def transform_rows(schema_in, transforms_in, rows_in, rows_out, id_field=None):
transforms = pickle_load(transforms_in)
if not transforms:
cp_ns(rows_in, rows_out)
else:
transform = TransformSequence(transforms)
transformed_header = sorted(json_load(schema_in).iterkeys())
if id_field is not None:
assert id_field not in transformed_header
transformed_header = [id_field] + transformed_header
tasks = []
if os.path.isdir(rows_in):
loom.util.mkdir_p(rows_out)
for f in os.listdir(rows_in):
tasks.append((
transform,
transformed_header,
os.path.join(rows_in, f),
os.path.join(rows_out, f),
))
else:
tasks.append((transform, transformed_header, rows_in, rows_out))
parallel_map(_transform_rows, tasks)
def transform_rows(schema_in, transforms_in, rows_in, rows_out, id_field=None):
transforms = pickle_load(transforms_in)
if not transforms:
cp_ns(rows_in, rows_out)
else:
transform = TransformSequence(transforms)
transformed_header = sorted(json_load(schema_in).iterkeys())
if id_field is not None:
assert id_field not in transformed_header
transformed_header = [id_field] + transformed_header
tasks = []
if os.path.isdir(rows_in):
loom.util.mkdir_p(rows_out)
for f in os.listdir(rows_in):
tasks.append((
transform,
transformed_header,
os.path.join(rows_in, f),
os.path.join(rows_out, f),
))
else:
tasks.append((transform, transformed_header, rows_in, rows_out))
parallel_map(_transform_rows, tasks)
def make_fake_consensus(paths, debug=False):
for key, destin in loom.store.iter_paths("samples.0", paths["consensus"]):
source = loom.store.get_path(paths, key)
cp_ns(source, destin)
def make_fake_consensus(paths, debug=False):
for key, destin in loom.store.iter_paths('samples.0', paths['consensus']):
source = loom.store.get_path(paths, key)
cp_ns(source, destin)
def generate_one((name, sample_count, force, debug)):
paths = loom.store.get_paths(name, sample_count=sample_count)
if not force and all(os.path.exists(f) for f in paths.itervalues()):
with open_compressed(paths['ingest']['version']) as f:
version = f.read().strip()
if version == loom.__version__:
return
print 'generating', name
mkdir_p(paths['root'])
with open_compressed(paths['ingest']['version'], 'w') as f:
f.write(loom.__version__)
config = CONFIGS[name]
chunk_size = max(10, (config['row_count'] + 7) / 8)
loom.transforms.make_fake_transforms(
transforms_out=paths['ingest']['transforms'])
loom.generate.generate(
init_out=paths['samples'][0]['init'],
rows_out=paths['ingest']['rows'],
model_out=paths['samples'][0]['model'],
groups_out=paths['samples'][0]['groups'],
assign_out=paths['samples'][0]['assign'],
**config)
loom.format.make_schema(
model_in=paths['samples'][0]['model'],
schema_out=paths['ingest']['schema'])
loom.format.make_fake_encoding(
schema_in=paths['ingest']['schema'],
model_in=paths['samples'][0]['model'],
encoding_out=paths['ingest']['encoding'])
loom.format.make_schema_row(
schema_in=paths['ingest']['schema'],
schema_row_out=paths['ingest']['schema_row'])
loom.runner.tare(
schema_row_in=paths['ingest']['schema_row'],
rows_in=paths['ingest']['rows'],
tares_out=paths['ingest']['tares'],
debug=debug)
loom.runner.sparsify(
schema_row_in=paths['ingest']['schema_row'],
tares_in=paths['ingest']['tares'],
rows_in=paths['ingest']['rows'],
rows_out=paths['ingest']['diffs'],
debug=debug)
loom.format.export_rows(
encoding_in=paths['ingest']['encoding'],
rows_in=paths['ingest']['rows'],
rows_csv_out=paths['ingest']['rows_csv'],
chunk_size=chunk_size)
loom.format.import_rowids(
rows_csv_in=paths['ingest']['rows_csv'],
rowids_out=paths['ingest']['rowids'],
id_field='_id')
protobuf_stream_dump([], paths['query']['query_log'])
loom.config.config_dump({}, paths['query']['config'])
for seed, sample in enumerate(paths['samples']):
loom.config.config_dump({'seed': seed}, sample['config'])
loom.generate.generate_init(
encoding_in=paths['ingest']['encoding'],
model_out=sample['init'],
seed=seed)
loom.runner.shuffle(
rows_in=paths['ingest']['diffs'],
rows_out=sample['shuffled'],
seed=seed,
debug=debug)
protobuf_stream_dump([], sample['infer_log'])
sample0 = paths['samples'][0]
for seed, sample in enumerate(paths['samples'][1:]):
if LOOM_DEBUG_MIX:
cp_ns(sample0['model'], sample['model'])
cp_ns(sample0['groups'], sample['groups'])
cp_ns(sample0['assign'], sample['assign'])
else:
loom.runner.mix(
config_in=sample['config'],
rows_in=paths['ingest']['rows'],
model_in=sample0['model'],
groups_in=sample0['groups'],
assign_in=sample0['assign'],
model_out=sample['model'],
groups_out=sample['groups'],
assign_out=sample['assign'],
debug=debug)
loom.consensus.make_fake_consensus(
paths=paths,
debug=debug)
def generate_one((name, sample_count, force, debug)):
paths = loom.store.get_paths(name, sample_count=sample_count)
if not force and all(os.path.exists(f) for f in paths.itervalues()):
with open_compressed(paths['ingest']['version']) as f:
version = f.read().strip()
if version == loom.__version__:
return
print 'generating', name
mkdir_p(paths['root'])
with open_compressed(paths['ingest']['version'], 'w') as f:
f.write(loom.__version__)
config = CONFIGS[name]
chunk_size = max(10, (config['row_count'] + 7) / 8)
loom.transforms.make_fake_transforms(
transforms_out=paths['ingest']['transforms'])
loom.generate.generate(
init_out=paths['samples'][0]['init'],
rows_out=paths['ingest']['rows'],
model_out=paths['samples'][0]['model'],
groups_out=paths['samples'][0]['groups'],
assign_out=paths['samples'][0]['assign'],
**config)
loom.format.make_schema(
model_in=paths['samples'][0]['model'],
schema_out=paths['ingest']['schema'])
loom.format.make_fake_encoding(
schema_in=paths['ingest']['schema'],
model_in=paths['samples'][0]['model'],
encoding_out=paths['ingest']['encoding'])
loom.format.make_schema_row(
schema_in=paths['ingest']['schema'],
schema_row_out=paths['ingest']['schema_row'])
loom.runner.tare(
schema_row_in=paths['ingest']['schema_row'],
rows_in=paths['ingest']['rows'],
tares_out=paths['ingest']['tares'],
debug=debug)
loom.runner.sparsify(
schema_row_in=paths['ingest']['schema_row'],
tares_in=paths['ingest']['tares'],
rows_in=paths['ingest']['rows'],
rows_out=paths['ingest']['diffs'],
debug=debug)
loom.format.export_rows(
encoding_in=paths['ingest']['encoding'],
rows_in=paths['ingest']['rows'],
rows_csv_out=paths['ingest']['rows_csv'],
chunk_size=chunk_size)
loom.format.import_rowids(
rows_csv_in=paths['ingest']['rows_csv'],
rowids_out=paths['ingest']['rowids'],
id_field='_id')
protobuf_stream_dump([], paths['query']['query_log'])
loom.config.config_dump({}, paths['query']['config'])
for seed, sample in enumerate(paths['samples']):
loom.config.config_dump({'seed': seed}, sample['config'])
loom.generate.generate_init(
encoding_in=paths['ingest']['encoding'],
model_out=sample['init'],
seed=seed)
loom.runner.shuffle(
rows_in=paths['ingest']['diffs'],
rows_out=sample['shuffled'],
seed=seed,
debug=debug)
protobuf_stream_dump([], sample['infer_log'])
sample0 = paths['samples'][0]
for seed, sample in enumerate(paths['samples'][1:]):
if LOOM_DEBUG_MIX:
cp_ns(sample0['model'], sample['model'])
cp_ns(sample0['groups'], sample['groups'])
cp_ns(sample0['assign'], sample['assign'])
else:
loom.runner.mix(
config_in=sample['config'],
rows_in=paths['ingest']['rows'],
model_in=sample0['model'],
groups_in=sample0['groups'],
assign_in=sample0['assign'],
model_out=sample['model'],
groups_out=sample['groups'],
assign_out=sample['assign'],
debug=debug)
loom.consensus.make_fake_consensus(
paths=paths,
debug=debug)
