMM(10, 0.0001) memm.fit(train_feat, train_labl, fe.num_feats) pred_tok, pred_seq = memm.predict_sequences(obsr_list) # Structured Perceptron using viterbi in the inference step '''percep = StructuredPerceptron(10, fe, 0.1) percep.fit(train_sequences) pred_tok, pred_seq = percep.predict_sequences(test_sequences) obsr_labl = [s.labels for s in test_sequences] test_seq = [" ".join(x) for x in obsr_labl] test_tok = [item for sublist in obsr_labl for item in sublist]''' # print results print metrics.classification_report(test_tok, pred_tok) print metrics.accuracy_score(test_tok, pred_tok) print metrics.accuracy_score(test_seq, pred_seq)
