# TODO: support corpora with alternatives to tagged_sents that work just as well if args.metrics and not hasattr(corpus, 'tagged_sents'): raise ValueError('%s does not support metrics' % args.corpus) ############ ## tagger ## ############ if args.trace: print 'loading tagger %s' % args.tagger if args.tagger == 'pattern': tagger = taggers.PatternTagger() else: tagger = load_model(args.tagger) ####################### ## coverage analysis ## ####################### if args.trace: print 'analyzing tag coverage of %s with %s\n' % (args.corpus, tagger.__class__.__name__) tags_found = FreqDist() unknown_words = set() if args.metrics: tags_actual = FreqDist() tag_refs = [] tag_test = []
# TODO: support corpora with alternatives to tagged_sents that work just as well if args.metrics and not hasattr(corpus, 'tagged_sents'): raise ValueError('%s does not support metrics' % args.corpus) ############ ## tagger ## ############ if args.trace: print('loading tagger %s' % args.tagger) if args.tagger == 'pattern': tagger = taggers.PatternTagger() else: tagger = load_model(args.tagger) ####################### ## coverage analysis ## ####################### if args.trace: print('analyzing tag coverage of %s with %s\n' % (args.corpus, tagger.__class__.__name__)) tags_found = collections.defaultdict(int) unknown_words = set() if args.metrics: tags_actual = collections.defaultdict(int) tag_refs = []
corpus = load_corpus_reader(args.corpus, reader=args.reader, fileids=args.fileids) if args.score and not hasattr(corpus, 'chunked_sents'): raise ValueError('%s does not support scoring' % args.corpus) ############ ## tagger ## ############ if args.trace: print 'loading tagger %s' % args.tagger if args.tagger == 'pattern': tagger = taggers.PatternTagger() else: tagger = load_model(args.tagger) if args.trace: print 'loading chunker %s' % args.chunker if args.chunker == 'pattern': chunker = chunkers.PatternChunker() else: chunker = load_model(args.chunker) ####################### ## coverage analysis ## ####################### if args.score: if args.trace:
fileids=args.fileids) if args.score and not hasattr(corpus, 'chunked_sents'): raise ValueError('%s does not support scoring' % args.corpus) ############ ## tagger ## ############ if args.trace: print 'loading tagger %s' % args.tagger if args.tagger == 'pattern': tagger = taggers.PatternTagger() else: tagger = load_model(args.tagger) if args.trace: print 'loading chunker %s' % args.chunker if args.chunker == 'pattern': chunker = chunkers.PatternChunker() else: chunker = load_model(args.chunker) ####################### ## coverage analysis ## ####################### if args.score: if args.trace: