adding HF database and parsing entries from it as computedentry, logic for filtering from element list

app.py

@@ -4,29 +4,40 @@ from pymatgen.analysis.phase_diagram import PhaseDiagram, PDPlotter
 from pymatgen.core.composition import Composition
 import plotly.graph_objs as go
 import os
+from pymatgen.entries.computed_entries import ComputedEntry
+from pymatgen.core import Composition
 
-MATERIALS_PROJECT_API_KEY = os.getenv('MATERIALS_PROJECT_API_KEY')
+from datasets import load_dataset
+
+# Load only the train split of the dataset
+dataset = load_dataset("LeMaterial/leDataset", split="train")
+
+# Convert the train split to a pandas DataFrame
+train_df = dataset.to_pandas()
 
 
 def create_phase_diagram(elements, max_e_above_hull, color_scheme, plot_style, functional, finite_temp):
     # Split elements and remove any whitespace
     element_list = [el.strip() for el in elements.split('-')]
 
-    with MPRester(MATERIALS_PROJECT_API_KEY) as m:
-        # Fetch all entries from the Materials Project database
-        entries = m.get_entries_in_chemsys(element_list, compatible_only=True, inc_structure='final')
-
-        # Fetch elemental entries (they are usually GGA calculations)
-        elemental_entries = m.get_entries_in_chemsys(element_list, compatible_only=True, inc_structure='final')
-        elemental_entries = [e for e in elemental_entries if e.composition.is_element]
+    # Fetch all entries from the Materials Project database
+    entries = [ComputedEntry( 
+        Composition(row["chemical_formula_descriptive"]), 
+        energy = row['energy'], 
+        correction = row['energy_corrected']-row['energy'], 
+        entry_id = row['immutable_id']) for n,row in df.iterrows() if len(
+        set(row['elements']).intersection(element_list))>0 and set(
+        row['elements']).issubset(element_list)]
+    # Fetch elemental entries (they are usually GGA calculations)
+    elemental_entries = [e for e in entries if e.composition.is_element]
 
-        # Filter entries based on functional
-        if functional == "GGA":
-            entries = [e for e in entries if not e.parameters.get("run_type", "").startswith("GGA+U")]
-        elif functional == "GGA+U":
-            entries = [e for e in entries if e.parameters.get("run_type", "").startswith("GGA+U")]
-            # Add elemental entries to ensure they are included
-            entries.extend([e for e in elemental_entries if e not in entries])
+    # Filter entries based on functional
+    if functional == "GGA":
+        entries = [e for e in entries if not e.parameters.get("run_type", "").startswith("GGA+U")]
+    elif functional == "GGA+U":
+        entries = [e for e in entries if e.parameters.get("run_type", "").startswith("GGA+U")]
+        # Add elemental entries to ensure they are included
+        entries.extend([e for e in elemental_entries if e not in entries])
 
     # Build the phase diagram
     try: