CPhasing
CPhasing copied to clipboard
Published
2 months ago
•
wangyibin
wangyibin
expected output type 'Null', got 'Int64'; set `return_dtype` to the proper datatype
老师您好！感谢您发布的CPhasing软件！我最近正在用它测试组装的单倍型基因组，我遇到了一些错误不知道应该怎么解决，还望老师可以给一些建议！ 这是我的运行命令：
export PATH=/media/APP/miniconda3/bin/:$PATH
export PYTHONPATH=/media/APP/python3.12/site-packages:$PYTHONPATH
export PATH=/media/APP/CPhasing/bin:$PATH
export PYTHONPATH=/media/APP/CPhasing:$PYTHONPATH
cphasing pipeline -f genome.fasta -hic1 HiC_1.fq.gz -hic2 HiC_2.fq.gz -t 40 -n 47
我遇到的问题是在第三步：
#----------------------------------#
# Running step 3. hyperpartition #
#----------------------------------#
[19:25:43] INFO Running hyperpartition with `basal(haploid)` cli.py:3952
mode.
INFO Load raw hypergraph from pairs file cli.py:4088
`../HiC.pairs.pqs`
INFO Extract edges from pairs. hypergraph.py:109
INFO Parsing pqs ... pqs.py:669
INFO Filtered the data with mapq >= 1. pqs.py:347
[19:25:56] ERROR expected output type 'Null', got 'Int64'; set cli.py:1189
`return_dtype` to the proper datatype
_RemoteTraceback:
"""
Traceback (most recent call last):
File
"/media/APP/python3.12/site
-packages/joblib/externals/loky/process_executor
.py", line 490, in _process_worker
r = call_item()
File
"/media/APP/python3.12/site
-packages/joblib/externals/loky/process_executor
.py", line 291, in __call__
return self.fn(*self.args, **self.kwargs)
~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
File
"/media/APP/python3.12/site
-packages/joblib/parallel.py", line 607, in
__call__
return [func(*args, **kwargs) for func,
args, kwargs in self.items]
~~~~^^^^^^^^^^^^^^^^^
File
"/media/APP/CPhasing/cphasing/pqs.py",
line 1107, in process_chunk_hg
return chunk.collect()
~~~~~~~~~~~~~^^
File
"/media/APP/python3.12/site
-packages/polars/_utils/deprecation.py", line
97, in wrapper
return function(*args, **kwargs)
File
"/media/APP/python3.12/site
-packages/polars/lazyframe/opt_flags.py", line
328, in wrapper
return function(*args, **kwargs)
File
"/media/APP/python3.12/site
-packages/polars/lazyframe/frame.py", line 2415,
in collect
return wrap_df(ldf.collect(engine,
callback))
~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
polars.exceptions.SchemaError: expected output
type 'Null', got 'Int64'; set `return_dtype` to
the proper datatype
"""
The above exception was the direct cause of the
following exception:
╭───── Traceback (most recent call last) ──────╮
│ /media/APP/CPhasing/cphasing/cli.py:1 │
│ 121 in pipeline │
│ │
│ 1118 │ │
│ 1119 │ today = datetime.now().strftime(" │
│ 1120 │ try: │
│ ❱ 1121 │ │ run(fasta, │
│ 1122 │ │ │ ul_data, │
│ 1123 │ │ │ porec_data, │
│ 1124 │ │ │ porectable, pairs, │
│ │
│ /media/APP/CPhasing/cphasing/pipeline │
│ /pipeline.py:1071 in run │
│ │
│ 1068 │ │ │ _out_sh.write("\n") │
│ 1069 │ │ │
│ 1070 │ │ try: │
│ ❱ 1071 │ │ │ hyperpartition.main(args= │
│ 1072 │ │ │ │ │ │ │ prog_name │
│ 1073 │ │ except SystemExit as e: │
│ 1074 │ │ │ exc_info = sys.exc_info() │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/rich_click/rich_command.py:216 │
│ in main │
│ │
│ 213 │ │ try: │
│ 214 │ │ │ try: │
│ 215 │ │ │ │ with self.make_context │
│ ❱ 216 │ │ │ │ │ rv = self.invoke(c │
│ 217 │ │ │ │ │ if not standalone_ │
│ 218 │ │ │ │ │ │ return rv │
│ 219 │ │ │ │ │ # it's not safe to │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/click/core.py:1246 in invoke │
│ │
│ 1243 │ │ │ echo(style(message, fg="r │
│ 1244 │ │ │
│ 1245 │ │ if self.callback is not None: │
│ ❱ 1246 │ │ │ return ctx.invoke(self.ca │
│ 1247 │ │
│ 1248 │ def shell_complete(self, ctx: Con │
│ 1249 │ │ """Return a list of completio │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/click/core.py:814 in invoke │
│ │
│ 811 │ │ │
│ 812 │ │ with augment_usage_errors(sel │
│ 813 │ │ │ with ctx: │
│ ❱ 814 │ │ │ │ return callback(*args │
│ 815 │ │
│ 816 │ def forward(self, cmd: Command, / │
│ 817 │ │ """Similar to :meth:`invoke` │
│ │
│ /media/APP/CPhasing/cphasing/cli.py:4 │
│ 089 in hyperpartition │
│ │
│ 4086 │ elif pairs: │
│ 4087 │ │ if is_file_changed(hcr_bed) o │
│ Path(hypergraph_path).exists(): │
│ 4088 │ │ │ logger.info(f"Load raw hy │
│ ❱ 4089 │ │ │ he = Extractor(hypergraph │
│ 4090 │ │ │ │ │ │ min_qualit │
│ edge_length=edge_length, │
│ 4091 │ │ │ │ │ │ hcr_invert │
│ 4092 │ │ │ he.save(hypergraph_path) │
│ │
│ /media/APP/CPhasing/cphasing/hypergra │
│ ph.py:95 in __init__ │
│ │
│ 92 │ │ self.log_dir = Path(log_dir) │
│ 93 │ │ self.log_dir.mkdir(parents=Tr │
│ 94 │ │ │
│ ❱ 95 │ │ self.edges = self.generate_ed │
│ 96 │ │
│ 97 │ @staticmethod │
│ 98 │ def _process_df(df, contig_idx, t │
│ │
│ /media/APP/CPhasing/cphasing/hypergra │
│ ph.py:159 in generate_edges │
│ │
│ 156 │ │ │ │ │
│ 157 │ │ │ │ chunks = p.read(min_m │
│ 158 │ │ │ │ │
│ ❱ 159 │ │ │ │ res = p.to_hg_df(chun │
│ 160 │ │ │ │ │ │ │ │ edge │
│ 161 │ │ │ │ │
│ 162 │ │ │ │ if Path(f"{pairs_pref │
│ │
│ /media/APP/CPhasing/cphasing/pqs.py:6 │
│ 75 in to_hg_df │
│ │
│ 672 │ │ for chunk in chunks: │
│ 673 │ │ │ args.append((Path(chunk). │
│ min_mapq, edge_length)) │
│ 674 │ │ │
│ ❱ 675 │ │ results = Parallel(n_jobs=sel │
│ 676 │ │ │ │ │ delayed(process_c │
│ 677 │ │ │ │ ) │
│ 678 │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:2072 in │
│ __call__ │
│ │
│ 2069 │ │ # dispatch of the tasks to th │
│ 2070 │ │ next(output) │
│ 2071 │ │ │
│ ❱ 2072 │ │ return output if self.return_ │
│ 2073 │ │
│ 2074 │ def __repr__(self): │
│ 2075 │ │ return "%s(n_jobs=%s)" % (sel │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:1682 in │
│ _get_outputs │
│ │
│ 1679 │ │ │ yield │
│ 1680 │ │ │ │
│ 1681 │ │ │ with self._backend.retrie │
│ ❱ 1682 │ │ │ │ yield from self._retr │
│ 1683 │ │ │
│ 1684 │ │ except GeneratorExit: │
│ 1685 │ │ │ # The generator has been │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:1784 in │
│ _retrieve │
│ │
│ 1781 │ │ │ # exception (e.g. `Genera │
│ 1782 │ │ │ # worker traceback. │
│ 1783 │ │ │ if self._aborting: │
│ ❱ 1784 │ │ │ │ self._raise_error_fas │
│ 1785 │ │ │ │ break │
│ 1786 │ │ │ │
│ 1787 │ │ │ nb_jobs = len(self._jobs) │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:1859 in │
│ _raise_error_fast │
│ │
│ 1856 │ │ # calling get_result. This jo │
│ 1857 │ │ # called directly or if the g │
│ 1858 │ │ if error_job is not None: │
│ ❱ 1859 │ │ │ error_job.get_result(self │
│ 1860 │ │
│ 1861 │ def _warn_exit_early(self): │
│ 1862 │ │ """Warn the user if the gener │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:758 in │
│ get_result │
│ │
│ 755 │ │ │ # We assume that the resu │
│ 756 │ │ │ # callback thread, and is │
│ 757 │ │ │ # be returned. │
│ ❱ 758 │ │ │ return self._return_or_ra │
│ 759 │ │ │
│ 760 │ │ # For other backends, the mai │
│ 761 │ │ try: │
│ │
│ /media/APP/python3.12/s │
│ ite-packages/joblib/parallel.py:773 in │
│ _return_or_raise │
│ │
│ 770 │ def _return_or_raise(self): │
│ 771 │ │ try: │
│ 772 │ │ │ if self.status == TASK_ER │
│ ❱ 773 │ │ │ │ raise self._result │
│ 774 │ │ │ return self._result │
│ 775 │ │ finally: │
│ 776 │ │ │ del self._result │
╰──────────────────────────────────────────────╯
SchemaError: expected output type 'Null', got
'Int64'; set `return_dtype` to the proper
datatype
希望老师能给一些解决报错的建议，万分感谢！！
你好，实在不好意思太久没关注这个github页面，没有及时回复。我尝试解决了这个bug，发布了新的版本 v0.2.7.beta.r304，希望对你以后再次使用能有帮助。
你好，实在不好意思太久没关注这个github页面，没有及时回复。我尝试解决了这个bug，发布了新的版本
v0.2.7.beta.r304，希望对你以后再次使用能有帮助。
感谢老师答复！我使用v0.2.7.beta.r304重新运行后还是得到一样的报错：
[10:34:28] INFO Running hyperpartition with basal(haploid) cli.py:4080
mode.
INFO Contig length stats: Max=1.25Mb, utilities.py:1514
95th-percentile=1.01Mb, Median=263.71Kb.
INFO Contig length distribution is relatively utilities.py:1526
uniform. Deactivating splitting.
INFO Load raw hypergraph from pairs file cli.py:4242
../HiC.pairs.pqs
INFO Extract edges from pairs. hypergraph.py:110
INFO Parsing pqs ... pqs.py:670
INFO Filtered the data with mapq >= 1. pqs.py:347
[10:35:23] ERROR expected output type 'Null', got 'Int64'; set cli.py:1258
return_dtype to the proper datatype
_RemoteTraceback:
还请老师再帮忙看看是什么问题呢？十分感谢！