Input contains NaN, infinity or a value too large for dtype('float64') in Component Binning Step

[adityabandla]

Hi Ziye,

I'm unable to figure out where the NaN values are being generated. The coverage and kmer frequency files look fine with no fully empty rows or columns. Fails with the following error

2024-02-12 17:39:30,960 - start estimate_bin_number
Traceback (most recent call last):
  File "./component_binning.py", line 476, in <module>
    bin_number = estimate_bin_number(X_t, candK, dataset_scale=dataset_scale, len_weight=length_weight)
  File "./component_binning.py", line 162, in estimate_bin_number
    kmeans.fit(X_mat, sample_weight=len_weight)
  File "3_miniconda3/envs/metabinner/lib/python3.7/site-packages/sklearn/cluster/_kmeans.py", line 859, in fit
    order=order, copy=self.copy_x)
  File "3_miniconda3/envs/metabinner/lib/python3.7/site-packages/sklearn/utils/validation.py", line 578, in check_array
    allow_nan=force_all_finite == 'allow-nan')
  File "3_miniconda3/envs/metabinner/lib/python3.7/site-packages/sklearn/utils/validation.py", line 60, in _assert_all_finite
    msg_dtype if msg_dtype is not None else X.dtype)
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

[ziyewang]

Hi,

Could you please check the coverage and kmer frequency files again (no NaN values and the separated )? I cannot confirm the issues from my end.

Best, Ziye