def repos2coocc(args):
log = logging.getLogger("repos2coocc")
id_extractor = IdentifiersBagExtractor(docfreq_threshold=args.min_docfreq,
split_stem=args.split)
session_name = "repos2coocc-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
uast_extractor = start_point \
.link(UastRow2Document()) \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(Cacher.maybe(args.persist))
log.info("Extracting UASTs...")
ndocs = uast_extractor.link(Counter()).execute()
log.info("Number of documents: %d", ndocs)
uast_extractor = uast_extractor.link(UastDeserializer())
df_model = create_or_load_ordered_df(
args, ndocs, uast_extractor.link(Uast2BagFeatures(id_extractor)))
token2index = root.session.sparkContext.broadcast(df_model.order)
uast_extractor \
.link(CooccConstructor(token2index=token2index,
token_parser=id_extractor.id2bag.token_parser,
namespace=id_extractor.NAMESPACE)) \
.link(CooccModelSaver(args.output, df_model)) \
.execute()
pipeline_graph(args, log, root)
def repos2df(args):
log = logging.getLogger("repos2df")
extractors = create_extractors_from_args(args)
session_name = "repos2df-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
uast_extractor = start_point \
.link(UastRow2Document()) \
.link(Cacher.maybe(args.persist))
log.info("Extracting UASTs...")
ndocs = uast_extractor.link(Counter()).execute()
log.info("Number of documents: %d", ndocs)
uast_extractor = uast_extractor.link(UastDeserializer())
quant = Uast2Quant(extractors)
uast_extractor.link(quant).execute()
if quant.levels:
log.info("Writing quantization levels to %s", args.quant)
QuantizationLevels().construct(quant.levels).save(args.quant)
df = uast_extractor \
.link(Uast2BagFeatures(extractors)) \
.link(BagFeatures2DocFreq()) \
.execute()
log.info("Writing docfreq model to %s", args.docfreq_out)
OrderedDocumentFrequencies().construct(ndocs, df).save(args.docfreq_out)
pipeline_graph(args, log, root)
def source2bags(args):
log = logging.getLogger("bags")
if os.path.exists(args.batches):
log.critical("%s must not exist", args.batches)
return 1
if not args.config:
args.config = []
try:
cassandra_utils.configure(args)
engine = create_engine("source2bags-%s" % uuid4(), **args.__dict__)
extractors = [
__extractors__[s](args.min_docfreq,
**__extractors__[s].get_kwargs_fromcmdline(args))
for s in args.feature
]
pipeline = Engine(engine, explain=args.explain).link(
DzhigurdaFiles(args.dzhigurda))
uasts = pipeline.link(UastExtractor(languages=[args.language]))
if args.persist is not None:
uasts = uasts.link(Cacher(args.persist))
uasts.link(MetadataSaver(args.keyspace, args.tables["meta"]))
uasts = uasts.link(UastDeserializer())
uasts.link(Repo2Quant(extractors, args.nb_partitions))
uasts.link(Repo2DocFreq(extractors))
pipeline.explode()
bags = uasts.link(Repo2WeightedSet(extractors))
if args.persist is not None:
bags = bags.link(Cacher(args.persist))
batcher = bags.link(BagsBatcher(extractors))
batcher.link(BagsBatchSaver(args.batches, batcher))
bags.link(BagsSaver(args.keyspace, args.tables["bags"]))
bags.explode()
log.info("Writing %s", args.docfreq)
batcher.model.save(args.docfreq)
if args.graph:
log.info("Dumping the graph to %s", args.graph)
with open(args.graph, "w") as f:
pipeline.graph(stream=f)
finally:
if args.pause:
input("Press Enter to exit...")
def repos2bow_entry_template(args,
select=HeadFiles,
cache_hook=None,
save_hook=None):
log = logging.getLogger("repos2bow")
extractors = create_extractors_from_args(args)
session_name = "repos2bow-%s" % uuid4()
root, start_point = create_uast_source(args, session_name, select=select)
uast_extractor = start_point.link(Moder(args.mode)) \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(Cacher.maybe(args.persist))
if cache_hook is not None:
uast_extractor.link(cache_hook()).execute()
# We link UastRow2Document after Cacher here because cache_hook() may want to have all possible
# Row items.
uast_extractor = uast_extractor.link(UastRow2Document())
log.info("Extracting UASTs and indexing documents...")
document_indexer = Indexer(Uast2BagFeatures.Columns.document)
uast_extractor.link(document_indexer).execute()
ndocs = len(document_indexer)
log.info("Number of documents: %d", ndocs)
uast_extractor = uast_extractor.link(UastDeserializer())
quant = Uast2Quant(extractors)
uast_extractor.link(quant).execute()
if quant.levels:
log.info("Writing quantization levels to %s", args.quant)
QuantizationLevels().construct(quant.levels).save(args.quant)
uast_extractor = uast_extractor \
.link(Uast2BagFeatures(extractors))
log.info("Calculating the document frequencies...")
df = uast_extractor.link(BagFeatures2DocFreq()).execute()
log.info("Writing docfreq to %s", args.docfreq)
df_model = OrderedDocumentFrequencies() \
.construct(ndocs, df) \
.prune(args.min_docfreq) \
.greatest(args.vocabulary_size) \
.save(args.docfreq)
bags_writer = uast_extractor \
.link(BagFeatures2TermFreq()) \
.link(TFIDF(df_model)) \
.link(document_indexer) \
.link(Indexer(Uast2BagFeatures.Columns.token, df_model.order))
if save_hook is not None:
bags_writer = bags_writer \
.link(Repartitioner.maybe(args.partitions * 10, args.shuffle)) \
.link(save_hook())
bags_writer.link(BOWWriter(document_indexer, df_model, args.bow, args.batch)) \
.execute()
pipeline_graph(args, log, root)
def repos2bow_index_template(args):
log = logging.getLogger("repos2bow_index")
extractors = create_extractors_from_args(args)
session_name = "repos2bow_index_features-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
uast_extractor = start_point.link(Moder(args.mode)) \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(UastRow2Document()) \
.link(Cacher.maybe(args.persist))
log.info("Extracting UASTs and indexing documents ...")
document_indexer = Indexer(Uast2BagFeatures.Columns.document)
uast_extractor.link(document_indexer).execute()
document_indexer.save_index(args.cached_index_path)
ndocs = len(document_indexer)
log.info("Number of documents: %d", ndocs)
uast_extractor = uast_extractor.link(UastDeserializer())
if args.quant:
create_or_apply_quant(args.quant, extractors, uast_extractor)
if args.docfreq_out:
create_or_load_ordered_df(args, ndocs, uast_extractor.link(Uast2BagFeatures(*extractors)))
pipeline_graph(args, log, root)
def test_cacher(self):
persistence = SparkDefault.STORAGE_LEVEL
cacher = Cacher(persistence)
cached_data = cacher(self.data)
self.assertTrue(cached_data.is_cached)
self.assertEqual(cacher.persistence, getattr(StorageLevel, persistence))
self.assertIn("head", cacher.__getstate__())
cacher = Cacher.maybe(persistence=None)
uncached_data = cacher(self.data)
self.assertEqual(uncached_data, self.data)
cacher = Cacher.maybe(persistence)
cached_data = cacher(self.data)
self.assertTrue(cached_data.is_cached)
cached_data = Cacher.maybe(persistence)(self.data)
self.assertFalse(cached_data.unpersist().is_cached)
def repos2coocc_entry(args):
log = logging.getLogger("repos2coocc")
id_extractor = IdentifiersBagExtractor(docfreq_threshold=args.min_docfreq,
split_stem=args.split)
session_name = "repos2coocc-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
uast_extractor = start_point \
.link(UastRow2Document()) \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(Cacher.maybe(args.persist))
log.info("Extracting UASTs...")
ndocs = uast_extractor.link(Counter()).execute()
log.info("Number of documents: %d", ndocs)
uast_extractor = uast_extractor.link(UastDeserializer())
df = uast_extractor \
.link(Uast2BagFeatures([id_extractor])) \
.link(BagFeatures2DocFreq()) \
.execute()
log.info("Writing document frequency model to %s...", args.docfreq)
df_model = OrderedDocumentFrequencies() \
.construct(ndocs, df) \
.prune(args.min_docfreq) \
.greatest(args.vocabulary_size) \
.save(args.docfreq)
token2index = root.session.sparkContext.broadcast(df_model.order)
uast_extractor \
.link(CooccConstructor(token2index=token2index,
token_parser=id_extractor.id2bag.token_parser,
namespace=id_extractor.NAMESPACE)) \
.link(CooccModelSaver(args.output, df_model)) \
.execute()
pipeline_graph(args, log, root)
def repos2bow_template(args, cache_hook: Transformer = None,
save_hook: Transformer = None):
log = logging.getLogger("repos2bow")
extractors = create_extractors_from_args(args)
session_name = "repos2bow-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
log.info("Loading the document index from %s ...", args.cached_index_path)
docfreq = DocumentFrequencies().load(source=args.cached_index_path)
document_index = {key: int(val) for (key, val) in docfreq}
try:
if args.quant is not None:
create_or_apply_quant(args.quant, extractors, None)
df_model = create_or_load_ordered_df(args, None, None)
except ValueError:
return 1
ec = EngineConstants.Columns
if args.mode == Moder.Options.repo:
def keymap(r):
return r[ec.RepositoryId]
else:
def keymap(r):
return r[ec.RepositoryId] + UastRow2Document.REPO_PATH_SEP + \
r[ec.Path] + UastRow2Document.PATH_BLOB_SEP + r[ec.BlobId]
log.info("Caching UASTs to disk after partitioning by document ...")
start_point = start_point.link(Moder(args.mode)) \
.link(Repartitioner.maybe(args.num_iterations, keymap=keymap)) \
.link(Cacher.maybe("DISK_ONLY"))
for num_part in range(args.num_iterations):
log.info("Running job %s of %s", num_part + 1, args.num_iterations)
selected_part = start_point \
.link(PartitionSelector(num_part)) \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(Cacher.maybe(args.persist))
if cache_hook is not None:
selected_part.link(cache_hook()).execute()
uast_extractor = selected_part \
.link(UastRow2Document()) \
.link(Cacher.maybe(args.persist))
log.info("Collecting distinct documents ...")
documents = uast_extractor \
.link(FieldsSelector([Uast2BagFeatures.Columns.document])) \
.link(Distinct()) \
.link(Collector()) \
.execute()
selected_part.unpersist()
documents = {row.document for row in documents}
reduced_doc_index = {
key: document_index[key] for key in document_index if key in documents}
document_indexer = Indexer(Uast2BagFeatures.Columns.document, reduced_doc_index)
log.info("Processing %s distinct documents", len(documents))
bags = uast_extractor \
.link(UastDeserializer()) \
.link(Uast2BagFeatures(*extractors)) \
.link(BagFeatures2TermFreq()) \
.link(Cacher.maybe(args.persist))
log.info("Extracting UASTs and collecting distinct tokens ...")
tokens = bags \
.link(FieldsSelector([Uast2BagFeatures.Columns.token])) \
.link(Distinct()) \
.link(Collector()) \
.execute()
uast_extractor.unpersist()
tokens = {row.token for row in tokens}
reduced_token_freq = {key: df_model[key] for key in df_model.df if key in tokens}
reduced_token_index = {key: df_model.order[key] for key in df_model.df if key in tokens}
log.info("Processing %s distinct tokens", len(reduced_token_freq))
log.info("Indexing by document and token ...")
bags_writer = bags \
.link(TFIDF(reduced_token_freq, df_model.docs, root.session.sparkContext)) \
.link(document_indexer) \
.link(Indexer(Uast2BagFeatures.Columns.token, reduced_token_index))
if save_hook is not None:
bags_writer = bags_writer \
.link(Repartitioner.maybe(args.partitions, args.shuffle)) \
.link(save_hook())
bow = args.bow.split(".asdf")[0] + "_" + str(num_part + 1) + ".asdf"
bags_writer \
.link(Repartitioner.maybe(
args.partitions, keymap=lambda x: x[Uast2BagFeatures.Columns.document])) \
.link(BOWWriter(document_indexer, df_model, bow, args.batch)) \
.execute()
bags.unpersist()
pipeline_graph(args, log, root)