BUG about the dataset

[ShenAoChen2001]

I have downloaded the avazu from the superlink in your github https://www.kaggle.com/c/avazu-ctr-prediction/data?select=train.gz.

then i run avazu_parse.py

the error appeared

[ShenAoChen2001]

D:\anaconda3\envs\dl\python.exe "D:\pycharm\PyCharm 2022.1.4\plugins\python\helpers\pydev\pydevd.py" --multiprocess --qt-support=auto --client 127.0.0.1 --port 59523 --file C:/Users/14760/Desktop/Code/EulerNet-main/DataSource/avazu_parse.py Connected to pydev debugger (build 221.6008.17) 100%|██████████| 100/100 [01:24<00:00, 1.19it/s] 9%|▊ | 2/23 [01:38<17:12, 49.19s/it] Traceback (most recent call last): File "D:\pycharm\PyCharm 2022.1.4\plugins\python\helpers\pydev\pydevd.py", line 1491, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\pycharm\PyCharm 2022.1.4\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "C:/Users/14760/Desktop/Code/EulerNet-main/DataSource/avazu_parse.py", line 67, in for key, val in lst.items(): RuntimeError: dictionary changed size during iteration

[Ethan-TZ]

@ShenAoChen2001 Hello, thanks for your attention to my work. It's possible that the version of the dataset you downloaded is incorrect. I have shared my source files, and you can download them from the following link. Avazu

[ShenAoChen2001]

@ShenAoChen2001 Hello, thanks for your attention to my work. It's possible that the version of the dataset you downloaded is incorrect. I have shared my source files, and you can download them from the following link. Avazu

thanks for your reply，the bug is not be solved，because the code for lst in tqdm(feat_list): idx = 1 for key, val in lst.items(): if val < thres: del lst[key] else: lst[key] = idx idx += 1

you delete the element.

I want to know can you run avazu_parse.py in your enviroment?

[Ethan-TZ]

@ShenAoChen2001 Yes, we follow the FmFM's script to process the dataset.

[ShenAoChen2001]

@ShenAoChen2001 Yes, we follow the FmFM's script to process the dataset.

好吧，我再看看咋回事。我还有一个问题python train.py --config_files=[dataset].yaml这句话里面的yaml文件是metaData文件里面的yaml么。

[Ethan-TZ]

@ShenAoChen2001 Yes. Additionally, I provide the processed dataset download at Here. You should put it into the /Cache folder, and run the code.