Merge pull request #353 from usnistgov/develop

Develop

jarvis_leaderboard/contributions/alignn_ff_12_2_24/run.sh → jarvis_leaderboard/contributions/alignn_ff/run.sh

@@ -2,11 +2,10 @@
 
 # Create logs directory if it doesn't exist
 mkdir -p logs
-
-jid_list=('JVASP-62940' 'JVASP-20092')
+#jid_list=('JVASP-1002')
 # Define arrays of JIDs and calculators
-#jid_list=('JVASP-1002' 'JVASP-890' 'JVASP-39' 'JVASP-30' 'JVASP-62940' 'JVASP-20092' 'JVASP-8003' 'JVASP-1192' 'JVASP-23' 'JVASP-1195' 'JVASP-96' 'JVASP-10591' 'JVASP-1198' 'JVASP-1312' 'JVASP-133719' 'JVASP-36873' 'JVASP-1327' 'JVASP-1372' 'JVASP-1408' 'JVASP-8184' 'JVASP-1174' 'JVASP-1177' 'JVASP-1180' 'JVASP-1183' 'JVASP-1186' 'JVASP-1189' 'JVASP-91' 'JVASP-8158' 'JVASP-8118' 'JVASP-107' 'JVASP-36018' 'JVASP-36408' 'JVASP-105410' 'JVASP-36403' 'JVASP-1008' 'JVASP-95268' 'JVASP-21211' 'JVASP-1023' 'JVASP-7836' 'JVASP-9166' 'JVASP-1201' 'JVASP-85478' 'JVASP-1115' 'JVASP-1112' 'JVASP-1103' 'JVASP-1109' 'JVASP-131' 'JVASP-149916' 'JVASP-111005' 'JVASP-25' 'JVASP-1067' 'JVASP-154954' 'JVASP-59712' 'JVASP-10703' 'JVASP-1213' 'JVASP-19007' 'JVASP-10114' 'JVASP-9175' 'JVASP-104' 'JVASP-10036' 'JVASP-18983' 'JVASP-1216' 'JVASP-79522' 'JVASP-1222' 'JVASP-10037' 'JVASP-110' 'JVASP-8082' 'JVASP-1240' 'JVASP-51480' 'JVASP-29539' 'JVASP-54' 'JVASP-29556' 'JVASP-1915' 'JVASP-75662' 'JVASP-101764' 'JVASP-22694' 'JVASP-4282' 'JVASP-76195' 'JVASP-8554' 'JVASP-149871' 'JVASP-2376' 'JVASP-14163' 'JVASP-26248' 'JVASP-18942' 'JVASP-3510' 'JVASP-5224' 'JVASP-8559' 'JVASP-85416' 'JVASP-9117' 'JVASP-90668' 'JVASP-10689' 'JVASP-106381' 'JVASP-108773' 'JVASP-101184' 'JVASP-103127' 'JVASP-104764' 'JVASP-102336' 'JVASP-110231' 'JVASP-108770' 'JVASP-101074' 'JVASP-149906' 'JVASP-99732' 'JVASP-106686' 'JVASP-110952' 'JVASP-106363' 'JVASP-972' 'JVASP-825' 'JVASP-813' 'JVASP-816' 'JVASP-802' 'JVASP-1029' 'JVASP-861' 'JVASP-943' 'JVASP-963' 'JVASP-14616' 'JVASP-867' 'JVASP-14968' 'JVASP-14970' 'JVASP-19780' 'JVASP-9147' 'JVASP-34249' 'JVASP-43367' 'JVASP-113' 'JVASP-41' 'JVASP-58349' 'JVASP-34674' 'JVASP-34656' 'JVASP-34249' 'JVASP-32')
-calculator_types=("alignn_ff_12_2_24")
+jid_list=('JVASP-1002' 'JVASP-890' 'JVASP-39' 'JVASP-30' 'JVASP-62940' 'JVASP-20092' 'JVASP-8003' 'JVASP-1192' 'JVASP-23' 'JVASP-1195' 'JVASP-96' 'JVASP-10591' 'JVASP-1198' 'JVASP-1312' 'JVASP-133719' 'JVASP-36873' 'JVASP-1327' 'JVASP-1372' 'JVASP-1408' 'JVASP-8184' 'JVASP-1174' 'JVASP-1177' 'JVASP-1180' 'JVASP-1183' 'JVASP-1186' 'JVASP-1189' 'JVASP-91' 'JVASP-8158' 'JVASP-8118' 'JVASP-107' 'JVASP-36018' 'JVASP-36408' 'JVASP-105410' 'JVASP-1008' 'JVASP-21211' 'JVASP-1023' 'JVASP-7836' 'JVASP-9166' 'JVASP-1201' 'JVASP-85478' 'JVASP-1115' 'JVASP-1112' 'JVASP-1103' 'JVASP-1109' 'JVASP-131' 'JVASP-149916' 'JVASP-111005' 'JVASP-25' 'JVASP-1067' 'JVASP-10703' 'JVASP-104' 'JVASP-10036' 'JVASP-18983' 'JVASP-1216' 'JVASP-79522' 'JVASP-1222' 'JVASP-10037' 'JVASP-110' 'JVASP-8082' 'JVASP-1240' 'JVASP-29539' 'JVASP-54' 'JVASP-1915' 'JVASP-22694' 'JVASP-4282' 'JVASP-76195' 'JVASP-8554' 'JVASP-149871' 'JVASP-2376' 'JVASP-3510' 'JVASP-5224' 'JVASP-8559' 'JVASP-85416' 'JVASP-9117' 'JVASP-90668' 'JVASP-103127' 'JVASP-104764' 'JVASP-110231' 'JVASP-108770' 'JVASP-149906' 'JVASP-99732' 'JVASP-106686' 'JVASP-106363' 'JVASP-972' 'JVASP-825' 'JVASP-813' 'JVASP-816' 'JVASP-802' 'JVASP-1029' 'JVASP-861' 'JVASP-943' 'JVASP-963' 'JVASP-14616' 'JVASP-867' 'JVASP-14968' 'JVASP-14970' 'JVASP-19780' 'JVASP-9147' 'JVASP-34249' 'JVASP-43367' 'JVASP-113' 'JVASP-41' 'JVASP-58349' 'JVASP-34674' 'JVASP-34249' 'JVASP-32')
+calculator_types=("mace")
 
 # Loop through each JID and calculator combination
 for jid in "${jid_list[@]}"; do
@@ -46,27 +45,18 @@ cat > input_${jid}_${calculator}.json <<JSON
       "constant_volume": false
     }
   },
-  "calculator_settings": {
-    "matgl": {
-      "model": "M3GNet-MP-2021.2.8-PES"
-    },
-    "alignn_ff": {
-      "stress_weight": 0.3
-    },
-    "chgnet": {}
-  },
   "phonon_settings": {
     "dim": [2, 2, 2],
     "distance": 0.2
   },
   "use_conventional_cell": false,
   "surface_settings": {
     "indices_list": [
-      [1, 0, 0], 
-      [1, 1, 1], 
-      [1, 1, 0], 
-      [0, 1, 1], 
-      [0, 0, 1], 
+      [1, 0, 0],
+      [1, 1, 1],
+      [1, 1, 0],
+      [0, 1, 1],
+      [0, 0, 1],
       [0, 1, 0]
     ],
     "layers": 4,

jarvis_leaderboard/contributions/alignn_ff/run_chipsff.py

@@ -0,0 +1,298 @@
+#!/usr/bin/env python
+import os
+import pandas as pd
+import plotly.express as px
+import argparse
+from jarvis.db.jsonutils import loadjson
+from chipsff.config import CHIPSFFConfig
+from tqdm import tqdm
+from chipsff.general_material_analyzer import MaterialsAnalyzer
+from chipsff.alignn_ff_db_analyzer import AlignnFFForcesAnalyzer
+from chipsff.mlearn_db_analyzer import MLearnForcesAnalyzer
+from chipsff.mptraj_analyzer import MPTrjAnalyzer
+from chipsff.scaling_analyzer import ScalingAnalyzer
+
+
+def analyze_multiple_structures(
+    jid_list, calculator_types, chemical_potentials_file, **kwargs
+):
+    """
+    Analyzes multiple structures with multiple calculators and aggregates error metrics.
+
+    Args:
+        jid_list (List[str]): List of JIDs to analyze.
+        calculator_types (List[str]): List of calculator types to use.
+        chemical_potentials_file (str): Path to the chemical potentials JSON file.
+        **kwargs: Additional keyword arguments for analysis settings.
+
+    Returns:
+        None
+    """
+    composite_error_data = {}
+
+    for calculator_type in calculator_types:
+        # List to store individual error DataFrames
+        error_dfs = []
+
+        for jid in tqdm(jid_list, total=len(jid_list)):
+            print(f"Analyzing {jid} with {calculator_type}...")
+            # Fetch calculator-specific settings
+            calc_settings = kwargs.get("calculator_settings", {}).get(
+                calculator_type, {}
+            )
+            analyzer = MaterialsAnalyzer(
+                jid=jid,
+                calculator_type=calculator_type,
+                chemical_potentials_file=chemical_potentials_file,
+                bulk_relaxation_settings=kwargs.get(
+                    "bulk_relaxation_settings"
+                ),
+                phonon_settings=kwargs.get("phonon_settings"),
+                properties_to_calculate=kwargs.get("properties_to_calculate"),
+                use_conventional_cell=kwargs.get(
+                    "use_conventional_cell", False
+                ),
+                surface_settings=kwargs.get("surface_settings"),
+                defect_settings=kwargs.get("defect_settings"),
+                phonon3_settings=kwargs.get("phonon3_settings"),
+                md_settings=kwargs.get("md_settings"),
+                calculator_settings=calc_settings,  # Pass calculator-specific settings
+            )
+            # Run analysis and get error data
+            error_dat = analyzer.run_all()
+            error_df = pd.DataFrame([error_dat])
+            error_dfs.append(error_df)
+
+        # Concatenate all error DataFrames
+        all_errors_df = pd.concat(error_dfs, ignore_index=True)
+
+        # Compute composite errors by ignoring NaN values
+        composite_error = all_errors_df.mean(skipna=True).to_dict()
+
+        # Store the composite error data for this calculator type
+        composite_error_data[calculator_type] = composite_error
+
+    # Once all materials and calculators have been processed, create a DataFrame
+    composite_df = pd.DataFrame(composite_error_data).transpose()
+
+    # Plot the composite scorecard
+    plot_composite_scorecard(composite_df)
+
+    # Save the composite dataframe
+    composite_df.to_csv("composite_error_data.csv", index=True)
+
+
+def analyze_multiple_interfaces(
+    film_jid_list,
+    substrate_jid_list,
+    calculator_types,
+    chemical_potentials_file,
+    film_index="1_1_0",
+    substrate_index="1_1_0",
+):
+    for calculator_type in calculator_types:
+        for film_jid in film_jid_list:
+            for substrate_jid in substrate_jid_list:
+                print(
+                    f"Analyzing interface between {film_jid} and {substrate_jid} with {calculator_type}..."
+                )
+                analyzer = MaterialsAnalyzer(
+                    calculator_type=calculator_type,
+                    chemical_potentials_file=chemical_potentials_file,
+                    film_jid=film_jid,
+                    substrate_jid=substrate_jid,
+                    film_index=film_index,
+                    substrate_index=substrate_index,
+                )
+                analyzer.analyze_interfaces()
+
+
+def plot_composite_scorecard(df):
+
+    fig = px.imshow(
+        df, text_auto=True, aspect="auto", labels=dict(color="Error")
+    )
+
+    # Update layout for larger font sizes
+    fig.update_layout(
+        font=dict(size=24),  # Adjust the font size
+        coloraxis_colorbar=dict(
+            title_font=dict(size=18), tickfont=dict(size=18)
+        ),
+    )
+
+    # Optionally adjust the text font size for cells
+    fig.update_traces(textfont=dict(size=18))  # Adjust text size in cells
+    fname_plot = "composite_error_scorecard.png"
+    fig.write_image(fname_plot)
+    fig.show()
+
+
+# Ensure that the necessary modules and functions are imported
+# from your existing codebase, such as `data`, `Atoms`, `voigt_6_to_full_3x3_stress`, etc.
+# Example:
+# from your_module import data, Atoms, voigt_6_to_full_3x3_stress, loadjson
+
+
+def main():
+    import pprint
+
+    parser = argparse.ArgumentParser(description="Run Materials Analyzer")
+    parser.add_argument(
+        "--input_file",
+        default="input.json",
+        type=str,
+        help="Path to the input configuration JSON file",
+    )
+    args = parser.parse_args()
+
+    input_file = loadjson(args.input_file)
+    input_file_data = CHIPSFFConfig(**input_file)
+    pprint.pprint(input_file_data.dict())
+
+    # Check if scaling test is requested
+    if input_file_data.scaling_test:
+        print("Running scaling test...")
+        scaling_analyzer = ScalingAnalyzer(input_file_data)
+        scaling_analyzer.run()
+    else:
+        # Determine the list of JIDs
+        if input_file_data.jid:
+            jid_list = [input_file_data.jid]
+        elif input_file_data.jid_list:
+            jid_list = input_file_data.jid_list
+        else:
+            jid_list = []
+
+        # Determine the list of calculators
+        if input_file_data.calculator_type:
+            calculator_list = [input_file_data.calculator_type]
+        elif input_file_data.calculator_types:
+            calculator_list = input_file_data.calculator_types
+        else:
+            calculator_list = []
+
+        # Handle film and substrate IDs for interface analysis
+        film_jids = input_file_data.film_id if input_file_data.film_id else []
+        substrate_jids = (
+            input_file_data.substrate_id
+            if input_file_data.substrate_id
+            else []
+        )
+
+        # Scenario 5: Batch Processing for Multiple JIDs and Calculators
+        if input_file_data.jid_list and input_file_data.calculator_types:
+            analyze_multiple_structures(
+                jid_list=input_file_data.jid_list,
+                calculator_types=input_file_data.calculator_types,
+                chemical_potentials_file=input_file_data.chemical_potentials_file,
+                bulk_relaxation_settings=input_file_data.bulk_relaxation_settings,
+                phonon_settings=input_file_data.phonon_settings,
+                properties_to_calculate=input_file_data.properties_to_calculate,
+                use_conventional_cell=input_file_data.use_conventional_cell,
+                surface_settings=input_file_data.surface_settings,
+                defect_settings=input_file_data.defect_settings,
+                phonon3_settings=input_file_data.phonon3_settings,
+                md_settings=input_file_data.md_settings,
+                calculator_settings=input_file_data.calculator_settings,  # Pass calculator-specific settings
+            )
+        else:
+            # Scenario 1 & 3: Single or Multiple JIDs with Single or Multiple Calculators
+            if jid_list and tqdm(calculator_list, total=len(calculator_list)):
+                for jid in tqdm(jid_list, total=len(jid_list)):
+                    for calculator_type in calculator_list:
+                        print(f"Analyzing {jid} with {calculator_type}...")
+                        # Fetch calculator-specific settings
+                        calc_settings = (
+                            input_file_data.calculator_settings.get(
+                                calculator_type, {}
+                            )
+                        )
+                        analyzer = MaterialsAnalyzer(
+                            jid=jid,
+                            calculator_type=calculator_type,
+                            chemical_potentials_file=input_file_data.chemical_potentials_file,
+                            bulk_relaxation_settings=input_file_data.bulk_relaxation_settings,
+                            phonon_settings=input_file_data.phonon_settings,
+                            properties_to_calculate=input_file_data.properties_to_calculate,
+                            use_conventional_cell=input_file_data.use_conventional_cell,
+                            surface_settings=input_file_data.surface_settings,
+                            defect_settings=input_file_data.defect_settings,
+                            phonon3_settings=input_file_data.phonon3_settings,
+                            md_settings=input_file_data.md_settings,
+                            calculator_settings=calc_settings,  # Pass calculator-specific settings
+                        )
+                        analyzer.run_all()
+
+        # Proceed with other scenarios that don't overlap with jid_list and calculator_types
+        # Scenario 2 & 4: Interface Calculations (Multiple Calculators and/or JIDs)
+        if film_jids and substrate_jids and calculator_list:
+            for film_jid, substrate_jid in zip(film_jids, substrate_jids):
+                for calculator_type in calculator_list:
+                    print(
+                        f"Analyzing interface between {film_jid} and {substrate_jid} with {calculator_type}..."
+                    )
+                    # Fetch calculator-specific settings
+                    calc_settings = input_file_data.calculator_settings.get(
+                        calculator_type, {}
+                    )
+                    analyzer = MaterialsAnalyzer(
+                        calculator_type=calculator_type,
+                        chemical_potentials_file=input_file_data.chemical_potentials_file,
+                        film_jid=film_jid,
+                        substrate_jid=substrate_jid,
+                        film_index=input_file_data.film_index,
+                        substrate_index=input_file_data.substrate_index,
+                        bulk_relaxation_settings=input_file_data.bulk_relaxation_settings,
+                        phonon_settings=input_file_data.phonon_settings,
+                        properties_to_calculate=input_file_data.properties_to_calculate,
+                        calculator_settings=calc_settings,  # Pass calculator-specific settings
+                    )
+                    analyzer.analyze_interfaces()
+
+        # Continue with other independent scenarios
+        # Scenario 6: MLearn Forces Comparison
+        if input_file_data.mlearn_elements and input_file_data.calculator_type:
+            print(
+                f"Running mlearn forces comparison for elements {input_file_data.mlearn_elements} with {input_file_data.calculator_type}..."
+            )
+            mlearn_analyzer = MLearnForcesAnalyzer(
+                calculator_type=input_file_data.calculator_type,
+                mlearn_elements=input_file_data.mlearn_elements,
+                calculator_settings=input_file_data.calculator_settings.get(
+                    input_file_data.calculator_type, {}
+                ),
+            )
+            mlearn_analyzer.run()
+
+        # Scenario 7: AlignnFF Forces Comparison
+        if input_file_data.alignn_ff_db and input_file_data.calculator_type:
+            print(
+                f"Running AlignnFF forces comparison with {input_file_data.calculator_type}..."
+            )
+            alignn_ff_analyzer = AlignnFFForcesAnalyzer(
+                calculator_type=input_file_data.calculator_type,
+                num_samples=input_file_data.num_samples,
+                calculator_settings=input_file_data.calculator_settings.get(
+                    input_file_data.calculator_type, {}
+                ),
+            )
+            alignn_ff_analyzer.run()
+
+        # Scenario 8: MPTrj Forces Comparison
+        if input_file_data.mptrj and input_file_data.calculator_type:
+            print(
+                f"Running MPTrj forces comparison with {input_file_data.calculator_type}..."
+            )
+            mptrj_analyzer = MPTrjAnalyzer(
+                calculator_type=input_file_data.calculator_type,
+                num_samples=input_file_data.num_samples,
+                calculator_settings=input_file_data.calculator_settings.get(
+                    input_file_data.calculator_type, {}
+                ),
+            )
+            mptrj_analyzer.run()
+
+
+if __name__ == "__main__":
+    main()