MAINT: Remove deprecated code for 0.6

statsmodels/base/model.py

@@ -1074,7 +1074,7 @@ def cov_params(self, r_matrix=None, column=None, scale=None, cov_p=None,
             return cov_p
 
     #TODO: make sure this works as needed for GLMs
-    def t_test(self, r_matrix, q_matrix=None, cov_p=None, scale=None,
+    def t_test(self, r_matrix, cov_p=None, scale=None,
                use_t=None):
         """
         Compute a t-test for a each linear hypothesis of the form Rb = q
@@ -1083,16 +1083,12 @@ def t_test(self, r_matrix, q_matrix=None, cov_p=None, scale=None,
         ----------
         r_matrix : array-like, str, tuple
             - array : If an array is given, a p x k 2d array or length k 1d
-              array specifying the linear restrictions.
+              array specifying the linear restrictions. It is assumed
+              that the linear combination is equal to zero.
             - str : The full hypotheses to test can be given as a string.
               See the examples.
-            - tuple : A tuple of arrays in the form (R, q), since q_matrix is
-              deprecated.
-        q_matrix : array-like or scalar, optional
-            This is deprecated. See `r_matrix` and the examples for more
-            information on new usage. Can be either a scalar or a length p
-            row vector. If omitted and r_matrix is an array, `q_matrix` is
-            assumed to be a conformable array of zeros.
+            - tuple : A tuple of arrays in the form (R, q). If q is given,
+              can be either a scalar or a length p row vector.
         cov_p : array-like, optional
             An alternative estimate for the parameter covariance matrix.
             If None is given, self.normalized_cov_params is used.
@@ -1158,12 +1154,6 @@ def t_test(self, r_matrix, q_matrix=None, cov_p=None, scale=None,
         patsy.DesignInfo.linear_constraint
         """
         from patsy import DesignInfo
-        if q_matrix is not None:
-            from warnings import warn
-            warn("The `q_matrix` keyword is deprecated and will be removed "
-                 "in 0.6.0. See the documentation for the new API",
-                 FutureWarning)
-            r_matrix = (r_matrix, q_matrix)
         names = self.model.data.param_names
         LC = DesignInfo(names).linear_constraint(r_matrix)
         r_matrix, q_matrix = LC.coefs, LC.constants
@@ -1212,8 +1202,7 @@ def t_test(self, r_matrix, q_matrix=None, cov_p=None, scale=None,
                                    df_denom=df_resid,
                                    distribution='norm')
 
-    def f_test(self, r_matrix, q_matrix=None, cov_p=None, scale=1.0,
-               invcov=None):
+    def f_test(self, r_matrix, cov_p=None, scale=1.0, invcov=None):
         """
         Compute the F-test for a joint linear hypothesis.
 
@@ -1224,16 +1213,12 @@ def f_test(self, r_matrix, q_matrix=None, cov_p=None, scale=1.0,
         ----------
         r_matrix : array-like, str, or tuple
             - array : An r x k array where r is the number of restrictions to
-              test and k is the number of regressors.
+              test and k is the number of regressors. It is assumed
+              that the linear combination is equal to zero.
             - str : The full hypotheses to test can be given as a string.
               See the examples.
-            - tuple : A tuple of arrays in the form (R, q), since q_matrix is
-              deprecated.
-        q_matrix : array-like
-            This is deprecated. See `r_matrix` and the examples for more
-            information on new usage. Can be either a scalar or a length p
-            row vector. If omitted and r_matrix is an array, `q_matrix` is
-            assumed to be a conformable array of zeros.
+            - tuple : A tuple of arrays in the form (R, q), ``q`` can be
+              either a scalar or a length k row vector.
         cov_p : array-like, optional
             An alternative estimate for the parameter covariance matrix.
             If None is given, self.normalized_cov_params is used.
@@ -1310,30 +1295,26 @@ def f_test(self, r_matrix, q_matrix=None, cov_p=None, scale=1.0,
         design matrix of the model. There can be problems in non-OLS models
         where the rank of the covariance of the noise is not full.
         """
-        res = self.wald_test(r_matrix, q_matrix=q_matrix, cov_p=cov_p,
-                             scale=scale, invcov=invcov, use_f=True)
+        res = self.wald_test(r_matrix, cov_p=cov_p, scale=scale,
+                             invcov=invcov, use_f=True)
         return res
 
     #TODO: untested for GLMs?
-    def wald_test(self, r_matrix, q_matrix=None, cov_p=None, scale=1.0,
-                  invcov=None, use_f=None):
+    def wald_test(self, r_matrix, cov_p=None, scale=1.0, invcov=None,
+                  use_f=None):
         """
         Compute a Wald-test for a joint linear hypothesis.
 
         Parameters
         ----------
         r_matrix : array-like, str, or tuple
             - array : An r x k array where r is the number of restrictions to
-              test and k is the number of regressors.
+              test and k is the number of regressors. It is assumed that the
+              linear combination is equal to zero.
             - str : The full hypotheses to test can be given as a string.
               See the examples.
-            - tuple : A tuple of arrays in the form (R, q), since q_matrix is
-              deprecated.
-        q_matrix : array-like
-            This is deprecated. See `r_matrix` and the examples for more
-            information on new usage. Can be either a scalar or a length p
-            row vector. If omitted and r_matrix is an array, `q_matrix` is
-            assumed to be a conformable array of zeros.
+            - tuple : A tuple of arrays in the form (R, q), ``q`` can be
+              either a scalar or a length p row vector.
         cov_p : array-like, optional
             An alternative estimate for the parameter covariance matrix.
             If None is given, self.normalized_cov_params is used.
@@ -1376,12 +1357,6 @@ def wald_test(self, r_matrix, q_matrix=None, cov_p=None, scale=1.0,
             use_f = (hasattr(self, 'use_t') and self.use_t)
 
         from patsy import DesignInfo
-        if q_matrix is not None:
-            from warnings import warn
-            warn("The `q_matrix` keyword is deprecated and will be removed "
-                 "in 0.6.0. See the documentation for the new API",
-                 FutureWarning)
-            r_matrix = (r_matrix, q_matrix)
         names = self.model.data.param_names
         LC = DesignInfo(names).linear_constraint(r_matrix)
         r_matrix, q_matrix = LC.coefs, LC.constants

statsmodels/discrete/discrete_model.py

@@ -2438,17 +2438,6 @@ def get_margeff(self, at='overall', method='dydx', atexog=None,
         from statsmodels.discrete.discrete_margins import DiscreteMargins
         return DiscreteMargins(self, (at, method, atexog, dummy, count))
 
-
-    def margeff(self, at='overall', method='dydx', atexog=None, dummy=False,
-            count=False):
-        """DEPRECATED: marginal effects, use get_margeff instead
-        """
-        import warnings
-        warnings.warn("This method is deprecated and will be removed in 0.6.0."
-                " Use get_margeff instead", FutureWarning)
-        return self.get_margeff(at, method, atexog, dummy, count)
-
-
     def summary(self, yname=None, xname=None, title=None, alpha=.05,
                 yname_list=None):
         """Summarize the Regression Results
@@ -2726,13 +2715,6 @@ def summary(self, yname=None, xname=None, title=None, alpha=.05,
         return smry
     summary.__doc__ = DiscreteResults.summary.__doc__
 
-    @cache_readonly
-    def resid(self):
-        import warnings
-        warnings.warn("This attribute is deprecated and will be removed in "
-                      "0.6.0. Use resid_dev instead.", FutureWarning)
-        return self.resid_dev
-
     @cache_readonly
     def resid_dev(self):
         """

statsmodels/distributions/tests/test_edgeworth.py

@@ -74,22 +74,24 @@ def test_too_few_cumulants(self):
         assert_raises(ValueError, ExpandedNormal, [1])
 
     def test_coefficients(self):
-        # 3rd order in n**(1/2)
-        ne3 = ExpandedNormal([0., 1., 1.])
-        assert_allclose(ne3._coef, [1., 0., 0., 1./6])
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore', UserWarning)
+            # 3rd order in n**(1/2)
+            ne3 = ExpandedNormal([0., 1., 1.])
+            assert_allclose(ne3._coef, [1., 0., 0., 1./6])
 
-        # 4th order in n**(1/2)
-        ne4 = ExpandedNormal([0., 1., 1., 1.])
-        assert_allclose(ne4._coef, [1., 0., 0., 1./6, 1./24, 0., 1./72])
+            # 4th order in n**(1/2)
+            ne4 = ExpandedNormal([0., 1., 1., 1.])
+            assert_allclose(ne4._coef, [1., 0., 0., 1./6, 1./24, 0., 1./72])
 
-        # 5th order
-        ne5 = ExpandedNormal([0., 1., 1., 1., 1.])
-        assert_allclose(ne5._coef, [1., 0., 0., 1./6, 1./24, 1./120,
-                1./72, 1./144, 0., 1./1296])
+            # 5th order
+            ne5 = ExpandedNormal([0., 1., 1., 1., 1.])
+            assert_allclose(ne5._coef, [1., 0., 0., 1./6, 1./24, 1./120,
+                    1./72, 1./144, 0., 1./1296])
 
-        # adding trailing zeroes increases the order
-        ne33 = ExpandedNormal([0., 1., 1., 0.])
-        assert_allclose(ne33._coef, [1., 0., 0., 1./6, 0., 0., 1./72])
+            # adding trailing zeroes increases the order
+            ne33 = ExpandedNormal([0., 1., 1., 0.])
+            assert_allclose(ne33._coef, [1., 0., 0., 1./6, 0., 0., 1./72])
 
     def test_normal(self):
         # with two cumulants, it's just a gaussian
@@ -101,7 +103,9 @@ def test_chi2_moments(self):
         # construct the expansion for \chi^2
         N, df = 6, 15
         cum = [_chi2_cumulant(n+1, df) for n in range(N)]
-        ne = ExpandedNormal(cum, name='edgw_chi2')
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", UserWarning)
+            ne = ExpandedNormal(cum, name='edgw_chi2')
 
         # compare the moments
         assert_allclose([_chi2_moment(n, df) for n in range(N)],

statsmodels/nonparametric/api.py

@@ -1,4 +1,4 @@
-from .kde import KDE, KDEUnivariate
+from .kde import KDEUnivariate
 from .smoothers_lowess import lowess
 from . import bandwidths
 

statsmodels/nonparametric/kde.py

@@ -265,13 +265,6 @@ def evaluate(self, point):
         return self.kernel.density(self.endog, point)
 
 
-class KDE(KDEUnivariate):
-    def __init__(self, endog):
-        self.endog = np.asarray(endog)
-        warnings.warn("KDE is deprecated and will be removed in 0.6, "
-                      "use KDEUnivariate instead", FutureWarning)
-
-
 #### Kernel Density Estimator Functions ####
 
 def kdensity(X, kernel="gau", bw="normal_reference", weights=None, gridsize=None,
@@ -460,7 +453,7 @@ def kdensityfft(X, kernel="gau", bw="normal_reference", weights=None, gridsize=N
     X = np.asarray(X)
     X = X[np.logical_and(X>clip[0], X<clip[1])] # won't work for two columns.
                                                 # will affect underlying data?
-    
+
     # Get kernel object corresponding to selection
     kern = kernel_switch[kernel]()
 

statsmodels/stats/tests/test_pairwise.py

@@ -5,7 +5,7 @@
 
 Author: Josef Perktold
 """
-
+import warnings
 from statsmodels.compat.python import BytesIO, asbytes, range
 import numpy as np
 from numpy.testing import (assert_almost_equal, assert_equal, assert_,
@@ -248,8 +248,10 @@ def test_incorrect_output(self):
         assert_raises(ValueError, MultiComparison, np.array([1] * 10), [1] * 10)
 
         # group_order doesn't select all observations, only one group left
-        assert_raises(ValueError, MultiComparison, np.array([1] * 10),
-                     [1, 2] * 5, group_order=[1])
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", UserWarning)
+            assert_raises(ValueError, MultiComparison, np.array([1] * 10),
+                         [1, 2] * 5, group_order=[1])
 
         # group_order doesn't select all observations,
         # we do tukey_hsd with reduced set of observations

statsmodels/tools/tools.py

@@ -444,18 +444,6 @@ def fullrank(X, r=None):
         value.append(V[:, order[i]])
     return np.asarray(np.transpose(value)).astype(np.float64)
 
-StepFunction = np.deprecate(StepFunction,
-                            old_name='statsmodels.tools.tools.StepFunction',
-                            new_name='statsmodels.distributions.StepFunction')
-monotone_fn_inverter = np.deprecate(monotone_fn_inverter,
-                                    old_name='statsmodels.tools.tools'
-                                             '.monotone_fn_inverter',
-                                    new_name='statsmodels.distributions'
-                                             '.monotone_fn_inverter')
-ECDF = np.deprecate(ECDF,
-                    old_name='statsmodels.tools.tools.ECDF',
-                    new_name='statsmodels.distributions.ECDF')
-
 
 def unsqueeze(data, axis, oldshape):
     """

statsmodels/tsa/arima_model.py

@@ -58,8 +58,7 @@
         The endogenous variable.
     order : iterable
         The (p,q) order of the model for the number of AR parameters,
-        differences, and MA parameters to use. Though optional, the order
-        keyword in fit is deprecated and it is recommended to give order here.
+        differences, and MA parameters to use.
     exog : array-like, optional
         An optional arry of exogenous variables. This should *not* include a
         constant or trend. You can specify this in the `fit` method."""
@@ -441,19 +440,14 @@ class ARMA(tsbase.TimeSeriesModel):
                                  "extra_sections" : _armax_notes %
                                  {"Model" : "ARMA"}}
 
-    def __init__(self, endog, order=None, exog=None, dates=None, freq=None,
+    def __init__(self, endog, order, exog=None, dates=None, freq=None,
                  missing='none'):
         super(ARMA, self).__init__(endog, exog, dates, freq, missing=missing)
         exog = self.data.exog  # get it after it's gone through processing
-        if order is None:
-            import warnings
-            warnings.warn("In the next release order will not be optional "
-                          "in the model constructor.", FutureWarning)
-        else:
-            _check_estimable(len(self.endog), sum(order))
-            self.k_ar = k_ar = order[0]
-            self.k_ma = k_ma = order[1]
-            self.k_lags = max(k_ar, k_ma+1)
+        _check_estimable(len(self.endog), sum(order))
+        self.k_ar = k_ar = order[0]
+        self.k_ma = k_ma = order[1]
+        self.k_lags = max(k_ar, k_ma+1)
         if exog is not None:
             if exog.ndim == 1:
                 exog = exog[:, None]
@@ -806,7 +800,7 @@ def loglike_css(self, params, set_sigma2=True):
         llf = -nobs/2.*(log(2*pi) + log(sigma2)) - ssr/(2*sigma2)
         return llf
 
-    def fit(self, order=None, start_params=None, trend='c', method="css-mle",
+    def fit(self, start_params=None, trend='c', method="css-mle",
             transparams=True, solver='lbfgs', maxiter=50, full_output=1,
             disp=5, callback=None, **kwargs):
         """
@@ -877,25 +871,6 @@ def fit(self, order=None, start_params=None, trend='c', method="css-mle",
         r, order = 'F')
 
         """
-        if order is not None:
-            import warnings
-            warnings.warn("The order argument to fit is deprecated. "
-                          "Please use the model constructor argument order. "
-                          "This will overwrite any order given in the model "
-                          "constructor.", FutureWarning)
-
-            _check_estimable(len(self.endog), sum(order))
-            # get model order and constants
-            self.k_ar = int(order[0])
-            self.k_ma = int(order[1])
-            self.k_lags = max(k_ar, k_ma + 1)
-        else:
-            try:
-                assert hasattr(self, "k_ar")
-                assert hasattr(self, "k_ma")
-            except:
-                raise ValueError("Please give order to the model constructor "
-                                 "before calling fit.")
         k_ar = self.k_ar
         k_ma = self.k_ma
 
@@ -1123,7 +1098,7 @@ def fit(self, start_params=None, trend='c', method="css-mle",
         r, order = 'F')
 
         """
-        arima_fit = super(ARIMA, self).fit(None, start_params, trend,
+        arima_fit = super(ARIMA, self).fit(start_params, trend,
                                            method, transparams, solver,
                                            maxiter, full_output, disp,
                                            callback, **kwargs)