pwact 0.3.1__py3-none-any.whl → 0.3.3__py3-none-any.whl

pwact/active_learning/environment.py

@@ -8,7 +8,7 @@ def comm_info():
     print("\n" + "=" * 50) 
     print("         PWACT Basic Information")
     print("=" * 50) 
-    print("Version: 0.3.0")
+    print("Version: 0.3.1")
     print("Compatible pwdata: >= 0.5.0")
     print("Compatible MatPL: >= 2025.3")
     print("Contact: support@pwmat.com")

pwact/active_learning/explore/run_model_md.py

@@ -80,7 +80,8 @@ class Explore(object):
     def back_explore(self):
         slurm_remain, slurm_success = get_slurm_job_run_info(self.real_md_dir, \
         job_patten="*-{}".format(EXPLORE_FILE_STRUCTURE.md_job), \
-        tag_patten="*-{}".format(EXPLORE_FILE_STRUCTURE.md_tag))
+        tag_patten="*-{}".format(EXPLORE_FILE_STRUCTURE.md_tag),
+        for_back = True)
         slurm_done = True if len(slurm_remain) == 0 and len(slurm_success) > 0 else False
         if slurm_done:
             # bk and do new job
@@ -180,9 +181,6 @@ class Explore(object):
             job_patten="*-{}".format(EXPLORE_FILE_STRUCTURE.md_job), \
             tag_patten="*-{}".format(EXPLORE_FILE_STRUCTURE.md_tag))
         # for slurm remain, check if tags done
-        slurm_done = True if len(slurm_remain) == 0 and len(slurm_success) > 0 else False
-        if slurm_done is False:
-            slurm_remain = recheck_slurm_by_jobtag(slurm_remain, EXPLORE_FILE_STRUCTURE.md_tag)
         if len(slurm_remain) > 0:
             #recover slurm jobs
             if len(slurm_remain) > 0:

pwact/active_learning/label/labeling.py

@@ -149,7 +149,8 @@ class Labeling(object):
         if self.input_param.scf.dft_style == DFT_STYLE.bigmodel:
             slurm_remain, slurm_success = get_slurm_job_run_info(self.real_bigmodel_dir, \
                 job_patten="*-{}".format(LABEL_FILE_STRUCTURE.bigmodel_job), \
-                tag_patten="*-{}".format(LABEL_FILE_STRUCTURE.bigmodel_tag))
+                tag_patten="*-{}".format(LABEL_FILE_STRUCTURE.bigmodel_tag),
+                for_back = True)
             slurm_done = True if len(slurm_remain) == 0 and len(slurm_success) > 0 else False        
         else:
             slurm_remain, slurm_success = get_slurm_job_run_info(self.real_scf_dir, \

pwact/active_learning/train/train_model.py

@@ -50,7 +50,8 @@ class ModelTrian(object):
     def back_train(self):
         slurm_remain, slurm_success = get_slurm_job_run_info(self.real_train_dir, \
             job_patten="*-{}".format(TRAIN_FILE_STRUCTUR.train_job), \
-            tag_patten="*-{}".format(TRAIN_FILE_STRUCTUR.train_tag))
+            tag_patten="*-{}".format(TRAIN_FILE_STRUCTUR.train_tag),
+            for_back = True)
         slurm_done = True if len(slurm_remain) == 0 and len(slurm_success) > 0 else False # len(slurm_remain) > 0 exist slurm jobs need to do
         if slurm_done:
             # bk and do new job

pwact/active_learning/user_input/resource.py

@@ -6,7 +6,7 @@ class Resource(object):
     # scf_style for init_bulk relabel
     def __init__(self, json_dict:dict, job_type:str=AL_WORK.run_iter, dft_style:str=None, scf_style:str=None) -> None:
         if job_type == AL_WORK.run_iter:
-            self.train_resource = self.get_resource(get_required_parameter("train", json_dict))
+            self.train_resource = self.get_resource(get_required_parameter("train", json_dict), default_groupsize=1)
             if self.train_resource.number_node > 1:
                 self.train_resource.number_node = 1
             if self.train_resource.gpu_per_node > 1:
@@ -16,28 +16,28 @@ class Resource(object):
             print("Warining: the resouce of node, gpu per node and cpu per node  in training automatically adjust to [1, 1, 1]")
             self.train_resource.command = self.train_resource.command.upper()
              
-            self.explore_resource = self.get_resource(get_required_parameter("explore", json_dict))
+            self.explore_resource = self.get_resource(get_required_parameter("explore", json_dict), default_groupsize=1)
             if "-in" in self.explore_resource.command:
                 self.explore_resource.command = self.explore_resource.command.split('-in')[0].strip()
             self.explore_resource.command = "{} -in {} > {}".format(self.explore_resource.command, LAMMPS.input_lammps, SLURM_OUT.md_out)
         else:
             if "explore" in json_dict.keys():
-                self.explore_resource = self.get_resource(get_required_parameter("explore", json_dict))
+                self.explore_resource = self.get_resource(get_required_parameter("explore", json_dict), default_groupsize=1)
             else:
                 self.explore_resource = None
         # check dft resource
         if "dft" in json_dict.keys():
-            self.dft_resource = self.get_resource(get_required_parameter("dft", json_dict))
+            self.dft_resource = self.get_resource(get_required_parameter("dft", json_dict), default_groupsize=-1)
         else:
             self.dft_resource = ResourceDetail("mpirun -np 1 PWmat", 1, 1, 1, 1, 1, None, None, None)
 
         if "direct" in json_dict.keys():
-            self.direct_resource = self.get_resource(get_required_parameter("direct", json_dict))
+            self.direct_resource = self.get_resource(get_required_parameter("direct", json_dict), default_groupsize=1)
         else:
             self.direct_resource = None
 
         if "scf" in json_dict.keys():
-            self.scf_resource = self.get_resource(get_parameter("scf", json_dict, None))
+            self.scf_resource = self.get_resource(get_parameter("scf", json_dict, None), default_groupsize=-1) 
         else:
             self.scf_resource = None
         # dftb_command = get_parameter("dftb_command", json_dict["dft"], None)
@@ -66,9 +66,9 @@ class Resource(object):
     #         cls._instance = cls(json_dict)
     #     return cls._instance
     
-    def get_resource(self, json_dict:dict):
+    def get_resource(self, json_dict:dict, default_groupsize=1):
         command = get_required_parameter("command", json_dict)
-        group_size = get_parameter("group_size", json_dict, 1)
+        group_size = get_parameter("group_size", json_dict, default_groupsize)
         parallel_num = get_parameter("parallel_num", json_dict, 1)
         number_node = get_parameter("number_node", json_dict, 1)
         gpu_per_node = get_parameter("gpu_per_node", json_dict, 0)

pwact/main.py

@@ -183,14 +183,20 @@ def gather_pwmata(input_cmds):
     pwdata_lists = sorted(pwdata_lists)
     save_dir = "./final_pwdata"
     res_data_list = []
-    for pwdata in pwdata_lists: # /path/iter.0001/label/result/md.000.sys.001.t.001
-        data_name = os.path.basename(pwdata) # md.000.sys.001.t.001
+
+    for pwdata in pwdata_lists: # /path/iter.0001/label/result/*
+        data_name = os.path.basename(pwdata) 
         iter_name = os.path.basename(os.path.dirname(os.path.dirname(os.path.dirname(pwdata)))) #iter.0001
-        target_dir = os.path.join(save_dir, iter_name, data_name) #./final_pwdata/iter.0001/md.000.sys.001.t.001
+        target_dir = os.path.join(save_dir, iter_name, data_name) #./final_pwdata/iter.0001
         copy_dir(pwdata, target_dir)
-        # print("target: {}\n source: {}\n".format(target_dir, pwdata))
-        res_data_list.append(target_dir)
-
+        for path, dirList, fileList in os.walk(pwdata):
+            for _ in fileList:
+                if "train.xyz" in _:
+                    res_data_list.append(os.path.join(path, _))
+        for root, dirs, files in os.walk(pwdata):
+                if 'energies.npy' in files:
+                    res_data_list.append(root)
+        
     result_lines = ["\"{}\",".format(_) for _ in res_data_list]
     result_lines = "\n".join(result_lines)
     # result_lines = result_lines[:-1] # Filter the last ','

pwact/utils/process_tool.py

@@ -8,7 +8,7 @@ def kill_process(pid:str, job_id:str):
     if job_id is None:
         try:
             # 发送终止信号 (SIGTERM) 给指定的进程
-            os.kill(pid, signal.SIGTERM)
+            os.kill(int(pid), signal.SIGTERM)
             print(f"process {pid} has been terminated.")
         except ProcessLookupError:
             print(f"process {pid} non-existent.")

pwact/utils/slurm_script.py

@@ -35,11 +35,13 @@ Obtain the execution status of the slurm jobs under the 'dir'
 
         0-scf.job 1-scf.job 2-scf.job 3-scf.job 4-scf.job
         0-tag.scf.success 1-tag.scf.success 2-tag.scf.success 3-tag.scf.success 4-tag.scf.success
+    new change:
+        only jugt the slurm file is done by the tag under each subwork tag. so the tag of job file is nouse maybe
 param {*} dir
 Returns: 
 Author: WU Xingxing
 '''
-def get_slurm_job_run_info(dir:str, job_patten:str="*.job", tag_patten:str="tag.*.success"):
+def get_slurm_job_run_info(dir:str, job_patten:str="*.job", tag_patten:str="tag.*.success", for_back:bool=False):
     slurm_job_files = sorted(glob.glob(os.path.join(dir, job_patten)))
     slrum_job_dirs = [int(os.path.basename(_).split('-')[0]) for _ in slurm_job_files]
 
@@ -49,14 +51,39 @@ def get_slurm_job_run_info(dir:str, job_patten:str="*.job", tag_patten:str="tag.
     slurm_failed = []
     slurm_success = []
 
-    for i, d in enumerate(slrum_job_dirs):
-        if d in slrum_tag_sucess_dirs:
-            slurm_success.append(slurm_job_files[i])
-        else:
-            slurm_failed.append(slurm_job_files[i])
+    if for_back is False:
+        for slurm_file in slurm_job_files:
+            if slurm_job_done_by_jobtag(slurm_file):
+                slurm_success.append(slurm_file)
+            else:
+                slurm_failed.append(slurm_file)
+    else:
+        for i, d in enumerate(slrum_job_dirs):
+            if d in slrum_tag_sucess_dirs:
+                slurm_success.append(slurm_job_files[i])
+            else:
+                slurm_failed.append(slurm_job_files[i])
             
     return slurm_failed, slurm_success
 
+
+def slurm_job_done_by_jobtag(slurm_file):
+    with open(slurm_file, 'r') as f:
+        content = f.read()
+    cd_pattern = r'cd\s+([^\n]+)'
+    directories = re.findall(cd_pattern, content)        
+    if not directories:
+        raise Exception("Error! There is no task in the slurm.job file {}".format(slurm_file))
+    for directory in directories:
+        directory = directory.strip()
+        success_file = glob.glob(os.path.join(directory, "*.success"))
+        if len(success_file) > 0:
+            continue
+        else:
+            return False
+    return True
+
+
 def recheck_slurm_by_jobtag(slurm_files:list[str], tag):
     remain_job = []
     for slurm_file in slurm_files:
@@ -76,6 +103,27 @@ def recheck_slurm_by_jobtag(slurm_files:list[str], tag):
                 break
     return remain_job
 
+# def slurm_job_is_done_by_jobtag(dir:str, job_patten:str="*.job", tag_patten:str="tag.*.success"):
+#     slurm_job_files = sorted(glob.glob(os.path.join(dir, job_patten)))
+#     slurm_failed = []
+#     for slurm_file in slurm_job_files:
+#         with open(slurm_file, 'r') as f:
+#             content = f.read()
+#         cd_pattern = r'cd\s+([^\n]+)'
+#         directories = re.findall(cd_pattern, content)        
+#         if not directories:
+#             raise Exception("Error! There is no task in the slurm.job file {}".format(slurm_file))
+#         for directory in directories:
+#             directory = directory.strip()
+#             success_file = os.path.join(directory, tag_patten)
+#             if os.path.exists(success_file):
+#                 continue
+#             else:
+#                 slurm_failed.append(slurm_file)
+#                 break
+#     return slurm_failed
+
+
 '''
 description: 
     split the job_list with groupsize
@@ -85,7 +133,7 @@ return {*} [["job1","job2",...,"job_groupseze"], ..., [..., "job_N", "NONE",...,
 author: wuxingxing
 '''
 def split_job_for_group(groupsize:int , job_list:list[str], parallel_num=1):
-    groupsize = 1 if groupsize is None else groupsize
+    groupsize = len(job_list) if groupsize == -1 else groupsize
     if groupsize > 1:
         groupsize_adj = ceil(groupsize/parallel_num)
         if groupsize_adj*parallel_num > groupsize:

{pwact-0.3.1.dist-info → pwact-0.3.3.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pwact
-Version: 0.3.1
-Summary: PWACT is an open-source automated active learning platform based on PWMLFF for efficient data sampling.
+Version: 0.3.3
+Summary: PWACT is an open-source automated active learning platform based on MatPL for efficient data sampling.
 Home-page: https://github.com/LonxunQuantum/PWact
 Author: LonxunQuantum
 Author-email: lonxun@pwmat.com

{pwact-0.3.1.dist-info → pwact-0.3.3.dist-info}/RECORD

@@ -1,9 +1,9 @@
 pwact/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/main.py,sha256=jCqNp0tn8P7R8EdPt81bqZlC-Ixjp_rnnFxMT7JAfXI,15375
+pwact/main.py,sha256=ZmfzShuphHUuVH9OsPV_obf0g0jK3ka9UwStim_YJ7s,15538
 pwact/active_learning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/active_learning/environment.py,sha256=oDeSMCnBnwRe3bA0l9miDyQGaIE-gcf2ML2eOE7rPJk,512
+pwact/active_learning/environment.py,sha256=aySFa--fTWAgIR9_PKwfJ9pLKVexmL22lJ1NTtnQuNo,512
 pwact/active_learning/explore/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/active_learning/explore/run_model_md.py,sha256=n3f6aSMr1Cpw_cSUrlH28JwoWW7VLwUMcF1XB0ao2sw,27448
+pwact/active_learning/explore/run_model_md.py,sha256=1mjQB63mMCSngjMA2cd0U3f8AcB9oM_wa6xBAfNOwi0,27255
 pwact/active_learning/explore/select_image.py,sha256=1zpTCs_15FRlffBYfy1HQ1r79p2dNM8u8ZHvPysQTvc,14597
 pwact/active_learning/init_bulk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/init_bulk/aimd.py,sha256=XzDlX2vylaljQKoUnv6nrI2NfiOdHZpq8qr3DenA1F4,10465
@@ -14,7 +14,7 @@ pwact/active_learning/init_bulk/init_bulk_run.py,sha256=1wXf4iFhMjrjhyI4JVRoIibE
 pwact/active_learning/init_bulk/relabel.py,sha256=gP_qqMWT_hMIcwFBdNmyVBHBpkQS52BzbQK80rGTvPQ,11974
 pwact/active_learning/init_bulk/relax.py,sha256=edyCZLEylUckIwOLBa55agUMo-aedj0dvoyG165YpuE,10450
 pwact/active_learning/label/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/active_learning/label/labeling.py,sha256=Vq2hH9i3DH4X0XidrzxwE-MzgYiWQ0VkFWZKj1Lhc_I,21800
+pwact/active_learning/label/labeling.py,sha256=9bTjw6wOJ63J-x9IAiDY2DddSBp3Pj0mxjVyY47lsok,21833
 pwact/active_learning/slurm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/slurm/slurm.py,sha256=-Dmc2B9y4_27THCR2tZFXnwJvMmifivJeZ2FX8iy2Tw,16881
 pwact/active_learning/slurm/slurm_tool.py,sha256=-4tc5dkpAUP0vmEdmqM8oYLcsUwixa4Z8h5_E9Gevdg,1249
@@ -22,12 +22,12 @@ pwact/active_learning/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJ
 pwact/active_learning/test/test.py,sha256=TXsk-gDDOHDLywVljpqA-zHK3-PrZbGAHnK1T7T6T-o,3587
 pwact/active_learning/train/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/train/dp_kpu.py,sha256=GkGKEGhLmOvPERqgTkf_0_vD9zOEPlBX2N7vuSQG_-c,9317
-pwact/active_learning/train/train_model.py,sha256=Hh6_yq_86Y4pqP60sbEaeCJexD9a-BTqop07l2FAQSI,12021
+pwact/active_learning/train/train_model.py,sha256=yaBcGLBnM7NpuZu0o7lzZp2NjWPWzHXyJ39oS6pmHB4,12050
 pwact/active_learning/user_input/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/user_input/cmd_infos.py,sha256=g1QW5Wi3JvmC5xEY4F-7AO1xBuJSjHG8IhZjom8haxQ,3728
 pwact/active_learning/user_input/init_bulk_input.py,sha256=M8IlT4ABJUEwomb6eQGq8d3h1darMHtDlws1fcq077k,9422
 pwact/active_learning/user_input/iter_input.py,sha256=TctIZ3WAWQ_waGuPaK6F_uZjRKFM8oidF5iVE4SAI1o,12752
-pwact/active_learning/user_input/resource.py,sha256=OtsJEAWmMknLyrPB309C6ipyL1fCXHriF8sjXs5pjmg,7351
+pwact/active_learning/user_input/resource.py,sha256=V1FkcoLrjzKTkbd_3dYok69KyiKmwRCwGBatWAb-WoU,7517
 pwact/active_learning/user_input/scf_param.py,sha256=QX_Dd6c9Q2sjV4lIKjfV7t-DgIwDKZp7fh2KY5HyKOU,11262
 pwact/active_learning/user_input/workdir.py,sha256=64J3wBbYzy6ztYHs513YHfEIF5d8zwv_WpF-U9HOEkA,8245
 pwact/active_learning/user_input/train_param/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -46,8 +46,8 @@ pwact/utils/file_operation.py,sha256=bfLezgJHD3BRtZFm0HwSGTNBPukVNICZFpXYWMs68A4
 pwact/utils/format_input_output.py,sha256=oYFydQy3-btXzieO2O2LbHFoeRyhPnLVE4c5TNgS-IQ,1798
 pwact/utils/json_operation.py,sha256=BqBsnIjk1URoMW_s2yu7Gk8IBxlir-oo6ivt8P3RIqg,1794
 pwact/utils/pre_al_data_util.py,sha256=QE-axnVYUIyORFiVs-WK9-UaJlMUFY816_rSyYOOJc8,2542
-pwact/utils/process_tool.py,sha256=j4yp9DoPshTxTX3g7SS-yuEbBVhuoYNNZdAv2mq3efE,876
-pwact/utils/slurm_script.py,sha256=tbclNkYBVM-t8GeiLGNK2s5kxypjy8luf4ZrlHEGjjM,8278
+pwact/utils/process_tool.py,sha256=bsSsS42toOWz6ZzWCq5_7TrLEBTAif5tz2FbSo4YT3E,881
+pwact/utils/slurm_script.py,sha256=t0gshBMgnf5nzLPphwIIV4KxmwI3RmTuknLLf9tTZCg,10173
 pwact/utils/tmp.py,sha256=en_GltoNwfA40vSHttMRi9cEg-8xnPZlvnnBq1_vHfw,2285
 pwact/utils/app_lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/utils/app_lib/common.py,sha256=lQmI-9Qumq62MNjr-eVlLL88ISDHBOb6vAfYYFcDIgM,6040
@@ -59,9 +59,9 @@ pwact/utils/app_lib/lammps.py,sha256=t3nkBqwkViO6UbnInGKAHiwVngHKayeat2pPEtaZZIU
 pwact/utils/app_lib/pwmat.py,sha256=PTRPkG_d00ibGhpCe2-4M7MW3dx2ZuAyb9hT2jl_LAs,18047
 pwact/utils/draw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/utils/draw/hist_model_devi.py,sha256=o1Try-ekith2A7S6u1mt3zuTqaQwyw5tdURReh8BeLY,4945
-pwact-0.3.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pwact-0.3.1.dist-info/METADATA,sha256=lDIsIiByaSvWIEV_cLqEAqWTuHVkHn9bvs825xYZwnk,612
-pwact-0.3.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pwact-0.3.1.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
-pwact-0.3.1.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
-pwact-0.3.1.dist-info/RECORD,,
+pwact-0.3.3.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pwact-0.3.3.dist-info/METADATA,sha256=RKEDTPP72Lhu1USAu-WcBUzqfT48mBAkeVtVF9rdO8w,611
+pwact-0.3.3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pwact-0.3.3.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
+pwact-0.3.3.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
+pwact-0.3.3.dist-info/RECORD,,