def test_mv(self):
system.echo("Hello, world!", "/tmp/labm8.tmp")
self._test(["Hello, world!"], fs.read("/tmp/labm8.tmp"))
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
self._test(False, fs.exists("/tmp/labm8.tmp.copy"))
fs.mv("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
self.assertEqual(["Hello, world!"], fs.read("/tmp/labm8.tmp.copy"))
self._test(False, fs.exists("/tmp/labm8.tmp"))
def test_mv():
system.echo("Hello, world!", "/tmp/labm8.tmp")
assert ["Hello, world!"] == fs.read("/tmp/labm8.tmp")
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
assert not fs.exists("/tmp/labm8.tmp.copy")
fs.mv("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
assert ["Hello, world!"] == fs.read("/tmp/labm8.tmp.copy")
assert not fs.exists("/tmp/labm8.tmp")
def test_cli():
fs.rm("kernels.db")
cli.main("db init kernels.db".split())
assert fs.exists("kernels.db")
corpus_path = tests.archive("tiny", "corpus")
cli.main("db explore kernels.db".split())
cli.main(f"fetch fs kernels.db {corpus_path}".split())
cli.main("preprocess kernels.db".split())
cli.main("db explore kernels.db".split())
fs.rm("kernels_out")
cli.main("db dump kernels.db -d kernels_out".split())
assert fs.isdir("kernels_out")
assert len(fs.ls("kernels_out")) >= 1
fs.rm("kernels.cl")
cli.main("db dump kernels.db kernels.cl --file-sep --eof --reverse".split())
assert fs.isfile("kernels.cl")
fs.rm("kernels_out")
cli.main("db dump kernels.db --input-samples -d kernels_out".split())
assert fs.isdir("kernels_out")
assert len(fs.ls("kernels_out")) == 250
fs.rm("kernels.db")
fs.rm("kernels_out")
def __init__(self, path, basecache=None):
"""
Create a new JSON cache.
Optionally supports populating the cache with values of an
existing cache.
Arguments:
basecache (TransientCache, optional): Cache to populate this new
cache with.
"""
super(JsonCache, self).__init__()
self.path = fs.abspath(path)
if fs.exists(self.path):
io.debug(("Loading cache '{0}'".format(self.path)))
with open(self.path) as file:
self._data = json.load(file)
if basecache is not None:
for key,val in basecache.items():
self._data[key] = val
# Register exit handler
atexit.register(self.write)
def main():
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
c = corpus.Corpus.from_json({"path": "~/data/github"})
print("CLgen: ", clgen.version())
print("Corpus size:", c.size)
print("Vocab size: ", c.vocab_size)
m.train()
p, _ = corpus.most_common_prototypes(c, 20)
for i, row in enumerate(p):
outpath = "./inference-p" + str(i + 1) + "-" + fs.basename(sys.argv[1])
if fs.exists(outpath):
continue
_, prototype = row
argspec = [' '.join(x.split()[:-1]) for x in prototype.split(',')]
print("argspec", ','.join([str(x) for x in argspec]))
s = sampler.from_json({
"kernels": {
"args": argspec,
"max_length": 5000
},
"sampler": {
"batch_size": 2000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def __init__(self, path, basecache=None):
"""
Create a new JSON cache.
Optionally supports populating the cache with values of an
existing cache.
Arguments:
basecache (TransientCache, optional): Cache to populate this new
cache with.
"""
super(JsonCache, self).__init__()
self.path = fs.abspath(path)
if fs.exists(self.path) and fs.read_file(self.path):
io.debug(("Loading cache '{0}'".format(self.path)))
with open(self.path) as file:
self._data = json.load(file)
if basecache is not None:
for key, val in basecache.items():
self._data[key] = val
# Register exit handler
atexit.register(self.write)
def train_and_save(model_desc, platform, source,
atomizer="CharacterAtomizer", maxlen=1024,
n_splits=10, split_i=0, seed=204):
np.random.seed(seed)
name = model_desc["name"]
outpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.model".format(
**vars())
if not fs.exists(outpath):
create_fn = model_desc.get("create_model", _nop)
train_fn = model_desc.get("train_fn", _nop)
save_fn = model_desc["save_fn"]
_atomizer = globals().get(atomizer)
# load training data
data_desc = load_data_desc(platform=platform, source=source,
max_seq_len=maxlen, atomizer=_atomizer)
train, test = get_training_data(data_desc, seed=seed, split_i=split_i,
n_splits=n_splits)
# create model
model = create_fn(seed=seed, data_desc=data_desc)
# train model
train_fn(model=model, train=train, seed=seed, platform=platform,
source=source)
fs.mkdir("models/{name}".format(**vars()))
save_fn(outpath, model)
print("model saved as", outpath)
# evaluate model
return load_and_test(model_desc, platform, source, n_splits=n_splits,
split_i=split_i, atomizer=atomizer, maxlen=maxlen,
seed=seed)
def main():
parser = ArgumentParser(description=__description__)
parser.add_argument("classification")
parser.add_argument("outdir")
args = parser.parse_args()
db.init("cc1")
session = db.make_session()
program_ids = [
x[0] for x in session.query(sql.distinct(CLSmithResult.program_id)) \
.filter(CLSmithResult.classification == args.classification).all()]
header = fs.read_file(dsmith.data_path("include", "clsmith.h"))
fs.mkdir(args.outdir)
for program_id in ProgressBar()(program_ids):
outpath = fs.path(args.outdir, program_id + ".cl")
if not fs.exists(outpath):
program = session.query(CLSmithProgram) \
.filter(CLSmithProgram.id == program_id).one()
pre, post = program.src.split('#include "CLSmith.h"')
inlined = pre + header + post
with open(outpath, "w") as outfile:
print(inlined, file=outfile)
def _find_weka():
"""
Look for Weka installation in system $PATH or /Applications. If
not found, return None.
"""
mac_path = '/Applications/Weka.app'
linux_path = system.which('weka')
return mac_path if fs.exists(mac_path) else linux_path
def _init_error(err: Exception, files_to_rm: List[str]=[]) -> None:
""" tidy up in case of error """
log.error("corpus creation failed. Deleting corpus files")
for path in files_to_rm:
if fs.exists(path):
log.info("removing", path)
fs.rm(path)
raise err
def assert_program_exists(path):
"""
Assert that a program exists.
If the given path does not exist and is not a file, raises
ProgramNotFoundError.
"""
if not fs.exists(path) or not fs.isfile(path):
raise ProgramNotFoundError(path)
def test_create_db_gh():
db_path = tests.data_path("db", "tmp.db", exists=False)
fs.rm(db_path)
dbutil.create_db(db_path, github=True)
assert fs.exists(db_path)
with pytest.raises(clgen.UserError):
dbutil.create_db(db_path, github=True)
def test_cp_dir():
fs.rm("/tmp/labm8")
fs.rm("/tmp/labm8.copy")
fs.mkdir("/tmp/labm8/foo/bar")
assert not fs.exists("/tmp/labm8.copy")
fs.cp("/tmp/labm8/", "/tmp/labm8.copy")
assert fs.isdir("/tmp/labm8.copy")
assert fs.isdir("/tmp/labm8.copy/foo")
assert fs.isdir("/tmp/labm8.copy/foo/bar")
def assert_program_exists(path):
"""
Assert that a program exists.
If the given path does not exist and is not a file, raises
ProgramNotFoundError.
"""
if not fs.exists(path) or not fs.isfile(path):
raise ProgramNotFoundError(path)
def test_cp_dir(self):
fs.rm("/tmp/labm8")
fs.rm("/tmp/labm8.copy")
fs.mkdir("/tmp/labm8/foo/bar")
self._test(False, fs.exists("/tmp/labm8.copy"))
fs.cp("/tmp/labm8/", "/tmp/labm8.copy")
self._test(True, fs.isdir("/tmp/labm8.copy"))
self._test(True, fs.isdir("/tmp/labm8.copy/foo"))
self._test(True, fs.isdir("/tmp/labm8.copy/foo/bar"))
def load_and_test(model_desc, platform, source,
atomizer="CharacterAtomizer", maxlen=1024, n_splits=10,
split_i=0, seed=204):
np.random.seed(seed)
name = model_desc["name"]
inpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.model".format(
**vars())
outpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.result".format(
**vars())
if fs.exists(outpath):
return load_result(model_desc, platform, source, n_splits=n_splits,
split_i=split_i, atomizer=atomizer, maxlen=maxlen,
seed=seed)
if not fs.exists(inpath):
return False
test_fn = model_desc["test_fn"]
load_fn = model_desc["load_fn"]
# load training data
_atomizer = globals().get(atomizer)
data_desc = load_data_desc(platform=platform, source=source,
max_seq_len=maxlen, atomizer=_atomizer,
quiet=True)
train, test = get_training_data(
data_desc, seed=seed, split_i=split_i, n_splits=n_splits)
# load model
model = load_fn(inpath)
print("model loaded from", inpath)
# test model
predictions = test_fn(model=model, test=test, seed=seed)
analysis = analyze(predictions, test)
test.update(analysis)
test["predictions"] = predictions
with open(outpath, 'wb') as outfile:
pickle.dump(test, outfile)
print("result saved to", outpath)
return test
def test_cp_overwrite():
system.echo("Hello, world!", "/tmp/labm8.tmp")
assert ["Hello, world!"] == fs.read("/tmp/labm8.tmp")
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
assert not fs.exists("/tmp/labm8.tmp.copy")
fs.cp("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
system.echo("Goodbye, world!", "/tmp/labm8.tmp")
fs.cp("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
assert fs.read("/tmp/labm8.tmp") == fs.read("/tmp/labm8.tmp.copy")
def test_cp_overwrite(self):
system.echo("Hello, world!", "/tmp/labm8.tmp")
self._test(["Hello, world!"], fs.read("/tmp/labm8.tmp"))
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
self._test(False, fs.exists("/tmp/labm8.tmp.copy"))
fs.cp("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
system.echo("Goodbye, world!", "/tmp/labm8.tmp")
fs.cp("/tmp/labm8.tmp", "/tmp/labm8.tmp.copy")
self._test(fs.read("/tmp/labm8.tmp"), fs.read("/tmp/labm8.tmp.copy"))
def test_scp_user():
system.echo("Hello, world!", "/tmp/labm8.tmp")
assert ["Hello, world!"] == fs.read("/tmp/labm8.tmp")
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
assert not fs.exists("/tmp/labm8.tmp.copy")
# Perform scp.
system.scp("localhost", "/tmp/labm8.tmp", "/tmp/labm8.tmp.copy",
path="labm8/data/test/bin", user="******")
assert fs.read("/tmp/labm8.tmp") == fs.read("/tmp/labm8.tmp.copy")
def test_scp_user(self):
system.echo("Hello, world!", "/tmp/labm8.tmp")
self._test(["Hello, world!"], fs.read("/tmp/labm8.tmp"))
# Cleanup any existing file.
fs.rm("/tmp/labm8.tmp.copy")
self._test(False, fs.exists("/tmp/labm8.tmp.copy"))
# Perform scp.
system.scp("localhost", "/tmp/labm8.tmp", "/tmp/labm8.tmp.copy",
path="tests/bin", user="******")
self._test(fs.read("/tmp/labm8.tmp"), fs.read("/tmp/labm8.tmp.copy"))
def __contains__(self, key):
"""
Check cache contents.
Arguments:
key: Key.
Returns:
bool: True if key in cache, else false.
"""
path = self.keypath(key)
return fs.exists(path)
def load_result(model_desc, platform, source,
atomizer="CharacterAtomizer", maxlen=1024,
n_splits=10, split_i=0, seed=204):
name = model_desc["name"]
inpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.result".format(**vars())
if not fs.exists(inpath):
return False
with open(inpath, 'rb') as infile:
result = pickle.load(infile)
return result
def __contains__(self, key):
"""
Check cache contents.
Arguments:
key: Key.
Returns:
bool: True if key in cache, else false.
"""
path = self.keypath(key)
return fs.exists(path)
def _init_error(err: Exception) -> None:
""" tidy up in case of error """
log.error("corpus creation failed. Deleting corpus files")
paths = [
fs.path(self.contentcache.path, "kernels.db"),
fs.path(self.cache.path, "corpus.txt"),
fs.path(self.cache.path, "tensor.npy"),
fs.path(self.cache.path, "atomizer.pkl")
]
for path in paths:
if fs.exists(path):
log.info("removing", path)
fs.rm(path)
raise err
def __delitem__(self, key):
"""
Delete cached file.
Arguments:
key: Key.
Raises:
KeyError: If file not in cache.
"""
path = self.keypath(key)
if fs.exists(path):
fs.rm(path)
else:
raise KeyError(key)
def __delitem__(self, key):
"""
Delete cached file.
Arguments:
key: Key.
Raises:
KeyError: If file not in cache.
"""
path = self.keypath(key)
if fs.exists(path):
fs.rm(path)
else:
raise KeyError(key)
def test_LockFile_force_replace_stale():
"""Test that lockfile is replaced if forced."""
with tempfile.TemporaryDirectory() as d:
path = pathlib.Path(d) / 'LOCK'
lock = lockfile.LockFile(path)
MAX_PROCESSES = 4194303 # OS-dependent. This value is for Linux
lock.acquire(pid=MAX_PROCESSES + 1)
assert lock.islocked
assert not lock.owned_by_self
with pytest.raises(lockfile.UnableToAcquireLockError):
lock.acquire()
lock.acquire(force=True)
assert lock.islocked
assert lock.owned_by_self
lock.release()
assert not fs.exists(lock.path)
def _incache(self, path: str) -> str:
"""
Assert that file is in cache.
Arguments:
path (str): File path.
Returns:
str: File path.
Raises:
Cache404: If file does not exist.
"""
if not fs.exists(path):
raise Cache404("file '{path}' not found".format(path=path))
return path
def to_dist(self, distpath: str, author: str = None) -> str:
"""
Create a dist file.
Arguments:
distpath (str): Path to dist file.
author (str, optional): Author name.
Returns:
str: Path to generated distfile.
"""
outpath = fs.abspath(distpath) + ".tar.bz2"
if fs.exists(outpath):
raise DistError("file {} exists".format(outpath))
meta = self.meta
if author is not None:
meta["author"] = author
log.debug(clgen.format_json(meta))
try:
tar = tarfile.open(outpath, 'w:bz2')
# write meta
metapath = mktemp(prefix="clgen-", suffix=".json")
clgen.write_file(metapath, clgen.format_json(meta))
log.debug("metafile:", metapath)
# create tarball
tar.add(metapath, arcname="meta.json")
# pack contents:
for path in meta["contents"]:
abspath = fs.path(cache.ROOT, path)
log.verbose("packing", abspath)
tar.add(abspath, arcname=fs.path("contents", path))
# tidy up
fs.rm(metapath)
tar.close()
except Exception as e:
tar.close()
fs.rm(metapath)
fs.rm(outpath)
raise e
return outpath
def __setitem__(self, key, value):
"""
Emplace file in cache.
Arguments:
key: Key.
value (str): Path of file to insert in cache.
Raises:
ValueError: If no "value" does nto exist.
"""
if not fs.exists(value):
raise ValueError(value)
path = self.keypath(key)
fs.mkdir(self.path)
fs.mv(value, path)
def __setitem__(self, key, value):
"""
Emplace file in cache.
Arguments:
key: Key.
value (str): Path of file to insert in cache.
Raises:
ValueError: If no "value" does nto exist.
"""
if not fs.exists(value):
raise ValueError(value)
path = self.keypath(key)
fs.mkdir(self.path)
fs.mv(value, path)
def __getitem__(self, key):
"""
Get path to file in cache.
Arguments:
key: Key.
Returns:
str: Path to cache value.
Raises:
KeyErorr: If key not in cache.
"""
path = self.keypath(key)
if fs.exists(path):
return path
else:
raise KeyError(key)
def __getitem__(self, key):
"""
Get path to file in cache.
Arguments:
key: Key.
Returns:
str: Path to cache value.
Raises:
KeyErorr: If key not in cache.
"""
path = self.keypath(key)
if fs.exists(path):
return path
else:
raise KeyError(key)
def read(path):
"""
Read the contents of a LockFile.
Arguments:
path (str): Path to lockfile.
Returns:
Tuple(int, datetime): The integer PID of the lock owner, and the
date the lock was required. If the lock is not claimed, both
values are None.
"""
if fs.exists(path):
with open(path) as infile:
components = infile.read().split()
pid = int(components[0])
date = datetime.date.fromtimestamp(float(components[1]))
return pid, date
else:
return None, None
def benchmark_inference(model_desc, platform, source,
atomizer="CharacterAtomizer", maxlen=1024, n_splits=10,
split_i=0, seed=204, n_runtimes=100):
np.random.seed(seed)
name = model_desc["name"]
inpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.model".format(
**vars())
outpath = "models/{name}/{platform}-{source}-{atomizer}:{maxlen}-{seed}-{n_splits}-{split_i}.result".format(
**vars())
if not fs.exists(inpath):
return False
test_fn = model_desc["test_fn"]
load_fn = model_desc["load_fn"]
# load training data
_atomizer = globals().get(atomizer)
data_desc = load_data_desc(platform=platform, source=source,
max_seq_len=maxlen, atomizer=_atomizer,
quiet=True)
train, test = get_training_data(
data_desc, seed=seed, split_i=split_i, n_splits=n_splits)
# load model
model = load_fn(inpath)
print("model loaded from", inpath)
# test model
runtimes = []
for i in range(n_runtimes):
start = time.time()
predictions = test_fn(model=model, test=test, seed=seed)
elapsed = (time.time() - start) / len(test["y"])
runtimes.append(elapsed)
return np.array(runtimes)
def main():
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
c = corpus.Corpus.from_json({"path": "~/data/github"})
print("CLgen: ", clgen.version())
print("Corpus size:", c.size)
print("Vocab size: ", c.vocab_size)
m.train()
p, _ = corpus.most_common_prototypes(c, 20)
for i, row in enumerate(p):
outpath = "./inference-p" + str(i + 1) + "-" + fs.basename(sys.argv[1])
if fs.exists(outpath):
print("skipped result for", outpath)
continue
else:
print("starting result for", outpath)
_, prototype = row
argspec = [' '.join(x.split()[:-1]) for x in prototype.split(',')]
print("argspec", ','.join([str(x) for x in argspec]))
s = sampler.from_json({
"kernels": {
"args": argspec,
"max_length": 5000
},
"sampler": {
"batch_size": 2000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def search(m, target_code, logpath, start_code=None):
# resume search
if fs.exists(logpath):
log = clgen.load_json_file(logpath)
print("resuming search of", len(get_steps(log)), "steps")
else:
log = []
steps = get_steps(log)
if start_code and not len(steps):
code = start_code
elif len(steps):
code = steps[-1]['data']['code']
else:
code = get_start_code(m)
target_features = get_features(target_code)
features = get_features(code)
distance = get_distance(target_features, features)
if get_entries(log, "init"):
init = get_entries(log, "init")[0]
assert(init['data']['target_code'] == target_code)
assert(init['data']['target_features'] == escape_features(target_features))
# load history from log
code_history = get_code_history(log)
else:
# create init entry
add_to_log(log, {
"start_code": code,
"start_features": escape_features(features),
"target_features": escape_features(target_features),
"target_code": target_code,
"distance": distance,
"model": m.meta
}, name="init")
write_log(log, logpath)
code_history = [code]
# keep track of best
if len(steps):
best = steps[-1]['data']['best']
else:
best = {
"distance": distance,
"code": code,
"improvement_count": 0
}
# maximum number of mutations before stopping search
MAX_STEPS = 1000
for i in range(len(steps), MAX_STEPS):
print("step", i, "of", MAX_STEPS)
newcode, mutate_idx, mutate_seed, attempts = get_mutation(m, code)
try:
features = get_features(newcode)
distance = get_distance(target_features, features)
except ValueError:
newcode = None
entry = {
"count": i,
"attempts": attempts
}
if newcode:
entry["base_code"] = code
entry["code"] = newcode
entry["distance"] = distance
entry["distance_diff"] = 1 - distance / best["distance"]
entry["features"] = escape_features(features)
entry["mutate_idx"] = mutate_idx
entry["mutate_seed"] = mutate_seed
code_history.append(code)
else:
print(" -> step back")
# step back
if len(code_history):
code = code_history.pop()
entry["step_back"] = code
if distance < best["distance"]:
print(" -> improvement {:.1f}%".format(
entry["distance_diff"] * 100))
best["distance"] = distance
best["code"] = newcode
best["features"] = escape_features(features)
best["improvement_count"] += 1
else:
if newcode:
print(" -> regression {:.1f}%".format(
entry["distance_diff"] * 100))
entry["best"] = best
add_to_log(log, entry, name="step")
write_log(log, logpath)
# doesn't have to be exactly zero but whatever
if distance <= 0.001:
print("found exact match!")
break
add_to_log(log, {
"best_code": best['code'],
"best_features": escape_features(best['features']),
"best_distance": best['distance']
}, name="end")
write_log(log, logpath)
def evaluate(model, embeddings, folder_data, samples_per_class, folder_results, dense_layer_size, print_summary,
num_epochs, batch_size):
# Set seed for reproducibility
seed = 204
####################################################################################################################
# Get data
vsamples_per_class = FLAGS.vsamples
# Data acquisition
num_classes = 104
y_train = np.empty(0) # training
X_train = list()
folder_data_train = folder_data + '_train'
y_val = np.empty(0) # validation
X_val = list()
folder_data_val = folder_data + '_val'
y_test = np.empty(0) # testing
X_test = list()
folder_data_test = folder_data + '_test'
print('Getting file names for', num_classes, 'classes from folders:')
print(folder_data_train)
print(folder_data_val)
print(folder_data_test)
for i in range(1, num_classes + 1): # loop over classes
# training: Read data file names
folder = os.path.join(folder_data_train, str(i))
assert os.path.exists(folder), "Folder: " + folder + ' does not exist'
print('\ttraining : Read file names from folder ', folder)
listing = os.listdir(folder + '/')
seq_files = [os.path.join(folder, f) for f in listing if f[-4:] == '.rec']
# training: Randomly pick programs
assert len(seq_files) >= samples_per_class, "Cannot sample " + str(samples_per_class) + " from " + str(
len(seq_files)) + " files found in " + folder
X_train += resample(seq_files, replace=False, n_samples=samples_per_class, random_state=seed)
y_train = np.concatenate([y_train, np.array([int(i)] * samples_per_class, dtype=np.int32)])
# validation: Read data file names
folder = os.path.join(folder_data_val, str(i))
assert os.path.exists(folder), "Folder: " + folder + ' does not exist'
print('\tvalidation: Read file names from folder ', folder)
listing = os.listdir(folder + '/')
seq_files = [os.path.join(folder, f) for f in listing if f[-4:] == '.rec']
# validation: Randomly pick programs
if vsamples_per_class > 0:
assert len(seq_files) >= vsamples_per_class, "Cannot sample " + str(vsamples_per_class) + " from " + str(
len(seq_files)) + " files found in " + folder
X_val += resample(seq_files, replace=False, n_samples=vsamples_per_class, random_state=seed)
y_val = np.concatenate([y_val, np.array([int(i)] * vsamples_per_class, dtype=np.int32)])
else:
assert len(seq_files) > 0, "No .rec files found in" + folder
X_val += seq_files
y_val = np.concatenate([y_val, np.array([int(i)] * len(seq_files), dtype=np.int32)])
# test: Read data file names
folder = os.path.join(folder_data_test, str(i))
assert os.path.exists(folder), "Folder: " + folder + ' does not exist'
print('\ttest : Read file names from folder ', folder)
listing = os.listdir(folder + '/')
seq_files = [os.path.join(folder, f) for f in listing if f[-4:] == '.rec']
assert len(seq_files) > 0, "No .rec files found in" + folder
X_test += seq_files
y_test = np.concatenate([y_test, np.array([int(i)] * len(seq_files), dtype=np.int32)])
# Load dictionary and cutoff statements
folder_vocabulary = FLAGS.vocabulary_dir
dictionary_pickle = os.path.join(folder_vocabulary, 'dic_pickle')
print('\tLoading dictionary from file', dictionary_pickle)
with open(dictionary_pickle, 'rb') as f:
dictionary = pickle.load(f)
unk_index = dictionary[rgx.unknown_token]
del dictionary
# Encode source codes and get max. sequence length
X_seq_train, maxlen_train = encode_srcs(X_train, 'training', unk_index)
X_seq_val, maxlen_val = encode_srcs(X_val, 'validation', unk_index)
X_seq_test, maxlen_test = encode_srcs(X_test, 'testing', unk_index)
maxlen = max(maxlen_train, maxlen_test, maxlen_val)
print('Max. sequence length overall:', maxlen)
print('Padding sequences')
X_seq_train = pad_src(X_seq_train, maxlen, unk_index)
X_seq_val = pad_src(X_seq_val, maxlen, unk_index)
X_seq_test = pad_src(X_seq_test, maxlen, unk_index)
# Get one-hot vectors for classification
print('YTRAIN\n', y_train)
y_1hot_train = get_onehot(y_train, num_classes)
y_1hot_val = get_onehot(y_val, num_classes)
####################################################################################################################
# Setup paths
# Set up names paths
model_name = model.__name__
model_path = os.path.join(folder_results,
"classifyapp/models/{}.model".format(model_name))
predictions_path = os.path.join(folder_results,
"classifyapp/predictions/{}.result".format(model_name))
# If predictions have already been made with these embeddings, load them
if fs.exists(predictions_path):
print("\tFound predictions in", predictions_path, ", skipping...")
with open(predictions_path, 'rb') as infile:
p = pickle.load(infile)
else: # could not find predictions already computed with these embeddings
# Embeddings
import tensorflow as tf # for embeddings lookup
embedding_matrix_normalized = tf.nn.l2_normalize(embeddings, axis=1)
vocabulary_size, embedding_dimension = embedding_matrix_normalized.shape
print('XSEQ:\n', X_seq_train)
print('EMB:\n', embedding_matrix_normalized)
gen_test = EmbeddingPredictionSequence(batch_size, X_seq_test, embedding_matrix_normalized)
# If models have already been made with these embeddings, load them
if fs.exists(model_path):
print("\n\tFound trained model in", model_path, ", skipping...")
model.restore(model_path)
else: # could not find models already computed with these embeddings
gen_train = EmbeddingSequence(batch_size, X_seq_train, y_1hot_train, embedding_matrix_normalized)
gen_val = EmbeddingSequence(batch_size, X_seq_val, y_1hot_val, embedding_matrix_normalized)
############################################################################################################
# Train
# Create a new model and train it
print('\n--- Initializing model...')
model.init(seed=seed,
maxlen=maxlen,
embedding_dim=int(embedding_dimension),
num_classes=num_classes,
dense_layer_size=dense_layer_size)
if print_summary:
model.model.summary()
print('\n--- Training model...')
model.train_gen(train_generator=gen_train,
validation_generator=gen_val,
verbose=True,
epochs=num_epochs)
# Save the model
fs.mkdir(fs.dirname(model_path))
model.save(model_path)
print('\tsaved model to', model_path)
################################################################################################################
# Test
# Test model
print('\n--- Testing model...')
p = model.predict_gen(generator=gen_test)[0]
# cache the prediction
fs.mkdir(fs.dirname(predictions_path))
with open(predictions_path, 'wb') as outfile:
pickle.dump(p, outfile)
print('\tsaved predictions to', predictions_path)
####################################################################################################################
# Return accuracy
accuracy = p == y_test # prediction accuracy
return accuracy
def test_finalise_figsize(self):
self._mkplot()
viz.finalise("/tmp/labm8.png", figsize=(10, 5))
self.assertTrue(fs.exists("/tmp/labm8.png"))
fs.rm("/tmp/labm8.png")
def test_exists(self):
self._test(True, fs.exists(__file__))
self._test(True, fs.exists("/"))
self._test(False, fs.exists("/not/a/real/path (I hope!)"))
def search(m, target_code, logpath, start_code=None):
# resume search
if fs.exists(logpath):
log = clgen.load_json_file(logpath)
print("resuming search of", len(get_steps(log)), "steps")
else:
log = []
steps = get_steps(log)
if start_code and not len(steps):
code = start_code
elif len(steps):
code = steps[-1]['data']['code']
else:
code = get_start_code(m)
target_features = get_features(target_code)
features = get_features(code)
distance = get_distance(target_features, features)
if get_entries(log, "init"):
init = get_entries(log, "init")[0]
assert (init['data']['target_code'] == target_code)
assert (init['data']['target_features'] == escape_features(
target_features))
# load history from log
code_history = get_code_history(log)
else:
# create init entry
add_to_log(log, {
"start_code": code,
"start_features": escape_features(features),
"target_features": escape_features(target_features),
"target_code": target_code,
"distance": distance,
"model": m.meta
},
name="init")
write_log(log, logpath)
code_history = [code]
# keep track of best
if len(steps):
best = steps[-1]['data']['best']
else:
best = {"distance": distance, "code": code, "improvement_count": 0}
# maximum number of mutations before stopping search
MAX_STEPS = 1000
for i in range(len(steps), MAX_STEPS):
print("step", i, "of", MAX_STEPS)
newcode, mutate_idx, mutate_seed, attempts = get_mutation(m, code)
try:
features = get_features(newcode)
distance = get_distance(target_features, features)
except ValueError:
newcode = None
entry = {"count": i, "attempts": attempts}
if newcode:
entry["base_code"] = code
entry["code"] = newcode
entry["distance"] = distance
entry["distance_diff"] = 1 - distance / best["distance"]
entry["features"] = escape_features(features)
entry["mutate_idx"] = mutate_idx
entry["mutate_seed"] = mutate_seed
code_history.append(code)
else:
print(" -> step back")
# step back
if len(code_history):
code = code_history.pop()
entry["step_back"] = code
if distance < best["distance"]:
print(" -> improvement {:.1f}%".format(entry["distance_diff"] *
100))
best["distance"] = distance
best["code"] = newcode
best["features"] = escape_features(features)
best["improvement_count"] += 1
else:
if newcode:
print(" -> regression {:.1f}%".format(
entry["distance_diff"] * 100))
entry["best"] = best
add_to_log(log, entry, name="step")
write_log(log, logpath)
# doesn't have to be exactly zero but whatever
if distance <= 0.001:
print("found exact match!")
break
add_to_log(log, {
"best_code": best['code'],
"best_features": escape_features(best['features']),
"best_distance": best['distance']
},
name="end")
write_log(log, logpath)
def test_finalise_figsize():
_MakeTestPlot()
viz.finalise("/tmp/labm8.png", figsize=(10, 5))
assert fs.exists("/tmp/labm8.png")
fs.rm("/tmp/labm8.png")
def test_finalise_tight():
_MakeTestPlot()
viz.finalise("/tmp/labm8.png", tight=True)
assert fs.exists("/tmp/labm8.png")
fs.rm("/tmp/labm8.png")
def test_finalise():
_MakeTestPlot()
viz.finalise("/tmp/labm8.png")
assert fs.exists("/tmp/labm8.png")
fs.rm("/tmp/labm8.png")
def islocked(self):
"""
Whether the directory is locked.
"""
return fs.exists(self.path)
def evaluate(model, device, data_folder, out_folder, embeddings,
dense_layer_size, print_summary, num_epochs, batch_size):
data = []
# Create device list
if device == 'all':
device_list = ["Cypress", "Tahiti", "Fermi", "Kepler"]
else:
device_list = [device]
for i, platform in enumerate(device_list):
print(
'\n------------------------------------------------------------------'
)
print('--- Platform', platform, '[', i + 1, '/ 4 ]')
print(
'------------------------------------------------------------------'
)
platform_name = platform2str(platform)
# Read data
oracle_file = os.path.join(data_folder, "pact-2014-oracles.csv")
oracles = pd.read_csv(oracle_file)
runtimes_file = os.path.join(data_folder, "pact-2014-runtimes.csv")
df = pd.read_csv(runtimes_file)
print('\tRead data from', oracle_file, '\n\tand', runtimes_file)
# Extract data
oracle_runtimes = np.array(
[float(x) for x in oracles["runtime_" + platform]])
y = np.array([int(x) for x in oracles["cf_" + platform]],
dtype=np.int32)
y_1hot = get_onehot(oracles, platform)
# Encode source codes
X_seq, maxlen = encode_srcs(data_folder, df)
# Embeddings
import tensorflow as tf # for embeddings lookup
embedding_matrix_normalized = tf.nn.l2_normalize(embeddings, axis=1)
vocabulary_size, embedding_dimension = embedding_matrix_normalized.shape
seq_ = tf.placeholder(dtype=tf.int32)
# Tensor of shape (num_input_files, sequence length, embbedding dimension)
embedding_input_ = tf.nn.embedding_lookup(embedding_matrix_normalized,
seq_)
# Make tf block less gpu memory
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
embedding_input = sess.run(embedding_input_,
feed_dict={seq_: X_seq})
# Leave-one-out cross-validation
kf = KFold(n_splits=len(y), shuffle=False)
for j, (train_index, test_index) in enumerate(kf.split(y)):
print('--- Cross validation step [', j + 1, '/ ', len(y), ']')
kernel = sorted(set(df["kernel"]))[test_index[0]]
X_cc, y_cc = get_magni_features(df, oracles, platform)
model_name = model.__name__
model_basename = model.__basename__
model_path = os.path.join(
out_folder,
"models/{model_basename}-{platform}-{j}.model".format(
model_basename=model_basename, platform=platform, j=j))
predictions_path = os.path.join(
out_folder,
"predictions/{model_basename}-{platform}-{j}.result".format(
model_basename=model_basename, platform=platform, j=j))
if fs.exists(predictions_path):
# load result from cache
print("\tFound predictions in", predictions_path,
", skipping...")
with open(predictions_path, 'rb') as infile:
p = pickle.load(infile)
else:
if fs.exists(model_path):
# load a trained model from cache
print("\n\tFound trained model in", model_path,
", skipping...")
model.restore(model_path)
else:
# Initialize model and print summary
print('\n--- Training model...')
model.init(seed, maxlen, int(embedding_dimension),
dense_layer_size)
if print_summary:
model.model.summary()
# Train and cache a model
model.train(sequences=embedding_input[train_index, :, :],
verbose=True,
y_1hot=y_1hot[train_index],
epochs=num_epochs,
batch_size=batch_size)
# cache the model
fs.mkdir(fs.dirname(model_path))
model.save(model_path)
print('\tsaved model to', model_path)
# test model
print('\n--- Testing model...')
p = model.predict(sequences=embedding_input[test_index, :, :],
batch_size=batch_size)[0]
# The runtimes of some coarsening factors are not recorded in the data table. If that is the case for
# the predicted cf, clamp it down to the highest cf for which the runtime is recorded
p = min(p, 2**(len(X_cc[test_index[0]]) - 1))
# cache the prediction
fs.mkdir(fs.dirname(predictions_path))
with open(predictions_path, 'wb') as outfile:
pickle.dump(p, outfile)
print('\tsaved predictions to', predictions_path)
o = y[test_index[0]] # oracle prediction (true value)
correct = p == o # predictions' correctness
# get runtime without thread coarsening
row = df[(df["kernel"] == kernel) & (df["cf"] == 1)]
assert (len(row) == 1) # sanity check
nocf_runtime = float(row["runtime_" + platform])
# get runtime of prediction
row = df[(df["kernel"] == kernel) & (df["cf"] == p)]
assert (len(row) == 1) # sanity check
p_runtime = float(row["runtime_" + platform])
# get runtime of oracle coarsening factor
o_runtime = oracle_runtimes[test_index[0]]
# speedup and % oracle
s_oracle = nocf_runtime / o_runtime
p_speedup = nocf_runtime / p_runtime
p_oracle = o_runtime / p_runtime
# record result
data.append({
"Model": model_name,
"Platform": platform_name,
"Kernel": kernel,
"Oracle-CF": o,
"Predicted-CF": p,
"Speedup": p_speedup,
"Oracle": p_oracle
})
return pd.DataFrame(data,
columns=[
"Model", "Platform", "Kernel", "Oracle-CF",
"Predicted-CF", "Speedup", "Oracle"
])
def test_exists():
assert fs.exists(__file__)
assert fs.exists("/")
assert not fs.exists("/not/a/real/path (I hope!)")
def test_finalise_tight(self):
self._mkplot()
viz.finalise("/tmp/labm8.png", tight=True)
self.assertTrue(fs.exists("/tmp/labm8.png"))
fs.rm("/tmp/labm8.png")