Merge pull request #69 from EthanJamesLew/enhancement/docstrings

WIP: document / reformat tuner, benchmarks, and top-level

autokoopman/__init__.py

@@ -1,4 +1,64 @@
-# TODO: update this
+"""
+AutoKoopman: Automated Koopman operator methods for data-driven dynamical 
+systems analysis and control.
+
+The AutoKoopman package provides a high-level system identification tool 
+that automatically optimizes all hyper-parameters to estimate accurate system 
+models with globally linearized representations. Implemented as a Python library 
+under shared class interfaces, AutoKoopman uses a collection of Koopman-based 
+algorithms centered on conventional dynamic mode decomposition and deep learning.
+
+The package includes functions for generating Koopman operator matrices from 
+time series data, as well as tools for computing eigenvalues and eigenvectors 
+of these matrices. AutoKoopman supports both discrete-time and continuous-time 
+system identification, and includes methods for extended dynamic mode 
+decomposition (EDMD), deep Koopman, and sparse identification of nonlinear 
+dynamics (SINDy). The package also provides major types of static observables, 
+including polynomial observables, neural network observables, and random 
+Fourier feature observables.
+
+AutoKoopman supports system identification with input and control, including 
+the Koopman operator with input and control (KIC) method. The package also 
+includes methods for online (streaming) system identification, including 
+online dynamic mode decomposition (DMD).
+
+Finally, AutoKoopman includes hyperparameter optimization methods for tuning 
+model parameters, including random search, grid search, and Bayesian 
+optimization.
+
+Use Cases
+----------
+The library is intended for a systems engineer/researcher who wishes to 
+leverage data-driven dynamical systems techniques. The user may have 
+measurements of their system with no prior model.
+
+Prediction: AutoKoopman can predict the evolution of a system over long time
+horizons by leveraging the globally linearized representation provided by 
+Koopman operator methods.
+
+Control: AutoKoopman can synthesize control signals that achieve desired 
+closed-loop behaviors and are optimal with respect to some objective by 
+using the Koopman operator with input and control (KIC) method.
+
+Verification: AutoKoopman can prove or falsify the safety requirements of 
+a system by providing a mathematical representation of the system dynamics 
+that can be analyzed and verified.
+
+For more information on the theory behind Koopman operator methods and 
+their use in system identification, see the following references:
+
+- Koopman, B. O. (1931). Hamiltonian systems and transformation in Hilbert 
+space. Proceedings of the National Academy of Sciences, 17(5), 315-318.
+- Mezic, I. (2013). Analysis of fluid flows via spectral properties of the 
+Koopman operator. Annual Review of Fluid Mechanics, 45, 357-378.
+- Proctor, J. L., & Brunton, S. L. (2020). Koopman operator-based system 
+identification: a survey of methods and recent advances. arXiv preprint 
+arXiv:2009.14544.
+
+For usage examples and additional documentation, see the package 
+documentation.
+"""
+
 __author__ = "Ethan Lew"
 __copyright__ = "Copyright 2023"
 __credits__ = [

autokoopman/_version.py

@@ -1,4 +1,3 @@
-
 # This file helps to compute a version number in source trees obtained from
 # git-archive tarball (such as those provided by githubs download-from-tag
 # feature). Distribution tarballs (built by setup.py sdist) and build
@@ -61,17 +60,18 @@ class NotThisMethod(Exception):
 
 def register_vcs_handler(vcs, method):  # decorator
     """Create decorator to mark a method as the handler of a VCS."""
+
     def decorate(f):
         """Store f in HANDLERS[vcs][method]."""
         if vcs not in HANDLERS:
             HANDLERS[vcs] = {}
         HANDLERS[vcs][method] = f
         return f
+
     return decorate
 
 
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
-                env=None):
+def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=None):
     """Call the given command(s)."""
     assert isinstance(commands, list)
     process = None
@@ -87,10 +87,14 @@ def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
         try:
             dispcmd = str([command] + args)
             # remember shell=False, so use git.cmd on windows, not just git
-            process = subprocess.Popen([command] + args, cwd=cwd, env=env,
-                                       stdout=subprocess.PIPE,
-                                       stderr=(subprocess.PIPE if hide_stderr
-                                               else None), **popen_kwargs)
+            process = subprocess.Popen(
+                [command] + args,
+                cwd=cwd,
+                env=env,
+                stdout=subprocess.PIPE,
+                stderr=(subprocess.PIPE if hide_stderr else None),
+                **popen_kwargs,
+            )
             break
         except OSError:
             e = sys.exc_info()[1]
@@ -125,15 +129,21 @@ def versions_from_parentdir(parentdir_prefix, root, verbose):
     for _ in range(3):
         dirname = os.path.basename(root)
         if dirname.startswith(parentdir_prefix):
-            return {"version": dirname[len(parentdir_prefix):],
-                    "full-revisionid": None,
-                    "dirty": False, "error": None, "date": None}
+            return {
+                "version": dirname[len(parentdir_prefix) :],
+                "full-revisionid": None,
+                "dirty": False,
+                "error": None,
+                "date": None,
+            }
         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(
+            "Tried directories %s but none started with prefix %s"
+            % (str(rootdirs), parentdir_prefix)
+        )
     raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
 
 
@@ -192,7 +202,7 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
     # 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 = {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
@@ -201,32 +211,39 @@ 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 = {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)))
     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):]
+            r = ref[len(tag_prefix) :]
             # Filter out refs that exactly match prefix or that don't start
             # with a number once the prefix is stripped (mostly a concern
             # when prefix is '')
-            if not re.match(r'\d', r):
+            if not re.match(r"\d", r):
                 continue
             if verbose:
                 print("picking %s" % r)
-            return {"version": r,
-                    "full-revisionid": keywords["full"].strip(),
-                    "dirty": False, "error": None,
-                    "date": date}
+            return {
+                "version": r,
+                "full-revisionid": keywords["full"].strip(),
+                "dirty": False,
+                "error": None,
+                "date": date,
+            }
     # no suitable tags, so version is "0+unknown", but full hex is still there
     if verbose:
         print("no suitable tags, using unknown + full revision id")
-    return {"version": "0+unknown",
-            "full-revisionid": keywords["full"].strip(),
-            "dirty": False, "error": "no suitable tags", "date": None}
+    return {
+        "version": "0+unknown",
+        "full-revisionid": keywords["full"].strip(),
+        "dirty": False,
+        "error": "no suitable tags",
+        "date": None,
+    }
 
 
 @register_vcs_handler("git", "pieces_from_vcs")
@@ -248,19 +265,27 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
     env.pop("GIT_DIR", None)
     runner = functools.partial(runner, env=env)
 
-    _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root,
-                   hide_stderr=not verbose)
+    _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=not verbose)
     if rc != 0:
         if verbose:
             print("Directory %s not under git control" % root)
         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 = runner(GITS, [
-        "describe", "--tags", "--dirty", "--always", "--long",
-        "--match", f"{tag_prefix}[[:digit:]]*"
-    ], cwd=root)
+    describe_out, rc = runner(
+        GITS,
+        [
+            "describe",
+            "--tags",
+            "--dirty",
+            "--always",
+            "--long",
+            "--match",
+            f"{tag_prefix}[[:digit:]]*",
+        ],
+        cwd=root,
+    )
     # --long was added in git-1.5.5
     if describe_out is None:
         raise NotThisMethod("'git describe' failed")
@@ -275,8 +300,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
     pieces["short"] = full_out[:7]  # maybe improved later
     pieces["error"] = None
 
-    branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"],
-                             cwd=root)
+    branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], cwd=root)
     # --abbrev-ref was added in git-1.6.3
     if rc != 0 or branch_name is None:
         raise NotThisMethod("'git rev-parse --abbrev-ref' returned error")
@@ -316,17 +340,16 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
     dirty = git_describe.endswith("-dirty")
     pieces["dirty"] = dirty
     if dirty:
-        git_describe = git_describe[:git_describe.rindex("-dirty")]
+        git_describe = git_describe[: git_describe.rindex("-dirty")]
 
     # now we have TAG-NUM-gHEX or HEX
 
     if "-" in git_describe:
         # TAG-NUM-gHEX
-        mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
+        mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
         if not mo:
             # unparsable. Maybe git-describe is misbehaving?
-            pieces["error"] = ("unable to parse git-describe output: '%s'"
-                               % describe_out)
+            pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
             return pieces
 
         # tag
@@ -335,10 +358,12 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
-            pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
-                               % (full_tag, tag_prefix))
+            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (
+                full_tag,
+                tag_prefix,
+            )
             return pieces
-        pieces["closest-tag"] = full_tag[len(tag_prefix):]
+        pieces["closest-tag"] = full_tag[len(tag_prefix) :]
 
         # distance: number of commits since tag
         pieces["distance"] = int(mo.group(2))
@@ -387,8 +412,7 @@ def render_pep440(pieces):
                 rendered += ".dirty"
     else:
         # exception #1
-        rendered = "0+untagged.%d.g%s" % (pieces["distance"],
-                                          pieces["short"])
+        rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
         if pieces["dirty"]:
             rendered += ".dirty"
     return rendered
@@ -417,8 +441,7 @@ def render_pep440_branch(pieces):
         rendered = "0"
         if pieces["branch"] != "master":
             rendered += ".dev0"
-        rendered += "+untagged.%d.g%s" % (pieces["distance"],
-                                          pieces["short"])
+        rendered += "+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
         if pieces["dirty"]:
             rendered += ".dirty"
     return rendered
@@ -579,11 +602,13 @@ def render_git_describe_long(pieces):
 def render(pieces, style):
     """Render the given version pieces into the requested style."""
     if pieces["error"]:
-        return {"version": "unknown",
-                "full-revisionid": pieces.get("long"),
-                "dirty": None,
-                "error": pieces["error"],
-                "date": None}
+        return {
+            "version": "unknown",
+            "full-revisionid": pieces.get("long"),
+            "dirty": None,
+            "error": pieces["error"],
+            "date": None,
+        }
 
     if not style or style == "default":
         style = "pep440"  # the default
@@ -607,9 +632,13 @@ def render(pieces, style):
     else:
         raise ValueError("unknown style '%s'" % style)
 
-    return {"version": rendered, "full-revisionid": pieces["long"],
-            "dirty": pieces["dirty"], "error": None,
-            "date": pieces.get("date")}
+    return {
+        "version": rendered,
+        "full-revisionid": pieces["long"],
+        "dirty": pieces["dirty"],
+        "error": None,
+        "date": pieces.get("date"),
+    }
 
 
 def get_versions():
@@ -623,8 +652,7 @@ def get_versions():
     verbose = cfg.verbose
 
     try:
-        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
-                                          verbose)
+        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, verbose)
     except NotThisMethod:
         pass
 
@@ -633,13 +661,16 @@ def get_versions():
         # versionfile_source is the relative path from the top of the source
         # tree (where the .git directory might live) to this file. Invert
         # this to find the root from __file__.
-        for _ in cfg.versionfile_source.split('/'):
+        for _ in cfg.versionfile_source.split("/"):
             root = os.path.dirname(root)
     except NameError:
-        return {"version": "0+unknown", "full-revisionid": None,
-                "dirty": None,
-                "error": "unable to find root of source tree",
-                "date": None}
+        return {
+            "version": "0+unknown",
+            "full-revisionid": None,
+            "dirty": None,
+            "error": "unable to find root of source tree",
+            "date": None,
+        }
 
     try:
         pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
@@ -653,6 +684,10 @@ def get_versions():
     except NotThisMethod:
         pass
 
-    return {"version": "0+unknown", "full-revisionid": None,
-            "dirty": None,
-            "error": "unable to compute version", "date": None}
+    return {
+        "version": "0+unknown",
+        "full-revisionid": None,
+        "dirty": None,
+        "error": "unable to compute version",
+        "date": None,
+    }

autokoopman/benchmark/__init__.py

@@ -0,0 +1,9 @@
+"""
+AutoKoopman benchmark module.
+
+The `autokoopman.benchmark` module provides classes for generating training and
+test trajectories for benchmarking the AutoKoopman algorithms. These 
+trajectories are generated from various common dynamical systems and 
+ARCH models using the `autokoopman.core.system` interfaces. Many of the 
+benchmark systems are symbolic, using `sympy` expressions.
+"""

autokoopman/benchmark/bio2.py

@@ -5,7 +5,7 @@
 
 class Bio2(asys.SymbolicContinuousSystem):
     r"""
-    Spring pendulum
+    Biological System 2
         A nine-dimensional continuous model which is adapted from a biological system given in [1].
 
         Initial set: