Some refactor improvments and bug fixes

bin/neuralxc

@@ -44,7 +44,7 @@ if __name__ == '__main__':
     adddat.set_defaults(func=add_data_driver)
 
     def inspectdat_driver(args):
-        subprocess.Popen('h5dump -n ' + args.hdf5, shell=True)
+        subprocess.Popen(f'h5dump -n {args.hdf5}', shell=True)
 
     #================ Inspect data ================
     inspectdat = datsub.add_parser('inspect', description='Inspect data in hdf5 file')

devtools/scripts/create_conda_env.py

@@ -57,7 +57,7 @@ def temp_cd():
 with open(args.conda_file, "r") as handle:
     yaml_script = loader(handle.read())
 
-python_replacement_string = "python {}*".format(args.python)
+python_replacement_string = f"python {args.python}*"
 
 try:
     for dep_index, dep_value in enumerate(yaml_script['dependencies']):
@@ -79,14 +79,17 @@ def temp_cd():
 if conda_path is None:
     raise RuntimeError("Could not find a conda binary in CONDA_EXE variable or in executable search path")
 
-print("CONDA ENV NAME  {}".format(args.name))
-print("PYTHON VERSION  {}".format(args.python))
-print("CONDA FILE NAME {}".format(args.conda_file))
-print("CONDA PATH      {}".format(conda_path))
+print(f"CONDA ENV NAME  {args.name}")
+print(f"PYTHON VERSION  {args.python}")
+print(f"CONDA FILE NAME {args.conda_file}")
+print(f"CONDA PATH      {conda_path}")
 
 # Write to a temp directory which will always be cleaned up
 with temp_cd():
     temp_file_name = "temp_script.yaml"
     with open(temp_file_name, 'w') as f:
         f.write(yaml.dump(yaml_script))
-    sp.call("{} env create -n {} -f {}".format(conda_path, args.name, temp_file_name), shell=True)
+    sp.call(
+        f"{conda_path} env create -n {args.name} -f {temp_file_name}",
+        shell=True,
+    )

examples/scripts/apply_subset.py

@@ -27,16 +27,14 @@ def get_structures_energies(path, unit=1):
 
 if __name__ == '__main__':
 
-    if len(sys.argv) == 5:
-        unit = float(sys.argv[4])
-    else:
-        unit = kcalpmol
-
+    unit = float(sys.argv[4]) if len(sys.argv) == 5 else kcalpmol
     print("using unit", unit)
     atoms = get_structures_energies(sys.argv[1], unit=unit)
-    if not sys.argv[2] == 'all':
-        subset = np.genfromtxt(sys.argv[2]).astype(int)
-    else:
-        subset = np.arange(len(atoms))
+    subset = (
+        np.arange(len(atoms))
+        if sys.argv[2] == 'all'
+        else np.genfromtxt(sys.argv[2]).astype(int)
+    )
+
     atoms_subset = [atoms[s] for s in subset]
     write(sys.argv[3], atoms_subset)

examples/scripts/fix_paths.py

@@ -2,11 +2,7 @@
 import os
 import sys
 
-if len(sys.argv) > 1:
-    path = sys.argv[1]
-else:
-    path = 'basis_sgdml_benzene.json'
-
+path = sys.argv[1] if len(sys.argv) > 1 else 'basis_sgdml_benzene.json'
 print('FILEPATH', path)
 
 basis = json.load(open(path, 'r'))

neuralxc/_version.py

@@ -24,8 +24,7 @@ def get_keywords():
     git_refnames = "$Format:%d$"
     git_full = "$Format:%H$"
     git_date = "$Format:%ci$"
-    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
-    return keywords
+    return {"refnames": git_refnames, "full": git_full, "date": git_date}
 
 
 class VersioneerConfig:
@@ -85,20 +84,20 @@ def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=
             if e.errno == errno.ENOENT:
                 continue
             if verbose:
-                print("unable to run %s" % dispcmd)
+                print(f"unable to run {dispcmd}")
                 print(e)
             return None, None
     else:
         if verbose:
-            print("unable to find command, tried %s" % (commands, ))
+            print(f"unable to find command, tried {commands}")
         return None, None
     stdout = p.communicate()[0].strip()
     if sys.version_info[0] >= 3:
         stdout = stdout.decode()
     if p.returncode != 0:
         if verbose:
-            print("unable to run %s (error)" % dispcmd)
-            print("stdout was %s" % stdout)
+            print(f"unable to run {dispcmd} (error)")
+            print(f"stdout was {stdout}")
         return None, p.returncode
     return stdout, p.returncode
 
@@ -112,7 +111,7 @@ def versions_from_parentdir(parentdir_prefix, root, verbose):
     """
     rootdirs = []
 
-    for i in range(3):
+    for _ in range(3):
         dirname = os.path.basename(root)
         if dirname.startswith(parentdir_prefix):
             return {
@@ -122,12 +121,14 @@ def versions_from_parentdir(parentdir_prefix, root, verbose):
                 "error": None,
                 "date": None
             }
-        else:
-            rootdirs.append(root)
-            root = os.path.dirname(root)  # up a level
+        rootdirs.append(root)
+        root = os.path.dirname(root)  # up a level
 
     if verbose:
-        print("Tried directories %s but none started with prefix %s" % (str(rootdirs), parentdir_prefix))
+        print(
+            f"Tried directories {rootdirs} but none started with prefix {parentdir_prefix}"
+        )
+
     raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
 
 
@@ -140,21 +141,17 @@ def git_get_keywords(versionfile_abs):
     # _version.py.
     keywords = {}
     try:
-        f = open(versionfile_abs, "r")
-        for line in f.readlines():
-            if line.strip().startswith("git_refnames ="):
-                mo = re.search(r'=\s*"(.*)"', line)
-                if mo:
-                    keywords["refnames"] = mo.group(1)
-            if line.strip().startswith("git_full ="):
-                mo = re.search(r'=\s*"(.*)"', line)
-                if mo:
-                    keywords["full"] = mo.group(1)
-            if line.strip().startswith("git_date ="):
-                mo = re.search(r'=\s*"(.*)"', line)
-                if mo:
-                    keywords["date"] = mo.group(1)
-        f.close()
+        with open(versionfile_abs, "r") as f:
+            for line in f:
+                if line.strip().startswith("git_refnames ="):
+                    if mo := re.search(r'=\s*"(.*)"', line):
+                        keywords["refnames"] = mo[1]
+                if line.strip().startswith("git_full ="):
+                    if mo := re.search(r'=\s*"(.*)"', line):
+                        keywords["full"] = mo[1]
+                if line.strip().startswith("git_date ="):
+                    if mo := re.search(r'=\s*"(.*)"', line):
+                        keywords["date"] = mo[1]
     except EnvironmentError:
         pass
     return keywords
@@ -179,11 +176,11 @@ 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 = {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 = {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
@@ -192,17 +189,17 @@ 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 = {r for r in refs if re.search(r'\d', r)}
         if verbose:
             print("discarding '%s', no digits" % ",".join(refs - tags))
     if verbose:
-        print("likely tags: %s" % ",".join(sorted(tags)))
+        print(f'likely tags: {",".join(sorted(tags))}')
     for ref in sorted(tags):
         # sorting will prefer e.g. "2.0" over "2.0rc1"
         if ref.startswith(tag_prefix):
             r = ref[len(tag_prefix):]
             if verbose:
-                print("picking %s" % r)
+                print(f"picking {r}")
             return {
                 "version": r,
                 "full-revisionid": keywords["full"].strip(),
@@ -230,21 +227,29 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
     expanded, and _version.py hasn't already been rewritten with a short
     version string, meaning we're inside a checked out source tree.
     """
-    GITS = ["git"]
-    if sys.platform == "win32":
-        GITS = ["git.cmd", "git.exe"]
-
+    GITS = ["git.cmd", "git.exe"] if sys.platform == "win32" else ["git"]
     out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=True)
     if rc != 0:
         if verbose:
-            print("Directory %s not under git control" % root)
+            print(f"Directory {root} not under git control")
         raise NotThisMethod("'git rev-parse --git-dir' returned error")
 
     # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
     # if there isn't one, this yields HEX[-dirty] (no NUM)
     describe_out, rc = run_command(
-        GITS, ["describe", "--tags", "--dirty", "--always", "--long", "--match",
-               "%s*" % tag_prefix], cwd=root)
+        GITS,
+        [
+            "describe",
+            "--tags",
+            "--dirty",
+            "--always",
+            "--long",
+            "--match",
+            f"{tag_prefix}*",
+        ],
+        cwd=root,
+    )
+
     # --long was added in git-1.5.5
     if describe_out is None:
         raise NotThisMethod("'git describe' failed")
@@ -254,11 +259,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
         raise NotThisMethod("'git rev-parse' failed")
     full_out = full_out.strip()
 
-    pieces = {}
-    pieces["long"] = full_out
-    pieces["short"] = full_out[:7]  # maybe improved later
-    pieces["error"] = None
-
+    pieces = {"long": full_out, "short": full_out[:7], "error": None}
     # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
     # TAG might have hyphens.
     git_describe = describe_out
@@ -280,7 +281,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
             return pieces
 
         # tag
-        full_tag = mo.group(1)
+        full_tag = mo[1]
         if not full_tag.startswith(tag_prefix):
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
@@ -290,10 +291,10 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
         pieces["closest-tag"] = full_tag[len(tag_prefix):]
 
         # distance: number of commits since tag
-        pieces["distance"] = int(mo.group(2))
+        pieces["distance"] = int(mo[2])
 
         # commit: short hex revision ID
-        pieces["short"] = mo.group(3)
+        pieces["short"] = mo[3]
 
     else:
         # HEX: no tags
@@ -310,9 +311,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
 
 def plus_or_dot(pieces):
     """Return a + if we don't already have one, else return a ."""
-    if "+" in pieces.get("closest-tag", ""):
-        return "."
-    return "+"
+    return "." if "+" in pieces.get("closest-tag", "") else "+"
 
 
 def render_pep440(pieces):
@@ -329,13 +328,11 @@ def render_pep440(pieces):
         if pieces["distance"] or pieces["dirty"]:
             rendered += plus_or_dot(pieces)
             rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
-            if pieces["dirty"]:
-                rendered += ".dirty"
     else:
         # exception #1
         rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
-        if pieces["dirty"]:
-            rendered += ".dirty"
+    if pieces["dirty"]:
+        rendered += ".dirty"
     return rendered
 
 
@@ -372,13 +369,13 @@ def render_pep440_post(pieces):
             if pieces["dirty"]:
                 rendered += ".dev0"
             rendered += plus_or_dot(pieces)
-            rendered += "g%s" % pieces["short"]
+            rendered += f'g{pieces["short"]}'
     else:
         # exception #1
         rendered = "0.post%d" % pieces["distance"]
         if pieces["dirty"]:
             rendered += ".dev0"
-        rendered += "+g%s" % pieces["short"]
+        rendered += f'+g{pieces["short"]}'
     return rendered
 
 
@@ -394,13 +391,11 @@ def render_pep440_old(pieces):
         rendered = pieces["closest-tag"]
         if pieces["distance"] or pieces["dirty"]:
             rendered += ".post%d" % pieces["distance"]
-            if pieces["dirty"]:
-                rendered += ".dev0"
     else:
         # exception #1
         rendered = "0.post%d" % pieces["distance"]
-        if pieces["dirty"]:
-            rendered += ".dev0"
+    if pieces["dirty"]:
+        rendered += ".dev0"
     return rendered