restructured configs

root_gnn_dgl/configs/{demo/finetuning_ttH_CP_Even_vs_Odd.yaml → stats_100K/finetuning_ttH_CP_even_vs_odd.yaml}

@@ -1,10 +1,10 @@
-Training_Name: finetuning_ttH_CP_Even_vs_Odd
-Training_Directory: trainings/demo/finetuning_ttH_CP_Even_vs_Odd
+Training_Name: finetuning_ttH_CP_even_vs_odd
+Training_Directory: trainings/stats_100K/finetuning_ttH_CP_even_vs_odd
 Model:
   module: models.GCN
   class: Transferred_Learning_Finetuning
   args:
-    pretraining_path: trainings/demo/pretraining_multiclass/model_epoch_100.pt # update to the last epoch of the pretraining
+    pretraining_path: trainings/stats_100K/pretraining_multiclass/model_epoch_100.pt # update to the last epoch of the pretraining
     pretraining_model:
       module: models.GCN
       class: Edge_Network
@@ -23,26 +23,26 @@ Model:
 Training:
   epochs: 500
   batch_size: 1024
-  learning_rate: 0.00001
+  learning_rate: 0.0001
   gamma: 0.99
 Datasets:
-  ttH_CP_Even: &dataset_defn
+  ttH_CP_even: &dataset_defn
     module: root_gnn_base.dataset
     class: LazyDataset
-    shuffle_chunks: 3
+    shuffle_chunks: 1
     batch_size: 1024
     padding_mode: NONE #one of STEPS, FIXED, or NONE
     args: &dataset_args
-      name: ttH_CP_Even
+      name: ttH_CP_even
       label: 0
-      weight_var: weight
-      chunks: 3
-      buffer_size: 1
+      # weight_var: weight
+      chunks: 1
+      buffer_size: 0
       file_names: ttH_NLO.root
       tree_name: output
       fold_var: Number
-      raw_dir: /global/cfs/projectdirs/atlas/joshua/root_gnn/root_gnn_dgl/data/ntuples/Hyy_pretraining/multilabel_10K/
-      save_dir: /pscratch/sd/j/joshuaho/GNN4Colliders/root_gnn_dgl/data/demo/finetuning_ttH_CP_Even_vs_Odd/
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_100K/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_100K/ttH_CP_even_vs_odd/
       node_branch_names:
         - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
         - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
@@ -54,14 +54,14 @@ Datasets:
       node_branch_types: [vector, vector, vector, vector, single]
       node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
     folding:
-      n_folds: 3
+      n_folds: 4
       test: [0]
       # validation: 1
-      train: [1, 2]
-  ttH_CP_Odd:
+      train: [1, 2, 3]
+  ttH_CP_odd:
     <<: *dataset_defn
     args:
       <<: *dataset_args
-      name: ttH_CP_Odd
+      name: ttH_CP_odd
       label: 1
       file_names: ttH_CPodd.root

root_gnn_dgl/configs/{demo → stats_100K}/pretraining_multiclass.yaml

@@ -1,5 +1,5 @@
 Training_Name: pretraining_multiclass
-Training_Directory: trainings/demo/pretraining_multiclass/
+Training_Directory: trainings/stats_100K/pretraining_multiclass/
 Model:
   module: models.GCN
   class: Edge_Network
@@ -27,19 +27,19 @@ Datasets:
   ttH: &dataset_defn
     module: root_gnn_base.dataset
     class: LazyDataset
-    shuffle_chunks: 3
+    shuffle_chunks: 1
     padding_mode: NONE #one of STEPS, FIXED, or NONE
     args: &dataset_args
       name: ttH
       label: 0
-      weight_var: weight
-      chunks: 3
-      buffer_size: 1
+      # weight_var: weight
+      chunks: 1
+      buffer_size: 0
       file_names: ttH_NLO_inc.root
       tree_name: output
       fold_var: Number
-      raw_dir: /global/cfs/projectdirs/atlas/joshua/root_gnn/root_gnn_dgl/data/ntuples/Hyy_pretraining/multilabel_10K/
-      save_dir: /pscratch/sd/j/joshuaho/GNN4Colliders/root_gnn_dgl/data/demo/pretraining_multiclass/
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_100K/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_100K/pretraining_multiclass/
       node_branch_names:
         - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
         - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
@@ -51,10 +51,10 @@ Datasets:
       node_branch_types: [vector, vector, vector, vector, single]
       node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
     folding:
-      n_folds: 3
+      n_folds: 4
       test: [0]
-      # validation: 1
-      train: [1, 2]
+      # validation: [1]
+      train: [1, 2, 3]
   tHjb:
     <<: *dataset_defn
     args: 

root_gnn_dgl/configs/stats_100K/ttH_CP_even_vs_odd.yaml

@@ -0,0 +1,57 @@
+Training_Name: ttH_CP_even_vs_odd
+Training_Directory: trainings/stats_100K/ttH_CP_even_vs_odd
+Model:
+  module: models.GCN
+  class: Edge_Network
+  args:
+    hid_size: 64
+    in_size: 7
+    out_size: 1
+    n_layers: 4
+    n_proc_steps: 4
+    dropout: 0
+Training:
+  epochs: 500
+  batch_size: 1024
+  learning_rate: 0.0001
+  gamma: 0.99
+Datasets:
+  ttH_CP_even: &dataset_defn
+    module: root_gnn_base.dataset
+    class: LazyDataset
+    shuffle_chunks: 1
+    batch_size: 1024
+    padding_mode: NONE #one of STEPS, FIXED, or NONE
+    args: &dataset_args
+      name: ttH_CP_even
+      label: 0
+      # weight_var: weight
+      chunks: 1
+      buffer_size: 0
+      file_names: ttH_NLO.root
+      tree_name: output
+      fold_var: Number
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_100K/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_100K/ttH_CP_even_vs_odd/
+      node_branch_names:
+        - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
+        - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
+        - [jet_phi, ele_phi, mu_phi, ph_phi, MET_phi]
+        - CALC_E
+        - [jet_btag, 0, 0, 0, 0]
+        - [0, ele_charge, mu_charge, 0, 0]
+        - NODE_TYPE
+      node_branch_types: [vector, vector, vector, vector, single]
+      node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
+    folding:
+      n_folds: 4
+      test: [0]
+      # validation: 1
+      train: [1, 2, 3]
+  ttH_CP_odd:
+    <<: *dataset_defn
+    args:
+      <<: *dataset_args
+      name: ttH_CP_odd
+      label: 1
+      file_names: ttH_CPodd.root

root_gnn_dgl/configs/stats_all/finetuning_ttH_CP_even_vs_odd.yaml

@@ -0,0 +1,62 @@
+Training_Name: finetuning_ttH_CP_even_vs_odd
+Training_Directory: trainings/stats_all/finetuning_ttH_CP_even_vs_odd
+Model:
+  module: models.GCN
+  class: Transferred_Learning_Finetuning
+  args:
+    pretraining_path: trainings/stats_100K/pretraining_multiclass/model_epoch_100.pt # update to the last epoch of the pretraining
+    pretraining_model:
+      module: models.GCN
+      class: Edge_Network
+      args:
+        hid_size: 64
+        in_size: 7
+        out_size: 12
+        n_layers: 4
+        n_proc_steps: 4
+    hid_size: 64
+    in_size: 7
+    out_size: 1
+    n_layers: 4
+    n_proc_steps: 4
+    dropout: 0
+Datasets:
+  ttH_CP_even: &dataset_defn
+    module: root_gnn_base.dataset
+    class: LazyDataset
+    shuffle_chunks: 10
+    batch_size: 1024
+    padding_mode: NONE #one of STEPS, FIXED, or NONE
+    args: &dataset_args
+      name: ttH_CP_even
+      label: 0
+      # weight_var: weight
+      chunks: 10
+      buffer_size: 3
+      file_names: ttH_NLO.root
+      tree_name: output
+      fold_var: Number
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_all/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_all/ttH_CP_even_vs_odd/
+      node_branch_names:
+        - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
+        - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
+        - [jet_phi, ele_phi, mu_phi, ph_phi, MET_phi]
+        - CALC_E
+        - [jet_btag, 0, 0, 0, 0]
+        - [0, ele_charge, mu_charge, 0, 0]
+        - NODE_TYPE
+      node_branch_types: [vector, vector, vector, vector, single]
+      node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
+    folding:
+      n_folds: 4
+      test: [0]
+      # validation: 1
+      train: [1, 2, 3]
+  ttH_CP_odd:
+    <<: *dataset_defn
+    args:
+      <<: *dataset_args
+      name: ttH_CP_odd
+      label: 1
+      file_names: ttH_CPodd.root

root_gnn_dgl/configs/stats_all/pretraining_multiclass.yaml

@@ -0,0 +1,134 @@
+Training_Name: pretraining_multiclass
+Training_Directory: trainings/stats_all/pretraining_multiclass/
+Model:
+  module: models.GCN
+  class: Edge_Network
+  args:
+    hid_size: 64
+    in_size: 7
+    out_size: 12
+    n_layers: 4
+    n_proc_steps: 4
+    dropout: 0
+Loss:
+  module: torch.nn
+  class: CrossEntropyLoss
+  args: {}
+  finish: 
+    module: torch.nn
+    class: Softmax
+    args: {dim: 1}
+Training:
+  epochs: 500
+  batch_size: 1024
+  learning_rate: 0.0001
+  gamma: 0.99
+Datasets:
+  ttH: &dataset_defn
+    module: root_gnn_base.dataset
+    class: LazyDataset
+    shuffle_chunks: 10
+    padding_mode: NONE #one of STEPS, FIXED, or NONE
+    args: &dataset_args
+      name: ttH
+      label: 0
+      # weight_var: weight
+      chunks: 10
+      buffer_size: 3
+      file_names: ttH_NLO_inc.root
+      tree_name: output
+      fold_var: Number
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_all/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_all/pretraining_multiclass/
+      node_branch_names:
+        - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
+        - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
+        - [jet_phi, ele_phi, mu_phi, ph_phi, MET_phi]
+        - CALC_E
+        - [jet_btag, 0, 0, 0, 0]
+        - [0, ele_charge, mu_charge, 0, 0]
+        - NODE_TYPE
+      node_branch_types: [vector, vector, vector, vector, single]
+      node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
+    folding:
+      n_folds: 4
+      test: [0]
+      # validation: [1]
+      train: [1, 2, 3]
+  tHjb:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: tHjb
+      label: 1
+      file_names: tHjb_NLO_inc.root
+  ggF:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ggF
+      label: 2
+      file_names: ggF_NLO_inc.root
+  VBF:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: VBF
+      label: 3
+      file_names: VBF_NLO_inc.root
+  WH:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: WH
+      label: 4
+      file_names: WH_NLO_inc.root
+  ZH:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ZH
+      label: 5
+      file_names: ZH_NLO_inc.root
+  ttyy:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ttyy_ch
+      label: 6
+      file_names: 'ttyy.root'
+  tttt:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: tttt
+      label: 7
+      file_names: 'tttt.root'
+  SingleT_schan:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: SingleT_schan
+      label: 8
+      file_names: 'SingleT_schan.root'
+  ttbar:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ttbar
+      label: 9
+      file_names: 'ttbar.root'
+  ttW:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ttW
+      label: 10
+      file_names: 'ttW.root'
+  ttt:
+    <<: *dataset_defn
+    args: 
+      <<: *dataset_args
+      name: ttt
+      label: 11
+      file_names: 'ttt.root'

root_gnn_dgl/configs/stats_all/ttH_CP_even_vs_odd.yaml

@@ -0,0 +1,57 @@
+Training_Name: ttH_CP_even_vs_odd
+Training_Directory: trainings/stats_all/ttH_CP_even_vs_odd
+Model:
+  module: models.GCN
+  class: Edge_Network
+  args:
+    hid_size: 64
+    in_size: 7
+    out_size: 1
+    n_layers: 4
+    n_proc_steps: 4
+    dropout: 0
+Training:
+  epochs: 500
+  batch_size: 1024
+  learning_rate: 0.0001
+  gamma: 0.99
+Datasets:
+  ttH_CP_even: &dataset_defn
+    module: root_gnn_base.dataset
+    class: LazyDataset
+    shuffle_chunks: 10
+    batch_size: 1024
+    padding_mode: NONE #one of STEPS, FIXED, or NONE
+    args: &dataset_args
+      name: ttH_CP_even
+      label: 0
+      # weight_var: weight
+      chunks: 10
+      buffer_size: 3
+      file_names: ttH_NLO.root
+      tree_name: output
+      fold_var: Number
+      raw_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/stats_all/
+      save_dir: /global/cfs/projectdirs/trn007/lbl_atlas/data/processed_graphs/stats_all/ttH_CP_even_vs_odd/
+      node_branch_names:
+        - [jet_pt, ele_pt, mu_pt, ph_pt, MET_met]
+        - [jet_eta, ele_eta, mu_eta, ph_eta, 0]
+        - [jet_phi, ele_phi, mu_phi, ph_phi, MET_phi]
+        - CALC_E
+        - [jet_btag, 0, 0, 0, 0]
+        - [0, ele_charge, mu_charge, 0, 0]
+        - NODE_TYPE
+      node_branch_types: [vector, vector, vector, vector, single]
+      node_feature_scales: [1e-1, 1, 1, 1e-1, 1, 1, 1]
+    folding:
+      n_folds: 4
+      test: [0]
+      # validation: 1
+      train: [1, 2, 3]
+  ttH_CP_odd:
+    <<: *dataset_defn
+    args:
+      <<: *dataset_args
+      name: ttH_CP_odd
+      label: 1
+      file_names: ttH_CPodd.root