proof_steps[split][-1]['goal_id'] = proof_data['goal_id']
proof_steps[split][-1]['length'] = proof_data['length']
else:
proof_steps[split][-1]['is_synthetic'] = False
if __name__ == '__main__':
arg_parser = argparse.ArgumentParser(description='Extract the proof steps from CoqGym for trainig ASTactic via supervised learning')
arg_parser.add_argument('--data_root', type=str, default='../data',
help='The folder for CoqGym')
arg_parser.add_argument('--output', type=str, default='./proof_steps/',
help='The output file')
arg_parser.add_argument('--filter', type=str, help='filter the proofs')
args = arg_parser.parse_args()
print(args)
iter_proofs(args.data_root, process_proof, include_synthetic=False, show_progress=True)
for split in ['train', 'valid']:
print("Proof steps {}: {}".format(split, len(proof_steps[split])))
for i, step in enumerate(proof_steps[split]):
dirname = os.path.join(args.output, split)
if not os.path.exists(dirname):
os.makedirs(dirname)
if args.filter:
pickle.dump(step, open(os.path.join(dirname, '%s-%08d.pickle' % (args.filter, i)), 'wb'))
else:
pickle.dump(step, open(os.path.join(dirname, '%08d.pickle' % i), 'wb'))
print('output saved to ', args.output)
data["num_goals"].append(len(proof_data["goals"]))
data["num_env_constants"].append(len(proof_data["env"]["constants"]))
data["num_env_inductives"].append(len(proof_data["env"]["inductives"]))
data["num_env"].append(
data["num_env_constants"][-1] + data["num_env_inductives"][-1]
)
# data['num_env_constants_same_file'].append(len([const for const in proof_data['env']['constants']
# if const['qualid'].startswith('SerTop.')]))
data["avg_size_local_context"].append(
np.mean([len(g["hypotheses"]) for g in proof_data["goals"].values()])
)
iter_proofs(
common.data_root,
process_proof,
include_synthetic=args.synthetic,
show_progress=True,
)
df = pd.DataFrame(data)
df.to_csv(args.output)
print("output saved to ", args.output)
# show some statistics
print(df.describe())
print(
df.groupby("project").agg(
{"name": "count", "num_steps": "mean", "num_goals": "mean", "num_env": "mean"}
)
)
ast_height = []
num_tokens = []
num_chars = []
has_argument = []
def process_proof(filename, proof_data):
global ast_height
global num_tokens
global num_chars
for step in proof_data['steps']:
if step['command'][1] != 'VernacExtend':
continue
if not step['command'][0].endswith('.'):
continue
tac_str = step['command'][0][:-1]
try:
tree = tree_builder.transform(grammar.parser.parse(tac_str))
except (UnexpectedCharacters, ParseError) as ex:
continue
ast_height.append(tree.height())
num_tokens.append(tree.num_tokens())
num_chars.append(len(tac_str))
has_argument.append(int(tree.has_argument()))
iter_proofs(common.data_root, process_proof, show_progress=True)
print(np.mean(ast_height), np.mean(num_tokens), np.mean(num_chars), np.mean(has_argument))
global abnormal_proofs
global abnormal_env_files
tempname = proof_data['name']
if tempname not in term_proofs:
return
goal_dict = proof_data['goals']
tempenv = proof_data['env']
"""
for xx in tempenv['constants']:
if xx['type'] == None:
abnormal_env_files.add(filename)
break
"""
for tempgoalid in goal_dict:
tempgoal = goal_dict[tempgoalid]
#if tempgoal['type'] == None:
# abnormal_proofs.add((filename, tempname))
for temphypo in tempgoal['hypotheses']:
# if temphypo['type'] == None:
# abnormal_proofs.add((filename, tempname))
if len(temphypo['term']) > 1:
special_terms_proofs.add((filename, tempname))
proj = filename.split(os.path.sep)[2]
iter_proofs(common.data_root,
count_proof,
include_synthetic=False,
show_progress=True)
print(special_terms_proofs)
# get the statistics of the proofs
import argparse
import common
from utils import iter_proofs
import pandas as pd
import numpy as np
import re
import pdb
oup = open('short_proofs.txt', 'wt')
def process_proof(filename, proof_data):
if 1 <= len(proof_data['steps']) <= 2:
print(proof_data['steps'][0]['command'][0])
oup.write(proof_data['steps'][0]['command'][0] + '\n')
iter_proofs(common.data_root, process_proof)
