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 main(model,
sampler,
print_file_list=False,
print_corpus_dir=False,
print_model_dir=False,
print_sampler_dir=False) -> None:
"""
Main entry point for clgen.
Arguments:
model (str): Path to model.
sample (str): Path to sampler.
print_corpus_dir (bool, optional): If True, print cache path and exit.
print_model_dir (bool, optional): If True, print cache path and exit.
print_sampler_dir (bool, optional): If True, print cache path and exit.
"""
import clgen.model
import clgen.sampler
from clgen import log
model_json = load_json_file(model)
model = clgen.model.from_json(model_json)
sampler_json = load_json_file(sampler)
sampler = clgen.sampler.from_json(sampler_json)
# print cache paths
if print_file_list:
files = sorted(
fs.ls(model.corpus.cache.path, abspaths=True, recursive=True) +
fs.ls(model.cache.path, abspaths=True, recursive=True) +
fs.ls(sampler.cache(model).path, abspaths=True, recursive=True))
print('\n'.join(files))
sys.exit(0)
elif print_corpus_dir:
print(model.corpus.cache.path)
sys.exit(0)
elif print_model_dir:
print(model.cache.path)
sys.exit(0)
elif print_sampler_dir:
print(sampler.cache(model).path)
sys.exit(0)
model.train()
sampler.sample(model)
argspec = ['__global float*', '__global float*', '__global float*', 'const int']
sampler = clgen.sampler.from_json({
"kernels": {
"args": argspec,
"max_length": 1000
},
"sampler": {
"batch_size": 100,
"max_kernels": 15
}
})
print("Seed text:", clgen.sampler.serialize_argspec(argspec), "\n")
sampler.cache(model).empty()
sampler.sample(model)
db = sampler.cache(model)["kernels.db"]
num_good_kernels = clgen.dbutil.num_good_kernels(db)
clgen.explore.explore(db)
conn = sqlite3.connect(db)
print(conn)
c = conn.cursor()
#c.execute("SELECT * FROM sqlite_master;")
c.execute("SELECT * FROM PreprocessedFiles WHERE status=0;")
rows = c.fetchall()
if not(os.path.isdir("generatedkernels")):
os.mkdir("./generatedkernels")
