Memory requirements

app.py

@@ -2,6 +2,7 @@ import os
 
 import gradio as gr
 import numpy as np
+import pandas as pd
 import plotly.graph_objs as go
 from datasets import concatenate_datasets, load_dataset
 from pymatgen.analysis.phase_diagram import PDPlotter, PhaseDiagram
@@ -38,7 +39,7 @@ for subset in subsets:
     datasets.append(dataset["train"])
 
 # Convert the train split to a pandas DataFrame
-dataset = concatenate_datasets(datasets)
+df = pd.concat([x.to_pandas() for x in datasets])
 train_df = dataset.to_pandas()
 del dataset
 
@@ -79,9 +80,11 @@ def create_phase_diagram(
                 coords_are_cartesian=True,
             ),
             energy=row["energy"],
-            correction=row["energy_corrected"] - row["energy"]
-            if not np.isnan(row["energy_corrected"])
-            else 0,
+            correction=(
+                row["energy_corrected"] - row["energy"]
+                if not np.isnan(row["energy_corrected"])
+                else 0
+            ),
             entry_id=row["immutable_id"],
             parameters={"run_type": row["functional"]},
         )