merge devel to master (v0.12.1) (#1507)

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "devel"

.github/workflows/test.yml

@@ -21,7 +21,9 @@ jobs:
       run: pip install -e .[test]
     - name: Test
       run: coverage run --source=./dpgen -m unittest -v && coverage report
-    - uses: codecov/codecov-action@v3
+    - uses: codecov/codecov-action@v4
+      env:
+        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
   pass:
     needs: [build]
     runs-on: ubuntu-latest

.mailmap

@@ -0,0 +1 @@
+Jinzhe Zeng <[email protected]>

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
     # there are many log files in tests
     # TODO: seperate py files and log files
@@ -28,7 +28,7 @@ repos:
 
 # Python
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.3
+    rev: v0.3.5
     hooks:
     - id: ruff
       args: ["--fix"]

MANIFEST.in

@@ -0,0 +1,4 @@
+prune conda
+prune doc
+prune tests
+prune examples

README.md

@@ -23,10 +23,10 @@ Yuzhi Zhang, Haidi Wang, Weijie Chen, Jinzhe Zeng, Linfeng Zhang, Han Wang, and
 
 ## Download and Install
 
-DP-GEN only supports Python 3.9 and above. You can use one of the following methods to install DP-GEN:
+DP-GEN only supports Python 3.9 and above. You can [setup a conda/pip environment](https://docs.deepmodeling.com/faq/conda.html), and then use one of the following methods to install DP-GEN:
 
 - Install via pip: `pip install dpgen`
-- Install via conda: `conda install -c conda-forge dpgen``
+- Install via conda: `conda install -c conda-forge dpgen`
 - Install from source code: `git clone https://github.com/deepmodeling/dpgen && pip install ./dpgen`
 
 To test if the installation is successful, you may execute

dpgen/auto_test/lib/lammps.py

@@ -189,9 +189,7 @@ def make_lammps_eval(conf, type_map, interaction, param):
     ret += (
         "thermo_style    custom step pe pxx pyy pzz pxy pxz pyz lx ly lz vol c_mype\n"
     )
-    ret += (
-        "dump            1 all custom 100 dump.relax id type xs ys zs fx fy fz\n"
-    )  # 06/09 give dump.relax
+    ret += "dump            1 all custom 100 dump.relax id type xs ys zs fx fy fz\n"  # 06/09 give dump.relax
     ret += "run    0\n"
     ret += "variable        N equal count(all)\n"
     ret += "variable        V equal vol\n"

dpgen/auto_test/lib/mfp_eosfit.py

@@ -1441,16 +1441,7 @@ def ext_velp(
     )
     for i in range(ndata):
         fw.write(
-            "{:12.6f}\t{:12.6f}\t{:12.6f}\t{:12.6f}\t{:12.6f}\t{:12.6f}\t{:12.6f}\t{:12.6f}\n".format(
-                vv[i],
-                ee[i],
-                cellaa[i],
-                cellbb[i],
-                cellcc[i],
-                cellbaba[i],
-                cellcaca[i],
-                cellca_cal[i],
-            )
+            f"{vv[i]:12.6f}\t{ee[i]:12.6f}\t{cellaa[i]:12.6f}\t{cellbb[i]:12.6f}\t{cellcc[i]:12.6f}\t{cellbaba[i]:12.6f}\t{cellcaca[i]:12.6f}\t{cellca_cal[i]:12.6f}\n"
         )
         fw.flush()
     fw.close()
@@ -1662,9 +1653,7 @@ def lsqfit_eos(
     )
     for i in range(len(vol)):
         fve.write(
-            "{:20f}\t{:20f}\t{:20f}\t{:20f}\n".format(
-                vol[i], repro_en[i], en[i], 100 * np.abs((en[i] - repro_en[i]) / en[i])
-            )
+            f"{vol[i]:20f}\t{repro_en[i]:20f}\t{en[i]:20f}\t{100 * np.abs((en[i] - repro_en[i]) / en[i]):20f}\n"
         )
         fve.flush()
         p_tmp = repro_press[i]

dpgen/auto_test/lib/pwscf.py

@@ -72,12 +72,7 @@ def _make_pwscf_03_config(sys_data):
     cc = 0
     for ii in range(ntypes):
         for jj in range(atom_numbs[ii]):
-            ret += "{} {:f} {:f} {:f}\n".format(
-                atom_names[ii],
-                coordinates[cc][0],
-                coordinates[cc][1],
-                coordinates[cc][2],
-            )
+            ret += f"{atom_names[ii]} {coordinates[cc][0]:f} {coordinates[cc][1]:f} {coordinates[cc][2]:f}\n"
             cc += 1
     return ret
 

dpgen/auto_test/reproduce.py

@@ -153,12 +153,7 @@ def post_repro(
             output_ener_tot.extend(output_task_result["energies"])
 
             init_epa = init_ener[jj - idid] / natoms
-            ptr_data += "{} {:7.3f}  {:7.3f}  {:7.3f}\n".format(
-                ii,
-                init_epa,
-                output_epa,
-                output_epa - init_epa,
-            )
+            ptr_data += f"{ii} {init_epa:7.3f}  {output_epa:7.3f}  {output_epa - init_epa:7.3f}\n"
         idid += nframe
         output_ener = np.array(output_ener)
         output_ener = np.reshape(output_ener, [-1, 1])

dpgen/collect/collect.py

@@ -8,6 +8,7 @@
 import dpdata
 
 from dpgen.generator.run import data_system_fmt
+from dpgen.util import expand_sys_str
 
 
 def collect_data(
@@ -18,7 +19,8 @@ def collect_data(
     # goto input
     cwd = os.getcwd()
     os.chdir(target_folder)
-    jdata = json.load(open(param_file))
+    with open(param_file) as fp:
+        jdata = json.load(fp)
     sys_configs_prefix = jdata.get("sys_configs_prefix", "")
     sys_configs = jdata.get("sys_configs", [])
     if verbose:
@@ -46,6 +48,7 @@ def collect_data(
     for ii in range(len(iters)):
         iter_data = glob.glob(os.path.join(iters[ii], "02.fp", "data.[0-9]*[0-9]"))
         iter_data.sort()
+        iter_data = sum([expand_sys_str(ii) for ii in iter_data], [])
         for jj in iter_data:
             sys = dpdata.LabeledSystem(jj, fmt="deepmd/npy")
             if merge:

dpgen/data/surf.py

@@ -415,7 +415,10 @@ def poscar_scale(poscar_in, poscar_out, scale):
     except AttributeError:
         poscar = Poscar.from_str("".join(lines))
     with open(poscar_out, "w") as fout:
-        fout.write(poscar.get_string(direct=False))
+        try:
+            fout.write(poscar.get_string(direct=False))
+        except AttributeError:
+            fout.write(poscar.get_str(direct=False))
 
 
 def make_scale(jdata):

dpgen/data/tools/bcc.py

@@ -17,7 +17,7 @@ def poscar_unit(latt):
     ret += f"{box[0][0]:.16f} {box[0][1]:.16f} {box[0][2]:.16f}\n"
     ret += f"{box[1][0]:.16f} {box[1][1]:.16f} {box[1][2]:.16f}\n"
     ret += f"{box[2][0]:.16f} {box[2][1]:.16f} {box[2][2]:.16f}\n"
-    ret += "Type\n"
+    ret += "X\n"
     ret += "%d\n" % numb_atoms()
     ret += "Direct\n"
     ret += f"{0.0:.16f} {0.0:.16f} {0.0:.16f}\n"

dpgen/data/tools/diamond.py

@@ -22,7 +22,7 @@ def poscar_unit(latt):
     ret += f"{box[0][0]:.16f} {box[0][1]:.16f} {box[0][2]:.16f}\n"
     ret += f"{box[1][0]:.16f} {box[1][1]:.16f} {box[1][2]:.16f}\n"
     ret += f"{box[2][0]:.16f} {box[2][1]:.16f} {box[2][2]:.16f}\n"
-    ret += "Type\n"
+    ret += "X\n"
     ret += "%d\n" % numb_atoms()
     ret += "Direct\n"
     ret += f"{0.12500000000000:.16f} {0.12500000000000:.16f} {0.12500000000000:.16f}\n"

dpgen/data/tools/fcc.py

@@ -17,7 +17,7 @@ def poscar_unit(latt):
     ret += f"{box[0][0]:.16f} {box[0][1]:.16f} {box[0][2]:.16f}\n"
     ret += f"{box[1][0]:.16f} {box[1][1]:.16f} {box[1][2]:.16f}\n"
     ret += f"{box[2][0]:.16f} {box[2][1]:.16f} {box[2][2]:.16f}\n"
-    ret += "Type\n"
+    ret += "X\n"
     ret += "%d\n" % numb_atoms()
     ret += "Direct\n"
     ret += f"{0.0:.16f} {0.0:.16f} {0.0:.16f}\n"

dpgen/data/tools/hcp.py

@@ -20,7 +20,7 @@ def poscar_unit(latt):
     ret += f"{box[0][0]:.16f} {box[0][1]:.16f} {box[0][2]:.16f}\n"
     ret += f"{box[1][0]:.16f} {box[1][1]:.16f} {box[1][2]:.16f}\n"
     ret += f"{box[2][0]:.16f} {box[2][1]:.16f} {box[2][2]:.16f}\n"
-    ret += "Type\n"
+    ret += "X\n"
     ret += "%d\n" % numb_atoms()
     ret += "Direct\n"
     ret += f"{0:.16f} {0:.16f} {0:.16f}\n"

dpgen/data/tools/ovito_file_convert.py

@@ -2,6 +2,7 @@
 """This Script is adapted from Alexander Stukowski, the author of OVITO.
 See: http://forum.ovito.org/index.php?topic=131.0 for details.
 """
+
 import argparse
 
 from ovito.io import export_file, import_file

dpgen/data/tools/sc.py

@@ -17,7 +17,7 @@ def poscar_unit(latt):
     ret += f"{box[0][0]:.16f} {box[0][1]:.16f} {box[0][2]:.16f}\n"
     ret += f"{box[1][0]:.16f} {box[1][1]:.16f} {box[1][2]:.16f}\n"
     ret += f"{box[2][0]:.16f} {box[2][1]:.16f} {box[2][2]:.16f}\n"
-    ret += "Type\n"
+    ret += "X\n"
     ret += "%d\n" % numb_atoms()
     ret += "Direct\n"
     ret += f"{0.0:.16f} {0.0:.16f} {0.0:.16f}\n"

dpgen/generator/arginfo.py

@@ -90,7 +90,7 @@ def training_args() -> list[Argument]:
     doc_numb_models = "Number of models to be trained in 00.train. 4 is recommend."
     doc_training_iter0_model_path = "The model used to init the first iter training. Number of element should be equal to numb_models."
     doc_training_init_model = "Iteration > 0, the model parameters will be initilized from the model trained at the previous iteration. Iteration == 0, the model parameters will be initialized from training_iter0_model_path."
-    doc_default_training_param = "Training parameters for deepmd-kit in 00.train. You can find instructions from here: (https://github.com/deepmodeling/deepmd-kit)."
+    doc_default_training_param = "Training parameters for deepmd-kit in 00.train. You can find instructions from `DeePMD-kit documentation <https://docs.deepmodeling.org/projects/deepmd/>`_."
     doc_dp_train_skip_neighbor_stat = "Append --skip-neighbor-stat flag to dp train."
     doc_dp_compress = "Use dp compress to compress the model."
     doc_training_reuse_iter = "The minimal index of iteration that continues training models from old models of last iteration."
@@ -221,8 +221,8 @@ def model_devi_jobs_template_args() -> Argument:
         "Through user-defined template, any freedom (function) that is permitted by the engine "
         "software could be inherited (invoked) in the workflow."
     )
-    doc_template_lmp = "The path to input.lammps template"
-    doc_template_plm = "The path to input.plumed template"
+    doc_template_lmp = "The path to input.lammps template. Instructions can be found in `LAMMPS documentation <https://docs.lammps.org/>`_."
+    doc_template_plm = "The path to input.plumed template. Instructions can be found in `PLUMED documentation <https://www.plumed.org/doc>`_."
 
     args = [
         Argument("lmp", str, optional=True, doc=doc_template_lmp),
@@ -325,10 +325,12 @@ def model_devi_lmp_args() -> list[Argument]:
     doc_model_devi_f_trust_hi = "Upper bound of forces for the selection. If list or dict, should be set for each index in sys_configs, respectively."
     doc_model_devi_v_trust_lo = "Lower bound of virial for the selection. If list or dict, should be set for each index in sys_configs, respectively. Should be used with DeePMD-kit v2.x."
     doc_model_devi_v_trust_hi = "Upper bound of virial for the selection. If list or dict, should be set for each index in sys_configs, respectively. Should be used with DeePMD-kit v2.x."
-    doc_model_devi_adapt_trust_lo = "Adaptively determines the lower trust levels of force and virial. This option should be used together with model_devi_numb_candi_f, model_devi_numb_candi_v and optionally with model_devi_perc_candi_f and model_devi_perc_candi_v. dpgen will make two sets:\n\n\
+    doc_model_devi_adapt_trust_lo = (
+        "Adaptively determines the lower trust levels of force and virial. This option should be used together with model_devi_numb_candi_f, model_devi_numb_candi_v and optionally with model_devi_perc_candi_f and model_devi_perc_candi_v. dpgen will make two sets:\n\n\
 - 1. From the frames with force model deviation lower than model_devi_f_trust_hi, select max(model_devi_numb_candi_f, model_devi_perc_candi_f*n_frames) frames with largest force model deviation. \n\n\
 - 2. From the frames with virial model deviation lower than model_devi_v_trust_hi, select max(model_devi_numb_candi_v, model_devi_perc_candi_v*n_frames) frames with largest virial model deviation. \n\n\
 The union of the two sets is made as candidate dataset."
+    )
     doc_model_devi_numb_candi_f = "See model_devi_adapt_trust_lo."
     doc_model_devi_numb_candi_v = "See model_devi_adapt_trust_lo."
     doc_model_devi_perc_candi_f = "See model_devi_adapt_trust_lo."
@@ -790,13 +792,14 @@ def fp_style_cp2k_args() -> list[Argument]:
     ]
 
 
+# amber/diff
 def fp_style_amber_diff_args() -> list[Argument]:
     """Arguments for FP style amber/diff.
 
     Returns
     -------
     list[dargs.Argument]
-        list of Gaussian fp style arguments
+        list of amber/diff fp style arguments
     """
     doc_fp_params_gaussian = "Parameters for FP calculation."
     doc_high_level = (
@@ -827,13 +830,49 @@ def fp_style_amber_diff_args() -> list[Argument]:
     ]
 
 
+# pwscf
+def fp_style_pwscf_args() -> list[Argument]:
+    """Arguments for FP style pwscf (Quantum Espresso).
+
+    Returns
+    -------
+    list[dargs.Argument]
+        list of pwscf fp style arguments
+    """
+    doc_fp_pp_path = "Directory of psuedo-potential file to be used for 02.fp exists."
+    doc_fp_pp_files = "Psuedo-potential file to be used for 02.fp. Note that the order of elements should correspond to the order in type_map."
+    doc_user_fp_params = "Parameters for pwscf calculation. Find details at https://www.quantum-espresso.org/Doc/INPUT_PW.html. When user_fp_params is set, the settings in fp_params will be ignored. If one wants to use user_fp_params, kspacing must be set in user_fp_params. kspacing is the spacing between kpoints, and helps to determin KPOINTS in pwscf."
+    doc_fp_params = (
+        "Parameters for pwscf calculation. It has lower priority than user_fp_params."
+    )
+    doc_ecut = "ecutwfc in pwscf."
+    doc_ediff = "conv_thr and ts_vdw_econv_thr in pwscf."
+    doc_kspacing = "The spacing between kpoints. Helps to determin KPOINTS in pwscf."
+    doc_smearing = "smearing in pwscf."
+    doc_sigma = "degauss in pwscf."
+
+    args = [
+        Argument("ecut", float, optional=False, doc=doc_ecut),
+        Argument("ediff", float, optional=False, doc=doc_ediff),
+        Argument("smearing", str, optional=False, doc=doc_smearing),
+        Argument("sigma", float, optional=False, doc=doc_sigma),
+        Argument("kspacing", float, optional=False, doc=doc_kspacing),
+    ]
+    return [
+        Argument("fp_pp_path", str, optional=False, doc=doc_fp_pp_path),
+        Argument("fp_pp_files", list[str], optional=False, doc=doc_fp_pp_files),
+        Argument("fp_params", dict, args, [], optional=True, doc=doc_fp_params),
+        Argument("user_fp_params", dict, optional=True, doc=doc_user_fp_params),
+    ]
+
+
 def fp_style_custom_args() -> list[Argument]:
     """Arguments for FP style custom.
 
     Returns
     -------
     list[dargs.Argument]
-        list of Gaussian fp style arguments
+        list of custom fp style arguments
     """
     doc_fp_params_custom = "Parameters for FP calculation."
     doc_input_fmt = "Input dpdata format of the custom FP code. Such format should only need the first argument as the file name."
@@ -883,7 +922,7 @@ def fp_style_variant_type_args() -> Variant:
                 "amber/diff", dict, fp_style_amber_diff_args(), doc=doc_amber_diff
             ),
             Argument("pwmat", dict, [], doc="TODO: add doc"),
-            Argument("pwscf", dict, [], doc="TODO: add doc"),
+            Argument("pwscf", dict, fp_style_pwscf_args()),
             Argument("custom", dict, fp_style_custom_args(), doc=doc_custom),
         ],
         optional=False,

dpgen/generator/lib/abacus_scf.py

@@ -401,9 +401,9 @@ def get_abacus_STRU(STRU, INPUT=None, n_ele=None):
     data["atom_types"] = types
     data["cells"] = cell
     data["coords"] = coords
-    data[
-        "atom_masses"
-    ] = masses  # Notice that this key is not defined in dpdata system.
+    data["atom_masses"] = (
+        masses  # Notice that this key is not defined in dpdata system.
+    )
     data["pp_files"] = pp_files
     data["orb_files"] = orb_files
     data["dpks_descriptor"] = dpks_descriptor