urllib error during B.importGenome in pip version

[erscott]

The pip version of the package generates an FTP error,
"IOError: [Errno ftr error] 200 Switching to Binary Mode", during bootstrap import of at least Human.GRCh37.75.tar.gz.

The traceback indicates line 46 of importation/Genomes.py may be causing the issue.
_getFile function:
line 46: urllib.urlretrieve (fil, finalFile)

The GitHub bloody branch replaces line 46 of importation/Genomes.py with an iterator and seems to resolve this issue.

You might want to update the pip version of pyGeno. Thanks for making this package available under Apache 2.0!

TRACEBACK:

IOError Traceback (most recent call last)
in ()
----> 1 get_ipython().magic(u'time B.importGenome("Human.GRCh37.75.tar.gz")')

/opt/conda/envs/python2/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in magic(self, arg_s)
2156 magic_name, _, magic_arg_s = arg_s.partition(' ')
2157 magic_name = magic_name.lstrip(prefilter.ESC_MAGIC)
-> 2158 return self.run_line_magic(magic_name, magic_arg_s)
2159
2160 #-------------------------------------------------------------------------

/opt/conda/envs/python2/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in run_line_magic(self, magic_name, line)
2077 kwargs['local_ns'] = sys._getframe(stack_depth).f_locals
2078 with self.builtin_trap:
-> 2079 result = fn(*args,**kwargs)
2080 return result
2081

in time(self, line, cell, local_ns)

/opt/conda/envs/python2/lib/python2.7/site-packages/IPython/core/magic.pyc in (f, *a, **k)
186 # but it's overkill for just that one bit of state.
187 def magic_deco(arg):
--> 188 call = lambda f, *a, **k: f(*a, **k)
189
190 if callable(arg):

/opt/conda/envs/python2/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in time(self, line, cell, local_ns)
1179 if mode=='eval':
1180 st = clock2()
-> 1181 out = eval(code, glob, local_ns)
1182 end = clock2()
1183 else:

in ()

/opt/conda/envs/python2/lib/python2.7/site-packages/pyGeno/bootstrap.pyc in importGenome(name, batchSize)
100 """Import a genome shipped with pyGeno. Most of the datawraps only contain URLs towards data provided by third parties."""
101 path = os.path.join(this_dir, "bootstrap_data", "genomes/" + name)
--> 102 PG.importGenome(path, batchSize)
103
104 def importSNPs(name) :

/opt/conda/envs/python2/lib/python2.7/site-packages/pyGeno/importation/Genomes.pyc in importGenome(packageFile, batchSize, verbose)
149 raise KeyError("The directory %s already exists, Please call deleteGenome() first if you want to reinstall" % seqTargetDir)
150
--> 151 gtfFile = _getFile(parser.get('gene_set', 'gtf'), packageDir)
152
153 chromosomesFiles = {}

/opt/conda/envs/python2/lib/python2.7/site-packages/pyGeno/importation/Genomes.pyc in _getFile(fil, directory)
44 printf("Downloading file: %s..." % fil)
45 finalFile = os.path.normpath('%s/%s' %(directory, fil.split('/')[-1]))
---> 46 urllib.urlretrieve (fil, finalFile)
47 printf('done.')
48 else :

/opt/conda/envs/python2/lib/python2.7/urllib.pyc in urlretrieve(url, filename, reporthook, data, context)
96 else:
97 opener = _urlopener
---> 98 return opener.retrieve(url, filename, reporthook, data)
99 def urlcleanup():
100 if _urlopener:

/opt/conda/envs/python2/lib/python2.7/urllib.pyc in retrieve(self, url, filename, reporthook, data)
243 except IOError:
244 pass
--> 245 fp = self.open(url, data)
246 try:
247 headers = fp.info()

/opt/conda/envs/python2/lib/python2.7/urllib.pyc in open(self, fullurl, data)
211 try:
212 if data is None:
--> 213 return getattr(self, name)(url)
214 else:
215 return getattr(self, name)(url, data)

/opt/conda/envs/python2/lib/python2.7/urllib.pyc in open_ftp(self, url)
556 value in ('a', 'A', 'i', 'I', 'd', 'D'):
557 type = value.upper()
--> 558 (fp, retrlen) = self.ftpcache[key].retrfile(file, type)
559 mtype = mimetypes.guess_type("ftp:" + url)[0]
560 headers = ""

/opt/conda/envs/python2/lib/python2.7/urllib.pyc in retrfile(self, file, type)
904 try:
905 cmd = 'RETR ' + file
--> 906 conn, retrlen = self.ftp.ntransfercmd(cmd)
907 except ftplib.error_perm, reason:
908 if str(reason)[:3] != '550':

/opt/conda/envs/python2/lib/python2.7/ftplib.pyc in ntransfercmd(self, cmd, rest)
332 size = None
333 if self.passiveserver:
--> 334 host, port = self.makepasv()
335 conn = socket.create_connection((host, port), self.timeout)
336 try:

/opt/conda/envs/python2/lib/python2.7/ftplib.pyc in makepasv(self)
310 def makepasv(self):
311 if self.af == socket.AF_INET:
--> 312 host, port = parse227(self.sendcmd('PASV'))
313 else:
314 host, port = parse229(self.sendcmd('EPSV'), self.sock.getpeername())

/opt/conda/envs/python2/lib/python2.7/ftplib.pyc in parse227(resp)
828
829 if resp[:3] != '227':
--> 830 raise error_reply, resp
831 global _227_re
832 if _227_re is None:

IOError: [Errno ftp error] 200 Switching to Binary mode.

[tariqdaouda]

Thank you. I was unable to push the current version of pyGeno to PyPi. I might be pulling pyGeno from PyPi for the next versions.

Could you try: pip install git+https://www.github.com/tariqdaouda/pyGeno ?

This version works for me.

[iranmdl]

Hi! I'm getting this error:

pip install git+https://www.github.com/tariqdaouda/pyGeno
Collecting git+https://www.github.com/tariqdaouda/pyGeno
  Cloning https://www.github.com/tariqdaouda/pyGeno to /tmp/pip-LC_Z2e-build
Collecting rabaDB>=1.0.4 (from pyGeno==1.3.1)
  Could not find a version that satisfies the requirement rabaDB>=1.0.4 (from pyGeno==1.3.1) (from versions: 1.0.1, 1.0.2)
No matching distribution found for rabaDB>=1.0.4 (from pyGeno==1.3.1)

[tariqdaouda]

First, can you do: pip install git+https://www.github.com/tariqdaouda/rabaDB ?