From 24314b530f55f65845f23d2ee4844d10d652078e Mon Sep 17 00:00:00 2001
From: mkirsz <s1351949@sms.ed.ac.uk>
Date: Sun, 22 Dec 2024 17:03:14 +0000
Subject: [PATCH] adjusted examples to reflect recent changes
---
examples/API/ex_1/config | 3 +-
examples/API/ex_1/ex1.cpp | 264 ++++++++++++++---------------
examples/API/ex_2/config_train | 3 +-
examples/API/ex_2/pot.tadah | 2 +-
examples/API/ex_hpo_1/config.train | 2 +-
examples/API/ex_hpo_1/targets | 8 +-
examples/CLI/ex_1/config.train | 2 +-
7 files changed, 141 insertions(+), 143 deletions(-)
diff --git a/examples/API/ex_1/config b/examples/API/ex_1/config
index 3de1553..2ffa081 100644
--- a/examples/API/ex_1/config
+++ b/examples/API/ex_1/config
@@ -7,8 +7,7 @@ ATOMS Ta
WATOMS 73
INIT2B true
-INIT3B false
-INITMB false
+TYPE2B D2_Blip 4 4 Ta Ta
RCUT2B 5.3
diff --git a/examples/API/ex_1/ex1.cpp b/examples/API/ex_1/ex1.cpp
index f6cd54c..bd890af 100644
--- a/examples/API/ex_1/ex1.cpp
+++ b/examples/API/ex_1/ex1.cpp
@@ -43,136 +43,136 @@
* https://journals.aps.org/prb/abstract/10.1103/PhysRevB.88.134101
*/
int main() {
-
- std::cout << "TRAINING STAGE" << std::endl;
- // Config file configures almost all model parameters.
- // See below for a more detailed explanation of used key-value(s) pairs.
- Config config("config");
-
- // First we load all training data from a list
- // of training datasets into StrutureDB object.
- // Paths to datasets are specified with a key DBFILE in a config file.
- std::cout << "StructureDB loading data..." << std::flush;
- StructureDB stdb(config);
- std::cout << "Done!" << std::endl;
-
- // Next we pass StructureDB object to the nearest neighbour calculator.
- // NNFinder will create full nearest neighbours lists for every atom
- // in every structure. These lists will be stored by individual Structures
- // in a StructureDB object.
- // The lists are calculated up to the max cutoff from the config file:
- // cutoff_max = max(RCUT2B, RCUT3B, RCUTMB).
- std::cout << "Calculating nearest neighbours..." << std::flush;
- NNFinder nnf(config);
- nnf.calc(stdb);
- std::cout << "Done!" << std::endl;
-
- // STEP 1a: Select descriptors.
- // All three types must be specified.
- // Use Dummy if given type is not required.
-
- // D2 - TWO-BODY
- //using D2=D2_LJ;
- //using D2=D2_BP;
- using D2=D2_Blip;
- //using D2=D2_Dummy;
- //using D2=D2_EAM;
-
- // D3 - THREE-BODY
- using D3=D3_Dummy;
-
- // DM - MANY-BODY
- //using DM=DM_EAM;
- //using DM=DM_EAD;
- using DM=DM_Dummy;
-
- // STEP 1b: Select cutoffs, C2 for D2, etc
- using C2=Cut_Cos;
- using C3=Cut_Dummy;
- using CM=Cut_Dummy;
-
- // STEP 1c: Prepare descriptor calculator
- DescriptorsCalc<D2,D3,DM,C2,C3,CM> dc(config);
-
- // STEP 2a: Select Basis Function (BF) or Kernels (K).
- // BF is used for M_BLR - Bayesian Linear Regression
- // K is used with M_KRR - Kernel Ridge Regression
- // See documentation for more BF and K
- using BF=DM_BF_Linear;
- //using BF=BF_Polynomial2;
- //using K=Kern_Linear;
- //using K=Kern_Quadratic;
-
- // STEP 2b: Select Model
- using M=M_BLR<BF>;
- //using M=M_KRR<K>;
-
- //// STEP 2c: Instantiate a model
- M model(config);
-
- //std::cout << "TRAINING STAGE..." << std::flush;
-
- // STEP 3: Training - Option 1.
- // Train with StructureDB only. We have to provide calculators here.
- // Descriptors are calculated in batches to construct a design matrix
- // and then are discarded.
- // This is usually the best choice unless you need descriptors for something else
- // after the training is done.
- model.train(stdb,dc);
-
- // STEP 3: Training - Option 2.
- // Train with StructureDB and precalcualted StDescriptorsDB.
- //StDescriptorsDB st_desc_db = dc.calc(stdb);
- //model.train(st_desc_db,stdb);
- std::cout << "Done!" << std::endl;
-
- // STEP 4: Save model to a text file.
- // Once model is trained we can dump it to a file.
- // Saved models can be used with LAMMPS or can be reloaded
- // to make predictions.
- std::cout << "Saving LAMMPS pot.tadah file..." << std::flush;
- Config param_file = model.get_param_file();
- std::ofstream outfile("pot.tadah");
- outfile << param_file << std::endl;
- outfile.close();
- std::cout << "Done!" << std::endl;
-
- std::cout << "PREDICTION STAGE..." << std::endl;
- // STEP 1: We will reuse LAMMPS param file and add to it
- // DBFILE(s) from config_pred file.
- // In other words training datasets go to the config file
- // and validation datasets are in the config_pred
- param_file.add("config_pred");
-
- // STEP 2: Load DBFILE from config_pred
- std::cout << "StructureDB loading data..." << std::flush;
- StructureDB stdb2(param_file);
- std::cout << "Done!" << std::endl;
-
- // STEP 3: Calculate nearest neighbours
- std::cout << "Calculating nearest neighbours..." << std::flush;
- NNFinder nnf2(param_file);
- nnf2.calc(stdb2);
- std::cout << "Done!" << std::endl;
-
- // STEP 4: Prepare DescriptorCalc
- DescriptorsCalc<D2,D3,DM,C2,C3,CM> dc2(param_file);
-
- // STEP 5: Results are saved to new StructureDB object
- // - it will only contain predicted values
- // so there are no atom positions, etc...
-
- bool err_bool=false; // predict error, requires LAMBDA -1
- t_type predicted_error; // container for prediction error
- std::cout << "Predicting..." << std::flush;
- StructureDB stpred = model.predict(param_file,stdb2,dc2);
- //StructureDB stpred = model.predict(param_file,stdb2,dc2,predicted_error);
- std::cout << "Done!" << std::endl;
-
- std::cout << "Dumping results to disk..." << std::flush;
- Output output(param_file,err_bool);
- output.print_predict_all(stdb,stpred,predicted_error);
- std::cout << "Done!" << std::endl;
-
- return 0;
+
+ std::cout << "TRAINING STAGE" << std::endl;
+ // Config file configures almost all model parameters.
+ // See below for a more detailed explanation of used key-value(s) pairs.
+ Config config("config");
+
+ // First we load all training data from a list
+ // of training datasets into StrutureDB object.
+ // Paths to datasets are specified with a key DBFILE in a config file.
+ std::cout << "StructureDB loading data..." << std::flush;
+ StructureDB stdb(config);
+ std::cout << "Done!" << std::endl;
+
+ // Next we pass StructureDB object to the nearest neighbour calculator.
+ // NNFinder will create full nearest neighbours lists for every atom
+ // in every structure. These lists will be stored by individual Structures
+ // in a StructureDB object.
+ // The lists are calculated up to the max cutoff from the config file:
+ // cutoff_max = max(RCUT2B, RCUT3B, RCUTMB).
+ std::cout << "Calculating nearest neighbours..." << std::flush;
+ NNFinder nnf(config);
+ nnf.calc(stdb);
+ std::cout << "Done!" << std::endl;
+
+ // STEP 1a: Select descriptors.
+ // All three types must be specified.
+ // Use Dummy if given type is not required.
+
+ // D2 - TWO-BODY
+ //using D2=D2_LJ;
+ //using D2=D2_BP;
+ using D2=D2_Blip;
+ //using D2=D2_Dummy;
+ //using D2=D2_EAM;
+
+ // D3 - THREE-BODY
+ using D3=D3_Dummy;
+
+ // DM - MANY-BODY
+ //using DM=DM_EAM;
+ //using DM=DM_EAD;
+ using DM=DM_Dummy;
+
+ // STEP 1b: Select cutoffs, C2 for D2, etc
+ using C2=Cut_Cos;
+ using C3=Cut_Dummy;
+ using CM=Cut_Dummy;
+
+ // STEP 1c: Prepare descriptor calculator
+ DescriptorsCalc<D2,D3,DM,C2,C3,CM> dc(config);
+
+ // STEP 2a: Select Basis Function (BF) or Kernels (K).
+ // BF is used for M_BLR - Bayesian Linear Regression
+ // K is used with M_KRR - Kernel Ridge Regression
+ // See documentation for more BF and K
+ using BF=DM_BF_Linear;
+ //using BF=BF_Polynomial2;
+ //using K=Kern_Linear;
+ //using K=Kern_Quadratic;
+
+ // STEP 2b: Select Model
+ using M=M_BLR<BF>;
+ //using M=M_KRR<K>;
+
+ //// STEP 2c: Instantiate a model
+ M model(config);
+
+ //std::cout << "TRAINING STAGE..." << std::flush;
+
+ // STEP 3: Training - Option 1.
+ // Train with StructureDB only. We have to provide calculators here.
+ // Descriptors are calculated in batches to construct a design matrix
+ // and then are discarded.
+ // This is usually the best choice unless you need descriptors for something else
+ // after the training is done.
+ model.train(stdb,dc);
+
+ // STEP 3: Training - Option 2.
+ // Train with StructureDB and precalcualted StDescriptorsDB.
+ //StDescriptorsDB st_desc_db = dc.calc(stdb);
+ //model.train(st_desc_db,stdb);
+ std::cout << "Done!" << std::endl;
+
+ // STEP 4: Save model to a text file.
+ // Once model is trained we can dump it to a file.
+ // Saved models can be used with LAMMPS or can be reloaded
+ // to make predictions.
+ std::cout << "Saving LAMMPS pot.tadah file..." << std::flush;
+ Config param_file = model.get_param_file();
+ std::ofstream outfile("pot.tadah");
+ outfile << param_file << std::endl;
+ outfile.close();
+ std::cout << "Done!" << std::endl;
+
+ std::cout << "PREDICTION STAGE..." << std::endl;
+ // STEP 1: We will reuse LAMMPS param file and add to it
+ // DBFILE(s) from config_pred file.
+ // In other words training datasets go to the config file
+ // and validation datasets are in the config_pred
+ param_file.add("config_pred");
+
+ // STEP 2: Load DBFILE from config_pred
+ std::cout << "StructureDB loading data..." << std::flush;
+ StructureDB stdb2(param_file);
+ std::cout << "Done!" << std::endl;
+
+ // STEP 3: Calculate nearest neighbours
+ std::cout << "Calculating nearest neighbours..." << std::flush;
+ NNFinder nnf2(param_file);
+ nnf2.calc(stdb2);
+ std::cout << "Done!" << std::endl;
+
+ // STEP 4: Prepare DescriptorCalc
+ DescriptorsCalc<D2,D3,DM,C2,C3,CM> dc2(param_file);
+
+ // STEP 5: Results are saved to new StructureDB object
+ // - it will only contain predicted values
+ // so there are no atom positions, etc...
+
+ bool err_bool=false; // predict error, requires LAMBDA -1
+ t_type predicted_error; // container for prediction error
+ std::cout << "Predicting..." << std::flush;
+ StructureDB stpred = model.predict(param_file,stdb2,dc2);
+ //StructureDB stpred = model.predict(param_file,stdb2,dc2,predicted_error);
+ std::cout << "Done!" << std::endl;
+
+ std::cout << "Dumping results to disk..." << std::flush;
+ Output output(param_file,err_bool);
+ output.print_predict_all(stdb,stpred,predicted_error);
+ std::cout << "Done!" << std::endl;
+
+ return 0;
}
diff --git a/examples/API/ex_2/config_train b/examples/API/ex_2/config_train
index 3de1553..2ffa081 100644
--- a/examples/API/ex_2/config_train
+++ b/examples/API/ex_2/config_train
@@ -7,8 +7,7 @@ ATOMS Ta
WATOMS 73
INIT2B true
-INIT3B false
-INITMB false
+TYPE2B D2_Blip 4 4 Ta Ta
RCUT2B 5.3
diff --git a/examples/API/ex_2/pot.tadah b/examples/API/ex_2/pot.tadah
index 7a1ac42..8e14f92 100644
--- a/examples/API/ex_2/pot.tadah
+++ b/examples/API/ex_2/pot.tadah
@@ -20,7 +20,7 @@ RCTYPE2B Cut_Cos
RCUT2B 5.3
SGRID2B -2 4 0.1 1.0
SWEIGHT 1
-TYPE2B D2_Blip
+TYPE2B D2_Blip 4 4 Ta Ta
VERBOSE 0
WATOMS 73
WEIGHTS -4.4157415513006 0.42189535112317 -0.37507712884283 -0.063288121709893 -0.052300112640426
diff --git a/examples/API/ex_hpo_1/config.train b/examples/API/ex_hpo_1/config.train
index 440e8e0..5166847 100644
--- a/examples/API/ex_hpo_1/config.train
+++ b/examples/API/ex_hpo_1/config.train
@@ -3,7 +3,7 @@ WATOMS 22
DBFILE tdata.db
INIT2B true
RCUT2B 5.3
-TYPE2B D2_Blip
+TYPE2B D2_Blip 5 5 Ti Ti
CGRID2B -1 5 1.0 5.0
SGRID2B -2 5 0.02 1.0
RCTYPE2B Cut_Cos
diff --git a/examples/API/ex_hpo_1/targets b/examples/API/ex_hpo_1/targets
index 4378dfc..a19cc92 100644
--- a/examples/API/ex_hpo_1/targets
+++ b/examples/API/ex_hpo_1/targets
@@ -7,10 +7,10 @@ POTEVERY 100 potdir # Controls how often the potential file is written
# Model Parameters to be Optimized
# The initial model is specified in a separate config file.
-OPTIM RCUT2B 5.0 6.0 # Optimize two-body cutoff within these bounds.
-OPTIM CGRID2B 1.0 6.0 # Optimize CGRID2B within these bounds.
-OPTIM SGRID2B 0.01 0.1 # Optimize SGRID2B within these bounds.
-OPTIM WATOMS 0.1 20 # Optimize atomic weights within these bounds.
+OPTIM RCUT2B (1) 5.0 6.0 # Optimize two-body cutoff within these bounds.
+OPTIM CGRID2B (1-5) 1.0 6.0 # Optimize CGRID2B within these bounds.
+OPTIM SGRID2B (1,2,3,4,5) 0.01 0.1 # Optimize SGRID2B within these bounds.
+OPTIM WATOMS (1) 0.1 20 # Optimize atomic weights within these bounds.
# Basic Optimization Targets with Weighted Inclusion in Global Loss
ERMSE 0 100 # Energy RMSE with weight 100, printed to properties.dat.
diff --git a/examples/CLI/ex_1/config.train b/examples/CLI/ex_1/config.train
index 2ca1796..87603a6 100644
--- a/examples/CLI/ex_1/config.train
+++ b/examples/CLI/ex_1/config.train
@@ -6,7 +6,7 @@ DBFILE tdata.db # Training dataset
INIT2B true # Use two-body descriptor
MODEL M_BLR BF_Linear # Use linear model
-TYPE2B D2_Blip # Use D2_Blip descriptor
+TYPE2B D2_Blip 4 4 Ta Ta # Use D2_Blip descriptor
RCTYPE2B Cut_Cos # Cutoff function for two-body descriptor
RCUT2B 5.3 # Cutoff distance
--
GitLab