Пример #1
0
def get_soft_text():
#     OUTPUT_FILE = WORKDIR() / _fkey() ("get_soft_text.tar.gz")
#     dfc = meta_df_rnaseq()
    BUFFER_ALL = BUFFER_RNASEQ() + BUFFER_CHIPSEQ()

    FORCE = 1

    OUTDIR = WORKDIR()/_fkey()
    shell.real__dir(dirname= OUTDIR)
    
    if not FORCE and shell.file__notEmpty(OUTDIR + '.tar.gz'):
        pass
    else:
        df_figureRegistry().to_csv(OUTDIR / 'figureRegistry.csv',index=0)
        def _worker(sample):
            sample = attrdict.AttrDict(sample)
            sample.title = "_".join([sample[k] for k in "data_acc,age,tissue,genotype,ztime,temperature".split(",")])
            res  = res= pyext.jf2( template_common())
            res = '\n'.join([x.strip() for x in res.splitlines()])
            sample.soft_text = res        
            pyext.printlines([sample.soft_text], OUTDIR / pyext.f("{sample.data_acc}.soft.txt"))
#             %sample.data_acc)

            
        [_worker(sample) for sample in pyext.df__iterdict( meta_df_rnaseq().fillna("NA"))]
        [_worker(sample) for sample in pyext.df__iterdict( meta_df_chipseq().fillna("NA"))]
        with pyext.TempDirScope(getTempDirName=lambda: OUTDIR/'_temp',
                                force=1) as tdir:
            tdir = tdir.d
#         tdir = OUTDIR / '_temp'
            shell.real__dir(dirname= tdir)
#             shell.shellexec(' '.join(["tar" ,"-C",tdir,"-xvzf", INPUTDIR()/"./src/polyq-0830.get_soft_text_jaehoon.tar.gz",]))
#             shell.shellexec(' '.join(["tar" ,"-C",tdir,"-xvzf", INPUTDIR()/"./src/polyq-0905.get_soft_text_Jaehoon0906.tar.gz",]))
    
#             shell.shellexec(' '.join(["tar" ,"-C",tdir,"-xvzf", INPUTDIR()/"./src/polyq-0907.katja.get_soft_text.tar.gz",]))
    
            shell.shellexec(' '.join(["unzip","-d",tdir, "-o",INPUTDIR()/"./src/polyq-0907-jaehoon.get_soft_text.zip", ]))
            for fname in tdir.glob('*.soft.txt'):
                DATA_ACC = fname.basename().replace('.soft.txt','',1)
    #             in df_figureRegistry()['DATA_ACC'].tolist()
                assert DATA_ACC in df_figureRegistry()['DATA_ACC'].tolist(),(DATA_ACC,  "JH0905")
                print('[JH0906]',fname.basename(),)
                pyext.file__link(fname, OUTDIR/fname.basename(),force=1)

            
        CMD = [
            "cd",OUTDIR,
            "&&tar","-cvzf",OUTDIR.realpath()+'.tar.gz',"*",
        ]
        CMD = ' '.join(pyext.stringList__flatten(CMD))
        res = shell.shellexec(CMD)
Пример #2
0
def main():
    temp = template_common()
    samples = meta_df_rnaseq()
    df = samples.fillna('NA')
    samples = pyext.df__iterdict( df)
    samples = list(samples)
    samples = [AttrDict(x) for x in samples]
    # Samples
    from pprint import pprint
#    pprint(samples)

    # print(samples[0])
    for sample in samples:
        sample['rawfile_detail'] = sample_get_rawfile_detail(sample)    
        sample['processing_protocol'] = sample_rnaseq_processing_protocol(sample)
        # processing_rnaseq_brachy(),
        # for sample in samples:
        pprint(sample)
        # pprint(samples)
        res = Template(temp, undefined=StrictUndefined).render(**locals())
        res = Template(res, undefined=StrictUndefined).render(**locals())
        # res = Template(res, undefined=StrictUndefined).render(**locals())
        # res =   pyext.jf2(temp)
        # break
        # res = pyext.jf2(res)
        res = clean(res)
        fn = (WORKDIR()+'.soft_files').makedirs_p()/sample['data_acc']+'.soft.txt'
        with io.open( fn,'w',encoding='utf8') as f:
            f.write(res)
            # print(res)
        # break
    # print(template_common())
    pass
Пример #3
0
def sample_init_full():
    its = [
        pyext.df__iterdict( meta_df_chipseq().fillna("NA")),
        pyext.df__iterdict( meta_df_rnaseq().fillna("NA")),
                           ]
    it = sum(map(list,its),[])
                               
                           
# #     it = pyext.df__iterdict( meta_df_rnaseq().fillna("NA"))
#     it =( list(pyext.df__iterdict( meta_df_chipseq().fillna("NA")))
#     +  list(pyext.df__iterdict( meta_df_rnaseq().fillna("NA")) ))
    def _worker(sample):
        sample = attrdict.AttrDict(sample)
        sample.title = "_".join([sample[k] for k in "data_acc,age,tissue,genotype,ztime,temperature".split(",")])
        return sample
    
    return map(_worker, it)