Merge tag 'v0.4.0rc2' into debian

Version 0.4.0 Release Candidate 2

* tag 'v0.4.0rc2':
  RLS: Set version number to 0.4.0rc2
  ENH: Do not warn on explicit prepend. Closes statsmodels#217.
  REF/BUG: fix nobs in old example
  REF: sandbox example make rpy optional in garch example
  BUG: fix statsmodels/examples for refactoring bugs, change the run_all.py (glob)
  TST: reduce precision test for breaks_hansen (reported by Yaroslav for Debian)
  BUG: Add return statement to predict. Needs tests! Closes statsmodels#220.
  ENH add IV2SLS to sandbox sysreg example
  BUG: fix import path in sandbox example
  Docs: add license for qsturng-py and license notice for ordereddict
  DOC: Update stale examples. Closes statsmodels#219.
  DOC: Fix example
  EX: Remove scikits.ts and larry from example
  EX: Add seed to example and use stationary coefs
  DOC: Fix lag 0 doc. Closes statsmodels#216.

COPYRIGHTS.txt

@@ -16,11 +16,11 @@ scipy
 pandas
 matplotlib
 scikit-learn
-
+qsturng-py http://code.google.com/p/qsturng-py/
 
 
 numpy (statsmodels.compatnp contains copy of entire model)
-------------------------------------------------------------------
+----------------------------------------------------------
 Copyright (c) 2005-2009, NumPy Developers.
 All rights reserved.
 
@@ -125,6 +125,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 
 matplotlib (copied from license.py)
+-----------------------------------
 
 
 LICENSE AGREEMENT FOR MATPLOTLIB %(version)s
@@ -214,3 +215,35 @@ OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
 DAMAGE.
 ---------------------------------------------------------------------------
 
+qsturng-py (code included in statsmodels.stats.libqsturng)
+--------------------------------------------------------------
+Copyright (c) 2011, Roger Lew [see LICENSE.txt]
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+  * Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+  * Redistributions in binary form must reproduce the above
+    copyright notice, this list of conditions and the following
+    disclaimer in the documentation and/or other materials provided
+    with the distribution.
+  * Neither the name of the organizations affiliated with the
+    contributors or the names of its contributors themselves may be
+    used to endorse or promote products derived from this software
+    without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+----------------------------------------------------------

setup.py

@@ -69,7 +69,7 @@ def check_dependency_versions(min_versions):
 MIN = 4
 REV = 0
 ISRELEASED = True
-VERSION = '%d.%d.%drc1' % (MAJ,MIN,REV)
+VERSION = '%d.%d.%drc2' % (MAJ,MIN,REV)
 
 classifiers = [ 'Development Status :: 4 - Beta',
               'Environment :: Console',

statsmodels/compatnp/ordereddict.py

@@ -1,6 +1,10 @@
 # Backport of OrderedDict() class that runs on Python 2.4, 2.5, 2.6, 2.7 and pypy.
 # Passes Python2.7's test suite and incorporates all the latest updates.
 
+#Author: Raymond Hettinger
+#License: MIT License
+#http://code.activestate.com/recipes/576693/ revision 9, downloaded 2012-03-28
+
 try:
     from thread import get_ident as _get_ident
 except ImportError:

statsmodels/examples/es_misc_poisson2.py

@@ -23,7 +23,7 @@ class Dummy(object):
 data_endog = np.random.poisson(np.exp(xbeta))
 
 #estimate discretemod.Poisson as benchmark
-from statsmodels.discretemod import Poisson
+from statsmodels.discrete.discrete_model import Poisson
 res_discrete = Poisson(data_endog, data_exog).fit()
 
 mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())

statsmodels/examples/ex_generic_mle.py

@@ -2,7 +2,7 @@
 import numpy as np
 from scipy import stats
 import statsmodels.api as sm
-from statsmodels.model import GenericLikelihoodModel
+from statsmodels.base.model import GenericLikelihoodModel
 
 
 data = sm.datasets.spector.load()

statsmodels/examples/ex_generic_mle_t.py

@@ -10,7 +10,7 @@
 
 from scipy import stats, special
 import statsmodels.api as sm
-from statsmodels.model import GenericLikelihoodModel
+from statsmodels.base.model import GenericLikelihoodModel
 
 #redefine some shortcuts
 np_log = np.log

statsmodels/examples/ex_generic_mle_tdist.py

@@ -10,7 +10,7 @@
 
 from scipy import stats, special, optimize
 import statsmodels.api as sm
-from statsmodels.model import GenericLikelihoodModel
+from statsmodels.base.model import GenericLikelihoodModel
 
 #redefine some shortcuts
 np_log = np.log
@@ -159,7 +159,7 @@ def nloglikeobs(self, params):
 
 #import for kstest based estimation
 #should be replace
-import statsmodels.sandbox.stats.distributions_patch
+import statsmodels.sandbox.distributions.sppatch
 
 class MyPareto(GenericLikelihoodModel):
     '''Maximum Likelihood Estimation pareto distribution
@@ -223,6 +223,7 @@ def fit_ks1_trim(self):
         originally published on stackoverflow
 
         '''
+        self.nobs = self.endog.shape[0]
         rvs = np.sort(self.endog)
         rvsmin = rvs.min()
 

statsmodels/examples/ex_pandas.py

@@ -28,9 +28,9 @@
 print results.cov_params()
 
 infl = results.get_influence()
-print infl.summary_obs()
+print infl.summary_table()
 
-raise
+#raise
 
 #Example RLM
 huber_t = sm.RLM(Y, X, M=sm.robust.norms.HuberT())

statsmodels/examples/run_all.py

@@ -7,8 +7,9 @@
 uncomment plt.show() to show all plot windows
 
 '''
+import matplotlib.pyplot as plt #matplotlib is required for many examples
 
-stop_on_error = False #True
+stop_on_error = True
 
 
 filelist = ['example_glsar.py', 'example_wls.py', 'example_gls.py',
@@ -18,6 +19,20 @@
             'example_ols_table.py',
             'tut_ols.py', 'tut_ols_rlm.py', 'tut_ols_wls.py']
 
+use_glob = True
+if use_glob:
+    import glob
+    filelist = glob.glob('*.py')
+
+print zip(range(len(filelist)), filelist)
+
+for fname in ['run_all.py', 'example_rpy.py']:
+    filelist.remove(fname)
+
+#filelist = filelist[15:]
+
+
+
 #temporarily disable show
 plt_show = plt.show
 def noop(*args):
@@ -28,6 +43,7 @@ def noop(*args):
 This is done mainly to check that they are up to date.
 (y/n) >>> """)
 if 'y' in cont.lower():
+    has_errors = []
     for run_all_f in filelist:
         try:
             print "\n\nExecuting example file", run_all_f
@@ -38,9 +54,13 @@ def noop(*args):
             print "**********************" + "*"*len(run_all_f)
             print "ERROR in example file", run_all_f
             print "**********************" + "*"*len(run_all_f)
+            has_errors.append(run_all_f)
             if stop_on_error:
                 raise
 
+print '\nModules that raised exception:'
+print has_errors
+
 #reenable show after closing windows
 plt.close('all')
 plt.show = plt_show

statsmodels/regression/linear_model.py

@@ -116,7 +116,8 @@ class GLS(base.LikelihoodModel):
     data.
 
     >>> gls_model = sm.GLS(data.endog, data.exog, sigma=sigma)
-    >>> gls_results = gls_model.results
+    >>> gls_results = gls_model.fit()
+    >>> print gls_results.summary()
 
     """
 
@@ -482,7 +483,6 @@ class OLS(WLS):
     >>>
     >>> model = sm.OLS(Y,X)
     >>> results = model.fit()
-    >>> # or results = model.results
     >>> results.params
     array([ 0.25      ,  2.14285714])
     >>> results.tvales

statsmodels/sandbox/examples/ex_cusum.py

@@ -11,8 +11,8 @@
 from numpy.testing import assert_almost_equal
 import statsmodels.api as sm
 from statsmodels.sandbox.regression.onewaygls import OneWayLS
-from statsmodels.sandbox.stats.diagnostic import (recursive_olsresiduals,
-                                                          recursive_olsresiduals2)
+from statsmodels.stats.diagnostic import recursive_olsresiduals
+from statsmodels.sandbox.stats.diagnostic import _recursive_olsresiduals2 as recursive_olsresiduals2
 
 #examples from ex_onewaygls.py
 #choose example

statsmodels/sandbox/examples/example_garch.py

@@ -29,13 +29,14 @@
 print 'ggres.params', ggres.params
 garchplot(ggmod.errorsest, ggmod.h, title='Garch estimated')
 
-
-from rpy import r
-r.library('fGarch')
-f = r.formula('~garch(1, 1)')
-fit = r.garchFit(f, data = ret - ret.mean(), include_mean=False)
-f = r.formula('~arma(1,1) + ~garch(1, 1)')
-fit = r.garchFit(f, data = ret)
+use_rpy = False
+if use_rpy:
+    from rpy import r
+    r.library('fGarch')
+    f = r.formula('~garch(1, 1)')
+    fit = r.garchFit(f, data = ret - ret.mean(), include_mean=False)
+    f = r.formula('~arma(1,1) + ~garch(1, 1)')
+    fit = r.garchFit(f, data = ret)
 
 
 ggmod0 = Garch0(ret - ret.mean())#hgjr4[:nobs])#-hgjr4.mean()) #errgjr4)

statsmodels/sandbox/examples/example_sysreg.py

@@ -131,6 +131,16 @@
 print correct_params
 print "Compare to output of R script statsmodels/sandbox/tests/macrodata.s"
 
+print '\nUsing IV2SLS'
+from statsmodels.sandbox.regression.gmm import IV2SLS
+miv = IV2SLS(macro_sys[0], macro_sys[1], instruments)
+resiv = miv.fit()
+print "equation 1"
+print resiv.params
+miv2 = IV2SLS(macro_sys[2], macro_sys[3], instruments)
+resiv2 = miv2.fit()
+print "equation 2"
+print resiv2.params
 
 ### Below is the same example using Greene's data ###
 

statsmodels/stats/tests/test_diagnostic.py

@@ -444,7 +444,7 @@ def test_breaks_hansen(self):
 
         bh = smsdia.breaks_hansen(self.res)
         assert_almost_equal(bh[0], breaks_nyblom_hansen['statistic'],
-                            decimal=14)
+                            decimal=13)
         #TODO: breaks_hansen doesn't return pvalues
 
 

statsmodels/tools/tools.py

@@ -286,9 +286,19 @@ def add_constant(data, prepend=False):
        code.
     '''
     if not prepend:
-        import warnings
-        warnings.warn("The default of `prepend` will be changed to True in the "
-                  "next release, use explicit prepend", FutureWarning)
+        import inspect
+        frame = inspect.currentframe().f_back
+        info = inspect.getframeinfo(frame)
+        try:
+            to_warn = '\n'.join(info.code_context)
+        except: # python 2.5 compatibility
+            to_warn = '\n'.join(info[3])
+        if to_warn:
+            import warnings
+            warnings.warn("The default of `prepend` will be changed to True "
+                          "in 0.5.0, use explicit prepend",
+                          FutureWarning)
+
     if _is_using_pandas(data, None):
         # work on a copy
         return _pandas_add_constant(data.copy(), prepend)

statsmodels/tsa/arima_model.py

@@ -841,7 +841,7 @@ def predict(self, start=None, end=None, exog=None):
             If the model is an ARMAX and out-of-sample forecasting is
             requestion, exog must be given.
         """
-        self.model.predict(self.params, start, end, exog)
+        return self.model.predict(self.params, start, end, exog)
 
     def forecast(self, steps=1, exog=None, alpha=.05):
         """

statsmodels/tsa/filters/bk_filter.py

@@ -49,7 +49,7 @@ def bkfilter(X, low=6, high=32, K=12):
     >>> import statsmodels.api as sm
     >>> dta = sm.datasets.macrodata.load()
     >>> X = dta.data['realinv']
-    >>> Y = sm.tsa.filters.baxter_king(X, 6, 24, 12)
+    >>> Y = sm.tsa.filters.bkfilter(X, 6, 24, 12)
     """
 #TODO: change the docstring to ..math::?
 #TODO: allow windowing functions to correct for Gibb's Phenomenon?