Merge pull request #835 from amas0/runset-cleanup

amas0 · web-flow · commit b8bcfab21d91 · 2025-11-07T22:25:59.000-05:00
Standardizes file naming conventions across the range of possible output files.
diff --git a/cmdstanpy/model.py b/cmdstanpy/model.py
@@ -288,12 +288,10 @@ def optimize(
         or to a temporary directory which is deleted upon session exit.
 
         Output files are either written to a temporary directory or to the
-        specified output directory.  Output filenames correspond to the template
-        '<model_name>-<YYYYMMDDHHMM>-<chain_id>' plus the file suffix which is
-        either '.csv' for the CmdStan output or '.txt' for
-        the console messages, e.g. 'bernoulli-201912081451-1.csv'.
-        Output files written to the temporary directory contain an additional
-        8-character random string, e.g. 'bernoulli-201912081451-1-5nm6as7u.csv'.
+        specified output directory. Optimize output filenames correspond to
+        the template '<model_name>-<YYYYMMDDHHMM>' plus the file suffix which is
+        either '.csv' for the CmdStan output or '_stdout.txt' for
+        the console messages, e.g. 'bernoulli-20251107142835.csv'.
 
         :param data: Values for all data variables in the model, specified
             either as a dictionary with entries matching the data variables,
@@ -328,7 +326,7 @@ def optimize(
 
         :param save_profile: Whether or not to profile auto-diff operations in
             labelled blocks of code.  If ``True``, CSV outputs are written to
-            file '<model_name>-<YYYYMMDDHHMM>-profile-<chain_id>'.
+            file '<model_name>-<YYYYMMDDHHMM>_profile.csv'.
             Introduced in CmdStan-2.26.
 
         :param algorithm: Algorithm to use. One of: 'BFGS', 'LBFGS', 'Newton'
@@ -497,11 +495,15 @@ def sample(
 
         Output files are either written to a temporary directory or to the
         specified output directory.  Ouput filenames correspond to the template
-        '<model_name>-<YYYYMMDDHHMM>-<chain_id>' plus the file suffix which is
-        either '.csv' for the CmdStan output or '.txt' for
-        the console messages, e.g. 'bernoulli-201912081451-1.csv'.
-        Output files written to the temporary directory contain an additional
-        8-character random string, e.g. 'bernoulli-201912081451-1-5nm6as7u.csv'.
+        '<model_name>-<YYYYMMDDHHMM>' plus additional bits to identify which
+        output file it corresponds to. CmdStan output will suffix with
+        '_<chain_id>.csv' if there is more than one chain, and simply'.csv'
+        in the single-chain case. For example, 'bernoulli-20251107144515_1.csv'.
+        Console message output is written to a text file suffixed
+        `_stdout_<chain_id>.txt` if each chain executes in a separate process
+        (default behavior) or simply `_stdout.txt` if done so in a single
+        process, such as when STAN_THREADS is enabled and you are sampling
+        more than one chain.
 
         :param data: Values for all data variables in the model, specified
             either as a dictionary with entries matching the data variables,
@@ -634,14 +636,17 @@ def sample(
         :param save_latent_dynamics: Whether or not to output the position and
             momentum information for the model parameters (unconstrained).
             If ``True``, CSV outputs are written to an output file
-            '<model_name>-<YYYYMMDDHHMM>-diagnostic-<chain_id>',
-            e.g. 'bernoulli-201912081451-diagnostic-1.csv', see
+            '<model_name>-<YYYYMMDDHHMM>_diagnostic_<chain_id>',
+            e.g. 'bernoulli-201912081451_diagnostic_1.csv', see
             https://mc-stan.org/docs/cmdstan-guide/stan_csv.html,
             section "Diagnostic CSV output file" for details.
 
         :param save_profile: Whether or not to profile auto-diff operations in
             labelled blocks of code.  If ``True``, CSV outputs are written to
-            file '<model_name>-<YYYYMMDDHHMM>-profile-<chain_id>'.
+            file '<model_name>-<YYYYMMDDHHMM>_profile_<chain_id>.csv' if each
+            chain runs in its own process, otherwise
+            '<model_name>-<YYYYMMDDHHMM>_profile.csv' if all chains run in a
+            single process.
             Introduced in CmdStan-2.26, see
             https://mc-stan.org/docs/cmdstan-guide/stan_csv.html,
             section "Profiling CSV output file" for details.
@@ -955,12 +960,16 @@ def generate_quantities(
         or to a temporary directory which is deleted upon session exit.
 
         Output files are either written to a temporary directory or to the
-        specified output directory.  Output filenames correspond to the template
-        '<model_name>-<YYYYMMDDHHMM>-<chain_id>' plus the file suffix which is
-        either '.csv' for the CmdStan output or '.txt' for
-        the console messages, e.g. 'bernoulli-201912081451-1.csv'.
-        Output files written to the temporary directory contain an additional
-        8-character random string, e.g. 'bernoulli-201912081451-1-5nm6as7u.csv'.
+        specified output directory.  Ouput filenames correspond to the template
+        '<model_name>-<YYYYMMDDHHMM>' plus additional bits to identify which
+        output file it corresponds to. CmdStan output will suffix with
+        '_<chain_id>.csv' if there is more than one chain, and simply'.csv'
+        in the single-chain case. For example, 'bernoulli-20251107144515_1.csv'.
+        Console message output is written to a text file suffixed
+        `_stdout_<chain_id>.txt` if each chain executes in a separate process
+        (default behavior) or simply `_stdout.txt` if done so in a single
+        process, such as when STAN_THREADS is enabled and you are sampling
+        more than one chain.
 
         :param data: Values for all data variables in the model, specified
             either as a dictionary with entries matching the data variables,
@@ -1146,11 +1155,9 @@ def variational(
 
         Output files are either written to a temporary directory or to the
         specified output directory.  Output filenames correspond to the template
-        '<model_name>-<YYYYMMDDHHMM>-<chain_id>' plus the file suffix which is
-        either '.csv' for the CmdStan output or '.txt' for
-        the console messages, e.g. 'bernoulli-201912081451-1.csv'.
-        Output files written to the temporary directory contain an additional
-        8-character random string, e.g. 'bernoulli-201912081451-1-5nm6as7u.csv'.
+        '<model_name>-<YYYYMMDDHHMM>' plus the file suffix which is
+        either '.csv' for the CmdStan output or '_stdout.txt' for
+        the console messages, e.g. 'bernoulli-201912081451.csv'.
 
         :param data: Values for all data variables in the model, specified
             either as a dictionary with entries matching the data variables,
@@ -1429,7 +1436,7 @@ def pathfinder(
 
         :param save_profile: Whether or not to profile auto-diff operations in
             labelled blocks of code.  If ``True``, CSV outputs are written to
-            file '<model_name>-<YYYYMMDDHHMM>-profile-<path_id>'.
+            file '<model_name>-<YYYYMMDDHHMM>_profile.csv'.
             Introduced in CmdStan-2.26, see
             https://mc-stan.org/docs/cmdstan-guide/stan_csv.html,
             section "Profiling CSV output file" for details.
@@ -1659,7 +1666,7 @@ def laplace_sample(
 
         :param save_profile: Whether or not to profile auto-diff operations in
             labelled blocks of code.  If ``True``, CSV outputs are written to
-            file '<model_name>-<YYYYMMDDHHMM>-profile-<path_id>'.
+            file '<model_name>-<YYYYMMDDHHMM>_profile.csv'.
             Introduced in CmdStan-2.26, see
             https://mc-stan.org/docs/cmdstan-guide/stan_csv.html,
             section "Profiling CSV output file" for details.
diff --git a/cmdstanpy/stanfit/gq.py b/cmdstanpy/stanfit/gq.py
@@ -725,10 +725,7 @@ def _previous_draws_pd(
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy/stanfit/laplace.py b/cmdstanpy/stanfit/laplace.py
@@ -309,10 +309,7 @@ def column_names(self) -> tuple[str, ...]:
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy/stanfit/mcmc.py b/cmdstanpy/stanfit/mcmc.py
@@ -811,10 +811,7 @@ def method_variables(self) -> dict[str, np.ndarray]:
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy/stanfit/mle.py b/cmdstanpy/stanfit/mle.py
@@ -295,10 +295,7 @@ def stan_variables(
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy/stanfit/pathfinder.py b/cmdstanpy/stanfit/pathfinder.py
@@ -216,10 +216,7 @@ def is_resampled(self) -> bool:
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy/stanfit/runset.py b/cmdstanpy/stanfit/runset.py
@@ -38,62 +38,59 @@ def __init__(
         self._args = args
         self._chains = chains
         self._one_process_per_chain = one_process_per_chain
-        if one_process_per_chain:
-            self._num_procs = chains
-        else:
-            self._num_procs = 1
+        self._num_procs = chains if one_process_per_chain else 1
         self._retcodes = [-1 for _ in range(self._num_procs)]
         self._timeout_flags = [False for _ in range(self._num_procs)]
         if chain_ids is None:
             chain_ids = [i + 1 for i in range(chains)]
         self._chain_ids = chain_ids
 
         if args.output_dir is not None:
-            self._output_dir = args.output_dir
-        else:
-            # make a per-run subdirectory of our master temp directory
-            self._output_dir = tempfile.mkdtemp(
-                prefix=args.model_name, dir=_TMPDIR
-            )
+            self._outdir = args.output_dir
+        else:  # make a per-run subdirectory of our master temp directory
+            self._outdir = tempfile.mkdtemp(prefix=args.model_name, dir=_TMPDIR)
 
         # output files prefix: ``<model_name>-<YYYYMMDDHHMM>_<chain_id>``
         self._base_outfile = (
             f'{args.model_name}-{datetime.now().strftime(time_fmt)}'
         )
-        # per-process outputs
-        self._stdout_files = [''] * self._num_procs
-        self._profile_files = [''] * self._num_procs  # optional
-        if one_process_per_chain:
-            for i in range(chains):
-                self._stdout_files[i] = self.file_path("-stdout.txt", id=i)
-                if args.save_profile:
-                    self._profile_files[i] = self.file_path(
-                        ".csv", extra="-profile", id=chain_ids[i]
-                    )
+        self._stdout_files, self._profile_files = [], []
+        self._csv_files, self._diagnostic_files = [], []
+
+        # per-process output files
+        if one_process_per_chain and chains > 1:
+            self._stdout_files = [
+                self.gen_file_name(".txt", extra="stdout", id=id)
+                for id in self._chain_ids
+            ]
+            if args.save_profile:
+                self._profile_files = [
+                    self.gen_file_name(".csv", extra="profile", id=id)
+                    for id in self._chain_ids
+                ]
         else:
-            self._stdout_files[0] = self.file_path("-stdout.txt")
+            self._stdout_files = [self.gen_file_name(".txt", extra="stdout")]
             if args.save_profile:
-                self._profile_files[0] = self.file_path(
-                    ".csv", extra="-profile"
-                )
+                self._profile_files = [
+                    self.gen_file_name(".csv", extra="profile")
+                ]
 
         # per-chain output files
-        self._csv_files: list[str] = [''] * chains
-        self._diagnostic_files = [''] * chains  # optional
-
         if chains == 1:
-            self._csv_files[0] = self.file_path(".csv")
+            self._csv_files = [self.gen_file_name(".csv")]
             if args.save_latent_dynamics:
-                self._diagnostic_files[0] = self.file_path(
-                    ".csv", extra="-diagnostic"
-                )
+                self._diagnostic_files = [
+                    self.gen_file_name(".csv", extra="diagnostic")
+                ]
         else:
-            for i in range(chains):
-                self._csv_files[i] = self.file_path(".csv", id=chain_ids[i])
-                if args.save_latent_dynamics:
-                    self._diagnostic_files[i] = self.file_path(
-                        ".csv", extra="-diagnostic", id=chain_ids[i]
-                    )
+            self._csv_files = [
+                self.gen_file_name(".csv", id=id) for id in self._chain_ids
+            ]
+            if args.save_latent_dynamics:
+                self._diagnostic_files = [
+                    self.gen_file_name(".csv", extra="diagnostic", id=id)
+                    for id in self._chain_ids
+                ]
 
     def __repr__(self) -> str:
         repr = 'RunSet: chains={}, chain_ids={}, num_processes={}'.format(
@@ -173,14 +170,14 @@ def cmd(self, idx: int) -> list[str]:
         else:
             return self._args.compose_command(
                 idx,
-                csv_file=self.file_path('.csv'),
+                csv_file=self.gen_file_name('.csv'),
                 diagnostic_file=(
-                    self.file_path(".csv", extra="-diagnostic")
+                    self.gen_file_name(".csv", extra="diagnostic")
                     if self._args.save_latent_dynamics
                     else None
                 ),
                 profile_file=(
-                    self.file_path(".csv", extra="-profile")
+                    self.gen_file_name(".csv", extra="profile")
                     if self._args.save_profile
                     else None
                 ),
@@ -201,10 +198,7 @@ def stdout_files(self) -> list[str]:
 
     def _check_retcodes(self) -> bool:
         """Returns ``True`` when all chains have retcode 0."""
-        for code in self._retcodes:
-            if code != 0:
-                return False
-        return True
+        return all(retcode == 0 for retcode in self._retcodes)
 
     @property
     def diagnostic_files(self) -> list[str]:
@@ -216,16 +210,17 @@ def profile_files(self) -> list[str]:
         """List of paths to CmdStan profiler files."""
         return self._profile_files
 
-    # pylint: disable=invalid-name
-    def file_path(
+    def gen_file_name(
         self, suffix: str, *, extra: str = "", id: int | None = None
     ) -> str:
+        """Generate a standard file name according to CmdStan output pattern"""
+        file = self._base_outfile
+        if extra:
+            file += f"_{extra}"
         if id is not None:
-            suffix = f"_{id}{suffix}"
-        file = os.path.join(
-            self._output_dir, f"{self._base_outfile}{extra}{suffix}"
-        )
-        return file
+            file += f"_{id}"
+        file += suffix
+        return os.path.join(self._outdir, file)
 
     def _retcode(self, idx: int) -> int:
         """Get retcode for process[idx]."""
diff --git a/cmdstanpy/stanfit/vb.py b/cmdstanpy/stanfit/vb.py
@@ -249,10 +249,7 @@ def variational_sample_pd(self) -> pd.DataFrame:
 
     def save_csvfiles(self, dir: str | None = None) -> None:
         """
-        Move output CSV files to specified directory.  If files were
-        written to the temporary session directory, clean filename.
-        E.g., save 'bernoulli-201912081451-1-5nm6as7u.csv' as
-        'bernoulli-201912081451-1.csv'.
+        Move output CSV files to specified directory.
 
         :param dir: directory path
 
diff --git a/cmdstanpy_tutorial.ipynb b/cmdstanpy_tutorial.ipynb
@@ -92,6 +92,7 @@
     "CmdStanPy will use the following optional packages, if installed:\n",
     "\n",
     "* `xarray`, an n-dimension labeled dataset package which can be used for outputs\n",
+    "* `polars`, a highly-optimized data manipulation library, which can speed up processing outputs of large Stan models\n",
     "\n",
     "To install CmdStanPy with all the optional packages:\n",
     "\n",
@@ -402,7 +403,7 @@
    "hash": "d31ce8e45781476cfd394e192e0962028add96ff436d4fd4e560a347d206b9cb"
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -416,9 +417,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.10.19"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/docsrc/users-guide/outputs.rst b/docsrc/users-guide/outputs.rst
@@ -8,9 +8,9 @@ CSV File Outputs
 
 Underlyingly, the CmdStan outputs are a set of per-chain
 `Stan CSV files <https://mc-stan.org/docs/cmdstan-guide/stan_csv_apdx.html#mcmc-sampler-csv-output>`__.
-The filenames follow the template '<model_name>-<YYYYMMDDHHMMSS>-<chain_id>'
-plus the file suffix '.csv'.
-CmdStanPy also captures the per-chain console and error messages.
+The filenames follow the template '<model_name>-<YYYYMMDDHHMMSS>_<chain_id>'
+plus the file suffix '.csv'. CmdStanPy also captures the per-chain console and
+error messages.
 
 .. ipython:: python
 
diff --git a/test/test_generate_quantities.py b/test/test_generate_quantities.py
@@ -532,7 +532,7 @@ def test_serialization() -> None:
     fit1 = model.generate_quantities(data=jdata, previous_fit=fit_sampling)
 
     dumped = pickle.dumps(fit1)
-    shutil.rmtree(fit1.runset._output_dir)
+    shutil.rmtree(fit1.runset._outdir)
     fit2: CmdStanGQ[CmdStanMCMC] = pickle.loads(dumped)
     variables1 = fit1.stan_variables()
     variables2 = fit2.stan_variables()
diff --git a/test/test_optimize.py b/test/test_optimize.py
diff --git a/test/test_runset.py b/test/test_runset.py
diff --git a/test/test_sample.py b/test/test_sample.py
diff --git a/test/test_variational.py b/test/test_variational.py
