crf_sample.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#===============================================================================
#
# Copyright (c) 2017 <> All Rights Reserved
#
#
# File: /Users/hain/ai/book-of-qna-code/ch2/crf/crf_sample.py
# Author: Hai Liang Wang
# Date: 2018-06-15:12:31:38
# Borrow from 
# https://github.com/TeamHG-Memex/sklearn-crfsuite/blob/master/docs/CoNLL2002.ipynb
#
#===============================================================================

"""
   
"""
from __future__ import print_function
from __future__ import division

__copyright__ = "Copyright (c) 2017 . All Rights Reserved"
__author__    = "Hai Liang Wang"
__date__      = "2018-06-15:12:31:38"


import os
import sys
curdir = os.path.dirname(os.path.abspath(__file__))
sys.path.append(curdir)

if sys.version_info[0] < 3:
    sys.setdefaultencoding("utf-8")
    reload(sys)
    # raise "Must be using Python 3"
else:
    unicode = str


from itertools import chain

import nltk
import sklearn
import scipy.stats
from sklearn.metrics import make_scorer
from sklearn.grid_search import RandomizedSearchCV

import sklearn_crfsuite
from sklearn_crfsuite import scorers
from sklearn_crfsuite import metrics

train_sents = list(nltk.corpus.conll2002.iob_sents('esp.train'))
test_sents = list(nltk.corpus.conll2002.iob_sents('esp.testb'))

def word2features(sent, i):
    word = sent[i][0]
    postag = sent[i][1]
    
    features = {
        'bias': 1.0,
        'word.lower()': word.lower(),
        'word[-3:]': word[-3:],
        'word[-2:]': word[-2:],
        '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.update({
            '-1:word.lower()': word1.lower(),
            '-1:word.istitle()': word1.istitle(),
            '-1:word.isupper()': word1.isupper(),
            '-1:postag': postag1,
            '-1:postag[:2]': postag1[:2],
        })
    else:
        features['BOS'] = True
        
    if i < len(sent)-1:
        word1 = sent[i+1][0]
        postag1 = sent[i+1][1]
        features.update({
            '+1:word.lower()': word1.lower(),
            '+1:word.istitle()': word1.istitle(),
            '+1:word.isupper()': word1.isupper(),
            '+1:postag': postag1,
            '+1:postag[:2]': postag1[:2],
        })
    else:
        features['EOS'] = True
                
    return features


def sent2features(sent):
    return [word2features(sent, i) for i in range(len(sent))]

def sent2labels(sent):
    return [label for token, postag, label in sent]

def sent2tokens(sent):
    return [token for token, postag, label in sent]

X_train = [sent2features(s) for s in train_sents]
y_train = [sent2labels(s) for s in train_sents]

X_test = [sent2features(s) for s in test_sents]
y_test = [sent2labels(s) for s in test_sents]

crf = sklearn_crfsuite.CRF(
    algorithm='lbfgs', 
    c1=0.1, 
    c2=0.1, 
    max_iterations=100, 
    all_possible_transitions=True
)
crf.fit(X_train, y_train)

labels = list(crf.classes_)
labels.remove('O')

y_pred = crf.predict(X_test)
metrics.flat_f1_score(y_test, y_pred, 
                      average='weighted', labels=labels)

# group B and I results
sorted_labels = sorted(
    labels, 
    key=lambda name: (name[1:], name[0])
)
print(metrics.flat_classification_report(
    y_test, y_pred, labels=sorted_labels, digits=3
))

# define fixed parameters and parameters to search
crf = sklearn_crfsuite.CRF(
    algorithm='lbfgs', 
    max_iterations=100, 
    all_possible_transitions=True
)
params_space = {
    'c1': scipy.stats.expon(scale=0.5),
    'c2': scipy.stats.expon(scale=0.05),
}

# use the same metric for evaluation
f1_scorer = make_scorer(metrics.flat_f1_score, 
                        average='weighted', labels=labels)

# search
rs = RandomizedSearchCV(crf, params_space, 
                        cv=3, 
                        verbose=1, 
                        n_jobs=-1, 
                        n_iter=50, 
                        scoring=f1_scorer)
rs.fit(X_train, y_train)

# crf = rs.best_estimator_
print('best params:', rs.best_params_)
print('best CV score:', rs.best_score_)
print('model size: {:0.2f}M'.format(rs.best_estimator_.size_ / 1000000))

crf = rs.best_estimator_
y_pred = crf.predict(X_test)
print(metrics.flat_classification_report(
    y_test, y_pred, labels=sorted_labels, digits=3
))

from collections import Counter

def print_transitions(trans_features):
    for (label_from, label_to), weight in trans_features:
        print("%-6s -> %-7s %0.6f" % (label_from, label_to, weight))

print("Top likely transitions:")
print_transitions(Counter(crf.transition_features_).most_common(20))

print("\nTop unlikely transitions:")
print_transitions(Counter(crf.transition_features_).most_common()[-20:])

def print_state_features(state_features):
    for (attr, label), weight in state_features:
        print("%0.6f %-8s %s" % (weight, label, attr))    

print("Top positive:")
print_state_features(Counter(crf.state_features_).most_common(30))

print("\nTop negative:")
print_state_features(Counter(crf.state_features_).most_common()[-30:])