Precompute CAN data

- Slower startup
- Much faster visualization (from O(n) to O(1))

main.py

@@ -9,13 +9,13 @@ import polars as pl
 import dash
 from dash import dcc, html, Input, Output
 import dash_bootstrap_components as dbc
+import numpy as np
 
 from parser import parse_log, parse_csv
 from decoder import decode_j1939_frames
 from stats.utils.extractor import load_data
-
+from stats.id_viewer import _format_can_id_vec, plot_bits
 from stats.frequency import calculate_frequency, plot_frequency
-from stats.id_viewer import prepare_data, plot_bits
 from stats.correlation import calculate_correlation, plot_correlation_heatmap
 from stats.entropy import calculate_byte_entropy, plot_entropy_heatmap
 
@@ -55,6 +55,33 @@ DATA = {
     "Bus 2": load_data(BUS2_DECODED)
 }
 
+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")
+
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    formatted = _format_can_id_vec(df[can_id_col])
+    df = df.assign(Formatted_ID=formatted)
+
+    df = df.sort_values(['Formatted_ID', 'Timestamp'], kind='stable')
+
+    grouped = {}
+    for can_id, group in df.groupby('Formatted_ID'):
+        byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in group.columns]
+        if not group.empty and len(byte_cols) > 0:
+            arr = group[byte_cols].to_numpy(dtype=np.float32, copy=False)
+            if len(arr) > 1:
+                changed = np.any(arr[1:] != arr[:-1], axis=1)
+                keep = np.concatenate(([True], changed))
+                group = group.iloc[keep]
+        grouped[can_id] = (group, byte_cols)
+
+    DATA_BY_ID[bus] = grouped
+
 app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
 app.config.suppress_callback_exceptions = True
 
@@ -87,12 +114,10 @@ def render_content(tab, bus):
     df = DATA[bus]
 
     if tab == 'freq':
-        stats = calculate_frequency(df)
-        fig = plot_frequency(stats, title=f"{bus} Frequency")
-        return dcc.Graph(figure=fig, style={'height': '80vh'})
+        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{bus}_freq"], style={'height': '80vh'})
 
     elif tab == 'id_viewer':
-        ids = sorted(df['ID'].unique().tolist())
+        ids = sorted(DATA_BY_ID[bus].keys())
         return html.Div([
             html.Label("Select CAN ID:"),
             dcc.Dropdown(
@@ -106,7 +131,7 @@ def render_content(tab, bus):
         ])
 
     elif tab == 'corr':
-        ids = sorted(df['ID'].unique().tolist())
+        ids = sorted(DATA_BY_ID[bus].keys())
         return html.Div([
             dbc.Row([
                 dbc.Col(html.Label("Method:"), width=1, className="mt-2"),
@@ -128,9 +153,7 @@ def render_content(tab, bus):
         ])
 
     elif tab == 'entropy':
-        entropy_df = calculate_byte_entropy(df)
-        fig = plot_entropy_heatmap(entropy_df, title=f"{bus} Byte-Level Entropy")
-        return dcc.Graph(figure=fig, style={'height': '80vh'})
+        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{bus}_entropy"], style={'height': '80vh'})
 
     return html.Div("Tab not found")
 
@@ -143,8 +166,12 @@ def render_content(tab, bus):
 def update_id_viewer(selected_id, bus, tab):
     if tab != 'id_viewer' or not selected_id:
         return dash.no_update
-    df = DATA[bus]
-    filtered_df, byte_cols = prepare_data(df, selected_id)
+
+    grouped_data = DATA_BY_ID.get(bus, {})
+    if selected_id not in grouped_data:
+        return dash.no_update
+
+    filtered_df, byte_cols = grouped_data[selected_id]
     return plot_bits(filtered_df, byte_cols, selected_id, title=f"{bus} Byte Visualization")
 
 @app.callback(
@@ -157,12 +184,21 @@ def update_id_viewer(selected_id, bus, tab):
 def update_corr(method, target, bus, tab):
     if tab != 'corr':
         return dash.no_update
-    df = DATA[bus]
+
     target_id = None if target == 'all' or not target else target
-    corr_df = calculate_correlation(df, method=method, target_id=target_id)
+    cache_key = (bus, method, target_id)
+
+    if cache_key not in CORR_CACHE:
+        df = DATA[bus]
+        corr_df = calculate_correlation(df, method=method, target_id=target_id)
+        CORR_CACHE[cache_key] = corr_df
+    else:
+        corr_df = CORR_CACHE[cache_key]
+
     title = f"{bus} Correlation"
     if target_id:
         title += f" ({target_id})"
+
     return plot_correlation_heatmap(corr_df, target_id=target_id, title=title)
 
 if __name__ == '__main__':