search

kordk / torch-ecpg

(GPU accelerated) eCpG mapper
BSD 3-Clause "New" or "Revised" License
2 stars 0 forks source link

mlr --cis: TypeError: can't convert np.ndarray of type numpy.object_ #34

Closed rituroy closed 1 year ago

rituroy commented 1 year ago

Using GTP data with tab delimited annotation files.

pwd /songlab/proj/cbi/torch_ecpg/simulation

/usr/bin/time -v tecpg run mlr --cis --p-only -g 200 -m 100000 /data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/cli.py:274: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support sep=None with delim_whitespace=False; you can avoid this warning by specifying engine='python'. M_annot = pandas.read_csv( /data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/cli.py:277: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support sep=None with delim_whitespace=False; you can avoid this warning by specifying engine='python'. G_annot = pandas.read_csv( [INFO] CUDA GPU detected. This device supports CUDA. [INFO] Reading 3 dataframes... [INFOTIMER] Reading 1/3: C.csv [INFO] Reading csv file /data/songlab/proj/cbi/torch_ecpg/simulation/data/C.csv with separator , [INFOTIMER] Read 1/3 in 0.0059 seconds [INFOTIMER] Reading 2/3: M.csv [INFO] Reading csv file /data/songlab/proj/cbi/torch_ecpg/simulation/data/M.csv with separator , [INFOTIMER] Read 2/3 in 26.8031 seconds [INFOTIMER] Reading 3/3: G.csv [INFO] Reading csv file /data/songlab/proj/cbi/torch_ecpg/simulation/data/G.csv with separator , [INFOTIMER] Read 3/3 in 1.2176 seconds [INFOTIMER] Finished reading 3 dataframes in 28.0269 seconds. [INFO] No region window provided. Resorting to default. [INFO] Using default window for cis of 1000000 bases [INFO] Initializing regression variables [INFO] Use CPU not supplied. Checking if CUDA is available. [INFO] Using CUDA [INFO] Running with 336 degrees of freedom [INFO] Initializing output directory [INFO] Removing directory /data/songlab/proj/cbi/torch_ecpg/simulation/output... [INFO] Creating directory /data/songlab/proj/cbi/torch_ecpg/simulation/output... Traceback (most recent call last): File "/home/ritu/anaconda3/envs/py310/bin/tecpg", line 33, in sys.exit(load_entry_point('tecpg', 'console_scripts', 'tecpg')()) File "/home/ritu/anaconda3/envs/py310/bin/tecpg", line 25, in importlib_load_entry_point return next(matches).load() File "/home/ritu/anaconda3/envs/py310/lib/python3.10/importlib/metadata/init.py", line 171, in load module = import_module(match.group('module')) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/importlib/init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "/data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/main.py", line 9, in main() File "/data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/main.py", line 6, in main start() File "/data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/cli.py", line 752, in start cli(obj={}) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 1130, in call return self.main(args, kwargs) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 1055, in main rv = self.invoke(ctx) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 1657, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 1657, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 1404, in invoke return ctx.invoke(self.callback, ctx.params) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/core.py", line 760, in invoke return __callback(args, kwargs) File "/home/ritu/anaconda3/envs/py310/lib/python3.10/site-packages/click/decorators.py", line 26, in new_func return f(get_current_context(), *args, *kwargs) File "/data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/cli.py", line 302, in mlr output = regression_full(args, logger) File "/data/songlab/proj/cbi/torch_ecpg/torch-ecpg/tecpg/regression_full.py", line 139, in regression_full G_chrom_t = torch.tensor(Gchrom, device=device, dtype=torch.int) TypeError: can't convert np.ndarray of type numpy.object. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool.

liamgd commented 1 year ago

The GTP annotation files contain NA values and have type issues with the chrom and pos numpy arrays.

This should be fixed in f076121 which sets the type of the numpy arrays to int and drops NA values, dropping the corresponding methylation and gene expression ids.