petecheng / time2graph Goto Github PK

师兄好！我在运行这个代码时，出现了这个错误，发现是索引值错误，
由于输入数据是50*64，于是将embed_size改为64，但还是不对。发现是由于representation_size赋值给embed_size，但不知在哪修改
具体错误如下：
Traceback (most recent call last):
File "E:\Users\Time2Graph-master\scripts\std_test.py", line 75, in
m.fit(X=x_train, Y=y_train, n_splits=args.n_splits, tuning=False, opt_args=xgb_options)
File "E:\Users\Time2Graph-master\time2graph\core\model.py", line 158, in fit
self.t2g.fit_embedding_model(x=X, y=Y, cache_dir=cache_dir)
File "E:\Users\Time2Graph-master\time2graph\core\model_embeds.py", line 117, in fit_embedding_model
shapelets=self.shapelets, warp=self.warp, init=init)
File "E:\Users\Time2Graph-master\time2graph\core\shapelet_embedding.py", line 157, in fit
cache_dir=self.cache_dir, **self.deepwalk_args)
File "E:\Users\Time2Graph-master\time2graph\core\shapelet_utils.py", line 361, in graph_embedding
ret.append(__embedding2mat(fpath=embedding_path, num_vertices=num_shapelet, embed_size=embed_size))
File "E:\Users\Time2Graph-master\time2graph\core\shapelet_utils.py", line 319, in __embedding2mat
mat[idx, k] = float(line[k + 1])
IndexError: list index out of range

Thanks for sharing! This is my first time coping code from Github so might meet a lot of stupid problems...
As title, I am trying to figure out the issue that it can't find 'module_path' in 'fit' function that was defined in class 'Time2Graph' in model.py. Problem might be appreared the same in run.py.

请问这个是什么原因？谢谢！

python3 scripts/std_test.py

[info]running with {'dataset': 'ucr-Earthquakes', 'n_splits': 5, 'model_cache': False, 'shapelet_cache': False, 'gpu_enable': False}
./dataset/UCRArchive_2018/Earthquakes/Earthquakes_TEST.tsv
[info]training: 0.18 positive ratio with 322
[info]test: 0.25 positive ratio with 139
init model
[info]initialize t2g model with {'kernel': 'xgb', 'kwargs': {'num_segment': 21, 'candidate_method': 'greedy'}, 'K': 50, 'C': 800, 'seg_length': 24, 'warp': 2, 'tflag': True, 'opt_metric': 'accuracy', 'mode': 'embedding', 'batch_size': 100, 'gpu_enable': False, 'percentile': 5, 'shapelets': None, 'sembeds': None, 'clf': None, 'lr': 0.01, 'p': 2, 'alpha': 0.1, 'beta': 0.05, 'multi_graph': False, 'debug': True, 'measurement': 'gdtw', 'verbose': False, 'global_flag': True}
[info]training ucr-Earthquakes_tim2graph_model ...
train model
[info]training embedding model...
[info]initialize ShapeletEmbedding model with ops: {'seg_length': 24, 'tflag': True, 'multi_graph': False, 'cache_dir': '/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/scripts/cache/', 'tanh': False, 'debug': True, 'percentile': 5, 'dist_threshold': -1, 'measurement': 'gdtw', 'mode': 'embedding', 'global_flag': True, 'deepwalk_args': {'num_segment': 21, 'candidate_method': 'greedy'}, 'embed_size': 256, 'embeddings': None}
[info]fit shape: (264, 504, 1)
[info]threshold(5) 0.012702378537505865, mean 0.2733875811100006
[info]15359 edges involved in shapelets graph
[info]embed_size: 256
[info]transition matrix size (1, 50, 50)
[info]run deepwalk with: deepwalk --input /home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/scripts/cache//0.edgelist --format weighted_edgelist --output /home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/scripts/cache//0.embeddings --representation-size 256
[info]embedding threshold 0.012702378537505865
[info]sdist size (322, 21, 50)
Traceback (most recent call last):
File "scripts/std_test.py", line 77, in
m.fit(X=x_train, Y=y_train, n_splits=args.n_splits, tuning=False, opt_args=xgb_options)
File "/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/time2graph/core/model.py", line 163, in fit
x = self.extract_features(X=X, init=self.init)
File "/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/time2graph/core/model.py", line 114, in extract_features
embed = self.t2g.embed(x=X, init=init)
File "/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/time2graph/core/model_embeds.py", line 101, in embed
return self.sembeds.time_series_embedding(time_series_set=x, shapelets=self.shapelets, warp=self.warp, init=init)
File "/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/time2graph/core/shapelet_embedding.py", line 183, in time_series_embedding
multi_graph=self.multi_graph, debug=self.debug, mode=self.mode),
File "/home/wangdong/tool/notebook/jupyter/time2graph/Time2Graph-master/time2graph/core/shapelet_embedding.py", line 80, in time_series_embeds_factory__
raise NotImplementedError('unsupported mode {}'.format(mode))
NotImplementedError: unsupported mode embedding

Thank you for sharing the code, but I have a problem running it, When I run the code with the following command:
"python scripts/run.py --dataset ucr-Earthquakes --K 50 --C 500 --num_segment 21 --seg_length 24 --data_size 1 --embed concate --percentile 5 --gpu_enable"
I get an error:
FileNotFoundError: [Errno 2] No such file or directory: '/home/internship/code/Time2Graph/scripts/cache/ucr-Earthquakes//0.embeddings'

I found this problem in shapelet_utils.py, and I don't see any way to generate this file.

I will be appreciated if you will to help me!

File "D:\Time2Graph\time2graph\utils\mp_utils.py", line 79, in run_slices
monitor.start()
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'parallel_monitor..monitor'

Traceback (most recent call last):
File "", line 1, in
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\Users\Vanellope\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input

Thank you for sharing you code. I found that when I used larger graph data, the MemoryError occured. Could you please help me?

Number of nodes: 183209
Number of walks: 1832090
Data size (walks*length): 73283600
Walking...
Traceback (most recent call last):
File "/search/odin/xxx/anaconda3/envs/push_py27/bin/deepwalk", line 11, in
load_entry_point('deepwalk==1.0.3', 'console_scripts', 'deepwalk')()
File "/search/odin/xxx/anaconda3/envs/push_py27/lib/python2.7/site-packages/deepwalk-1.0.3-py2.7.egg/deepwalk/main.py", line 151, in main
process(args)
File "/search/odin/xxx/anaconda3/envs/push_py27/lib/python2.7/site-packages/deepwalk-1.0.3-py2.7.egg/deepwalk/main.py", line 80, in process
walks = weighted_random_walk.random_walk(G, num_paths=args.number_walks,path_length=args.walk_length, alpha=0)
File "/search/odin/xxx/anaconda3/envs/push_py27/lib/python2.7/site-packages/deepwalk-1.0.3-py2.7.egg/deepwalk/weighted_random_walk.py", line 42, in random_walk
transitionMatrix = getTransitionMatrix(G, nodes)
File "/search/odin/xxx/anaconda3/envs/push_py27/lib/python2.7/site-packages/deepwalk-1.0.3-py2.7.egg/deepwalk/weighted_random_walk.py", line 6, in getTransitionMatrix
matrix = np.zeros([len(nodes), len(nodes)])
MemoryError