incorporate our data and our fields

app.py

@@ -6,9 +6,41 @@ from crystal_toolkit.settings import SETTINGS
 import dash
 from dash import html, dcc
 from dash.dependencies import Input, Output, State
+from pymatgen.core import Structure
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+
+# Load only the train split of the dataset
+dataset = load_dataset(
+    "LeMaterial/leDataset",
+    token=HF_TOKEN,
+    split="train",
+    columns=[
+        "lattice_vectors",
+        "species_at_sites",
+        "cartesian_site_positions",
+        "energy",
+        "energy_corrected",
+        "immutable_id",
+        "elements",
+        "functional",
+        "stress_tensor",
+        "magnetic_moments",
+        "forces",
+        "band_gap_direct",
+        "band_gap_indirect",
+        "dos_ef",
+        "charges",
+        "functional",
+        "chemical_formula_reduced",
+        "chemical_formula_descriptive",
+        "total_magnetization"
+    ],
+)
 
-# Set your Materials Project API key
-MATERIALS_PROJECT_API_KEY = os.getenv('MATERIALS_PROJECT_API_KEY')
+# Convert the train split to a pandas DataFrame
+train_df = dataset.to_pandas()
+del dataset
 
 # Initialize the Dash app
 app = dash.Dash(__name__, assets_folder=SETTINGS.ASSETS_PATH)
@@ -51,12 +83,15 @@ layout = html.Div([
 
 # Function to search for materials
 def search_materials(query):
-    with MPRester(MATERIALS_PROJECT_API_KEY) as mpr:
-        results = mpr.summary.search(
-            chemsys=query,
-            fields=["material_id", "formula_pretty"]
-        )
-    options = [{'label': f"{res.formula_pretty} ({res.material_id})", 'value': res.material_id} for res in results]
+    element_list = [el.strip() for el in query.split("-")]
+    isubset = lambda x: set(x).issubset(element_list)
+    isintersection = lambda x: len(set(x).intersection(element_list)) > 0
+    entries_df = train_df[
+        [isintersection(l) and isubset(l) for l in train_df.elements.values.tolist()]
+    ]
+
+    options = [{'label': f"{res.chemical_formula_reduced} ({res.immutable_id}) Calculated with {res.functional}", 'value': n} for n,res in entries_df.iterrows()]
+    del entries_df
     return options
 
 
@@ -86,26 +121,23 @@ def update_material_dropdown(n_clicks, query):
 def display_material(n_clicks, material_id):
     if n_clicks is None or not material_id:
         return '', ''
-    with MPRester(MATERIALS_PROJECT_API_KEY) as mpr:
-        material = mpr.get_structure_by_material_id(material_id)
-        summary = mpr.summary.get_data_by_id(material_id)
+    row = train_df.iloc[material_id]
+
+    structure = Structure([x for y in row['lattice_vectors'] for x in y],
+                          row['species_at_sites'],
+                          row['cartesian_site_positions'],
+                          coords_are_cartesian= True)
 
     # Create the StructureMoleculeComponent
-    structure_component = ctc.StructureMoleculeComponent(material)
+    structure_component = ctc.StructureMoleculeComponent(structure)
 
     # Extract key properties
     properties = {
-        "Material ID": material_id,
-        "Formula": summary.formula_pretty,
-        "Energy Above Hull (eV/atom)": summary.energy_above_hull,
-        "Space Group": summary.symmetry.symbol,
-        "Band Gap (eV)": summary.band_gap,
-        "Formation Energy (eV/atom)": summary.formation_energy_per_atom,
-        "Magnetic Ordering": summary.ordering,
-        "Total Magnetization (μB/f.u.)": summary.total_magnetization,
-        "Is Stable": summary.is_stable,
-        "Crystal System": summary.symmetry.crystal_system,
-        "Density (g/cm³)": summary.density,
+        "Material ID": row.immutable_id,
+        "Formula": row.chemical_formula_descriptive,
+        "Energy per atom (eV/atom)": row.energy/len(row.species_at_sites),
+        "Band Gap (eV)": row.band_gap_direct or row.band_gap_indirect,
+        "Total Magnetization (μB/f.u.)": row.total_magnetization,
     }
 
     # Format properties as an HTML table