Filter-Bubble /
e2e-Dutch
| Conditions | 14 |
| Total Lines | 86 |
| Code Lines | 71 |
| Lines | 0 |
| Ratio | 0 % |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like e2edutch.predict.main() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
| 1 | import sys |
||
| 42 | def main(args=None): |
||
| 43 | parser = get_parser() |
||
| 44 | args = parser.parse_args() |
||
| 45 | if args.verbose: |
||
| 46 | logging.basicConfig(level=logging.DEBUG) |
||
| 47 | config = util.initialize_from_env(args.config, args.cfg_file) |
||
| 48 | |||
| 49 | # Input file in .jsonlines format or .conll. |
||
| 50 | input_filename = args.input_filename |
||
| 51 | |||
| 52 | ext_input = os.path.splitext(input_filename)[-1] |
||
| 53 | if ext_input not in ['.conll', '.jsonlines', '.txt', '.naf']: |
||
| 54 | raise Exception( |
||
| 55 | 'Input file should be .naf, .conll, .txt or .jsonlines, but is {}.' |
||
| 56 | .format(ext_input)) |
||
| 57 | |||
| 58 | if ext_input == '.conll': |
||
| 59 | labels = collections.defaultdict(set) |
||
| 60 | stats = collections.defaultdict(int) |
||
| 61 | docs = minimize.minimize_partition( |
||
| 62 | input_filename, labels, stats, args.word_col) |
||
| 63 | elif ext_input == '.jsonlines': |
||
| 64 | docs = read_jsonlines(input_filename) |
||
| 65 | elif ext_input == '.naf': |
||
| 66 | naf_obj = naf.get_naf(input_filename) |
||
| 67 | jsonlines_obj, term_ids, tok_ids = naf.get_jsonlines(naf_obj) |
||
| 68 | docs = [jsonlines_obj] |
||
| 69 | else: |
||
| 70 | text = open(input_filename).read() |
||
| 71 | docs = [util.create_example(text)] |
||
| 72 | |||
| 73 | output_file = args.output_file |
||
| 74 | model = cm.CorefModel(config) |
||
| 75 | sentences = {} |
||
| 76 | predictions = {} |
||
| 77 | with tf.Session() as session: |
||
| 78 | model.restore(session) |
||
| 79 | for example_num, example in enumerate(docs): |
||
| 80 | # logging.info(example['doc_key']) |
||
| 81 | tensorized_example = model.tensorize_example( |
||
| 82 | example, is_training=False) |
||
| 83 | feed_dict = {i: t for i, t in zip( |
||
| 84 | model.input_tensors, tensorized_example)} |
||
| 85 | _, _, _, top_span_starts, top_span_ends, top_antecedents, top_antecedent_scores = session.run( |
||
| 86 | model.predictions, feed_dict=feed_dict) |
||
| 87 | predicted_antecedents = model.get_predicted_antecedents( |
||
| 88 | top_antecedents, top_antecedent_scores) |
||
| 89 | example["predicted_clusters"], _ = model.get_predicted_clusters( |
||
| 90 | top_span_starts, top_span_ends, predicted_antecedents) |
||
| 91 | if args.format_out == 'jsonlines': |
||
| 92 | output_file.write(json.dumps(example)) |
||
| 93 | output_file.write("\n") |
||
| 94 | else: |
||
| 95 | predictions[example['doc_key']] = example["predicted_clusters"] |
||
| 96 | sentences[example['doc_key']] = example["sentences"] |
||
| 97 | if example_num % 100 == 0: |
||
| 98 | logging.info("Decoded {} examples.".format(example_num + 1)) |
||
| 99 | if args.format_out == 'conll': |
||
| 100 | conll.output_conll(output_file, sentences, predictions) |
||
| 101 | elif args.format_out == 'naf': |
||
| 102 | # Check number of docs - what to do if multiple? |
||
| 103 | # Create naf obj if input format was not naf |
||
| 104 | if ext_input != '.naf': |
||
| 105 | # To do: add linguistic processing layers for terms and tokens |
||
| 106 | logging.warn( |
||
| 107 | 'Outputting NAF when input was not naf,' |
||
| 108 | + 'no dependency information available') |
||
| 109 | for doc_key in sentences: |
||
| 110 | naf_obj, term_ids = naf.get_naf_from_sentences( |
||
| 111 | sentences[doc_key]) |
||
| 112 | naf_obj = naf.create_coref_layer( |
||
| 113 | naf_obj, predictions[doc_key], term_ids) |
||
| 114 | naf_obj = naf.add_linguistic_processors(naf_obj) |
||
| 115 | buffer = io.BytesIO() |
||
| 116 | naf_obj.dump(buffer) |
||
| 117 | output_file.write(buffer.getvalue().decode('utf-8')) |
||
| 118 | # To do, make sepearate outputs? |
||
| 119 | # TO do, use dependency information from conll? |
||
| 120 | else: |
||
| 121 | # We only have one input doc |
||
| 122 | naf_obj = naf.create_coref_layer( |
||
| 123 | naf_obj, example["predicted_clusters"], term_ids) |
||
| 124 | naf_obj = naf.add_linguistic_processors(naf_obj) |
||
| 125 | buffer = io.BytesIO() |
||
| 126 | naf_obj.dump(buffer) |
||
| 127 | output_file.write(buffer.getvalue().decode('utf-8')) |
||
| 128 | |||
| 132 |
Loading history...