pwact 0.1.20__py3-none-any.whl → 0.1.22__py3-none-any.whl

pwact/active_learning/explore/select_image.py

@@ -118,7 +118,51 @@ def select_image(
     print("Image select result:\n {}\n\n".format(summary_info))
     return summary
 
-        
+def print_select_image(
+    md_dir:str, 
+    save_dir:str,
+    devi_name:str,
+    lower:float, 
+    higer:float
+):
+    #1. get model_deviation file
+    model_deviation_patten = "{}/{}".format(get_sub_md_sys_template_name(), devi_name)
+    model_devi_files = search_files(md_dir, model_deviation_patten)
+    model_devi_files = sorted(model_devi_files)
+    md_sys_dict = sort_model_devi_files(model_devi_files)
+    
+    error_pd =None
+    accurate_pd =None
+    rand_candi =None
+    remove_candi =None
+
+    for md in md_sys_dict.keys():
+        sys_dict = md_sys_dict[md]
+        for sys_idx, sys in enumerate(sys_dict.keys()):
+            devi_files = sys_dict[sys]
+            tmp_devi_pd, _base_kpu = read_pd_files(devi_files)
+            if len(_base_kpu) > 0: # for kpu upper and lower
+                _lower = np.mean(_base_kpu)*lower
+                _higer = _lower * higer
+            else:
+                _lower = lower
+                _higer = higer
+            tmp_error_pd, tmp_accurate_pd, tmp_rand_candi, tmp_remove_candi = select_pd(tmp_devi_pd, _lower, _higer, 10000000)
+            error_pd = pd.concat([error_pd, tmp_error_pd]) if error_pd is not None else tmp_error_pd
+            accurate_pd = pd.concat([accurate_pd, tmp_accurate_pd]) if error_pd is not None else tmp_accurate_pd
+            rand_candi = pd.concat([rand_candi, tmp_rand_candi]) if error_pd is not None else tmp_rand_candi
+            remove_candi = pd.concat([remove_candi, tmp_remove_candi]) if error_pd is not None else tmp_remove_candi
+    summary_info, summary = count_info(save_dir, error_pd, accurate_pd, rand_candi, remove_candi)
+    
+    # summary_info, summary = select_image(save_dir=self.select_dir, 
+    #                 devi_pd=devi_pd, 
+    #                 lower=self.input_param.strategy.lower_model_deiv_f, 
+    #                 higer=self.input_param.strategy.upper_model_deiv_f, 
+    #                 max_select=self.input_param.strategy.max_select)
+    print("Image select result (lower {} upper {}):\n {}\n\n".format(lower, higer, summary_info))
+    return summary
+
+
 def select_pd(devi_pd:DataFrame, lower:float, higer:float, max_select:float):
     accurate_pd  = devi_pd[devi_pd[EXPLORE_FILE_STRUCTURE.devi_columns[0]] < lower]
     candidate_pd = devi_pd[(devi_pd[EXPLORE_FILE_STRUCTURE.devi_columns[0]] >= lower) & (devi_pd[EXPLORE_FILE_STRUCTURE.devi_columns[0]] < higer)]
@@ -135,7 +179,7 @@ def select_pd(devi_pd:DataFrame, lower:float, higer:float, max_select:float):
     return error_pd, accurate_pd, cand_rand_candi, cand_remove_candi
 
 def read_pd_files(model_devi_files:list[str]):
-    devi_pd = pd.DataFrame(columns=EXPLORE_FILE_STRUCTURE.devi_columns)
+    devi_pd = pd.DataFrame()#columns=EXPLORE_FILE_STRUCTURE.devi_columns
     base_force_kpu = []
     if os.path.basename(model_devi_files[0]) == EXPLORE_FILE_STRUCTURE.kpu_model_devi:
         for devi_file in model_devi_files:
@@ -169,41 +213,39 @@ def read_pd_files(model_devi_files:list[str]):
 
 def count_info(save_dir, error_pd, accurate_pd, rand_candi, remove_candi):
     #5. save select info
-    if not os.path.exists(save_dir):
-        os.makedirs(save_dir)
     total_num = error_pd.shape[0] + accurate_pd.shape[0] + rand_candi.shape[0] + remove_candi.shape[0]
     cand_num = rand_candi.shape[0] + remove_candi.shape[0]
     summary = "Total structures {}    accurate {} rate {:.2f}%    selected {} rate {:.2f}%    error {} rate {:.2f}%\n"\
         .format(total_num, accurate_pd.shape[0], accurate_pd.shape[0]/total_num*100, \
                     cand_num, cand_num/total_num*100, \
                         error_pd.shape[0], error_pd.shape[0]/total_num*100)
-
-    accurate_pd.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.accurate))
     candi_info = ""
-    rand_candi.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.candidate))
-    
     if remove_candi.shape[0] == 0:
         candi_info += "Candidate configurations: {}\n        Select details in file {}\n".format(
             cand_num, EXPLORE_FILE_STRUCTURE.candidate)
     else:
-        remove_candi.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.candidate_delete))
         candi_info += "Candidate configurations: {}, randomly select {}, delete {}\n        Select details in file {}\n        Delete details in file {}.\n".format(
             cand_num, rand_candi.shape[0], remove_candi.shape[0],\
             EXPLORE_FILE_STRUCTURE.candidate, EXPLORE_FILE_STRUCTURE.candidate_delete)
-
-    error_pd.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.failed))
-    
     summary_info = ""
-
     summary_info += summary
     summary_info += "\nSelect by model deviation force:\n"
     summary_info += "Accurate configurations: {}, details in file {}\n".\
         format(accurate_pd.shape[0], EXPLORE_FILE_STRUCTURE.accurate)
-        
     summary_info += candi_info
-        
     summary_info += "Error configurations: {}, details in file {}\n".\
         format(error_pd.shape[0], EXPLORE_FILE_STRUCTURE.failed)
-    
-    write_to_file(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.select_summary), summary_info, "w")
-    return summary_info, summary    
+
+    if save_dir is not None:
+        if not os.path.exists(save_dir):
+            os.makedirs(save_dir)
+        accurate_pd.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.accurate))
+        rand_candi.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.candidate))
+        if remove_candi.shape[0] > 0:
+            remove_candi.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.candidate_delete))
+        error_pd.to_csv(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.failed))
+        write_to_file(os.path.join(save_dir, EXPLORE_FILE_STRUCTURE.select_summary), summary_info, "w")
+        
+    return summary_info, summary
+
+

pwact/active_learning/user_input/cmd_infos.py

@@ -39,6 +39,8 @@ def cmd_infos(cmd_type=None):
         cmd_info = cmd_info_run_iter()
     elif cmd_type == "kill":
         cmd_info = cmd_info_kill()
+    elif cmd_type == "filter":
+        cmd_info = cmd_info_filter()
     print(cmd_info)
 
 
@@ -64,3 +66,11 @@ def cmd_info_kill():
     cmd_info += "'pwact kill init_bulk' for 'init_bulk' tasks\n"
     cmd_info += "'pwact kill run' for 'run' tasks\n\n"
     return cmd_info
+
+def cmd_info_filter():
+    cmd_info = ""
+    cmd_info += "filter" + "\n"
+    cmd_info += "you could use this method to test the selection results corresponding to the upper and lower limit settings\n"
+    cmd_info += "example:\n"
+    cmd_info += "'pwact filter -i iter.0000/explore/md -l 0.01 -u 0.02 -s'\n\n"
+    return cmd_info

pwact/main.py

@@ -23,7 +23,7 @@ from pwact.active_learning.init_bulk.init_bulk_run import init_bulk_run, scancel
 from pwact.active_learning.environment import check_envs
 
 from pwact.data_format.configop import extract_pwdata
-from pwact.active_learning.explore.select_image import select_image
+from pwact.active_learning.explore.select_image import select_image, print_select_image
 from pwact.utils.process_tool import kill_process
 def run_iter():
     system_json = json.load(open(sys.argv[2]))
@@ -299,6 +299,26 @@ def kill_job():
         
     # for run iters jobs
 
+def filter_test(input_cmds):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i', '--md_dir', help="specify the md dir such as 'iter.0000/temp_run_iter_work/explore/md' or iter.0000/explore/md", type=str, required=True)
+    parser.add_argument('-l', '--lower', help="specify lower limit value", type=float, required=True)
+    parser.add_argument('-u', '--upper', help="specify upper limit value", type=float, required=True)
+    parser.add_argument('-s', '--save', action='store_true', help="if '-s' is set, save the detailed information of the selected configs to CSV files")
+    
+    args = parser.parse_args(input_cmds)
+    if not os.path.exists(args.md_dir):
+        raise Exception("ERROR! The input md_dir {} not found!".format(args.md_dir))
+
+    save_dir = os.path.join(os.getcwd(), "filter_test_result") if args.save else None
+    summary = print_select_image(
+                md_dir=args.md_dir, 
+                save_dir=save_dir,
+                devi_name=EXPLORE_FILE_STRUCTURE.get_devi_name(UNCERTAINTY.committee),
+                lower=args.lower,  
+                higer=args.upper
+        )
+
 def main():
     environment_check()
     if len(sys.argv) == 1 or "-h".upper() == sys.argv[1].upper() or \
@@ -343,7 +363,14 @@ def main():
             cmd_infos("kill")
         else:
             kill_job()
-        
+    
+    elif "filter_test".upper() == sys.argv[1].upper() or "filter".upper() == sys.argv[1].upper():
+        if len(sys.argv) == 2 or "-h".upper() == sys.argv[2].upper() or \
+            "help".upper() == sys.argv[2].upper() or "-help".upper() == sys.argv[2].upper() or "--help".upper() == sys.argv[2].upper():
+            cmd_infos("filter")
+        else:
+            filter_test(sys.argv[2:])
+
     else:
         print("ERROR! The input cmd {} can not be recognized, please check.".format(sys.argv[1]))
         print("\n\n\nYou can enter the following command.\n\n\n")

{pwact-0.1.20.dist-info → pwact-0.1.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pwact
-Version: 0.1.20
+Version: 0.1.22
 Summary: PWACT is an open-source automated active learning platform based on PWMLFF for efficient data sampling.
 Home-page: https://github.com/LonxunQuantum/PWact
 Author: LonxunQuantum

{pwact-0.1.20.dist-info → pwact-0.1.22.dist-info}/RECORD

@@ -1,10 +1,10 @@
 pwact/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/main.py,sha256=biHSGluE1a1onAa4pQxI3ArOeY5BIAUIuszkkl_7xsk,15340
+pwact/main.py,sha256=61QOZIBvxP-ddz2uI9JD35T-LIDU09NuARbWkNOI3pA,16872
 pwact/active_learning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/environment.py,sha256=KvyMaOXrM-HMMma4SnoOQFO6fZxDsk0Fsyyy7xqfGCo,684
 pwact/active_learning/explore/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/explore/run_model_md.py,sha256=uSW-ZaXH7NHexnMDm3Qb7ny4rRhk9KZ3dds2D9AVDeo,19891
-pwact/active_learning/explore/select_image.py,sha256=QAoD1CxaC5Xn3W5rQHxTNWMN53K2wABLsw03XCJEFPg,10527
+pwact/active_learning/explore/select_image.py,sha256=dmsMoxFwQ7JDPHK2vRFzUfXeEovT86cmUnmEm-qrfwE,12665
 pwact/active_learning/init_bulk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/init_bulk/aimd.py,sha256=XzDlX2vylaljQKoUnv6nrI2NfiOdHZpq8qr3DenA1F4,10465
 pwact/active_learning/init_bulk/duplicate_scale.py,sha256=Z9mYBASy9gNLTV_db8lqfXpcahHbrQq6emae169P2wM,9468
@@ -22,7 +22,7 @@ pwact/active_learning/train/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMp
 pwact/active_learning/train/dp_kpu.py,sha256=GkGKEGhLmOvPERqgTkf_0_vD9zOEPlBX2N7vuSQG_-c,9317
 pwact/active_learning/train/train_model.py,sha256=NXqTKrl7Lb_UGt2-Lq_gLM9iZDAZFY09nxP_aGtBdrE,10525
 pwact/active_learning/user_input/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/active_learning/user_input/cmd_infos.py,sha256=oiSgtGk85zyujNXbB86Igs1YiBIOssWw-6UVs3lQtYc,2974
+pwact/active_learning/user_input/cmd_infos.py,sha256=qyUYxsxnqZS2hxDbbeyyqsB2kps5z5nBCBa2iK0QE68,3372
 pwact/active_learning/user_input/init_bulk_input.py,sha256=NCUAB1xpa67MXHRRWAkmWZjkQbTibE4EjmtlOmr0HdQ,6762
 pwact/active_learning/user_input/iter_input.py,sha256=zwFCI6dDFIEVWitEqBBZP7TtrSvxMbmSUEPiM0Z8ZOk,10732
 pwact/active_learning/user_input/resource.py,sha256=bg1rkdjIzuj7pDUvp6h1yMWFT0PqYzH4BfX5tJ7MZzc,6812
@@ -52,9 +52,9 @@ pwact/utils/app_lib/cp2k.py,sha256=ljhCCHmZ2kfoXEXn5O7-D56EgTLn2a7H3y_TIkHiasY,1
 pwact/utils/app_lib/cp2k_dp.py,sha256=VP4gyPGhLcMAqAjrqCQSUiiGlESNlyYz7Gs3Q4QoUHo,6912
 pwact/utils/app_lib/lammps.py,sha256=2oxHJHdDxfDDWWmnjo0gMNwgGvxABwuDgDlb8kbhgfk,8037
 pwact/utils/app_lib/pwmat.py,sha256=PTRPkG_d00ibGhpCe2-4M7MW3dx2ZuAyb9hT2jl_LAs,18047
-pwact-0.1.20.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pwact-0.1.20.dist-info/METADATA,sha256=li8i3kvKzRyuwxxGZx9Xtu9h-Woc25WU15QT0Tbu0tQ,3659
-pwact-0.1.20.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pwact-0.1.20.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
-pwact-0.1.20.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
-pwact-0.1.20.dist-info/RECORD,,
+pwact-0.1.22.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pwact-0.1.22.dist-info/METADATA,sha256=Gd3Y11fJq-d9Pt-06_RMwmZTQj_dSbN1c9VyeZ5YdD4,3659
+pwact-0.1.22.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pwact-0.1.22.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
+pwact-0.1.22.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
+pwact-0.1.22.dist-info/RECORD,,