def _create_kernels_db(self, path: str, encoding: str = "default") -> None:
"""creates and caches kernels.db"""
log.debug("creating database")
# create a database and put it in the cache
tmppath = fs.path(self.contentcache.path, "kernels.db.tmp")
dbutil.create_db(tmppath)
self.contentcache["kernels.db"] = tmppath
# get a list of files in the corpus
filelist = [
f for f in fs.ls(path, abspaths=True, recursive=True)
if fs.isfile(f)
]
# import files into database
fetch.fetch_fs(self.contentcache["kernels.db"], filelist)
# preprocess files
preprocess.preprocess_db(self.contentcache["kernels.db"])
# encode kernel db
encode(self.contentcache["kernels.db"], encoding)
# print database stats
explore.explore(self.contentcache["kernels.db"])
def evaluate(model, sampler):
""" evaluate sampling efficiency """
print("starting sampling")
sampler.sample(model)
print("preprocessing sample")
sample_db = sampler.cache(model)["kernels.db"]
preprocess.preprocess_db(sample_db)
num_kernels = dbutil.num_rows_in(sample_db, "ContentFiles")
num_good_kernels = dbutil.num_good_kernels(sample_db)
num_ugly_kernels = dbutil.num_rows_in(sample_db, "PreprocessedFiles",
"WHERE status=2")
discard_rate = 1 - (num_good_kernels / num_kernels)
ugly_rate = 1 - (num_ugly_kernels / num_kernels)
total_charcount = dbutil.cc(sample_db, "ContentFiles")
good_charcount = dbutil.cc(sample_db,
"PreprocessedFiles",
condition="WHERE status=0")
return {
"argspec": sampler.kernel_opts["args"],
"host": system.HOSTNAME,
"date": time.nowstr(),
"num_kernels": num_kernels,
"num_good_kernels": num_good_kernels,
"discard_rate": discard_rate,
"ugly_rate": ugly_rate,
"total_charcount": total_charcount,
"good_charcount": good_charcount,
"corpus_dir": model.corpus.cache.path,
"model_dir": model.cache.path,
"sampler_dir": sampler.cache(model).path,
}
def evaluate(model, sampler):
""" evaluate sampling efficiency """
print("starting sampling")
sampler.sample(model)
print("preprocessing sample")
sample_db = sampler.cache(model)["kernels.db"]
preprocess.preprocess_db(sample_db)
num_kernels = dbutil.num_rows_in(sample_db, "ContentFiles")
num_good_kernels = dbutil.num_good_kernels(sample_db)
num_ugly_kernels = dbutil.num_rows_in(sample_db, "PreprocessedFiles",
"WHERE status=2")
discard_rate = 1 - (num_good_kernels / num_kernels)
ugly_rate = 1 - (num_ugly_kernels / num_kernels)
total_charcount = dbutil.cc(sample_db, "ContentFiles")
good_charcount = dbutil.cc(sample_db, "PreprocessedFiles",
condition="WHERE status=0")
return {
"argspec": sampler.kernel_opts["args"],
"host": system.HOSTNAME,
"date": time.nowstr(),
"num_kernels": num_kernels,
"num_good_kernels": num_good_kernels,
"discard_rate": discard_rate,
"ugly_rate": ugly_rate,
"total_charcount": total_charcount,
"good_charcount": good_charcount,
"corpus_dir": model.corpus.cache.path,
"model_dir": model.cache.path,
"sampler_dir": sampler.cache(model).path,
}
def evaluate(model, sampler):
""" evaluate sampling efficiency """
model.cache.empty() # clear checkpoint cache
print("starting training")
tstart = time() # start timer
model.train() # train model
training_time = time() - tstart
# clear the sample cache
sampler.cache(model).empty()
# sample kernels and time
print("starting sampling")
tstart = time()
sampler.sample(model)
tend = time()
elapsed = tend - tstart
# preprocess sample
sample_db = sampler.cache(model)["kernels.db"]
preprocess.preprocess_db(sample_db)
num_kernels = dbutil.num_rows_in(sample_db, "ContentFiles")
num_good_kernels = dbutil.num_good_kernels(sample_db)
num_ugly_kernels = dbutil.num_rows_in(sample_db, "PreprocessedFiles",
"WHERE status=2")
discard_rate = 1 - (num_good_kernels / num_kernels)
ugly_rate = 1 - (num_ugly_kernels / num_kernels)
total_charcount = dbutil.cc(sample_db, "ContentFiles")
good_charcount = dbutil.cc(sample_db,
"PreprocessedFiles",
condition="WHERE status=0")
efficiency = good_charcount / total_charcount
throughput = good_charcount / elapsed
return {
"training_time": training_time,
"sampling_time": elapsed,
"num_kernels": num_kernels,
"num_good_kernels": num_good_kernels,
"discard_rate": discard_rate,
"ugly_rate": ugly_rate,
"total_charcount": total_charcount,
"good_charcount": good_charcount,
"efficiency": efficiency, # good_chars / total_chars
"throughput": throughput, # good_chars / second
"corpus_dir": model.corpus.cache.path,
"model_dir": model.cache.path,
"sampler_dir": sampler.cache(model).path,
}
def evaluate(model, sampler):
""" evaluate sampling efficiency """
model.cache.empty() # clear checkpoint cache
print("starting training")
tstart = time() # start timer
model.train() # train model
training_time = time() - tstart
# clear the sample cache
sampler.cache(model).empty()
# sample kernels and time
print("starting sampling")
tstart = time()
sampler.sample(model)
tend = time()
elapsed = tend - tstart
# preprocess sample
sample_db = sampler.cache(model)["kernels.db"]
preprocess.preprocess_db(sample_db)
num_kernels = dbutil.num_rows_in(sample_db, "ContentFiles")
num_good_kernels = dbutil.num_good_kernels(sample_db)
num_ugly_kernels = dbutil.num_rows_in(sample_db, "PreprocessedFiles",
"WHERE status=2")
discard_rate = 1 - (num_good_kernels / num_kernels)
ugly_rate = 1 - (num_ugly_kernels / num_kernels)
total_charcount = dbutil.cc(sample_db, "ContentFiles")
good_charcount = dbutil.cc(sample_db, "PreprocessedFiles",
condition="WHERE status=0")
efficiency = good_charcount / total_charcount
throughput = good_charcount / elapsed
return {
"training_time": training_time,
"sampling_time": elapsed,
"num_kernels": num_kernels,
"num_good_kernels": num_good_kernels,
"discard_rate": discard_rate,
"ugly_rate": ugly_rate,
"total_charcount": total_charcount,
"good_charcount": good_charcount,
"efficiency": efficiency, # good_chars / total_chars
"throughput": throughput, # good_chars / second
"corpus_dir": model.corpus.cache.path,
"model_dir": model.cache.path,
"sampler_dir": sampler.cache(model).path,
}
def sample_iteration(self, model: Model, quiet: bool = False) -> None:
"""
Run one sample iteration.
Arguments:
model (Model): CLgen model.
"""
assert (isinstance(model, Model))
cache = self.cache(model)
if self.kernel_opts.get("args", None):
start_text = serialize_argspec(self.kernel_opts["args"])
else:
start_text = "__kernel void A("
tmppath = fs.path(cache.path,
"sampler-{pid}.tmp.cl".format(pid=system.PID))
with open(tmppath, "w") as outfile:
opts = {
"output": outfile,
"num_samples": self.batch_size,
"temperature": self.kernel_opts.get("temperature", 1),
"max_length": self.kernel_opts.get("max_length", 10000),
"seed_text": start_text,
"quiet": quiet
}
model.sample(**opts)
sys.stdout.flush()
sys.stderr.flush()
fetch.process_sample_file(cache["kernels.db"],
tmppath,
max_kernel_len=opts["max_length"],
quiet=True)
if self.static_checker:
# TODO: Parse dynamic checker requirement
preprocess.preprocess_db(cache["kernels.db"])
fs.rm(tmppath)
