parent
9b06ce3840
commit
c1e07eabb6
@ -1,21 +0,0 @@
|
||||
import csv
|
||||
|
||||
import pandas as pd
|
||||
import json
|
||||
import sentence_transformers.util
|
||||
import torch
|
||||
from sentence_transformers import SentenceTransformer
|
||||
from torch import nn
|
||||
|
||||
if __name__ == '__main__':
|
||||
directory = r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-ACM_dirty'
|
||||
train = pd.read_csv(directory + r'\train.csv', encoding='ISO-8859-1')
|
||||
valid = pd.read_csv(directory + r'\valid.csv', encoding='ISO-8859-1')
|
||||
test = pd.read_csv(directory + r'\test.csv', encoding='ISO-8859-1')
|
||||
train = train[train['label'] == 1]
|
||||
valid = valid[valid['label'] == 1]
|
||||
test = test[test['label'] == 1]
|
||||
matches = pd.concat([train, valid, test])
|
||||
matches.drop(columns=['label'], inplace=True)
|
||||
matches = matches.sort_values(by='ltable_id')
|
||||
matches.to_csv(directory + r'\matches.csv', sep=',', index=False, header=True)
|
||||
@ -1,27 +0,0 @@
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
if __name__ == '__main__':
|
||||
lt = pd.read_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\tmdb.csv',
|
||||
encoding='ISO-8859-1', sep=',')
|
||||
rt = pd.read_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\tvdb.csv',
|
||||
encoding='ISO-8859-1', sep=',')
|
||||
mapping = pd.read_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\gt.csv',
|
||||
encoding='ISO-8859-1', sep=',')
|
||||
# 删除列
|
||||
# lt.drop(columns=['numberOfSeasons', 'numberOfEpisodes', 'birthDate', 'last_air_date', 'release_year', 'runtime',
|
||||
# 'genre_list', 'origin_country'], inplace=True)
|
||||
# rt.drop(columns=['job'], inplace=True)
|
||||
# 列名调整
|
||||
# rt = rt.rename(columns={'birthDate': 'birthYear', 'release_year': 'startYear',
|
||||
# 'last_air_date': 'endYear', 'runtime': 'runtimeMinutes'})
|
||||
# 列顺序调整
|
||||
# rt = rt[['id', 'title', 'name', 'episodeNumber', 'seasonNumber', 'birthYear', 'endYear', 'startYear', 'genre_list',
|
||||
# 'runtimeMinutes']]
|
||||
# lt.to_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\tmdb.csv', sep=',', index=False, header=True, quoting=1)
|
||||
# rt.to_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\tvdb.csv', sep=',', index=False, header=True, quoting=1)
|
||||
# mapping.to_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\TMDB-TVDB\gt.csv',
|
||||
# sep=',', index=False, header=True, quoting=1)
|
||||
print(1)
|
||||
|
||||
|
||||
@ -1,13 +0,0 @@
|
||||
import pandas as pd
|
||||
from sentence_transformers import SentenceTransformer
|
||||
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForTableQuestionAnswering
|
||||
|
||||
if __name__ == '__main__':
|
||||
path = r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-ACM\tableA.csv'
|
||||
table = pd.read_csv(path, low_memory=False, encoding='ISO-8859-1')
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(r'E:\Data\Research\Models\tapas-large-finetuned-wtq')
|
||||
model = AutoModelForTableQuestionAnswering.from_pretrained(r'E:\Data\Research\Models\tapas-large-finetuned-wtq')
|
||||
encoding = tokenizer(table, return_tensors="pt")
|
||||
embedding = tokenizer.encode(table, return_tensors="pt")
|
||||
print(1)
|
||||
@ -1,159 +0,0 @@
|
||||
import json
|
||||
import multiprocessing
|
||||
import os
|
||||
import time
|
||||
|
||||
import ConfigSpace
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import torch
|
||||
from tqdm import tqdm
|
||||
from ConfigSpace.read_and_write import json as csj
|
||||
from md_discovery import discovery_executor
|
||||
from settings import er_output_dir, hpo_output_dir
|
||||
|
||||
|
||||
def fuck(i):
|
||||
i = i * i + 1
|
||||
|
||||
|
||||
def test1():
|
||||
li = [[[6, 6, 2],
|
||||
[2, 4, 6],
|
||||
[2, 4, 7],
|
||||
[3, 6, 4]],
|
||||
[[6, 2, 7],
|
||||
[3, 2, 4],
|
||||
[5, 3, 5],
|
||||
[6, 2, 4]],
|
||||
[[7, 2, 2],
|
||||
[6, 3, 2],
|
||||
[6, 4, 3],
|
||||
[6, 5, 6]]]
|
||||
tensor = torch.Tensor(li)
|
||||
norm_tensor = torch.nn.functional.normalize(tensor, dim=2)
|
||||
print(norm_tensor, '\n')
|
||||
sim_ten = torch.matmul(norm_tensor, norm_tensor.transpose(1, 2))
|
||||
print(sim_ten / 2 + 0.5, '\n')
|
||||
print(sim_ten.size())
|
||||
|
||||
|
||||
def test2():
|
||||
multiprocessing.set_start_method("spawn")
|
||||
manager = multiprocessing.Manager()
|
||||
lock = manager.Lock()
|
||||
pool = multiprocessing.Pool(16)
|
||||
with manager:
|
||||
for _ in tqdm(range(0, 1000)):
|
||||
result = pool.apply_async(fuck, args=(_,))
|
||||
print(result)
|
||||
|
||||
|
||||
def test3():
|
||||
dic = {'description': 0, 'id': 1, 'manufacturer': 0, 'name': 0.9309734582901001, 'price': 0.912541675567627}
|
||||
ll = list(dic.values())
|
||||
ten = torch.Tensor(ll)
|
||||
t = ten.unsqueeze(1)
|
||||
t = t.unsqueeze(2)
|
||||
y = t.repeat(1, 742, 742)
|
||||
print(ten)
|
||||
print(y)
|
||||
print(torch.isfinite(ten))
|
||||
print(torch.count_nonzero(y).item())
|
||||
|
||||
|
||||
def test4():
|
||||
one_bool_tensor = torch.ones((3, 3, 3), dtype=torch.bool)
|
||||
print(torch.count_nonzero(one_bool_tensor).item())
|
||||
|
||||
|
||||
def test5():
|
||||
ten1 = torch.tensor([[1, 2, 3],
|
||||
[7, 8, 9]])
|
||||
ten2 = torch.tensor([[4, 5, 6],
|
||||
[11, 12, 15]])
|
||||
result = ten1 * ten2
|
||||
r = torch.sum(result, 1)
|
||||
print('\n')
|
||||
print(result)
|
||||
print(r)
|
||||
|
||||
|
||||
def test6():
|
||||
table_tensor = torch.tensor([[[1., 2., 3.],
|
||||
[4., 5., 6.],
|
||||
[7., 8., 9.]],
|
||||
[[1., 2., 3.],
|
||||
[4., 5., 6.],
|
||||
[7., 8., 9.]]])
|
||||
t = torch.tensor([[1., 2., 3.],
|
||||
[4., 5., 6.]])
|
||||
norm1 = torch.nn.functional.normalize(table_tensor, dim=1)
|
||||
norm2 = torch.nn.functional.normalize(table_tensor, dim=2)
|
||||
print('\n')
|
||||
print(norm1)
|
||||
print(norm2)
|
||||
print(t.shape)
|
||||
|
||||
|
||||
def test7():
|
||||
iterations = 1
|
||||
filename_list = os.listdir(er_output_dir)
|
||||
if len(filename_list) > 0:
|
||||
for _ in filename_list:
|
||||
if _.startswith('eval_result'):
|
||||
iterations = int(_[12:13]) + 1
|
||||
print(iterations)
|
||||
|
||||
|
||||
def test8():
|
||||
with open(hpo_output_dir + "configspace.json", 'r') as load_f:
|
||||
dict_configspace = json.load(load_f)
|
||||
str_configspace = json.dumps(dict_configspace)
|
||||
configspace = csj.read(str_configspace)
|
||||
|
||||
|
||||
def test9():
|
||||
df = pd.read_json(r'./datasets/t.json', encoding='ISO-8859-1', lines=True)
|
||||
df.to_csv(r'./datasets/s.csv')
|
||||
d = pd.read_csv(r'./datasets/s.csv', encoding='ISO-8859-1')
|
||||
print(1)
|
||||
|
||||
|
||||
def test10():
|
||||
rtable = pd.read_csv(r'E:\Data\Research\Projects\matching_dependency\ml_er\output\predictions.csv',
|
||||
encoding='ISO-8859-1')
|
||||
print(1)
|
||||
rtable.columns = ["id", "title", "authors", "venue", "year"]
|
||||
rtable.to_csv(r'E:\Data\Research\Projects\matching_dependency\datasets\DBLP-GoogleScholar\tableB.csv',
|
||||
sep=',', index=False, header=True, quoting=1)
|
||||
|
||||
|
||||
def test11():
|
||||
values = {
|
||||
'block_attr': 'class',
|
||||
'confidence_thresh': 0.2717823249253852,
|
||||
'ml_blocker': 'attr_equiv',
|
||||
'ml_matcher': 'ln',
|
||||
'similarity_thresh': 0.20681820299103484,
|
||||
'support_thresh': 129,
|
||||
}
|
||||
with open(hpo_output_dir + "incumbent.json", "w") as f:
|
||||
json.dump(values, f, indent=4)
|
||||
|
||||
|
||||
def test12():
|
||||
with open(hpo_output_dir + "incumbent.json", 'r') as f:
|
||||
dic = json.load(f)
|
||||
for _ in dic.keys():
|
||||
print(f'Key:{_}\tValue:{dic[_]}\tType:{type(dic[_])}')
|
||||
|
||||
|
||||
def test13():
|
||||
outcome_dir = r'E:\Data\Research\Outcome'
|
||||
configs_dir = r'\Magellan+Smac+roberta-large-nli-stsb-mean-tokens'
|
||||
datasets_list = os.listdir(outcome_dir)
|
||||
f = []
|
||||
for _ in datasets_list:
|
||||
f.append(outcome_dir + rf'\{_}' + configs_dir)
|
||||
print(f)
|
||||
Loading…
Reference in new issue