Skip to content

Commit

Permalink
WIP: debugging sqlite errors
Browse files Browse the repository at this point in the history
  • Loading branch information
@piskvorky
piskvorky committed Dec 2, 2011
0 parents commit 3725dfa
Show file tree
Hide file tree
Showing 8 changed files with 1,666 additions and 0 deletions.
63 changes: 63 additions & 0 deletions README.rst
@@ -0,0 +1,63 @@
==============================================
gensim -- Python Framework for Topic Modelling
==============================================



Gensim is a Python library for *Vector Space Modelling* with very large corpora.
Target audience is the *Natural Language Processing* (NLP) community.


Features
---------

* All algorithms are **memory-independent** w.r.t. the corpus size (can process input larger than RAM),
* **Intuitive interfaces**

* easy to plug in your own input corpus/datastream (trivial streaming API)
* easy to extend with other Vector Space algorithms (trivial transformation API)

* Efficient implementations of popular algorithms, such as online **Latent Semantic Analysis**,
**Latent Dirichlet Allocation** or **Random Projections**
* **Distributed computing**: can run *Latent Semantic Analysis* and *Latent Dirichlet Allocation* on a cluster of computers.
* Extensive `HTML documentation and tutorials <http://radimrehurek.com/gensim/>`_.


If this feature list left you scratching your head, you can first read more about the `Vector
Space Model <http://en.wikipedia.org/wiki/Vector_space_model>`_ and `unsupervised
document analysis <http://en.wikipedia.org/wiki/Latent_semantic_indexing>`_ on Wikipedia.

Installation
------------

This software depends on `NumPy and Scipy <http://www.scipy.org/Download>`_, two Python packages for scientific computing.
You must have them installed prior to installing `gensim`.

The simple way to install `gensim` is::

sudo easy_install gensim

Or, if you have instead downloaded and unzipped the `source tar.gz <http://pypi.python.org/pypi/gensim>`_ package,
you'll need to run::

python setup.py test
sudo python setup.py install


For alternative modes of installation (without root priviledges, development
installation, optional install features), see the `documentation <http://radimrehurek.com/gensim/install.html>`_.

This version has been tested under Python 2.5 and 2.6, but should run on any 2.5 <= Python < 3.0.

Documentation
-------------

Manual for the gensim package is available in `HTML <http://radimrehurek.com/gensim/>`_. It
contains a walk-through of all its features and a complete reference section.
It is also included in the source distribution package.

----------------

Gensim is open source software, and has been released under the
`GNU LGPL license <http://www.gnu.org/licenses/lgpl.html>`_.
Copyright (c) 2011 Radim Rehurek
284 changes: 284 additions & 0 deletions ez_setup.py
@@ -0,0 +1,284 @@
#!python
"""Bootstrap setuptools installation
If you want to use setuptools in your package's setup.py, just include this
file in the same directory with it, and add this to the top of your setup.py::
from ez_setup import use_setuptools
use_setuptools()
If you want to require a specific version of setuptools, set a download
mirror, or use an alternate download directory, you can do so by supplying
the appropriate options to ``use_setuptools()``.
This file can also be run as a script to install or upgrade setuptools.
"""
import sys
DEFAULT_VERSION = "0.6c11"
DEFAULT_URL = "http://pypi.python.org/packages/%s/s/setuptools/" % sys.version[:3]

md5_data = {
'setuptools-0.6b1-py2.3.egg': '8822caf901250d848b996b7f25c6e6ca',
'setuptools-0.6b1-py2.4.egg': 'b79a8a403e4502fbb85ee3f1941735cb',
'setuptools-0.6b2-py2.3.egg': '5657759d8a6d8fc44070a9d07272d99b',
'setuptools-0.6b2-py2.4.egg': '4996a8d169d2be661fa32a6e52e4f82a',
'setuptools-0.6b3-py2.3.egg': 'bb31c0fc7399a63579975cad9f5a0618',
'setuptools-0.6b3-py2.4.egg': '38a8c6b3d6ecd22247f179f7da669fac',
'setuptools-0.6b4-py2.3.egg': '62045a24ed4e1ebc77fe039aa4e6f7e5',
'setuptools-0.6b4-py2.4.egg': '4cb2a185d228dacffb2d17f103b3b1c4',
'setuptools-0.6c1-py2.3.egg': 'b3f2b5539d65cb7f74ad79127f1a908c',
'setuptools-0.6c1-py2.4.egg': 'b45adeda0667d2d2ffe14009364f2a4b',
'setuptools-0.6c10-py2.3.egg': 'ce1e2ab5d3a0256456d9fc13800a7090',
'setuptools-0.6c10-py2.4.egg': '57d6d9d6e9b80772c59a53a8433a5dd4',
'setuptools-0.6c10-py2.5.egg': 'de46ac8b1c97c895572e5e8596aeb8c7',
'setuptools-0.6c10-py2.6.egg': '58ea40aef06da02ce641495523a0b7f5',
'setuptools-0.6c11-py2.3.egg': '2baeac6e13d414a9d28e7ba5b5a596de',
'setuptools-0.6c11-py2.4.egg': 'bd639f9b0eac4c42497034dec2ec0c2b',
'setuptools-0.6c11-py2.5.egg': '64c94f3bf7a72a13ec83e0b24f2749b2',
'setuptools-0.6c11-py2.6.egg': 'bfa92100bd772d5a213eedd356d64086',
'setuptools-0.6c2-py2.3.egg': 'f0064bf6aa2b7d0f3ba0b43f20817c27',
'setuptools-0.6c2-py2.4.egg': '616192eec35f47e8ea16cd6a122b7277',
'setuptools-0.6c3-py2.3.egg': 'f181fa125dfe85a259c9cd6f1d7b78fa',
'setuptools-0.6c3-py2.4.egg': 'e0ed74682c998bfb73bf803a50e7b71e',
'setuptools-0.6c3-py2.5.egg': 'abef16fdd61955514841c7c6bd98965e',
'setuptools-0.6c4-py2.3.egg': 'b0b9131acab32022bfac7f44c5d7971f',
'setuptools-0.6c4-py2.4.egg': '2a1f9656d4fbf3c97bf946c0a124e6e2',
'setuptools-0.6c4-py2.5.egg': '8f5a052e32cdb9c72bcf4b5526f28afc',
'setuptools-0.6c5-py2.3.egg': 'ee9fd80965da04f2f3e6b3576e9d8167',
'setuptools-0.6c5-py2.4.egg': 'afe2adf1c01701ee841761f5bcd8aa64',
'setuptools-0.6c5-py2.5.egg': 'a8d3f61494ccaa8714dfed37bccd3d5d',
'setuptools-0.6c6-py2.3.egg': '35686b78116a668847237b69d549ec20',
'setuptools-0.6c6-py2.4.egg': '3c56af57be3225019260a644430065ab',
'setuptools-0.6c6-py2.5.egg': 'b2f8a7520709a5b34f80946de5f02f53',
'setuptools-0.6c7-py2.3.egg': '209fdf9adc3a615e5115b725658e13e2',
'setuptools-0.6c7-py2.4.egg': '5a8f954807d46a0fb67cf1f26c55a82e',
'setuptools-0.6c7-py2.5.egg': '45d2ad28f9750e7434111fde831e8372',
'setuptools-0.6c8-py2.3.egg': '50759d29b349db8cfd807ba8303f1902',
'setuptools-0.6c8-py2.4.egg': 'cba38d74f7d483c06e9daa6070cce6de',
'setuptools-0.6c8-py2.5.egg': '1721747ee329dc150590a58b3e1ac95b',
'setuptools-0.6c9-py2.3.egg': 'a83c4020414807b496e4cfbe08507c03',
'setuptools-0.6c9-py2.4.egg': '260a2be2e5388d66bdaee06abec6342a',
'setuptools-0.6c9-py2.5.egg': 'fe67c3e5a17b12c0e7c541b7ea43a8e6',
'setuptools-0.6c9-py2.6.egg': 'ca37b1ff16fa2ede6e19383e7b59245a',
}

import sys, os
try: from hashlib import md5
except ImportError: from md5 import md5

def _validate_md5(egg_name, data):
if egg_name in md5_data:
digest = md5(data).hexdigest()
if digest != md5_data[egg_name]:
print >>sys.stderr, (
"md5 validation of %s failed! (Possible download problem?)"
% egg_name
)
sys.exit(2)
return data

def use_setuptools(
version=DEFAULT_VERSION, download_base=DEFAULT_URL, to_dir=os.curdir,
download_delay=15
):
"""Automatically find/download setuptools and make it available on sys.path
`version` should be a valid setuptools version number that is available
as an egg for download under the `download_base` URL (which should end with
a '/'). `to_dir` is the directory where setuptools will be downloaded, if
it is not already available. If `download_delay` is specified, it should
be the number of seconds that will be paused before initiating a download,
should one be required. If an older version of setuptools is installed,
this routine will print a message to ``sys.stderr`` and raise SystemExit in
an attempt to abort the calling script.
"""
was_imported = 'pkg_resources' in sys.modules or 'setuptools' in sys.modules
def do_download():
egg = download_setuptools(version, download_base, to_dir, download_delay)
sys.path.insert(0, egg)
import setuptools; setuptools.bootstrap_install_from = egg
try:
import pkg_resources
except ImportError:
return do_download()
try:
pkg_resources.require("setuptools>="+version); return
except pkg_resources.VersionConflict, e:
if was_imported:
print >>sys.stderr, (
"The required version of setuptools (>=%s) is not available, and\n"
"can't be installed while this script is running. Please install\n"
" a more recent version first, using 'easy_install -U setuptools'."
"\n\n(Currently using %r)"
) % (version, e.args[0])
sys.exit(2)
else:
del pkg_resources, sys.modules['pkg_resources'] # reload ok
return do_download()
except pkg_resources.DistributionNotFound:
return do_download()

def download_setuptools(
version=DEFAULT_VERSION, download_base=DEFAULT_URL, to_dir=os.curdir,
delay = 15
):
"""Download setuptools from a specified location and return its filename
`version` should be a valid setuptools version number that is available
as an egg for download under the `download_base` URL (which should end
with a '/'). `to_dir` is the directory where the egg will be downloaded.
`delay` is the number of seconds to pause before an actual download attempt.
"""
import urllib2, shutil
egg_name = "setuptools-%s-py%s.egg" % (version,sys.version[:3])
url = download_base + egg_name
saveto = os.path.join(to_dir, egg_name)
src = dst = None
if not os.path.exists(saveto): # Avoid repeated downloads
try:
from distutils import log
if delay:
log.warn("""
---------------------------------------------------------------------------
This script requires setuptools version %s to run (even to display
help). I will attempt to download it for you (from
%s), but
you may need to enable firewall access for this script first.
I will start the download in %d seconds.
(Note: if this machine does not have network access, please obtain the file
%s
and place it in this directory before rerunning this script.)
---------------------------------------------------------------------------""",
version, download_base, delay, url
); from time import sleep; sleep(delay)
log.warn("Downloading %s", url)
src = urllib2.urlopen(url)
# Read/write all in one block, so we don't create a corrupt file
# if the download is interrupted.
data = _validate_md5(egg_name, src.read())
dst = open(saveto,"wb"); dst.write(data)
finally:
if src: src.close()
if dst: dst.close()
return os.path.realpath(saveto)




































def main(argv, version=DEFAULT_VERSION):
"""Install or upgrade setuptools and EasyInstall"""
try:
import setuptools
except ImportError:
egg = None
try:
egg = download_setuptools(version, delay=0)
sys.path.insert(0,egg)
from setuptools.command.easy_install import main
return main(list(argv)+[egg]) # we're done here
finally:
if egg and os.path.exists(egg):
os.unlink(egg)
else:
if setuptools.__version__ == '0.0.1':
print >>sys.stderr, (
"You have an obsolete version of setuptools installed. Please\n"
"remove it from your system entirely before rerunning this script."
)
sys.exit(2)

req = "setuptools>="+version
import pkg_resources
try:
pkg_resources.require(req)
except pkg_resources.VersionConflict:
try:
from setuptools.command.easy_install import main
except ImportError:
from easy_install import main
main(list(argv)+[download_setuptools(delay=0)])
sys.exit(0) # try to force an exit
else:
if argv:
from setuptools.command.easy_install import main
main(argv)
else:
print "Setuptools version",version,"or greater has been installed."
print '(Run "ez_setup.py -U setuptools" to reinstall or upgrade.)'

def update_md5(filenames):
"""Update our built-in md5 registry"""

import re

for name in filenames:
base = os.path.basename(name)
f = open(name,'rb')
md5_data[base] = md5(f.read()).hexdigest()
f.close()

data = [" %r: %r,\n" % it for it in md5_data.items()]
data.sort()
repl = "".join(data)

import inspect
srcfile = inspect.getsourcefile(sys.modules[__name__])
f = open(srcfile, 'rb'); src = f.read(); f.close()

match = re.search("\nmd5_data = {\n([^}]+)}", src)
if not match:
print >>sys.stderr, "Internal error!"
sys.exit(2)

src = src[:match.start(1)] + repl + src[match.end(1):]
f = open(srcfile,'w')
f.write(src)
f.close()


if __name__=='__main__':
if len(sys.argv)>2 and sys.argv[1]=='--md5update':
update_md5(sys.argv[2:])
else:
main(sys.argv[1:])






0 comments on commit 3725dfa

Please sign in to comment.