PEP8 fixes for Gensim

ez_setup.py

@@ -32,19 +32,23 @@
 DEFAULT_VERSION = "1.3.2"
 DEFAULT_URL = "https://pypi.python.org/packages/source/s/setuptools/"
 
+
 def _python_cmd(*args):
     args = (sys.executable,) + args
     return subprocess.call(args) == 0
 
+
 def _check_call_py24(cmd, *args, **kwargs):
     res = subprocess.call(cmd, *args, **kwargs)
+
     class CalledProcessError(Exception):
         pass
     if not res == 0:
         msg = "Command '%s' return non-zero exit status %d" % (cmd, res)
         raise CalledProcessError(msg)
 vars(subprocess).setdefault('check_call', _check_call_py24)
 
+
 def _install(tarball, install_args=()):
     # extracting the tarball
     tmpdir = tempfile.mkdtemp()
@@ -137,11 +141,11 @@ def use_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
         e = sys.exc_info()[1]
         if was_imported:
             sys.stderr.write(
-            "The required version of setuptools (>=%s) is not available,\n"
-            "and can't be installed while this script is running. Please\n"
-            "install a more recent version first, using\n"
-            "'easy_install -U setuptools'."
-            "\n\n(Currently using %r)\n" % (version, e.args[0]))
+                "The required version of setuptools (>=%s) is not available,\n"
+                "and can't be installed while this script is running. Please\n"
+                "install a more recent version first, using\n"
+                "'easy_install -U setuptools'."
+                "\n\n(Currently using %r)\n" % (version, e.args[0]))
             sys.exit(2)
         else:
             del pkg_resources, sys.modules['pkg_resources']    # reload ok
@@ -151,6 +155,7 @@ def use_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
         return _do_download(version, download_base, to_dir,
                             download_delay)
 
+
 def _clean_check(cmd, target):
     """
     Run the command to download target. If the command fails, clean up before
@@ -163,6 +168,7 @@ def _clean_check(cmd, target):
             os.unlink(target)
         raise
 
+
 def download_file_powershell(url, target):
     """
     Download the file at url to target using Powershell (which will validate
@@ -172,10 +178,12 @@ def download_file_powershell(url, target):
     cmd = [
         'powershell',
         '-Command',
-        "(new-object System.Net.WebClient).DownloadFile(%(url)r, %(target)r)" % vars(),
+        "(new-object System.Net.WebClient).DownloadFile(%(url)r, %(target)r)" %
+        vars(),
     ]
     _clean_check(cmd, target)
 
+
 def has_powershell():
     if platform.system() != 'Windows':
         return False
@@ -192,10 +200,12 @@ def has_powershell():
 
 download_file_powershell.viable = has_powershell
 
+
 def download_file_curl(url, target):
     cmd = ['curl', url, '--silent', '--output', target]
     _clean_check(cmd, target)
 
+
 def has_curl():
     cmd = ['curl', '--version']
     devnull = open(os.path.devnull, 'wb')
@@ -210,10 +220,12 @@ def has_curl():
 
 download_file_curl.viable = has_curl
 
+
 def download_file_wget(url, target):
     cmd = ['wget', url, '--quiet', '--output-document', target]
     _clean_check(cmd, target)
 
+
 def has_wget():
     cmd = ['wget', '--version']
     devnull = open(os.path.devnull, 'wb')
@@ -228,6 +240,7 @@ def has_wget():
 
 download_file_wget.viable = has_wget
 
+
 def download_file_insecure(url, target):
     """
     Use Python to download the file, even though it cannot authenticate the
@@ -253,6 +266,7 @@ def download_file_insecure(url, target):
 
 download_file_insecure.viable = lambda: True
 
+
 def get_best_downloader():
     downloaders = [
         download_file_powershell,
@@ -265,6 +279,7 @@ def get_best_downloader():
         if dl.viable():
             return dl
 
+
 def download_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
                         to_dir=os.curdir, delay=15,
                         downloader_factory=get_best_downloader):
@@ -350,6 +365,7 @@ def _build_install_args(options):
         install_args.append('--user')
     return install_args
 
+
 def _parse_args():
     """
     Parse the command line for options
@@ -371,10 +387,12 @@ def _parse_args():
     # positional arguments are ignored
     return options
 
+
 def main(version=DEFAULT_VERSION):
     """Install or upgrade setuptools and EasyInstall"""
     options = _parse_args()
-    tarball = download_setuptools(download_base=options.download_base,
+    tarball = download_setuptools(
+        download_base=options.download_base,
         downloader_factory=options.downloader_factory)
     return _install(tarball, _build_install_args(options))
 

gensim/__init__.py

@@ -7,16 +7,18 @@
 import logging
 
 try:
-    __version__ = __import__('pkg_resources').get_distribution('gensim').version
+    __version__ = __import__(
+        'pkg_resources').get_distribution('gensim').version
 except:
     __version__ = '?'
 
 
 class NullHandler(logging.Handler):
     """For python versions <= 2.6; same as `logging.NullHandler` in 2.7."""
+
     def emit(self, record):
         pass
 
 logger = logging.getLogger('gensim')
-if len(logger.handlers) == 0:	# To ensure reload() doesn't add another one
-    logger.addHandler(NullHandler())
+if len(logger.handlers) == 0:  # To ensure reload() doesn't add another one
+    logger.addHandler(NullHandler())

gensim/corpora/__init__.py

@@ -3,7 +3,8 @@
 """
 
 # bring corpus classes directly into package namespace, to save some typing
-from .indexedcorpus import IndexedCorpus # must appear before the other classes
+# must appear before the other classes
+from .indexedcorpus import IndexedCorpus
 
 from .mmcorpus import MmCorpus
 from .bleicorpus import BleiCorpus

gensim/corpora/bleicorpus.py

@@ -51,11 +51,11 @@ def __init__(self, fname, fname_vocab=None):
             fname_base, _ = path.splitext(fname)
             fname_dir = path.dirname(fname)
             for fname_vocab in [
-                        utils.smart_extension(fname, '.vocab'),
-                        utils.smart_extension(fname, '/vocab.txt'),
-                        utils.smart_extension(fname_base, '.vocab'),
-                        utils.smart_extension(fname_dir, '/vocab.txt'),
-                        ]:
+                utils.smart_extension(fname, '.vocab'),
+                utils.smart_extension(fname, '/vocab.txt'),
+                utils.smart_extension(fname_base, '.vocab'),
+                utils.smart_extension(fname_dir, '/vocab.txt'),
+            ]:
                 if path.exists(fname_vocab):
                     break
             else:
@@ -79,7 +79,9 @@ def __iter__(self):
     def line2doc(self, line):
         parts = utils.to_unicode(line).split()
         if int(parts[0]) != len(parts) - 1:
-            raise ValueError("invalid format in %s: %s" % (self.fname, repr(line)))
+            raise ValueError(
+                "invalid format in %s: %s" %
+                (self.fname, repr(line)))
         doc = [part.rsplit(':', 1) for part in parts[1:]]
         doc = [(int(p1), float(p2)) for p1, p2 in doc]
         return doc
@@ -96,7 +98,8 @@ def save_corpus(fname, corpus, id2word=None, metadata=False):
         call it directly, call `serialize` instead.
         """
         if id2word is None:
-            logger.info("no word id mapping provided; initializing from corpus")
+            logger.info(
+                "no word id mapping provided; initializing from corpus")
             id2word = utils.dict_from_corpus(corpus)
             num_terms = len(id2word)
         else:
@@ -109,14 +112,25 @@ def save_corpus(fname, corpus, id2word=None, metadata=False):
                 doc = list(doc)
                 offsets.append(fout.tell())
                 parts = ["%i:%g" % p for p in doc if abs(p[1]) > 1e-7]
-                fout.write(utils.to_utf8("%i %s\n" % (len(doc), ' '.join(parts))))
+                fout.write(
+                    utils.to_utf8(
+                        "%i %s\n" %
+                        (len(doc), ' '.join(parts))))
 
-        # write out vocabulary, in a format compatible with Blei's topics.py script
+        # write out vocabulary, in a format compatible with Blei's topics.py
+        # script
         fname_vocab = utils.smart_extension(fname, '.vocab')
-        logger.info("saving vocabulary of %i words to %s" % (num_terms, fname_vocab))
+        logger.info(
+            "saving vocabulary of %i words to %s" %
+            (num_terms, fname_vocab))
         with utils.smart_open(fname_vocab, 'wb') as fout:
             for featureid in xrange(num_terms):
-                fout.write(utils.to_utf8("%s\n" % id2word.get(featureid, '---')))
+                fout.write(
+                    utils.to_utf8(
+                        "%s\n" %
+                        id2word.get(
+                            featureid,
+                            '---')))
 
         return offsets
 

gensim/corpora/csvcorpus.py

@@ -45,7 +45,8 @@ def __init__(self, fname, labels):
         head = ''.join(itertools.islice(utils.smart_open(self.fname), 5))
         self.headers = csv.Sniffer().has_header(head)
         self.dialect = csv.Sniffer().sniff(head)
-        logger.info("sniffed CSV delimiter=%r, headers=%s" % (self.dialect.delimiter, self.headers))
+        logger.info("sniffed CSV delimiter=%r, headers=%s" %
+                    (self.dialect.delimiter, self.headers))
 
     def __iter__(self):
         """