error occur while creating training data

[ACui96]

• my las data location:

• my create script:

python createTrainingData.py --data-name autoWell --data-dir data/McMurray_data/las/00-03-32-080-07W4-0.LAS --output-dir data/train/McMurray_data --log-name GR

• and the result:

(AutomatedWellLogCorrelation) D:\workspace\pycharm\AutomatedWellLogCorrelation>python createTrainingData.py --data-name autoWell --data-dir data\McMurray_data\las\ --output
-dir data\train\McMurray_data
Something broke No objects to concatenate

Has this error occur to you ,can you tell me how to fix it, thanks~!

[ACui96]

I have solve this problem by modify the fllowing code:

files = [os.path.join(self.dataDir, i) for i in files if i.endswith('.LAS')]

but there is new ereor occur:

(AutomatedWellLogCorrelation) D:\workspace\pycharm\AutomatedWellLogCorrelation>python createTrainingData.py --data-name autoWell --data-dir data\McMurray_data\las\ --output
-dir data\train\McMurray_data
D:\ProgramData\Anaconda3\envs\AutomatedWellLogCorrelation\lib\site-packages\sklearn\utils\validation.py:72: FutureWarning: Pass max_patches=10 as keyword args. From version
 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
  "will result in an error", FutureWarning)
not enough values to unpack (expected 2, got 1)
D:\ProgramData\Anaconda3\envs\AutomatedWellLogCorrelation\lib\site-packages\sklearn\utils\validation.py:72: FutureWarning: Pass max_patches=10 as keyword args. From version
 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
  "will result in an error", FutureWarning)
not enough values to unpack (expected 2, got 1)
D:\ProgramData\Anaconda3\envs\AutomatedWellLogCorrelation\lib\site-packages\sklearn\utils\validation.py:72: FutureWarning: Pass max_patches=10 as keyword args. From version
 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
  "will result in an error", FutureWarning)
not enough values to unpack (expected 2, got 1)
...
...

I debuged the code and found that it was caused by the fllowing code, line 113 of file createTrainingData.py:

Parallel(n_jobs=self.cpuCount)(delayed(self.saveLasPatches)(wellGrps.get_group(i), i) for i in lasData['Well'].unique())

can you tell me the possible reason to this error , thanks

[hpratama]

Hi there, I also got this issue! I think the problem is in line 181 where there is a function called "extract_patches". This function is not available on my sklearn version, which is 0.24.2

I solved this issue by looking back to the old sklearn version, you can find the code on this link:

Link

By adding the extract_patches function manually from those links, I can extract the logs to .npy format.

Hope this help :)