evaluate_crf.py

# Evaluation of trained model
# Start remove 'O' labels
labels = list(crf.classes_)
labels.remove('O')
print("trained labels :",labels)

# start prediction and calculate f-score
y_pred = crf.predict(X_test)
print (metrics.flat_f1_score(y_test, y_pred,
                      average='weighted', labels=labels,zero_division=True))

# Inspect evaluation per class
# group B and I results
sorted_labels = sorted(
    labels,
    key=lambda name: (name[1:], name[0])
)