Merge branch 'develop'

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
     exclude: ^example/AlN-LDA/
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.6.5
+  rev: v0.6.7
   hooks:
   - id: ruff
     args: [ "--fix", "--show-fixes" ]

c/real_to_reciprocal.c

@@ -80,8 +80,8 @@ void r2r_real_to_reciprocal(lapack_complex_double *fc3_reciprocal,
                             const AtomTriplets *atom_triplets,
                             const long openmp_per_triplets) {
     long i, j, num_band, num_patom, num_satom, adrs_vec;
-    lapack_complex_double *pre_phase_factors, *phase_factor0, *phase_factor1,
-        *phase_factor2;
+    lapack_complex_double *pre_phase_factors, *phase_factors, *phase_factor0,
+        *phase_factor1, *phase_factor2;
 
     num_patom = atom_triplets->multi_dims[1];
     num_satom = atom_triplets->multi_dims[0];
@@ -92,12 +92,11 @@ void r2r_real_to_reciprocal(lapack_complex_double *fc3_reciprocal,
         pre_phase_factors[i] = get_pre_phase_factor(i, q_vecs, atom_triplets);
     }
 
-    phase_factor0 = (lapack_complex_double *)malloc(
-        sizeof(lapack_complex_double) * num_patom * num_satom);
-    phase_factor1 = (lapack_complex_double *)malloc(
-        sizeof(lapack_complex_double) * num_patom * num_satom);
-    phase_factor2 = (lapack_complex_double *)malloc(
-        sizeof(lapack_complex_double) * num_patom * num_satom);
+    phase_factors = (lapack_complex_double *)malloc(
+        sizeof(lapack_complex_double) * 3 * num_patom * num_satom);
+    phase_factor0 = phase_factors;
+    phase_factor1 = phase_factors + num_patom * num_satom;
+    phase_factor2 = phase_factors + 2 * num_patom * num_satom;
     for (i = 0; i < num_patom; i++) {
         for (j = 0; j < num_satom; j++) {
             adrs_vec = j * atom_triplets->multi_dims[1] + i;
@@ -132,11 +131,10 @@ void r2r_real_to_reciprocal(lapack_complex_double *fc3_reciprocal,
 
     free(pre_phase_factors);
     pre_phase_factors = NULL;
-    free(phase_factor0);
+    free(phase_factors);
+    phase_factors = NULL;
+    phase_factor0 = NULL;
     phase_factor1 = NULL;
-    free(phase_factor1);
-    phase_factor1 = NULL;
-    free(phase_factor2);
     phase_factor2 = NULL;
 }
 

doc/changelog.md

@@ -2,6 +2,10 @@
 
 # Change Log
 
+## Sep-24-2024: Version 3.5.2
+
+- Fix a memory leak.
+
 ## Sep-19-2024: Version 3.5.1
 
 - A small fix.

doc/conf.py

@@ -60,7 +60,7 @@ copyright = "2015, Atsushi Togo"
 # The short X.Y version.
 version = "3.5"
 # The full version, including alpha/beta/rc tags.
-release = "3.5.1"
+release = "3.5.2"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

doc/pypolymlp.md

@@ -15,13 +15,15 @@ The training process involves using a dataset consisting of supercell
 displacements, forces, and energies. The trained MLPs are then employed to
 compute forces for supercells with specific displacements.
 
-For more details on the methodology, refer to <u>A. Togo and A. Seko, J. Chem. Phys.
-**160**, 211001 (2024)</u> [[doi](https://doi.org/10.1063/5.0211296)].
+For further details on combining phono3py calculations with pypolymlp, refer to
+<u>A. Togo and A. Seko, J. Chem. Phys. **160**, 211001 (2024)</u>
+[[doi](https://doi.org/10.1063/5.0211296)]
+[[arxiv](https://arxiv.org/abs/2401.17531)].
 
 An example of its usage can be found in the `example/NaCl-pypolymlp` directory
 in the distribution from GitHub or PyPI.
 
-## Requirement
+## Requirements
 
 - [pypolymlp](https://github.com/sekocha/pypolymlp)
 - [symfc](https://github.com/symfc/symfc)
@@ -36,7 +38,8 @@ in the distribution from GitHub or PyPI.
    supercells. The dataset must be stored in a phono3py-yaml-like file, e.g.,
    `phono3py_params.yaml`. Use {ref}`--cf3 <cf3_option>` and {ref}`--sp
    <sp_option>` option simultaneously.
-4. Develop MLPs. At this step `phono3py.pmlp` is saved.
+4. Develop MLPs. By default, 90 and 10 percents of the dataset are used for the
+   training and test, respectively. At this step `phono3py.pmlp` is saved.
 5. Generate displacements in supercells either systematic or random displacements.
 6. Evaluate MLPs for forces of the supercells generated in step 5.
 7. Calculate force constants from displacement-force dataset from steps 5 and 6.
@@ -227,7 +230,7 @@ displacement distance of 0.001 Angstrom. The forces for these supercells are
 then evaluated using pypolymlp. Both the generated displacements and the
 corresponding forces are stored in the `phono3py_mlp_eval_dataset` file.
 
-### Steps 4-6: Force constants calculation (random displacements in step 5)
+### Steps 4-7: Force constants calculation (random displacements in step 5)
 
 After developing MLPs, random displacements are generated by specifying
 {ref}`--rd <random_displacements_option>` option. To compute force constants
@@ -244,7 +247,7 @@ Having `phono3py_params.yaml`, phono3py is executed with `--pypolymlp` option,
  | |_) | | | | (_) | | | | (_) |__) | |_) | |_| |
  | .__/|_| |_|\___/|_| |_|\___/____/| .__/ \__, |
  |_|                                |_|    |___/
-                       3.5.0-dev22+g575c4107
+                                           3.5.0
 
 -------------------------[time 2024-09-19 15:33:23]-------------------------
 Compiled with OpenMP support (max 10 threads).
@@ -327,3 +330,48 @@ displacements are generated. These displacements are then inverted, resulting in
 an additional 200 supercells. In total, 400 supercells are created. The forces
 for these supercells are then evaluated. Finally, the force constants are
 calculated using symfc.
+
+## Convergence with respect to dataset size
+
+In general, increasing the amount of data improves the accuracy of representing
+force constants. Therefore, it is recommended to check the convergence of the
+target property with respect to the number of supercells in the training
+dataset. Lattice thermal conductivity may be a convenient property to monitor
+when assessing convergence.
+
+## Parameters for developing MLPs
+
+A few parameters can be specified using the `--mlp-params` option for the
+development of MLPs. The parameters are provided as a string, e.g.,
+
+```bash
+% phono3py-load phono3py_params.yaml --pypolymlp --mlp-params="ntrain=80, ntest=20"
+```
+
+Parameters are separated by commas for configuration. A brief explanation of the
+available parameters can be found in the docstring of `PypolymlpParams` that is
+found by
+
+```python
+In [1]: from phonopy.interface.pypolymlp import PypolymlpParams
+
+In [2]: help(PypolymlpParams)
+```
+
+`ntrain` and `ntest` are implemented in phono3py, while the remaining parameters
+are directly passed to pypolymlp. Optimizing pypolymlp parameters can be
+difficult, both in terms of achieving accuracy and managing the computational
+resources required. The current default parameters are likely suitable for
+systems up to ternary compounds. For binary systems, the calculations can
+generally be run on standard laptop computers, but for ternary systems, around
+40 GB of memory or more may be necessary.
+
+For parameter adjustments, it is recommended to consult the
+[pypolymlp](https://github.com/sekocha/pypolymlp) documentation and review the
+ relevant research papers.
+
+### `ntrain` and `ntest`
+
+This method provides a straightforward dataset split: the first `ntrain`
+supercells from the list are used for training, while the last `ntest`
+supercells are reserved for testing.

phono3py/file_IO.py

@@ -413,6 +413,26 @@ def read_fc2_from_hdf5(filename="fc2.hdf5", p2s_map=None):
     )
 
 
+def write_datasets_to_hdf5(
+    dataset: dict,
+    phonon_dataset: dict = None,
+    filename: str = "datasets.hdf5",
+    compression: str = "gzip",
+):
+    """Write dataset and phonon_dataset in datasets.hdf5."""
+
+    def _write_dataset(w, dataset: dict, group_name: str):
+        dataset_w = w.create_group(group_name)
+        for key in dataset:
+            dataset_w.create_dataset(key, data=dataset[key], compression=compression)
+
+    with h5py.File(filename, "w") as w:
+        w.create_dataset("version", data=np.bytes_(__version__))
+        _write_dataset(w, dataset, "dataset")
+        if phonon_dataset:
+            _write_dataset(w, phonon_dataset, "phonon_dataset")
+
+
 def write_grid_address_to_hdf5(
     grid_address,
     mesh,

phono3py/phonon3/interaction.py

@@ -304,7 +304,7 @@ class Interaction:
 
     def get_triplets_at_q(
         self,
-    ) -> tuple(np.ndarray, np.ndarray, np.ndarray, np.ndarray):
+    ) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
         """Return grid point triplets information.
 
         triplets_at_q is in BZ-grid.
@@ -414,7 +414,7 @@ class Interaction:
         )
         return self.zero_value_positions
 
-    def get_phonons(self) -> tuple(np.ndarray, np.ndarray, np.ndarray):
+    def get_phonons(self) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
         """Return phonons on grid.
 
         Returns
@@ -538,7 +538,7 @@ class Interaction:
 
     def get_primitive_and_supercell_correspondence(
         self,
-    ) -> tuple(np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray):
+    ) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
         """Return atomic pair information."""
         return (self._svecs, self._multi, self._p2s, self._s2p, self._masses)
 

phono3py/version.py

@@ -34,4 +34,4 @@
 # ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 # POSSIBILITY OF SUCH DAMAGE.
 
-__version__ = "3.5.1"
+__version__ = "3.5.2"