def add_tokenizer_args(parser: argparse.ArgumentParser,
default_values: Dict[str, Any] = {}) -> None:
parser.add_argument("--num-keywords",
dest="num_keywords",
type=int,
default=default_values.get("num-keywordes", 60))
parser.add_argument("--tokenizer",
choices=list(tokenizers.keys()),
type=str,
default=default_values.get("tokenizer",
list(tokenizers.keys())[0]))
parser.add_argument("--num-relevance-samples",
dest="num_relevance_samples",
type=int,
default=default_values.get("num_relevance_samples",
1000))
parser.add_argument("--save-tokens",
dest="save_tokens",
default=default_values.get("save-tokens", None))
parser.add_argument("--load-tokens",
dest="load_tokens",
default=default_values.get("load-tokens", None))
parser.add_argument("--print-keywords",
dest="print_keywords",
default=False,
action='store_const',
const=True)
def get_data(args: List[str]) -> None:
parser = argparse.ArgumentParser(
description="Parse datafiles into multiple formats")
parser.add_argument("format",
choices=[
"terms", "goals", "hyps+goal", "hyps+goal+tactic",
"tacvector"
])
parser.add_argument("scrape_file", type=Path2)
parser.add_argument("--tokenizer",
choices=list(tokenizers.keys()),
type=str,
default=list(tokenizers.keys())[0])
parser.add_argument("--max-tuples",
dest="max_tuples",
default=None,
type=int)
parser.add_argument("--num-keywords",
dest="num_keywords",
default=100,
type=int)
parser.add_argument("--num-head-keywords",
dest="num_head_keywords",
type=int,
default=100)
parser.add_argument("--num-tactic-keywords",
dest="num_tactic_keywords",
type=int,
default=50)
parser.add_argument("--print-keywords",
dest="print_keywords",
action='store_true')
parser.add_argument("--max-length",
dest="max_length",
default=None,
type=int)
parser.add_argument("--lineend",
dest="lineend",
default=False,
const=True,
action='store_const')
parser.add_argument("--context-filter",
dest="context_filter",
default="default")
parser.add_argument("--verbose", action="store_true")
arg_values = parser.parse_args(args)
if arg_values.format == "terms":
terms, tokenizer = data.term_data(
data.RawDataset(
list(
itertools.islice(
data.read_text_data(arg_values.scrape_file),
arg_values.max_tuples))),
tokenizers[arg_values.tokenizer], arg_values.num_keywords, 2)
if arg_values.max_length:
terms = [
data.normalizeSentenceLength(term, arg_values.max_length)
for term in terms
]
for term in terms:
print(tokenizer.toString(
list(itertools.takewhile(lambda x: x != data.EOS_token,
term))),
end="\\n\n" if arg_values.lineend else "\n")
elif arg_values.format == "goals":
dataset = data.get_text_data(arg_values)
for prev_tactics, hyps, goal, tactic in dataset:
print(goal)
elif arg_values.format == "hyps+goal":
dataset = data.get_text_data(arg_values)
for prev_tactics, hyps, goal, tactic in dataset:
for hyp in hyps:
print(hyp)
print("================================")
print(goal)
elif arg_values.format == "hyps+goal+tactic":
dataset = data.get_text_data(arg_values)
for prev_tactics, hyps, goal, tactic in dataset:
for hyp in hyps:
print(hyp)
print("================================")
print(goal)
print("====> {}".format(tactic))
pass
elif arg_values.format == "tacvector":
dataset = data.get_text_data(arg_values)
embedding = SimpleEmbedding()
eprint("Encoding tactics...", guard=arg_values.verbose)
answers = [
embedding.encode_token(serapi_instance.get_stem(datum.tactic))
for datum in dataset
]
stripped_data = [strip_scraped_output(scraped) for scraped in dataset]
eprint("Constructing features...", guard=arg_values.verbose)
word_feature_functions = [
word_feature_constructor(stripped_data, arg_values)
for word_feature_constructor in features.word_feature_constructors
]
vec_features_functions = [
vec_feature_constructor(stripped_data, arg_values)
for vec_feature_constructor in features.vec_feature_constructors
]
eprint("Extracting features...", guard=arg_values.verbose)
word_features = [[feature(c) for feature in word_feature_functions]
for c in stripped_data]
vec_features = [[
feature_val for feature in vec_features_functions
for feature_val in feature(c)
] for c in stripped_data]
eprint("Done", guard=arg_values.verbose)
for word_feat, vec_feat, tactic in zip(word_features, vec_features,
answers):
print(",".join(
list(map(str, word_feat)) + list(map(str, vec_feat)) +
[str(tactic)]))
def get_data(args: List[str]) -> None:
parser = argparse.ArgumentParser(
description="Parse datafiles into multiple formats")
parser.add_argument("format",
choices=[
"terms", "goals", "hyps+goal", "hyps+goal+tactic",
"tacvector", "scrapefile-rd", "scrapefile"
])
parser.add_argument("scrape_file", type=Path2)
parser.add_argument("--tokenizer",
choices=list(tokenizers.keys()),
type=str,
default=list(tokenizers.keys())[0])
parser.add_argument("--max-tuples",
dest="max_tuples",
default=None,
type=int)
parser.add_argument("--num-keywords",
dest="num_keywords",
default=100,
type=int)
parser.add_argument("--num-head-keywords",
dest="num_head_keywords",
type=int,
default=100)
parser.add_argument("--num-tactic-keywords",
dest="num_tactic_keywords",
type=int,
default=50)
parser.add_argument("--print-keywords",
dest="print_keywords",
action='store_true')
parser.add_argument("--no-truncate-semicolons",
dest="truncate_semicolons",
action='store_false')
parser.add_argument("--max-length",
dest="max_length",
default=30,
type=int)
parser.add_argument("--lineend",
dest="lineend",
default=False,
const=True,
action='store_const')
parser.add_argument("-j", "--num-threads", default=None, type=int)
parser.add_argument("--context-filter",
dest="context_filter",
default="default")
parser.add_argument('-v', "--verbose", action="count")
parser.add_argument("--num-threads", "-j", type=int, default=None)
parser.add_argument("--no-use-substitutions",
action='store_false',
dest='use_substitutions')
parser.add_argument("--no-normalize-numeric-args",
action='store_false',
dest='normalize_numeric_args')
parser.add_argument("--sort", action='store_true')
arg_values = parser.parse_args(args)
if arg_values.format == "terms":
terms, tokenizer = data.term_data(
data.RawDataset(
list(
itertools.islice(
data.read_text_data(arg_values.scrape_file),
arg_values.max_tuples))),
tokenizers[arg_values.tokenizer], arg_values.num_keywords, 2)
if arg_values.max_length:
terms = [
data.normalizeSentenceLength(term, arg_values.max_length)
for term in terms
]
for term in terms:
print(tokenizer.toString(
list(itertools.takewhile(lambda x: x != data.EOS_token,
term))),
end="\\n\n" if arg_values.lineend else "\n")
else:
dataset = data.get_text_data(arg_values)
if arg_values.sort:
dataset = data.RawDataset(
sorted(dataset, key=lambda d: len(d.hypotheses), reverse=True))
if arg_values.format == "goals":
for relevant_lemmas, prev_tactics, hyps, goal, tactic in dataset:
print(goal)
elif arg_values.format == "hyps+goal":
for relevant_lemmas, prev_tactics, hyps, goal, tactic in dataset:
for hyp in hyps:
print(hyp)
print("================================")
print(goal)
elif arg_values.format == "hyps+goal+tactic":
for relevant_lemmas, prev_tactics, hyps, goal, tactic in dataset:
for hyp in hyps:
print(hyp)
print("================================")
print(goal)
print("====> {}".format(tactic))
pass
elif arg_values.format == "tacvector":
embedding = SimpleEmbedding()
eprint("Encoding tactics...", guard=arg_values.verbose)
answers = [
embedding.encode_token(serapi_instance.get_stem(datum.tactic))
for datum in dataset
]
stripped_data = [
strip_scraped_output(scraped) for scraped in dataset
]
eprint("Constructing features...", guard=arg_values.verbose)
word_feature_functions = [
word_feature_constructor(stripped_data,
arg_values) # type: ignore
for word_feature_constructor in
features.word_feature_constructors
]
vec_features_functions = [
vec_feature_constructor(stripped_data, arg_values) for
vec_feature_constructor in features.vec_feature_constructors
]
eprint("Extracting features...", guard=arg_values.verbose)
word_features = [[
feature(c) for feature in word_feature_functions
] for c in stripped_data]
vec_features = [[
feature_val for feature in vec_features_functions
for feature_val in feature(c)
] for c in stripped_data]
eprint("Done", guard=arg_values.verbose)
for word_feat, vec_feat, tactic in zip(word_features, vec_features,
answers):
print(",".join(
list(map(str, word_feat)) + list(map(str, vec_feat)) +
[str(tactic)]))
elif arg_values.format == "scrapefile-rd":
for point in dataset:
print(
json.dumps({
"relevant_lemmas": point.relevant_lemmas,
"prev_tactics": point.prev_tactics,
"context": {
"fg_goals": [{
"hypotheses": point.hypotheses,
"goal": point.goal
}],
"bg_goals": [],
"shelved_goals": [],
"given_up_goals": []
},
"tactic": point.tactic
}))
elif arg_values.format == "scrapefile":
for point in dataset:
print(
json.dumps({
"relevant_lemmas": point.relevant_lemmas,
"prev_tactics": point.prev_tactics,
"prev_hyps": point.hypotheses,
"prev_goal": point.goal,
"tactic": point.tactic
}))
def add_std_args(parser: argparse.ArgumentParser,
default_values: Dict[str, Any] = {}) -> None:
parser.add_argument("scrape_file")
parser.add_argument("save_file")
parser.add_argument("--num-threads",
"-j",
dest="num_threads",
type=int,
default=default_values.get("num-threads", None))
parser.add_argument("--num-epochs",
dest="num_epochs",
type=int,
default=default_values.get("num-epochs", 20))
parser.add_argument("--batch-size",
dest="batch_size",
type=int,
default=default_values.get("batch-size", 256))
parser.add_argument("--max-length",
dest="max_length",
type=int,
default=default_values.get("max-length", 100))
parser.add_argument("--max-tuples",
dest="max_tuples",
type=int,
default=default_values.get("max-tuples", None))
parser.add_argument("--start-from",
dest="start_from",
type=str,
default=default_values.get("start-from", None))
parser.add_argument("--print-every",
dest="print_every",
type=int,
default=default_values.get("print-every", 5))
parser.add_argument("--hidden-size",
dest="hidden_size",
type=int,
default=default_values.get("hidden-size", 128))
parser.add_argument("--learning-rate",
dest="learning_rate",
type=float,
default=default_values.get("learning-rate", .7))
parser.add_argument("--epoch-step",
dest="epoch_step",
type=int,
default=default_values.get("epoch-step", 10))
parser.add_argument("--gamma",
dest="gamma",
type=float,
default=default_values.get("gamma", 0.8))
parser.add_argument("--num-encoder-layers",
dest="num_encoder_layers",
type=int,
default=default_values.get("num-encoder-layers", 3))
parser.add_argument("--num-decoder-layers",
dest="num_decoder_layers",
type=int,
default=default_values.get("num-decoder-layers", 3))
parser.add_argument("--num-keywords",
dest="num_keywords",
type=int,
default=default_values.get("num-keywordes", 60))
parser.add_argument("--tokenizer",
choices=list(tokenizers.keys()),
type=str,
default=default_values.get("tokenizer",
list(tokenizers.keys())[0]))
parser.add_argument("--save-tokens",
dest="save_tokens",
default=default_values.get("save-tokens", None))
parser.add_argument("--load-tokens",
dest="load_tokens",
default=default_values.get("load-tokens", None))
parser.add_argument("--optimizer",
choices=list(optimizers.keys()),
type=str,
default=default_values.get("optimizer",
list(optimizers.keys())[0]))
parser.add_argument("--context-filter",
dest="context_filter",
type=str,
default=default_values.get("context-filter",
"goal-changes%no-args"))
