[WIP] Do not import the sklearn package from setup.py

.gitignore

@@ -52,3 +52,6 @@ benchmarks/bench_covertype_data/
 *.prefs
 .pydevproject
 .idea
+
+# Generated when running setup.py
+sklearn/version.py

setup.py

@@ -8,8 +8,26 @@
 import sys
 import os
 import shutil
+import subprocess
 from distutils.command.clean import clean as Clean
 
+
+DISTNAME = 'scikit-learn'
+DESCRIPTION = 'A set of python modules for machine learning and data mining'
+LONG_DESCRIPTION = open('README.rst').read()
+MAINTAINER = 'Andreas Mueller'
+MAINTAINER_EMAIL = 'amueller@ais.uni-bonn.de'
+URL = 'http://scikit-learn.org'
+LICENSE = 'new BSD'
+DOWNLOAD_URL = 'http://sourceforge.net/projects/scikit-learn/files/'
+
+MAJOR               = 0
+MINOR               = 15
+MICRO               = 0
+ISRELEASED          = False
+VERSION             = '%d.%d.%d' % (MAJOR, MINOR, MICRO)
+
+
 if sys.version_info[0] < 3:
     import __builtin__ as builtins
 else:
@@ -20,20 +38,71 @@
 # avoid attempting to load components that aren't built yet.
 builtins.__SKLEARN_SETUP__ = True
 
-DISTNAME = 'scikit-learn'
-DESCRIPTION = 'A set of python modules for machine learning and data mining'
-LONG_DESCRIPTION = open('README.rst').read()
-MAINTAINER = 'Andreas Mueller'
-MAINTAINER_EMAIL = 'amueller@ais.uni-bonn.de'
-URL = 'http://scikit-learn.org'
-LICENSE = 'new BSD'
-DOWNLOAD_URL = 'http://sourceforge.net/projects/scikit-learn/files/'
+# Return the git revision as a string
+def git_version():
+    def _minimal_ext_cmd(cmd):
+        # construct minimal environment
+        env = {}
+        for k in ['SYSTEMROOT', 'PATH']:
+            v = os.environ.get(k)
+            if v is not None:
+                env[k] = v
+        # LANGUAGE is used on win32
+        env['LANGUAGE'] = 'C'
+        env['LANG'] = 'C'
+        env['LC_ALL'] = 'C'
+        out = subprocess.Popen(cmd, stdout = subprocess.PIPE,
+                               env=env).communicate()[0]
+        return out
+
+    try:
+        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
+        GIT_REVISION = out.strip().decode('ascii')
+    except OSError:
+        GIT_REVISION = "Unknown"
+
+    return GIT_REVISION
+
+
+def get_version_info():
+    FULLVERSION = VERSION
+    if os.path.exists('.git'):
+        GIT_REVISION = git_version()
+    else:
+        GIT_REVISION = "Unknown"
+
+    if not ISRELEASED:
+        FULLVERSION += '.dev-' + GIT_REVISION[:7]
+
+    return FULLVERSION, GIT_REVISION
+
+
+def write_version_py(filename='sklearn/version.py'):
+    content = """
+# THIS FILE IS GENERATED FROM SETUP.PY
+short_version = '%(version)s'
+version = '%(version)s'
+full_version = '%(full_version)s'
+git_revision = '%(git_revision)s'
+release = %(isrelease)s
+
+if not release:
+    version = full_version
+"""
+    FULLVERSION, GIT_REVISION = get_version_info()
+
+    a = open(filename, 'w')
+    try:
+        a.write(content % {'version': VERSION,
+                           'full_version' : FULLVERSION,
+                           'git_revision' : GIT_REVISION,
+                           'isrelease': str(ISRELEASED)})
+    finally:
+        a.close()
+    return FULLVERSION
 
-# We can actually import a restricted version of sklearn that
-# does not need the compiled code
-import sklearn
+FULLVERSION = write_version_py()
 
-VERSION = sklearn.__version__
 
 ###############################################################################
 # Optional setuptools features
@@ -101,7 +170,7 @@ def setup_package():
                     description=DESCRIPTION,
                     license=LICENSE,
                     url=URL,
-                    version=VERSION,
+                    version=FULLVERSION,
                     download_url=DOWNLOAD_URL,
                     long_description=LONG_DESCRIPTION,
                     classifiers=['Intended Audience :: Science/Research',
@@ -138,7 +207,7 @@ def setup_package():
         except ImportError:
             from distutils.core import setup
 
-        metadata['version'] = VERSION
+        metadata['version'] = FULLVERSION
     else:
         from numpy.distutils.core import setup
 

sklearn/__init__.py

@@ -15,27 +15,24 @@
 import sys
 import re
 import warnings
-__version__ = '0.15-git'
 
 # Make sure that DeprecationWarning within this package always gets printed
 warnings.filterwarnings('always', category=DeprecationWarning,
                         module='^{0}\.'.format(re.escape(__name__)))
 
 try:
-    # This variable is injected in the __builtins__ by the build
-    # process. It used to enable importing subpackages of sklearn when
-    # the binaries are not built
-    __SKLEARN_SETUP__
+    # This builtins variable is defined by setup.py when building the project.
+    in_setup = __SKLEARN_SETUP__
 except NameError:
-    __SKLEARN_SETUP__ = False
+    in_setup = False
 
-if __SKLEARN_SETUP__:
-    sys.stderr.write('Partial import of sklearn during the build process.\n')
-    # We are not importing the rest of the scikit during the build
-    # process, as it may not be compiled yet
-else:
+if not in_setup:
+    # Trigger the build check only when run once the build is actually
+    # complete.
     from . import __check_build
     from .base import clone
+    from .version import full_version as __version__
+
 
     def test(*args, **kwargs):
         import warnings