Merge pull request #9612 from jreback/rpy

DEPR: deprecate pandas.rpy (GH9602)

Author: jreback

doc/source/r_interface.rst

@@ -13,11 +13,9 @@
 rpy2 / R interface
 ******************
 
-.. note::
-
-   This is all highly experimental. I would like to get more people involved
-   with building a nice RPy2 interface for pandas
+.. warning::
 
+   In v0.16.0, the ``pandas.rpy`` interface has been **deprecated and will be removed in a future version**. Similar functionaility can be accessed thru the `rpy2 <http://rpy.sourceforge.net/>`_ project.
 
 If your computer has R and rpy2 (> 2.2) installed (which will be left to the
 reader), you will be able to leverage the below functionality. On Windows,

doc/source/whatsnew/v0.13.0.txt

@@ -617,6 +617,7 @@ Enhancements
 
   .. code-block:: python
 
+     # note that pandas.rpy was deprecated in v0.16.0
      import pandas.rpy.common as com
      com.load_data('Titanic')
 

doc/source/whatsnew/v0.16.0.txt

@@ -387,6 +387,10 @@ Deprecations
 - The ``pandas.sandbox.qtpandas`` interface is deprecated and will be removed in a future version.
   We refer users to the external package `pandas-qt <https://github.com/datalyze-solutions/pandas-qt>`_. (:issue:`9615`)
 
+- The ``pandas.rpy`` interface is deprecated and will be removed in a future version.
+  Similar functionaility can be accessed thru the `rpy2 <http://rpy.sourceforge.net/>`_ project (:issue:`9602`)
+
+
 .. _whatsnew_0160.prior_deprecations:
 
 Removal of prior version deprecations/changes

pandas/rpy/__init__.py

@@ -1,3 +1,12 @@
+
+# GH9602
+# deprecate rpy to instead directly use rpy2
+
+import warnings
+warnings.warn("The pandas.rpy module is deprecated and will be "
+              "removed in a future version. We refer to external packages "
+              "like rpy2, found here: http://rpy.sourceforge.net", FutureWarning)
+
 try:
     from .common import importr, r, load_data
 except ImportError:

pandas/stats/tests/test_var.py

@@ -21,16 +21,6 @@
 reload(_pvar)
 from pandas.stats.var import VAR
 
-try:
-    import rpy2.robjects as robj
-    from rpy2.robjects import r
-    from rpy2.robjects.packages import importr
-    import pandas.rpy.common as rpy
-    vars = importr('vars')
-    urca = importr('urca')
-except ImportError:
-    pass
-
 DECIMAL_6 = 6
 DECIMAL_5 = 5
 DECIMAL_4 = 4
@@ -99,97 +89,5 @@ def __init__(self):
         self.res2 = results_var.MacrodataResults()
 
 
-class RVAR(object):
-    """
-    Estimates VAR model using R vars package and rpy
-    """
-
-    def __init__(self, data, p=1, type='both'):
-        self.rdata = data
-        self.p = p
-        self.type = type
-
-        self.pydata = rpy.convert_robj(data)
-        self._estimate = None
-        self.estimate()
-
-    @property
-    def aic(self):
-        pass
-
-    @property
-    def bic(self):
-        pass
-
-    @property
-    def beta(self):
-        return rpy.convert_robj(r.coef(self._estimate))
-
-    def summary(self, equation=None):
-        print(r.summary(self._estimate, equation=equation))
-
-    def output(self):
-        print(self._estimate)
-
-    def estimate(self):
-        self._estimate = r.VAR(self.rdata, p=self.p, type=self.type)
-
-    def plot(self, names=None):
-        r.plot(model._estimate, names=names)
-
-    def serial_test(self, lags_pt=16, type='PT.asymptotic'):
-        f = r['serial.test']
-
-        test = f(self._estimate, **{'lags.pt': lags_pt,
-                                    'type': type})
-
-        return test
-
-    def data_summary(self):
-        print(r.summary(self.rdata))
-
-
-class TestVAR(TestCase):
-
-    def setUp(self):
-        try:
-            import rpy2
-        except ImportError:
-            raise nose.SkipTest("No rpy2")
-
-        self.rdata = rpy.load_data('Canada', package='vars', convert=False)
-        self.data = rpy.load_data('Canada', package='vars', convert=True)
-
-        self.res = VAR(self.data)
-        self.ref = RVAR(self.rdata)
-
-    def test_foo(self):
-        pass
-
 if __name__ == '__main__':
-    # canada = rpy.load_data('Canada', package='vars', convert=False)
-
-    # model = RVAR(canada, p=1)
-
-    # summary(Canada)
-
-    # plot(Canada, nc=2, xlab="")ppp
-
-    # adf1 <- summary(ur.df(Canada[, "prod"], type = "trend", lags = 2))
-    # adf1
-
-    # adf2 <- summary(ur.df(diff(Canada[, "prod"]), type = "drift", lags = 1))
-    # adf2
-
-    # VARselect(Canada, lag.max = 8, type = "both")
-
-    # Canada <- Canada[, c("prod", "e", "U", "rw")]
-
-    # p1ct <- VAR(Canada, p = 1, type = "both")
-    # p1ct
-
-    # coefs <- coef(p1ct)
-    # class(coefs)
-
-    # run_module_suite()
     unittest.main()

pandas/util/print_versions.py

@@ -83,7 +83,6 @@ def show_versions(as_json=False):
         ("html5lib", lambda mod: mod.__version__),
         ("httplib2", lambda mod: mod.__version__),
         ("apiclient", lambda mod: mod.__version__),
-        ("rpy2", lambda mod: mod.__version__),
         ("sqlalchemy", lambda mod: mod.__version__),
         ("pymysql", lambda mod: mod.__version__),
         ("psycopg2", lambda mod: mod.__version__),