Improve split strategy for more reliable training evaluation

Group samples by identical inputs before splitting, add target-aware stratification options, and cover the behavior with tests so repeated-input rows no longer leak across train, validation, and test sets.

Made-with: Cursor

configs/default.yaml

@@ -5,6 +5,10 @@ data_path: data/dataset.txt
 
 split_ratios: [0.7, 0.15, 0.15]  # train, val, test；可改为 [0.8, 0.1, 0.1]
 random_seed: 42
+# 切分策略：按 8 维输入分组，避免“同输入异输出”跨集合泄漏；再按目标分桶近似分层
+split_mode: grouped_stratified  # grouped_stratified | random
+split_stratify_target: V_pi
+split_stratify_bins: 10
 
 remove_duplicate_rows: true
 
@@ -32,7 +36,8 @@ model:
   hidden_dims: [200, 300, 350, 300, 200]
   output_dim: 3
   batchnorm: false
-  dropout: 0.0
+  # 温和 dropout，实测略优于全 0（见 results/run_20260419_163305）
+  dropout: 0.05
   residual: false
 
 optimizer:
@@ -55,7 +60,8 @@ training:
 loss:
   type: huber  # huber | weighted_mse
   huber_delta: 1.0
-  target_weights: [1.0, 1.0, 1.0]
+  # BW_3dB, IL, V_pi；略加重 V_pi 以小幅提升其测试 R²
+  target_weights: [1.0, 1.0, 1.2]
 
 # 总输出目录；每次训练会在其下创建 run_时间戳/
 output_dir: results

configs/mild_reg.yaml

@@ -0,0 +1,59 @@
+# 温和正则 + 略提高 V_pi 权重（在 default 基线上小幅改动，便于对比）
+# 使用: python -m src.main train --config configs/mild_reg.yaml
+
+data_path: data/dataset.txt
+
+split_ratios: [0.7, 0.15, 0.15]
+random_seed: 42
+split_mode: grouped_stratified
+split_stratify_target: V_pi
+split_stratify_bins: 10
+
+remove_duplicate_rows: true
+
+outlier_strategy: none
+outlier_apply_to: targets
+outlier_config:
+  iqr_k: 1.5
+  zscore_threshold: 4.0
+  quantile_lower: 0.001
+  quantile_upper: 0.999
+
+filter_v_pi_range: true
+v_pi_min: 0.0
+v_pi_max: 500.0
+
+remove_nonpositive_vpi: false
+
+model:
+  input_dim: 8
+  hidden_dims: [200, 300, 350, 300, 200]
+  output_dim: 3
+  batchnorm: false
+  dropout: 0.05
+  residual: false
+
+optimizer:
+  name: adamw
+  lr: 0.001
+  weight_decay: 0.0001
+
+scheduler:
+  type: cosine
+  plateau_factor: 0.5
+  plateau_patience: 10
+  plateau_min_lr: 1.0e-6
+
+training:
+  batch_size: 128
+  epochs: 300
+  early_stopping_patience: 30
+  num_workers: 0
+
+loss:
+  type: huber
+  huber_delta: 1.0
+  target_weights: [1.0, 1.0, 1.2]
+
+output_dir: results
+last_run_dir: null

configs/reg_vpi_try1.yaml

@@ -0,0 +1,59 @@
+# 实验：较强正则 + 提高 V_pi 损失权重（2026-04-19 试跑）
+# 结果：早停偏早，test 整体差于 default 基线；仅作记录，日常训练请用 default.yaml
+
+data_path: data/dataset.txt
+
+split_ratios: [0.7, 0.15, 0.15]
+random_seed: 42
+split_mode: grouped_stratified
+split_stratify_target: V_pi
+split_stratify_bins: 10
+
+remove_duplicate_rows: true
+
+outlier_strategy: none
+outlier_apply_to: targets
+outlier_config:
+  iqr_k: 1.5
+  zscore_threshold: 4.0
+  quantile_lower: 0.001
+  quantile_upper: 0.999
+
+filter_v_pi_range: true
+v_pi_min: 0.0
+v_pi_max: 500.0
+
+remove_nonpositive_vpi: false
+
+model:
+  input_dim: 8
+  hidden_dims: [200, 300, 350, 300, 200]
+  output_dim: 3
+  batchnorm: false
+  dropout: 0.15
+  residual: false
+
+optimizer:
+  name: adamw
+  lr: 0.001
+  weight_decay: 0.0002
+
+scheduler:
+  type: cosine
+  plateau_factor: 0.5
+  plateau_patience: 10
+  plateau_min_lr: 1.0e-6
+
+training:
+  batch_size: 128
+  epochs: 300
+  early_stopping_patience: 30
+  num_workers: 0
+
+loss:
+  type: huber
+  huber_delta: 1.0
+  target_weights: [1.0, 1.0, 1.75]
+
+output_dir: results
+last_run_dir: null