pwact 0.1.23__py3-none-any.whl → 0.1.25__py3-none-any.whl

pwact/active_learning/label/labeling.py

@@ -245,7 +245,7 @@ class Labeling(object):
             for sub_md_sys in sub_md_sys_dir_list:
                 out_mlmd_list =search_files(sub_md_sys, "*-{}/{}".format(LABEL_FILE_STRUCTURE.scf, DFT_STYLE.get_scf_config(self.resource.dft_style)))
                 # do a sorted?
-                md_sys_mlmd.append(out_mlmd_list)
+                md_sys_mlmd.extend(out_mlmd_list)
         return md_sys_mlmd
 
     def get_aimd_list(self):
@@ -279,14 +279,23 @@ class Labeling(object):
 
         # scf files to pwdata format
         scf_configs = self.collect_scf_configs()
-        for scf_md in scf_configs:
-            datasets_path_name = os.path.basename(os.path.dirname(os.path.dirname(scf_md[0])))#md.001.sys.001.t.000.p.000
-            extract_pwdata(data_list=scf_md,
-                data_format      =DFT_STYLE.get_format_by_postfix(os.path.basename(scf_md[0])),
-                datasets_path    =os.path.join(self.result_dir, datasets_path_name),
+
+        extract_pwdata(data_list=scf_configs,
+                data_format      =DFT_STYLE.get_format_by_postfix(os.path.basename(scf_configs[0])),
+                datasets_path    =self.result_dir,
                 train_valid_ratio=self.input_param.train.train_valid_ratio, 
                 data_shuffle     =self.input_param.train.data_shuffle, 
                 merge_data       =True
-            )
+        )
+
+        # for id, scf_md in enumerate(scf_configs):
+        #     datasets_path_name = os.path.basename(os.path.dirname(os.path.dirname(scf_md[0])))#md.001.sys.001.t.000.p.000
+        #     extract_pwdata(data_list=scf_md,
+        #         data_format      =DFT_STYLE.get_format_by_postfix(os.path.basename(scf_md[0])),
+        #         datasets_path    =os.path.join(self.result_dir, "{}-{}".format(id, datasets_path_name)),
+        #         train_valid_ratio=self.input_param.train.train_valid_ratio, 
+        #         data_shuffle     =self.input_param.train.data_shuffle, 
+        #         merge_data       =True
+        #     )
         # copy to main dir
         copy_dir(self.result_dir, self.real_result_dir)

pwact/active_learning/user_input/cmd_infos.py

@@ -21,19 +21,23 @@ def cmd_infos(cmd_type=None):
         cmd_info += "'pwact kill init_bulk' for 'init_bulk' tasks\n"
         cmd_info += "'pwact kill run' for 'run' tasks\n\n"
 
-        cmd_info += "to_pwdata".lower() + "\n\n"
+        cmd_info += "gather_pwdata".lower() + "\n"
+        cmd_info += "you could use this method to extract pwdatas after active learing done.\nFor more detail for this command, you could use 'pwact gather_pwdata -h'\n\n"
+
+        cmd_info += "filter" + "\n"
+        cmd_info += "you could use this method to test the selection results corresponding to the upper and lower limit settings,  you could use 'pwact filter -h'\n"
+
+        cmd_info += "to_pwdata".lower() + "\n"
         cmd_info += "(This method has been abandoned, new conversion methods refer to the pwdata documentation http://doc.lonxun.com/PWMLFF/Appendix-2/)\n\n"
-        cmd_info += "you could use this method to change outcars or movements to pwdata format.\nFor more detail for this command, you could use 'PWact to_pwdata -h'\n\n"
+        cmd_info += "you could use this method to change outcars or movements to pwdata format.\nFor more detail for this command, you could use 'pwact to_pwdata -h'\n\n"
 
-        cmd_info += "gather_pwdata".lower() + "\n"
-        cmd_info += "you could use this method to extract pwdatas after active learing done.\nFor more detail for this command, you could use 'PWact gather_pwdata -h'\n\n"
-        
         cmd_info += "\n\n"
         cmd_info += "examples of pwact are located at the dir 'pwact/example'\n"
         cmd_info += "you can alse download them from github link:\n"
         cmd_info += "https://github.com/LonxunQuantum/PWact/tree/main/pwact/example\n\n"
         cmd_info += "or download from BaiduNetdisk included the calculation results of examples:\n"
         cmd_info += "https://pan.baidu.com/s/14E0u_7cpntiBZgg-C1S5XA?pwd=pwmt\n\n"
+
     elif cmd_type == "init_bulk":
         cmd_info = cmd_info_init_bulk()
     elif cmd_type == "run":

pwact/data_format/configop.py

@@ -150,57 +150,32 @@ def extract_pwdata(data_list:list[str],
     # if data_format == DFT_STYLE.cp2k:
     #     raise Exception("not relized cp2k pwdata convert")
 
-    data_name = None
-    if merge_data:
-        data_name = os.path.basename(datasets_path)
-        if not os.path.isabs(datasets_path):
-            # data_name = datasets_path
-            datasets_path = os.path.dirname(os.path.join(os.getcwd(), datasets_path))
+    if not os.path.isabs(datasets_path):
+        # data_name = datasets_path
+        datasets_path = os.path.join(os.getcwd(), datasets_path)
+    image_data = None
+    for data_path in data_list:
+        if image_data is not None:
+            tmp_config = Config(data_format, data_path)
+            # if not isinstance(tmp_config, list):
+            #     tmp_config = [tmp_config]
+            image_data.images.extend(tmp_config.images)
         else:
-            datasets_path = os.path.dirname(datasets_path)
-        image_data = None
-        for data_path in data_list:
-            if image_data is not None:
-                tmp_config = Config(data_format, data_path)
-                # if not isinstance(tmp_config, list):
-                #     tmp_config = [tmp_config]
-                image_data.images.extend(tmp_config.images)
-            else:
-                image_data = Config(data_format, data_path)
-                
-                if not isinstance(image_data.images, list):
-                    image_data.images = [image_data.images]
+            image_data = Config(data_format, data_path)
             
-                # if not isinstance(image_data, list):
-                #     image_data = [image_data]
-        if interval > 1:
-            tmp = []
-            for i in range(0, len(image_data.images)):
-                if i % interval == 0:
-                    tmp.append(image_data.images[i])
-            image_data.images = tmp
+            if not isinstance(image_data.images, list):
+                image_data.images = [image_data.images]
+        
+            # if not isinstance(image_data, list):
+            #     image_data = [image_data]
+    if interval > 1:
+        tmp = []
+        for i in range(0, len(image_data.images)):
+            if i % interval == 0:
+                tmp.append(image_data.images[i])
+        image_data.images = tmp
 
-        image_data.to(
-                    output_path=datasets_path,
-                    save_format=PWDATA.pwmlff_npy,
-                    data_name=data_name,
-                    train_ratio = train_valid_ratio, 
-                    train_data_path="train", 
-                    valid_data_path="valid", 
-                    random=data_shuffle,
-                    seed = 2024, 
-                    retain_raw = False
-                    )
-    else:
-        for data_path in data_list:
-            image_data = Config(data_format, data_path)
-            if interval > 1:
-                tmp = []
-                for i in range(0, len(image_data.images)):
-                    if i % interval == 0:
-                        tmp.append(image_data.images[i])
-                image_data.images = tmp
-            image_data.to(
+    image_data.to(
                 output_path=datasets_path,
                 save_format=PWDATA.pwmlff_npy,
                 train_ratio = train_valid_ratio, 

pwact/utils/tmp.py

@@ -0,0 +1,63 @@
+from pwdata import Config
+import os, sys, glob
+import numpy as np
+
+def count_pwdata():
+    work_dir = "/data/home/wuxingxing/datas/debugs/dengjiapei/run_iter/mlmd_pwdata"
+    dir_list = glob.glob(os.path.join(work_dir, "*"))
+    res = []
+    for dir in dir_list:
+        # train
+        train_num = np.load(os.path.join(dir, "train/energies.npy")).shape[0]
+        res.append(train_num)
+
+        if os.path.exists(os.path.join(dir, "valid/energies.npy")):
+            test_num = np.load(os.path.join(dir, "valid/energies.npy")).shape[0]
+            res.append(test_num)
+            print("{} {} {}".format( dir, train_num, test_num))
+        else:
+            print("{} {}".format(dir, train_num))
+    print(np.sum(res))
+
+def count_outmlmd():
+    work_dir = "/data/home/wuxingxing/datas/debugs/dengjiapei/run_iter/iter.0000/label/scf"
+    mlmds = glob.glob(os.path.join(work_dir, "*/*/*/OUT.MLMD"))
+    print(len(mlmds))
+
+def save_mlmd():
+    work_dir = "/data/home/wuxingxing/datas/debugs/dengjiapei/run_iter"
+    data_list = glob.glob(os.path.join(work_dir, "iter.*/label/scf/*/*/*/OUT.MLMD"))
+    datasets_path = "/data/home/wuxingxing/datas/debugs/dengjiapei/run_iter/mlmd_pwdata"
+    # data_name = datasets_path
+    image_data = None
+    for data_path in data_list:
+        if image_data is not None:
+            tmp_config = Config("pwmat/movement", data_path)
+            # if not isinstance(tmp_config, list):
+            #     tmp_config = [tmp_config]
+            image_data.images.extend(tmp_config.images)
+        else:
+            image_data = Config("pwmat/movement", data_path)
+            
+            if not isinstance(image_data.images, list):
+                image_data.images = [image_data.images]
+        
+            # if not isinstance(image_data, list):
+            #     image_data = [image_data]
+    image_data.to(
+                output_path=datasets_path,
+                save_format="pwmlff/npy",
+                train_ratio = 0.8, 
+                train_data_path="train", 
+                valid_data_path="valid", 
+                random=True,
+                seed = 2024, 
+                retain_raw = False
+                )
+    print(len(image_data.images))
+
+
+if __name__=="__main__":
+    count_pwdata()
+    # count_outmlmd()
+    # save_mlmd()

{pwact-0.1.23.dist-info → pwact-0.1.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pwact
-Version: 0.1.23
+Version: 0.1.25
 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-0.1.23.dist-info → pwact-0.1.25.dist-info}/RECORD

@@ -12,7 +12,7 @@ pwact/active_learning/init_bulk/init_bulk_run.py,sha256=FG1EAXvuBJ1ERCg2htFVooif
 pwact/active_learning/init_bulk/relabel.py,sha256=DJR90gnC_AIWkcbWGcf2FYVCwPU40iP1uB48cTgGn7k,10447
 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=LwbjJzft3dU59FkL9Ux8O0ERdmok5RDBqVRsILEehV0,15236
+pwact/active_learning/label/labeling.py,sha256=tAFyTZjg64cNkG2_3p8qn5pc5F3je64UBgXnJT5PYtU,15687
 pwact/active_learning/slurm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/active_learning/slurm/slurm.py,sha256=xIDePutt8Q00--61y-RemT4Ky6qL9258kykaxKhIw8w,15637
 pwact/active_learning/slurm/slurm_tool.py,sha256=-4tc5dkpAUP0vmEdmqM8oYLcsUwixa4Z8h5_E9Gevdg,1249
@@ -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=GFmX1lTF14qQeb-NrbgzoDaJv4asgCi5cdoHVeHaVzM,3532
+pwact/active_learning/user_input/cmd_infos.py,sha256=3oWe9AhCxM9rWcRs3bezD7pb1TC5o0bCcvg-k36xEPY,3726
 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
@@ -37,7 +37,7 @@ pwact/active_learning/user_input/train_param/train_param.py,sha256=hsdVojgQZbQGS
 pwact/active_learning/user_input/train_param/work_file_param.py,sha256=tmedoLodmkcSK6uRIXTML0BhXFkgE96zPX0_kAXmGoo,11631
 pwact/bin/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/data_format/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pwact/data_format/configop.py,sha256=b-Hf4o5DsUyl4p3JmByqc85NtKb12Zzn_penaqyPveU,13068
+pwact/data_format/configop.py,sha256=S2WaES4-9_FX_o6fLaBMw2uSIF1cUMLGj9APRRASy6Q,11984
 pwact/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/utils/constant.py,sha256=ZM43rI0JNHA_nVKdRW1YvPGCEkomRNgdmA3_L8hAVSY,18379
 pwact/utils/file_operation.py,sha256=O26X-qUQuSkVRSVnJx4BPDrPtueVW7sfNvdJ_Y-PN2Q,8554
@@ -46,15 +46,16 @@ pwact/utils/json_operation.py,sha256=BqBsnIjk1URoMW_s2yu7Gk8IBxlir-oo6ivt8P3RIqg
 pwact/utils/pre_al_data_util.py,sha256=QE-axnVYUIyORFiVs-WK9-UaJlMUFY816_rSyYOOJc8,2542
 pwact/utils/process_tool.py,sha256=trzp6GbP_SYFiS_vheobV_FI4PSWVJvX3xHsFQ6DWME,478
 pwact/utils/slurm_script.py,sha256=mgueOrhYteg6XXvJitdjmbV4lzxMujuna9Jxr3wgC7Q,8237
+pwact/utils/tmp.py,sha256=SFzYEcNz-5rB0k2Os2tScBqiW3DMCepkuTqcsSE7RrQ,2277
 pwact/utils/app_lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pwact/utils/app_lib/common.py,sha256=lQmI-9Qumq62MNjr-eVlLL88ISDHBOb6vAfYYFcDIgM,6040
 pwact/utils/app_lib/cp2k.py,sha256=ljhCCHmZ2kfoXEXn5O7-D56EgTLn2a7H3y_TIkHiasY,13157
 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-0.1.23.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pwact-0.1.23.dist-info/METADATA,sha256=L8NmuHQ-mT-l4I_siSS1X4hH4AJcF35SCJqxe8A08p4,3659
-pwact-0.1.23.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pwact-0.1.23.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
-pwact-0.1.23.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
-pwact-0.1.23.dist-info/RECORD,,
+pwact-0.1.25.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pwact-0.1.25.dist-info/METADATA,sha256=zcuKIBxeaicBdKupPFrFCKBd5x04ErxG4lhPX_7uTJQ,3659
+pwact-0.1.25.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pwact-0.1.25.dist-info/entry_points.txt,sha256=p61auAnpbn8E2WjvHNBA7rb9_NRAOCew4zdcCj33cGc,42
+pwact-0.1.25.dist-info/top_level.txt,sha256=fY1_7sH5Lke4dC9L8MbYM4fT5aat5eCkAmpkIzY1SlM,6
+pwact-0.1.25.dist-info/RECORD,,