Merge pull request #6412 from bashtage/forward-port-diagnostics

CLN/MAINT: Port non-diagnostic changes

.codacy.yml

@@ -2,7 +2,7 @@
 engines:
  pylint:
    enabled: true
-   python_version: 2
+   python_version: 3
 exclude_paths:
   - '**/_version.py'
   - 'versioneer.py'

docs/source/diagnostic.rst

@@ -218,11 +218,3 @@ individual outliers and might not be able to identify groups of outliers.
    - det_cov_params_not_obsi
    - params_not_obsi
    - sigma2_not_obsi
-
-
-
-Unit Root Tests
----------------
-
-:py:func:`unitroot_adf <statsmodels.stats.diagnostic.unitroot_adf>`
-  - same as adfuller but with different signature

docs/source/spelling_wordlist.txt

@@ -2295,3 +2295,6 @@ cp
 bp
 sirf
 parametrized
+nonlinearity
+lexicographically
+Appender

pyproject.toml

@@ -0,0 +1,11 @@
+[build-system]
+requires = [
+    "setuptools",
+    "wheel",
+    "cython>=0.29.14",
+    "numpy==1.14.5; python_version=='3.5'",
+    "numpy==1.14.5; python_version=='3.6'",
+    "numpy==1.14.5; python_version>='3.7'",
+    "numpy==1.17.5; python_version>='3.8'",
+    "scipy>=1.0",
+]

statsmodels/graphics/gofplots.py

@@ -497,7 +497,7 @@ def qqplot(data, dist=stats.norm, distargs=(), a=0, loc=0, scale=1, fit=False,
     data : array_like
         A 1d data array.
     dist : callable
-        Comparrison distribution. The default is
+        Comparison distribution. The default is
         scipy.stats.distributions.norm (a standard normal).
     distargs : tuple
         A tuple of arguments passed to dist to specify it fully

statsmodels/graphics/regressionplots.py

@@ -309,7 +309,7 @@ def plot_partregress(endog, exog_i, exog_others, data=None,
        The endogenous or response variable. If string is given, you can use a
        arbitrary translations as with a formula.
     exog_i : {ndarray, str}
-        THe exogenous, explanatory variable. If string is given, you can use a
+        The exogenous, explanatory variable. If string is given, you can use a
         arbitrary translations as with a formula.
     exog_others : {ndarray, list[str]}
         Any other exogenous, explanatory variables. If a list of strings is

statsmodels/multivariate/plots.py

@@ -9,7 +9,7 @@ def plot_scree(eigenvals, total_var, ncomp=None, x_label='factor'):
     Parameters
     ----------
     eigenvals : array_like
-        THe eigenvalues
+        The eigenvalues
     total_var : float
         the total variance (for plotting percent variance explained)
     ncomp : int, optional

statsmodels/regression/linear_model.py

@@ -55,7 +55,8 @@
 
 __docformat__ = 'restructuredtext en'
 
-__all__ = ['GLS', 'WLS', 'OLS', 'GLSAR', 'PredictionResults']
+__all__ = ['GLS', 'WLS', 'OLS', 'GLSAR', 'PredictionResults',
+           'RegressionResultsWrapper']
 
 
 _fit_regularized_doc =\

statsmodels/sandbox/distributions/extras.py

@@ -904,7 +904,7 @@ def absfunc(x):
 *     CORREL REAL, array of correlation coefficients; the correlation
 *            coefficient in row I column J of the correlation matrix
 *            should be stored in CORREL( J + ((I-2)*(I-1))/2 ), for J < I.
-*            THe correlation matrix must be positive semidefinite.
+*            The correlation matrix must be positive semidefinite.
 *     MAXPTS INTEGER, maximum number of function values allowed. This
 *            parameter can be used to limit the time. A sensible
 *            strategy is to start with MAXPTS = 1000*N, and then

statsmodels/sandbox/stats/ex_newtests.py

@@ -1,6 +1,4 @@
-
-from .diagnostic import unitroot_adf
-
+from statsmodels.tsa.stattools import adfuller
 import statsmodels.datasets.macrodata.data as macro
 
 macrod = macro.load(as_pandas=False).data
@@ -26,5 +24,6 @@
 
 print('%-10s %5s %-8s' % ('variable', 'trend', '  adf'))
 for name, torder in datatrendli:
-    adf_, pval = unitroot_adf(macrod[name], trendorder=torder)[:2]
+    c_order = {0: "nc", 1: "c"}
+    adf_, pval = adfuller(macrod[name], regression=c_order[torder])[:2]
     print('%-10s %5d %8.4f %8.4f' % (name, torder, adf_, pval))

statsmodels/sandbox/tools/mctools.py

@@ -144,7 +144,7 @@ def run(self, nrepl, statindices=None, dgpargs=[], statsargs=[]):
             for ii in range(1, nrepl-1, nreturns):
                 x = dgp(*dgpargs) #(1e-4+np.random.randn(nobs)).cumsum()
                 #should I ravel?
-                mcres[ii] = statfun(x, *statsargs) #unitroot_adf(x, 2,trendorder=0, autolag=None)
+                mcres[ii] = statfun(x, *statsargs)
         #more than one return statistic
         else:
             self.nreturn = nreturns = len(statindices)

statsmodels/stats/stattools.py

@@ -76,7 +76,7 @@ def omni_normtest(resids, axis=0):
 
 def jarque_bera(resids, axis=0):
     r"""
-    Calculates the Jarque-Bera test for normality
+    The Jarque-Bera test of normality.
 
     Parameters
     ----------

statsmodels/tools/validation/validation.py

@@ -44,7 +44,7 @@ def array_like(obj, name, dtype=np.double, ndim=1, maxdim=None,
         __array__ method returns an array, or any (nested) sequence.
     name : str
         Name of the variable to use in exceptions
-    dtype : {None, numpy.dtype}
+    dtype : {None, numpy.dtype, str}
         Required dtype. Default is double. If None, does not change the dtype
         of obj (if present) or uses NumPy to automatically detect the dtype
     ndim : {int, None}

statsmodels/tsa/ar_model.py

@@ -1830,6 +1830,7 @@ def test_serial_correlation(self, lags=None, model_df=None):
         See Also
         --------
         statsmodels.stats.diagnostic.acorr_ljungbox
+            Ljung-Box test for serial correlation.
         """
         # Deferred to prevent circular import
         from statsmodels.stats.diagnostic import acorr_ljungbox

statsmodels/tsa/statespace/mlemodel.py

@@ -2910,6 +2910,7 @@ def test_normality(self, method):
         See Also
         --------
         statsmodels.stats.stattools.jarque_bera
+            The Jarque-Bera test of normality.
         """
         if method is None:
             method = 'jarquebera'

statsmodels/tsa/tests/test_adfuller_lag.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-"""Test for autolag of adfuller, unitroot_adf
+"""Test for autolag of adfuller
 
 Created on Wed May 30 21:39:46 2012
 Author: Josef Perktold