junshan-kit 2.7.3__py2.py3-none-any.whl → 2.8.5__py2.py3-none-any.whl

junshan_kit/DataProcessor.py

@@ -8,9 +8,11 @@
 import pandas as pd
 import numpy as np
 import torch, bz2
+from typing import Optional
 from torch.utils.data import random_split, Subset
 from sklearn.datasets import load_svmlight_file
 from sklearn.preprocessing import StandardScaler
+from junshan_kit import ParametersHub
 
 
 class CSV_TO_Pandas:
@@ -386,7 +388,7 @@ def get_libsvm_bz2_data(train_path, test_path, data_name, Paras, split = True):
     transform = "-1 → 0 for binary, y-1 for multi-class"
     train_data = LibSVMDataset_bz2(train_path)
 
-    if data_name in ["Duke", "Ijcnn"]:
+    if data_name in ["Duke", "Ijcnn", "RCV1"]:
         test_data = LibSVMDataset_bz2(test_path)
         split = False
     else:
@@ -410,3 +412,48 @@ def get_libsvm_bz2_data(train_path, test_path, data_name, Paras, split = True):
     # assert False
 
     return train_dataset, test_dataset, transform
+
+
+def subset(dataset, ratio_or_num, seed=None) -> Subset:
+    """
+    Randomly sample a subset from a dataset.
+
+    Parameters
+    ----------
+    dataset : torch.utils.data.Dataset
+        The dataset to sample from.
+    ratio_or_num : float or int
+        If float in (0, 1], treated as sampling ratio.
+        Otherwise, treated as absolute number of samples.
+    seed : int, optional
+        Random seed for reproducibility.
+
+    Returns
+    -------
+    torch.utils.data.Subset
+        A randomly sampled subset of the dataset.
+    """
+
+    if ratio_or_num < 0:
+        raise ValueError(f"ratio_or_num must be non-negative, got {ratio_or_num}")
+
+    dataset_len = len(dataset)
+
+    # Determine number of samples
+    if isinstance(ratio_or_num, float) and 0 < ratio_or_num <= 1:
+        num = max(1, int(round(dataset_len * ratio_or_num)))
+    else:
+        num = int(ratio_or_num)
+
+    # Clamp to valid range
+    num = min(max(num, 1), dataset_len)
+
+    # Create and seed generator
+    generator = torch.Generator()
+    if seed is not None:
+        generator.manual_seed(seed)
+
+    # Random sampling
+    indices = torch.randperm(dataset_len, generator=generator)[:num].tolist()
+
+    return Subset(dataset, indices)

junshan_kit/FiguresHub.py

@@ -1,7 +1,7 @@
 """
 ----------------------------------------------------------------------
 >>> Author       : Junshan Yin
->>> Last Updated : 2025-11-14
+>>> Last Updated : 2025-12-19
 ----------------------------------------------------------------------
 """
 import math, os
@@ -22,6 +22,8 @@ def marker_schedule(marker_schedule=None):
             "SPSmax": "4",  # tri-right
             "SPBM-PF": "*",  # star
             "SPBM-TR": "s",  # star
+            "SPBM-PF-NoneCut": "s",  # circle
+            "SPBM-TR-NoneCut": "s",  # circle
         }
         
     else:
@@ -64,6 +66,8 @@ def colors_schedule(colors_schedule=None):
             "SPSmax":    "#BA6262",  
             "SPBM-PF":   "#1f77b4",  
             "SPBM-TR":   "#d62728",  
+            "SPBM-PF-NoneCut": "#8c564b",
+            "SPBM-TR-NoneCut": "#e377c2",
         }
 
     else:
@@ -112,7 +116,7 @@ def Search_Paras(Paras, args, model_name, data_name, optimizer_name, metric_key
         fig.delaxes(axes[i])
 
     
-    plt.suptitle(f'{model_name} on {data_name} - {optimizer_name} (training/test samples: {Paras["train_data_num"]}/{Paras["test_data_num"]}), {Paras["device"]}', fontsize=16)
+    plt.suptitle(f'{model_name} on {data_name} - {optimizer_name}, (training, test) = ({Paras['train_data_num']}/{Paras['train_data_all_num']}, {Paras['test_data_num']}/{Paras['test_data_all_num']}), {Paras["device"]}, batch_size: {Paras["batch_size"]}', fontsize=16)
     plt.tight_layout(rect=(0, 0, 1, 0.9))
 
     filename = f'{Paras["Results_folder"]}/{metric_key}_{ParametersHub.model_abbr(model_name)}_{data_name}_{optimizer_name}.pdf'
@@ -220,19 +224,19 @@ def Mul_Plot(model_name, info_dict, Exp_name = "SPBM", cols = 3, save_path = Non
     )
 
     plt.tight_layout()
-    if save_name is None:
-        save_path = f'{model_name}.pdf'
+    if save_path is None:
+        save_path_ = f'{model_name}.pdf'
     else:
-        os.makedirs(save_name, exist_ok=True)
-        save_path = f'{save_name}/{save_name}.pdf'
-    plt.savefig(save_path, bbox_inches="tight")
+        os.makedirs(save_path, exist_ok=True)
+        save_path_ = f'{save_path}/{save_name}.pdf'
+    plt.savefig(save_path_, bbox_inches="tight")
     if fig_show:
         plt.show()
     plt.close()  # Colse the fig
     
 
 
-def Opt_Paras_Plot(model_name, info_dict, Exp_name = "SPBM", svae_path = None, save_name = None, fig_show = False):
+def Opt_Paras_Plot(model_name, info_dict, Exp_name = "SPBM", save_path = None, save_name = None, fig_show = False):
 
     mpl.rcParams['font.family'] = 'Times New Roman'
     mpl.rcParams["mathtext.fontset"] = "stix"
@@ -271,16 +275,16 @@ def Opt_Paras_Plot(model_name, info_dict, Exp_name = "SPBM", svae_path = None, s
     plt.tight_layout()  # Adjust layout so the legend fits
     plt.xlabel("epochs")  # Or whatever your x-axis represents
     plt.ylabel(f'{ParametersHub.fig_ylabel(info_dict[data_name]["metric_key"])}')  
-    if save_name is None:
-        save_path = f'{model_name}.pdf'
+    if save_path is None:
+        save_path_ = f'{model_name}.pdf'
     else:
-        os.makedirs(save_name, exist_ok=True)
-        save_path = f'{save_name}/{save_name}.pdf'
-    plt.savefig(save_path, bbox_inches="tight")
-
+        os.makedirs(save_path, exist_ok=True)
+        save_path_ = f'{save_path}/{save_name}.pdf'
+    plt.savefig(save_path_, bbox_inches="tight")
     if fig_show:
         plt.show()
     
     plt.close()
     
 
+

junshan_kit/OptimizerHup/SPBM.py

@@ -226,7 +226,6 @@ class TR_NoneCut(Optimizer):
         super().__init__(params, defaults)
         self.model = model
         self.cutting_num = hyperparams['cutting_number']
-        self.M = hyperparams['M']
         self.delta = hyperparams['delta']
         self.Paras = Paras
 
@@ -254,7 +253,9 @@ class TR_NoneCut(Optimizer):
             Gk, rk, ek = SPBM_func.get_var(x_his, f_his, g_his, self.delta)
             
             # SOVER (dual)
-            xk = SPBM_func.subproblem_tr_NoneLower(Gk, ek, xk, rk, self.Paras)
+            # xk = SPBM_func.subproblem_tr_NoneLower(Gk, ek, xk, rk, self.Paras)
+
+            xk = SPBM_func.subproblem_tr_2(Gk, ek, xk, rk, self.Paras)
             
             # print(len(self.f_his))
             vector_to_parameters(xk, self.model.parameters())
@@ -312,7 +313,6 @@ class PF_NoneCut(Optimizer):
         super().__init__(params, defaults)
         self.model = model
         self.cutting_num = hyperparams['cutting_number']
-        self.M = hyperparams['M']
         self.delta = hyperparams['delta']
         self.Paras = Paras
 
@@ -340,7 +340,9 @@ class PF_NoneCut(Optimizer):
             Gk, rk, ek = SPBM_func.get_var(x_his, f_his, g_his, self.delta)
             
             # SOVER (dual)
-            xk = SPBM_func.subproblem_pf_NoneLower(Gk, ek, xk, self.delta, self.Paras)
+            # xk = SPBM_func.subproblem_pf_NoneLower(Gk, ek, xk, self.delta, self.Paras)
+
+            xk = SPBM_func.subproblem_pf(Gk, ek, xk, self.delta, self.Paras)
             
             # print(len(self.f_his))
             vector_to_parameters(xk, self.model.parameters())

junshan_kit/ParametersHub.py

@@ -59,6 +59,8 @@ class args:
             "AIP": "Adult_Income_Prediction",
             "CCFD": "Credit_Card_Fraud_Detection",
             "Ijcnn": "Ijcnn",
+            "RCV1": "RCV1",
+            "w8a": "w8a",
             "DHI":"Diabetes_Health_Indicators",
             "EVP": "Electric_Vehicle_Population",
             "GHP": "Global_House_Purchase",
@@ -166,6 +168,13 @@ class args:
             # required=True,
             help = "search_grid: 1: "
         )
+
+        parser.add_argument(
+            "--OptParas",
+            type=int,
+            nargs=1,
+            help="Number of optimization steps for parameter tuning (default: 1)"
+        )
 # <args_from_command>
 
         args = parser.parse_args()
@@ -177,16 +186,19 @@ class args:
 # <args>
 
 def UpdateOtherParas(args, OtherParas):
+    # <time_str>
     if args.time_str is not None:
         time_str = args.time_str[0]
     else:
         time_str = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
     
+    # <user_search_grid> 
     if args.user_search_grid is not None:
         OtherParas["user_search_grid"] = args.user_search_grid[0]
     else:
         OtherParas["user_search_grid"] = None
 
+    # <send_email>
     if args.send_email is not None:
         OtherParas["from_email"] = args.send_email[0]
         OtherParas["to_email"] = args.send_email[1]
@@ -195,6 +207,11 @@ def UpdateOtherParas(args, OtherParas):
     else:
         OtherParas["send_email"] = False
     
+    if args.OptParas is not None:
+        OtherParas["SeleParasOn"] = False
+    else:
+        OtherParas["SeleParasOn"] = True
+    
     OtherParas["time_str"] = time_str
     OtherParas["results_folder_name"] = f'Results_{OtherParas["exp_name"]}'
 
@@ -428,7 +445,6 @@ def optimizer_paras_dict(Paras, OtherParas)->dict:
     # ----------- SPBM-TR-NoneCut -----------
     "SPBM-TR-NoneCut": {
         "params": {
-            "M": [1e-5],
             "delta": (
                 [2**i for i in range(-8, 9)]
                 if OtherParas["SeleParasOn"]
@@ -453,7 +469,6 @@ def optimizer_paras_dict(Paras, OtherParas)->dict:
     # ----------- SPBM-PF-NoneCut -----------
     "SPBM-PF-NoneCut": {
         "params": {
-            "M": [1e-5],
             "delta": (
                 [2**i for i in range(-8, 9)]
                 if OtherParas["SeleParasOn"]
@@ -592,6 +607,7 @@ def set_marker_point(epoch_num: int) -> list:
         6: [0, 2, 4, 6],
         8: [0, 2, 4, 6, 8],
         10: [0, 2, 4, 6, 8, 10],
+        50: [0, 10, 20, 30, 40, 50],
         100: [0, 20, 40, 60, 80, 100],
         200: [0, 40, 80, 120, 160, 200],
     }

junshan_kit/Print_Info.py

@@ -13,7 +13,7 @@ def training_info(args, data_name, optimizer_name, hyperparams, Paras, model_nam
     if Paras["use_color"]:
         print("\033[90m" + "-" * 115 + "\033[0m")
         print(
-            f"\033[32m✅ \033[34mDataset:\033[32m {data_name}, \t\033[34mBatch-size:\033[32m {args.bs}, \t\033[34m(training, test) = \033[32m ({Paras['train_data_num']}, {Paras['test_data_num']}), \t\033[34m device:\033[32m {Paras['device']}"
+            f"\033[32m✅ \033[34mDataset:\033[32m {data_name}, \t\033[34mBatch-size:\033[32m {args.bs}, \t\033[34m(training, test) = \033[32m ({Paras['train_data_num']}/{Paras['train_data_all_num']}, {Paras['test_data_num']}/{Paras['test_data_all_num']}), \t\033[34m device:\033[32m {Paras['device']}"
         )
         print(
             f"\033[32m✅ \033[34mOptimizer:\033[32m {optimizer_name}, \t\033[34mParams:\033[32m {hyperparams}"
@@ -27,7 +27,7 @@ def training_info(args, data_name, optimizer_name, hyperparams, Paras, model_nam
     else:
         print("-" * 115)
         print(
-            f"✅ Dataset: {data_name}, \tBatch-size: {args.bs}, \t(training, test) = ({Paras['train_data_num']}, {Paras['test_data_num']}), \tdevice: {Paras['device']}"
+            f"✅ Dataset: {data_name}, \tBatch-size: {args.bs}, \t(training, test) = ({Paras['train_data_num']}/{Paras['train_data_all_num']}, {Paras['test_data_num']}/{Paras['test_data_all_num']}), \tdevice: {Paras['device']}"
         )
         print(f"✅ Optimizer: {optimizer_name}, \tParams: {hyperparams}")
         print(

junshan_kit/TrainingHub.py

@@ -90,8 +90,8 @@ def load_data(model_name, data_name, Paras):
         assert False
 
     # Computing the number of data
-    Paras["train_data_num"] = len(train_dataset)
-    Paras["test_data_num"] = len(test_dataset)
+    Paras["train_data_num"], Paras["test_data_num"] = len(train_dataset), len(test_dataset)
+    Paras["train_data_all_num"], Paras["test_data_all_num"] = len(train_dataset), len(test_dataset)
 
     return train_dataset, test_dataset, Paras
 

{junshan_kit-2.7.3.dist-info → junshan_kit-2.8.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junshan_kit
-Version: 2.7.3
+Version: 2.8.5
 Summary: This is an optimization tool.
 Author-email: Junshan Yin <junshanyin@163.com>
 Requires-Dist: cvxpy==1.6.5

{junshan_kit-2.7.3.dist-info → junshan_kit-2.8.5.dist-info}/RECORD

@@ -1,20 +1,20 @@
 junshan_kit/BenchmarkFunctions.py,sha256=tXgZGg-CjTNz78nMyVEQflVFIJDgmmePytXjY_RT9BM,120
 junshan_kit/Check_Info.py,sha256=Z6Ls2S7Fl4h8S9s0NB8jP_YpSLZInvQAeyjIXzq5Bpc,1872
 junshan_kit/DataHub.py,sha256=6RCNr8dBTqK-8ey4m-baMU1qOsJP6swOFkaraGdk0fM,6801
-junshan_kit/DataProcessor.py,sha256=W2bzugcYnwQC403GdvSmGDBhfz8X1KxJBkOAVg1vHHk,14385
+junshan_kit/DataProcessor.py,sha256=Uc9ixhnVmGf5PoGIe3vvhobH_ADtDAosG9MTjnB1KDQ,15677
 junshan_kit/DataSets.py,sha256=DcpwWRm1_B29hIDjOhvaeKAYYeBknEW2QqsS_qm8Hxs,13367
 junshan_kit/Evaluate_Metrics.py,sha256=PQBGU8fETIvDon1VMdouZ1dhG2n7XHYGbzs2EQUA9FM,3392
-junshan_kit/FiguresHub.py,sha256=116cvRUGUcBqIAs0_xiRzZCzgnPaqmgI5kvNu6cAd_Q,10181
+junshan_kit/FiguresHub.py,sha256=TVbo9ioEECrH_iJjpt0HgkCoiAdFEcTdtiUtzDNYrJY,10455
 junshan_kit/ModelsHub.py,sha256=xM6cwLecq9vukrt1c9l7l9dy7mQn3yq0ZwrRg5f_CfM,7995
-junshan_kit/ParametersHub.py,sha256=RSgsSlH0bgehn27lleKfboT1MuLAyIMxZ5FWC-ANbhA,19822
-junshan_kit/Print_Info.py,sha256=uBLpeynOYSZTN8LbJupSH1SuLZ-7cMU3Yp3IlVJWB1s,4772
-junshan_kit/TrainingHub.py,sha256=WV3cUz4JsEdGTpbTqgnU3WmlKeob8RAOuL993EsADj0,11469
+junshan_kit/ParametersHub.py,sha256=_LvkdV95vKSU4h2LtF7W63EaF5mRBg85ZHf0ymb28tA,20248
+junshan_kit/Print_Info.py,sha256=7pfd_mGEuQdQGyz6kcSSvjVRCrPgi5RafQgi7ZSS9VU,4890
+junshan_kit/TrainingHub.py,sha256=unoI8zzm0oekUxz-3retHCFhxwx6j8e6Tp9VQDywTPg,11565
 junshan_kit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 junshan_kit/kit.py,sha256=tQGoJJQZW9BeadX2cuwhvOxX2riHBZG0iFExelS4MIY,11487
 junshan_kit/OptimizerHup/OptimizerFactory.py,sha256=x1_cE5ZSkKffdY0uCIirocBNj2X-u_R-V5jNawJ1EfA,4607
-junshan_kit/OptimizerHup/SPBM.py,sha256=2Yg8Fmc8OkYOrjevD8eAGfI-m-fefoOldybtlp4ZEEs,13730
+junshan_kit/OptimizerHup/SPBM.py,sha256=h449QddeN0MvUIQeKcNxFsdxdBuhN354sGc_sN2LZR8,13816
 junshan_kit/OptimizerHup/SPBM_func.py,sha256=5Fz6eHYIVGMoR_CBDA_Xk_1dnPRq3K16DUNoNaWQ2Ag,17301
 junshan_kit/OptimizerHup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-junshan_kit-2.7.3.dist-info/METADATA,sha256=_mIq2RLQUdQECGnjRK4qABiPr41BGiK-aCkk4EQVKik,455
-junshan_kit-2.7.3.dist-info/WHEEL,sha256=aha0VrrYvgDJ3Xxl3db_g_MDIW-ZexDdrc_m-Hk8YY4,105
-junshan_kit-2.7.3.dist-info/RECORD,,
+junshan_kit-2.8.5.dist-info/METADATA,sha256=vxUXFvPqaGc2liYh0A3B4CmlbdlrK1CVdRNx0i7RoRA,455
+junshan_kit-2.8.5.dist-info/WHEEL,sha256=aha0VrrYvgDJ3Xxl3db_g_MDIW-ZexDdrc_m-Hk8YY4,105
+junshan_kit-2.8.5.dist-info/RECORD,,