Getting ValueError: Found array with 0 sample(s)

[mddoctorcode]

Enjoying trying out your library for my own research, but currently facing a value error issue on my gene expression matrix.
My matrix is in a tsv file (532 rows and 25_000 columns) and formatted according to the input specification in your instructions, here is a small subset with dummy-values:

,A1BG,A1BG-AS1,
patient_1,4.79958059136717,8.50538531670602,
patient_2,4.79958059136717,6.48580010706974,

When running the following code:

from puree import *

p = PUREE()
purities_and_logs = p.get_output(test_data_path="my_gene_file.tsv", gene_id_nomenclature='HGNC')

I get the Value Error shown below:

****Error****
Traceback (most recent call last):
  File "predict_purity.py", line 99, in <module>
    main()
  File "predict_purity.py", line 81, in main
    imputed_values = values_imputer.transform(predictor.data)
  File "/usr/local/lib/python3.8/site-packages/sklearn/impute/_base.py", line 470, in transform
    X = self._validate_input(X, in_fit=False)
  File "/usr/local/lib/python3.8/site-packages/sklearn/impute/_base.py", line 287, in _validate_input
    raise ve
  File "/usr/local/lib/python3.8/site-packages/sklearn/impute/_base.py", line 270, in _validate_input
    X = self._validate_data(
  File "/usr/local/lib/python3.8/site-packages/sklearn/base.py", line 557, in _validate_data
    X = check_array(X, **check_params)
  File "/usr/local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 797, in check_array
    raise ValueError(
ValueError: Found array with 0 sample(s) (shape=(0, 158)) while a minimum of 1 is required.

[erevkov]

Hi, thank you for your interest in PUREE!

Unfortunately, I was not able to reproduce your error exactly - I tried running the method on the small comma-separated 2x2 subset with dummy values you presented above and it worked correctly (i.e. failed with an appropriate error).

One reason why the method might be failing for the tab-separated file is due to the input matrix formatting, in particular due to inconsistent delimiter character. Would you mind double-checking the formatting of your .tsv file (e.g. that it is consistently tab-separated)? Alternatively, could you post a small dummy subset of tab-separated values that fails on your side?