Fix join statement and more linting

Author: mroeschke

asv_bench/benchmarks/frame_ctor.py

@@ -132,7 +132,7 @@ def setup(self, offset, n_steps):
         offset = getattr(offsets, offset)
         self.idx = get_index_for_offset(offset(n_steps, **kwargs))
         self.df = DataFrame(np.random.randn(len(self.idx), 10), index=self.idx)
-        self.d = dict([(col, self.df[col]) for col in self.df.columns])
+        self.d = dict((col, self.df[col]) for col in self.df.columns)
 
     def time_frame_ctor(self, offset, n_steps):
         DataFrame(self.d)

asv_bench/benchmarks/io_bench.py

@@ -202,7 +202,7 @@ class read_json_lines(object):
     def setup(self):
         self.N = 100000
         self.C = 5
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]))
+        self.df = DataFrame(dict(('float{0}'.format(i), randn(self.N)) for i in range(self.C)))
         self.df.to_json(self.fname,orient="records",lines=True)
 
     def teardown(self):

asv_bench/benchmarks/packers.py

@@ -17,7 +17,7 @@ def _setup(self):
         self.N = 100000
         self.C = 5
         self.index = date_range('20000101', periods=self.N, freq='H')
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]), index=self.index)
+        self.df = DataFrame(dict(('float{0}'.format(i), randn(self.N)) for i in range(self.C)), index=self.index)
         self.df2 = self.df.copy()
         self.df2['object'] = [('%08x' % randrange((16 ** 8))) for _ in range(self.N)]
         self.remove(self.f)

asv_bench/vbench_to_asv.py

@@ -69,7 +69,7 @@ def visit_ClassDef(self, node):
         return node
 
     def visit_TryExcept(self, node):
-        if any([isinstance(x, (ast.Import, ast.ImportFrom)) for x in node.body]):
+        if any(isinstance(x, (ast.Import, ast.ImportFrom)) for x in node.body):
             self.imports.append(node)
         else:
             self.generic_visit(node)

ci/lint.sh

@@ -84,7 +84,7 @@ if [ "$LINT" ]; then
     fi
     echo "Check for invalid testing DONE"
 
-    echo "Check for use of lists in built-in Python functions"
+    echo "Check for use of lists instead of generators in built-in Python functions"
 
     # Example: Avoid `any([i for i in some_iterator])` in favor of `any(i for i in some_iterator)`
     #
@@ -95,7 +95,7 @@ if [ "$LINT" ]; then
     if [ $? = "0" ]; then
         RET=1
     fi
-    echo "Check for use of lists in built-in Python functions DONE"
+    echo "Check for use of lists instead of generators in built-in Python functions DONE"
 
 else
     echo "NOT Linting"

doc/source/conf.py

@@ -78,7 +78,7 @@
 # JP: added from sphinxdocs
 autosummary_generate = False
 
-if any([re.match("\s*api\s*", l) for l in index_rst_lines]):
+if any(re.match("\s*api\s*", l) for l in index_rst_lines):
     autosummary_generate = True
 
 files_to_delete = []
@@ -89,7 +89,7 @@
 
     _file_basename = os.path.splitext(f)[0]
     _regex_to_match = "\s*{}\s*$".format(_file_basename)
-    if not any([re.match(_regex_to_match, line) for line in index_rst_lines]):
+    if not any(re.match(_regex_to_match, line) for line in index_rst_lines):
         files_to_delete.append(f)
 
 if files_to_delete:

doc/sphinxext/ipython_sphinxext/ipython_directive.py

@@ -522,7 +522,7 @@ def process_output(self, data, output_prompt,
                 source = self.directive.state.document.current_source
                 content = self.directive.content
                 # Add tabs and join into a single string.
-                content = '\n'.join([TAB + line for line in content])
+                content = '\n'.join(TAB + line for line in content)
 
             # Make sure the output contains the output prompt.
             ind = found.find(output_prompt)

doc/sphinxext/numpydoc/compiler_unparse.py

@@ -399,7 +399,7 @@ def _Return(self, t):
         self._fill("return ")
         if t.value:
             if isinstance(t.value, Tuple):
-                text = ', '.join([ name.name for name in t.value.asList() ])
+                text = ', '.join(name.name for name in t.value.asList())
                 self._write(text)
             else:
                 self._dispatch(t.value)

doc/sphinxext/numpydoc/docscrape.py

@@ -270,7 +270,7 @@ def _parse_summary(self):
         # If several signatures present, take the last one
         while True:
             summary = self._doc.read_to_next_empty_line()
-            summary_str = " ".join([s.strip() for s in summary]).strip()
+            summary_str = " ".join(s.strip() for s in summary).strip()
             if re.compile('^([\w., ]+=)?\s*[\w\.]+\(.*\)$').match(summary_str):
                 self['Signature'] = summary_str
                 if not self._is_at_section():
@@ -289,7 +289,7 @@ def _parse(self):
 
         for (section,content) in self._read_sections():
             if not section.startswith('..'):
-                section = ' '.join([s.capitalize() for s in section.split(' ')])
+                section = ' '.join(s.capitalize() for s in section.split(' '))
             if section in ('Parameters', 'Returns', 'Raises', 'Warns',
                            'Other Parameters', 'Attributes', 'Methods'):
                 self[section] = self._parse_param_list(content)

doc/sphinxext/numpydoc/docscrape_sphinx.py

@@ -130,7 +130,7 @@ def _str_member_list(self, name):
                 out += [''] + autosum
 
             if others:
-                maxlen_0 = max(3, max([len(x[0]) for x in others]))
+                maxlen_0 = max(3, max(len(x[0]) for x in others))
                 hdr = sixu("=")*maxlen_0 + sixu("  ") + sixu("=")*10
                 fmt = sixu('%%%ds  %%s  ') % (maxlen_0,)
                 out += ['', hdr]
@@ -203,7 +203,7 @@ def _str_references(self):
                 m = re.match(r'.. \[([a-z0-9._-]+)\]', line, re.I)
                 if m:
                     items.append(m.group(1))
-            out += ['   ' + ", ".join(["[%s]_" % item for item in items]), '']
+            out += ['   ' + ", ".join("[%s]_" % item for item in items), '']
         return out
 
     def _str_examples(self):

doc/sphinxext/numpydoc/phantom_import.py

@@ -60,7 +60,7 @@ def import_phantom_module(xml_file):
     # Sort items so that
     # - Base classes come before classes inherited from them
     # - Modules come before their contents
-    all_nodes = dict([(n.attrib['id'], n) for n in root])
+    all_nodes = dict((n.attrib['id'], n) for n in root)
 
     def _get_bases(node, recurse=False):
         bases = [x.attrib['ref'] for x in node.findall('base')]

pandas/io/sql.py

@@ -1186,7 +1186,7 @@ def has_table(self, name, schema=None):
     def get_table(self, table_name, schema=None):
         schema = schema or self.meta.schema
         if schema:
-            tbl = self.meta.tables.get('.'.join(schema, table_name))
+            tbl = self.meta.tables.get('.'.join([schema, table_name]))
         else:
             tbl = self.meta.tables.get(table_name)
 

scripts/api_rst_coverage.py

@@ -22,7 +22,7 @@ def class_name_sort_key(x):
     api_rst_members = set()
     file_name = '../doc/source/api.rst'
     with open(file_name, 'r') as f:
-        pattern = re.compile('({})\.(\w+)'.format('|'.join([cls.__name__ for cls in classes])))
+        pattern = re.compile('({})\.(\w+)'.format('|'.join(cls.__name__ for cls in classes)))
         for line in f:
             match = pattern.search(line)
             if match:

scripts/find_commits_touching_func.py

@@ -88,7 +88,7 @@ def get_hits(defname,files=()):
         # remove comment lines
         lines = [x for x in lines if not re.search("^\w+\s*\(.+\)\s*#",x)]
         hits = set(map(lambda x: x.split(" ")[0],lines))
-        cs.update(set([Hit(commit=c,path=f) for c in hits]))
+        cs.update(set(Hit(commit=c,path=f) for c in hits))
 
     return cs
 
@@ -101,12 +101,12 @@ def get_commit_vitals(c,hlen=HASH_LEN):
     return h[:hlen],s,parse_date(d)
 
 def file_filter(state,dirname,fnames):
-    if args.dir_masks and not any([re.search(x,dirname) for x in args.dir_masks]):
+    if args.dir_masks and not any(re.search(x,dirname) for x in args.dir_masks):
         return
     for f in fnames:
         p = os.path.abspath(os.path.join(os.path.realpath(dirname),f))
-        if  any([re.search(x,f) for x in args.file_masks])\
-            or any([re.search(x,p) for x in args.path_masks]):
+        if  any(re.search(x,f) for x in args.file_masks)\
+            or any(re.search(x,p) for x in args.path_masks):
             if os.path.isfile(p):
                 state['files'].append(p)
 

scripts/merge-pr.py

@@ -160,7 +160,7 @@ def merge_pr(pr_num, target_ref):
     if body is not None:
         merge_message_flags += ["-m", '\n'.join(textwrap.wrap(body))]
 
-    authors = "\n".join(["Author: %s" % a for a in distinct_authors])
+    authors = "\n".join("Author: %s" % a for a in distinct_authorsS)
 
     merge_message_flags += ["-m", authors]
 

versioneer.py

@@ -606,11 +606,11 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         if verbose:
             print("keywords are unexpanded, not using")
         raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
-    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    refs = set(r.strip() for r in refnames.strip("()").split(","))
     # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
     # just "foo-1.0". If we see a "tag: " prefix, prefer those.
     TAG = "tag: "
-    tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
+    tags = set(r[len(TAG):] for r in refs if r.startswith(TAG))
     if not tags:
         # Either we're using git < 1.8.3, or there really are no tags. We use
         # a heuristic: assume all version tags have a digit. The old git %%d
@@ -619,7 +619,7 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         # between branches and tags. By ignoring refnames without digits, we
         # filter out many common branch names like "release" and
         # "stabilization", as well as "HEAD" and "master".
-        tags = set([r for r in refs if re.search(r'\d', r)])
+        tags = set(r for r in refs if re.search(r'\d', r))
         if verbose:
             print("discarding '%%s', no digits" %% ",".join(refs-tags))
     if verbose:
@@ -960,11 +960,11 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         if verbose:
             print("keywords are unexpanded, not using")
         raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
-    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    refs = set(r.strip() for r in refnames.strip("()").split(","))
     # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
     # just "foo-1.0". If we see a "tag: " prefix, prefer those.
     TAG = "tag: "
-    tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
+    tags = set(r[len(TAG):] for r in refs if r.startswith(TAG))
     if not tags:
         # Either we're using git < 1.8.3, or there really are no tags. We use
         # a heuristic: assume all version tags have a digit. The old git %d
@@ -973,7 +973,7 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         # between branches and tags. By ignoring refnames without digits, we
         # filter out many common branch names like "release" and
         # "stabilization", as well as "HEAD" and "master".
-        tags = set([r for r in refs if re.search(r'\d', r)])
+        tags = set(r for r in refs if re.search(r'\d', r))
         if verbose:
             print("discarding '%s', no digits" % ",".join(refs-tags))
     if verbose: