Parallelize data processing tasks with ThreadPoolExecutor

main.py

@@ -4,6 +4,7 @@
 
 import os
 from pathlib import Path
+from concurrent.futures import ThreadPoolExecutor
 
 import polars as pl
 import dash
@@ -59,9 +60,10 @@ PRECOMPUTED_FIGURES = {}
 DATA_BY_ID = {}
 CORR_CACHE = {}
 
-for bus, df in DATA.items():
-    PRECOMPUTED_FIGURES[f"{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{bus} Frequency")
-    PRECOMPUTED_FIGURES[f"{bus}_entropy"] = plot_entropy_heatmap(calculate_byte_entropy(df), title=f"{bus} Byte-Level Entropy")
+def process_bus_data(bus, df):
+    precomp = {}
+    precomp[f"{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{bus} Frequency")
+    precomp[f"{bus}_entropy"] = plot_entropy_heatmap(calculate_byte_entropy(df), title=f"{bus} Byte-Level Entropy")
 
     can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
     formatted = _format_can_id_vec(df[can_id_col])
@@ -80,7 +82,15 @@ for bus, df in DATA.items():
                 group = group.iloc[keep]
         grouped[can_id] = (group, byte_cols)
 
-    DATA_BY_ID[bus] = grouped
+    return precomp, grouped
+
+with ThreadPoolExecutor() as executor:
+    futures = {executor.submit(process_bus_data, bus, df): bus for bus, df in DATA.items()}
+    for future in futures:
+        bus = futures[future]
+        precomp, grouped = future.result()
+        PRECOMPUTED_FIGURES.update(precomp)
+        DATA_BY_ID[bus] = grouped
 
 app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
 app.config.suppress_callback_exceptions = True
@@ -209,4 +219,4 @@ def update_corr(method, target, bus, tab):
     return plot_correlation_heatmap(corr_df, target_id=target_id, title=title)
 
 if __name__ == '__main__':
-    app.run(debug=False)
+    app.run(debug=True)