# Ideally the process would be lossless, giving a SMATCH score of 1.0
if __name__ == '__main__':
setup_logging(logfname='logs/serial_deserial.log', level=WARN)
corpus_dir = 'amrlib/data/LDC2020T02'
in_fn = 'test.txt'
out_dir = 'amrlib/data/test_parse_t5'
ref_out_fn = in_fn + '.roundtrip_ref'
gen_out_fn = in_fn + '.roundtrip_gen'
# Make the out directory
os.makedirs(out_dir, exist_ok=True)
# Load the reference graphs
fname = os.path.join(corpus_dir, in_fn)
print('Loading', fname)
ref_amr_entries = load_amr_entries(fname)
ref_in_graphs = [get_graph_only(e) for e in ref_amr_entries]
print('Loaded %d reference graphs' % len(ref_in_graphs))
# Simulate the generated graphs by running the original references throught the serializer
print('Reloading and serializing', fname)
gen_in_graphs = load_and_serialize(fname)
gen_in_graphs = gen_in_graphs['serials']
clip_index_set = set() # empty - just so code below is a copy of post-process for generation
# process the generated graphs through penman
gen_out_graphs = []
bad_graphs = set()
for i, graph in enumerate(gen_in_graphs):
# skip anything on the clips
if i in clip_index_set:
#!/usr/bin/python3
import setup_run_dir # this import tricks script to run from 2 levels up
from amrlib.graph_processing.amr_plot import AMRPlot
from amrlib.graph_processing.amr_loading import load_amr_entries
if __name__ == '__main__':
input_file = 'amrlib/data/LDC2020T02/test.txt'
snum = 4 # id numbers start at 1 so they are 1 more than snum
# Load the file
entries = load_amr_entries(input_file)
print('Found %d entries' % len(entries))
print()
# Parse AMR
entry = entries[snum]
plot = AMRPlot()
plot.build_from_graph(entry, debug=False)
plot.view()
logger = logging.getLogger(__name__)
# Run the aligner on the LDC files with existing alignments for comparison
# The ISI hand alignments are for LDC2014T12 (AMR1) the test-concensus.txt and dev-concensus.txt files
if __name__ == '__main__':
setup_logging(level=WARN, logfname='logs/rbw_aligner.log')
silence_penman()
in_fname = 'amrlib/data/amr_annotation_1.0/data/split/test/amr-release-1.0-test-consensus.txt'
out_fname = 'amrlib/data/alignments/test-aligned.txt'
# in_fname = 'amrlib/data/amr_annotation_1.0/data/split/dev/amr-release-1.0-dev-consensus.txt'
# out_fname = 'amrlib/data/alignments/dev-aligned.txt'
# Load and convert to a penman graph
print('Loading', in_fname)
entries = load_amr_entries(in_fname)
print('Loaded %d entries' % len(entries))
# Convert to penman and add lemmas
print('Annotating')
load_spacy(
) # do this in the main process to prevent doing it multiple times
graphs = []
annotate = partial(add_lemmas, snt_key='snt',
verify_tok_key=None) # no existing tok key
with Pool() as pool:
for graph in pool.imap(annotate, entries):
if graph is not None:
graphs.append(graph)
print('%d graphs left with the same tokenization length' % len(graphs))
# (num_beams=16, batch_size=4) run-time = 29min
batch_size = 4
num_beams = 16
use_tense = True
rm_clips = True
# Create the filenames based on above parameters
extension = '.tagged' if use_tense else '.nowiki'
extension += '.clipped' if rm_clips else '.noclip'
extension += '.beam' + str(num_beams)
gen_fn = 'test.txt.generated' + extension
ref_fn = 'test.txt.ref_sents' + extension
fpath = os.path.join(corpus_dir, test_fn)
print('Loading test data from', fpath)
graphs = load_amr_entries(fpath)
sents = [get_sentence(g) for g in graphs]
print('Loading model, tokenizer and data')
inference = Inference(model_dir,
batch_size=batch_size,
num_beams=num_beams,
device=device)
print('Generating')
answers, clips = inference.generate(graphs,
disable_progress=False,
use_tense=use_tense)
# Filter out any clipped graphs as invalid tests
# This will raise the BLEU score
# xx.nowiki # standard AMR
# xx.nowiki.tagged # pos tags added
# xx.nowiki.tdata # the above 2 combined
# Take graphs that are annotated (tokens, pos, ...) and align them then tag the graphs.
# Save files with the tagged and untagged data together in a single training file
if __name__ == '__main__':
setup_logging(level=WARN, logfname='logs/create_td_gen_t5wtense.log')
silence_penman()
data_dir = 'amrlib/data/tdata_generate_t5wtense'
base_fns = ('dev.txt', 'test.txt', 'train.txt')
# Loop through the files
for base_fn in base_fns:
infn = os.path.join(data_dir, base_fn + '.features.nowiki')
print('Loading and processing', infn)
entries = load_amr_entries(infn)
tagged_entries = []
for entry in tqdm(entries, ncols=100):
tagged_entry = ModelInputHelper(entry).get_tagged_with_meta()
tagged_entries.append(tagged_entry)
# Save tagged data only to a new file
# outfn = infn + '.tagged'
# print('Saving to', outfn)
# with open(outfn, 'w') as f:
# for entry in tagged_entries:
# f.write(entry + '\n\n')
# Save the tagged and untagged entries into a single file, shuffled together
all_entries = entries + tagged_entries
shuffle(all_entries)
outfn = infn + '.tdata'
print('Saving to', outfn)
