sklearn-crfsuite

import sklearn_crfsuite from sklearn_crfsuite import metrics # Dummy data for a simple sequence labeling task (e.g., POS tagging) # Each sentence is a list of (word, pos_tag) # Features are extracted for each word, labels are the expected tags def word2features(sent, i): word = sent[i][0] postag = sent[i][1] features = { 'bias': 1.0, 'word.lower()': word.lower(), 'word.isupper()': word.isupper(), 'word.istitle()': word.istitle(), 'word.isdigit()': word.isdigit(), 'postag': postag, 'postag[:2]': postag[:2], } if i > 0: word1 = sent[i-1][0] postag1 = sent[i-1][1] features[' -1:word.lower()'] = word1.lower() features[' -1:word.istitle()'] = word1.istitle() features[' -1:word.isupper()'] = word1.isupper() features[' -1:postag'] = postag1 features[' -1:postag[:2]'] = postag1[:2] else: features['BOS'] = True # Beginning of Sentence if i < len(sent)-1: word1 = sent[i+1][0] postag1 = sent[i+1][1] features['+1:word.lower()'] = word1.lower() features['+1:word.istitle()'] = word1.istitle() features['+1:word.isupper()'] = word1.isupper() features['+1:postag'] = postag1 features['+1:postag[:2]'] = postag1[:2] else: features['EOS'] = True # End of Sentence return features def sent2features(sent): return [word2features(sent, i) for i in range(len(sent))] def sent2labels(sent): return [label for word, label in sent] train_sents = [ [('The', 'DT'), ('quick', 'JJ'), ('brown', 'JJ'), ('fox', 'NN'), ('jumps', 'VBZ'), ('over', 'IN'), ('the', 'DT'), ('lazy', 'JJ'), ('dog', 'NN')], [('I', 'PRP'), ('love', 'VBP'), ('Python', 'NNP')], [('Natural', 'JJ'), ('Language', 'NNP'), ('Processing', 'NNP'), ('is', 'VBZ'), ('fun', 'JJ')], ] X_train = [sent2features(s) for s in train_sents] y_train = [sent2labels(s) for s in train_sents] # Initialize and train the CRF model crf = sklearn_crfsuite.CRF( algorithm='lbfgs', c1=0.1, # L1 regularization c2=0.1, # L2 regularization max_iterations=100, all_possible_transitions=True ) crf.fit(X_train, y_train) # Make predictions on new data test_sents = [ [('A', 'DT'), ('fast', 'JJ'), ('red', 'JJ'), ('car', 'NN'), ('drives', 'VBZ'), ('by', 'IN')], ] X_test = [sent2features(s) for s in test_sents] y_pred = crf.predict(X_test) print("Predicted labels for test sentence:") for sent_idx, labels in enumerate(y_pred): print(f"Sentence {sent_idx+1}: {labels}") # Example of using metrics (requires scikit-learn) y_true = [sent2labels(s) for s in test_sents] # In a real scenario, this would be actual ground truth if y_true: print("\nClassification Report:") print(metrics.flat_classification_report(y_true, y_pred))