MAINT: Fix automatically documented issues

Fix a number of small issues found with auto code analysis tool

Author: bashtage

archive/docs/fix_longtable.py

@@ -7,8 +7,8 @@
 read_file_path = os.path.join(BUILDDIR,'latex','statsmodels.tex')
 write_file_path = os.path.join(BUILDDIR, 'latex','statsmodels_tmp.tex')
 
-read_file = open(read_file_path,'r')
-write_file = open(write_file_path, 'w')
+read_file = open(read_file_path, 'r', encoding="utf-8")
+write_file = open(write_file_path, 'w', encoding="utf-8")
 
 for line in read_file:
     if 'longtable}{LL' in line:

docs/source/conf.py

@@ -405,7 +405,7 @@
 # ghissue config
 github_project_url = 'https://github.com/statsmodels/statsmodels'
 
-example_context = yaml.safe_load(open('examples/landing.yml'))
+example_context = yaml.safe_load(open('examples/landing.yml', encoding="utf-8"))
 html_context.update({'examples': example_context})
 
 # --------------- DOCTEST -------------------

examples/python/generic_mle.py

@@ -130,7 +130,7 @@ def nloglikeobs(self, params):
     def fit(self, start_params=None, maxiter=10000, maxfun=5000, **kwds):
         # we have one additional parameter and we need to add it for summary
         self.exog_names.append('alpha')
-        if start_params == None:
+        if start_params is None:
             # Reasonable starting values
             start_params = np.append(np.zeros(self.exog.shape[1]), .5)
             # intercept

examples/run_all.py

@@ -28,7 +28,7 @@ def no_show(*args):
     EXAMPLE_FILES = glob.glob('python/*.py')
     for example in EXAMPLE_FILES:
         KNOWN_BAD_FILE = any([bf in example for bf in BAD_FILES])
-        with open(example, 'r') as pyfile:
+        with open(example, 'r', encoding="utf-8") as pyfile:
             code = pyfile.read()
             try:
                 sys.stdout = REDIRECT_STDOUT

setup.py

@@ -50,7 +50,7 @@
 # These are strictly installation requirements. Builds requirements are
 # managed in pyproject.toml
 INSTALL_REQUIRES = []
-with open("requirements.txt") as req:
+with open("requirements.txt", encoding="utf-8") as req:
     for line in req.readlines():
         INSTALL_REQUIRES.append(line.split("#")[0].strip())
 
@@ -266,11 +266,11 @@ def check_source(source_name):
 def process_tempita(source_name):
     """Runs pyx.in files through tempita is needed"""
     if source_name.endswith("pyx.in"):
-        with open(source_name, "r") as templated:
+        with open(source_name, "r", encoding="utf-8") as templated:
             pyx_template = templated.read()
         pyx = Tempita.sub(pyx_template)
         pyx_filename = source_name[:-3]
-        with open(pyx_filename, "w") as pyx_file:
+        with open(pyx_filename, "w", encoding="utf-8") as pyx_file:
             pyx_file.write(pyx)
         file_stats = os.stat(source_name)
         try:

statsmodels/base/tests/test_penalized.py

@@ -67,7 +67,7 @@ def setup_class(cls):
         cls._initialize()
 
     @classmethod
-    def _generate_endog(self, linpred):
+    def _generate_endog(cls, linpred):
         mu = np.exp(linpred)
         np.random.seed(999)
         y = np.random.poisson(mu)
@@ -404,7 +404,7 @@ def test_cov_type(self):
 class CheckPenalizedLogit(CheckPenalizedPoisson):
 
     @classmethod
-    def _generate_endog(self, linpred):
+    def _generate_endog(cls, linpred):
         mu = 1 / (1 + np.exp(-linpred + linpred.mean() - 0.5))
         np.random.seed(999)
         y = np.random.rand(len(mu)) < mu
@@ -517,7 +517,7 @@ def test_zeros(self):
 class CheckPenalizedBinomCount(CheckPenalizedPoisson):
 
     @classmethod
-    def _generate_endog(self, linpred):
+    def _generate_endog(cls, linpred):
         mu = 1 / (1 + np.exp(-linpred + linpred.mean() - 0.5))
         np.random.seed(999)
         n_trials = 5 * np.ones(len(mu), int)
@@ -614,7 +614,7 @@ def _initialize(cls):
 class CheckPenalizedGaussian(CheckPenalizedPoisson):
 
     @classmethod
-    def _generate_endog(self, linpred):
+    def _generate_endog(cls, linpred):
         sig_e = np.sqrt(0.1)
         np.random.seed(999)
         y = linpred + sig_e * np.random.rand(len(linpred))

statsmodels/datasets/utils.py

@@ -119,7 +119,8 @@ def _get_cache(cache):
 
 def _cache_it(data, cache_path):
     import zlib
-    open(cache_path, "wb").write(zlib.compress(data))
+    with open(cache_path, "wb") as zf:
+        zf.write(zlib.compress(data))
 
 
 def _open_cache(cache_path):

statsmodels/discrete/tests/test_discrete.py

@@ -1617,7 +1617,7 @@ def test_issue_339():
     smry = "\n".join(res1.summary().as_text().split('\n')[9:])
     cur_dir = os.path.dirname(os.path.abspath(__file__))
     test_case_file = os.path.join(cur_dir, 'results', 'mn_logit_summary.txt')
-    with open(test_case_file, 'r') as fd:
+    with open(test_case_file, 'r', encoding="utf-8") as fd:
         test_case = fd.read()
     np.testing.assert_equal(smry, test_case[:-1])
     # smoke test for summary2

statsmodels/examples/ex_lowess.py

@@ -65,7 +65,7 @@
 rpath = os.path.split(statsmodels.nonparametric.tests.results.__file__)[0]
 rfile = os.path.join(rpath, 'test_lowess_frac.csv')
 test_data = np.genfromtxt(open(rfile, 'rb'),
-                                  delimiter = ',', names = True)
+                          delimiter=',', names=True)
 expected_lowess_23 = np.array([test_data['x'], test_data['out_2_3']]).T
 expected_lowess_15 = np.array([test_data['x'], test_data['out_1_5']]).T
 

statsmodels/examples/run_all.py

@@ -49,7 +49,7 @@ def noop(*args):
         try:
             print("\n\nExecuting example file", run_all_f)
             print("-----------------------" + "-"*len(run_all_f))
-            exec(open(run_all_f).read())
+            exec(open(run_all_f, encoding="utf-8").read())
         except:
             #f might be overwritten in the executed file
             print("**********************" + "*"*len(run_all_f))