Minor title changes

Reviewed-on: erickahmed/CANveyor#8

main.py

@@ -2,191 +2,306 @@
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
-import os
-from pathlib import Path
-from concurrent.futures import ThreadPoolExecutor
+"""CANveyor dashboard entry point.
+
+Handles raw log ingestion, J1939 decoding, precomputation of
+statistical figures, and exposes a Dash application for browsing the
+processed data.
+"""
+
+import os
+from concurrent.futures import ThreadPoolExecutor
+from pathlib import Path
+from typing import Dict, List, Tuple
 
-import polars as pl
 import dash
-from dash import dcc, html, Input, Output, State
 import dash_bootstrap_components as dbc
 import numpy as np
+import pandas as pd
+import polars as pl
+from dash import dcc, html, Input, Output, State
 
-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 logs.view import get_logs_table_component, prepare_logs_data
+from parser import parse_csv, parse_log
 from stats.correlation import calculate_correlation, plot_correlation_heatmap
 from stats.entropy import calculate_byte_entropy, plot_entropy_heatmap
-from logs.view import get_logs_table_component, prepare_logs_data
+from stats.frequency import calculate_frequency, plot_frequency
+from stats.id_viewer import _format_can_id_vec, plot_bits
+from stats.utils.loader import load_data
+from vehicle import get_vehicle_module
 
 RAW_LOG_DIR = "data/logs"
-PAGE_SIZE = 25000
+CSV_DIR = "data/csv"
+PARQUET_DIR = "data/parquet"
+PAGE_SIZE = 25_000
+BYTE_COLS = [f"b{i}" for i in range(8)]
+BUS_OPTIONS = [
+    {"label": "Bus 1", "value": "Bus 1"},
+    {"label": "Bus 2", "value": "Bus 2"},
+]
 
-def parse_vehicle_from_filename(filename: str):
+DATA: Dict[str, Dict[str, pd.DataFrame]] = {}
+VEHICLE_META: Dict[str, Dict[str, str]] = {}
+PRECOMPUTED_FIGURES: Dict[str, object] = {}
+DATA_BY_ID: Dict[Tuple[str, str], Dict[str, Tuple[pd.DataFrame, List[str]]]] = {}
+CORR_CACHE: Dict[Tuple, object] = {}
+PREPARED_LOGS_CACHE: Dict[Tuple[str, str], pd.DataFrame] = {}
+
+
+def parse_vehicle_from_filename(filename: str) -> Tuple[str, str, str]:
+    """Derive (vehicle, brand, model) from a log file name."""
     stem = Path(filename).stem
-    if '-' in stem:
-        brand, model_part = stem.split('-', 1)
+    if "-" in stem:
+        brand, model_part = stem.split("-", 1)
     else:
         brand, model_part = stem, "Unknown"
-    model = model_part.replace('_', ' ')
+    model = model_part.replace("_", " ")
     vehicle = f"{brand} {model}".strip()
     return vehicle, brand, model
 
-def run_pipeline():
-    os.makedirs(RAW_LOG_DIR, exist_ok=True)
-    os.makedirs("data/csv", exist_ok=True)
-    os.makedirs("data/parquet", exist_ok=True)
+
+def _vehicle_paths(vehicle: str) -> Dict[str, str]:
+    """Return all intermediate file paths for a given vehicle."""
+    return {
+        "bus1_csv": f"{CSV_DIR}/{vehicle}_bus1.csv",
+        "bus2_csv": f"{CSV_DIR}/{vehicle}_bus2.csv",
+        "bus1_parquet": f"{PARQUET_DIR}/{vehicle}_bus1.parquet",
+        "bus2_parquet": f"{PARQUET_DIR}/{vehicle}_bus2.parquet",
+        "bus1_decoded": f"{PARQUET_DIR}/{vehicle}_bus1_decoded.parquet",
+        "bus2_decoded": f"{PARQUET_DIR}/{vehicle}_bus2_decoded.parquet",
+    }
+
+
+def run_pipeline() -> None:
+    """Parse raw log files, convert to parquet, and decode J1939 frames."""
+    for directory in (RAW_LOG_DIR, CSV_DIR, PARQUET_DIR):
+        os.makedirs(directory, exist_ok=True)
 
+    for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
+        vehicle, _, _ = parse_vehicle_from_filename(log_file.name)
+        paths = _vehicle_paths(vehicle)
+
+        if Path(paths["bus1_decoded"]).exists() and Path(paths["bus2_decoded"]).exists():
+            continue
+
+        print(f"Parsing raw log: {log_file.name}...")
+        parse_log(str(log_file), paths["bus1_csv"], paths["bus2_csv"])
+
+        print("Converting to parquet...")
+        parse_csv(paths["bus1_csv"]).sink_parquet(paths["bus1_parquet"])
+        parse_csv(paths["bus2_csv"]).sink_parquet(paths["bus2_parquet"])
+
+        print("Decoding J1939...")
+        df1 = pl.read_parquet(paths["bus1_parquet"])
+        df2 = pl.read_parquet(paths["bus2_parquet"])
+        decode_j1939_frames(df1).write_parquet(paths["bus1_decoded"])
+        decode_j1939_frames(df2).write_parquet(paths["bus2_decoded"])
+
+
+def load_vehicle_data() -> None:
+    """Load all decoded parquet files into the in-memory DATA store."""
     for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
         vehicle, brand, model = parse_vehicle_from_filename(log_file.name)
+        VEHICLE_META[vehicle] = {"brand": brand, "model": model}
 
-        bus1_csv = f"data/csv/{vehicle}_bus1.csv"
-        bus2_csv = f"data/csv/{vehicle}_bus2.csv"
-        bus1_parquet = f"data/parquet/{vehicle}_bus1.parquet"
-        bus2_parquet = f"data/parquet/{vehicle}_bus2.parquet"
-        bus1_decoded = f"data/parquet/{vehicle}_bus1_decoded.parquet"
-        bus2_decoded = f"data/parquet/{vehicle}_bus2_decoded.parquet"
+        paths = _vehicle_paths(vehicle)
+        if Path(paths["bus1_decoded"]).exists() and Path(paths["bus2_decoded"]).exists():
+            DATA[vehicle] = {
+                "Bus 1": load_data(paths["bus1_decoded"]),
+                "Bus 2": load_data(paths["bus2_decoded"]),
+            }
 
-        if not Path(bus1_decoded).exists() or not Path(bus2_decoded).exists():
-            print(f"Parsing raw log: {log_file.name}...")
-            parse_log(str(log_file), bus1_csv, bus2_csv)
 
-            print("Converting to parquet...")
-            parse_csv(bus1_csv).sink_parquet(bus1_parquet)
-            parse_csv(bus2_csv).sink_parquet(bus2_parquet)
+def _can_id_column(df: pd.DataFrame) -> str:
+    return "ID" if "ID" in df.columns else "Identifier"
 
-            print("Decoding J1939...")
-            df1 = pl.read_parquet(bus1_parquet)
-            df2 = pl.read_parquet(bus2_parquet)
-            dec1 = decode_j1939_frames(df1)
-            dec2 = decode_j1939_frames(df2)
-            dec1.write_parquet(bus1_decoded)
-            dec2.write_parquet(bus2_decoded)
 
-run_pipeline()
+def _downsample_unchanged(group: pd.DataFrame, byte_cols: List[str]) -> pd.DataFrame:
+    """Keep only rows where at least one byte changed vs. the previous row."""
+    if group.empty or not byte_cols:
+        return group
+    arr = group[byte_cols].to_numpy(dtype=np.float32, copy=False)
+    if len(arr) <= 1:
+        return group
+    changed = np.any(arr[1:] != arr[:-1], axis=1)
+    keep = np.concatenate(([True], changed))
+    return group.iloc[keep]
 
-print("Loading data into memory...")
-DATA = {}
-VEHICLE_META = {}
 
-for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
-    vehicle, brand, model = parse_vehicle_from_filename(log_file.name)
-    VEHICLE_META[vehicle] = {"brand": brand, "model": model}
+def process_bus_data(
+    vehicle: str, bus: str, df: pd.DataFrame
+) -> Tuple[str, str, Dict[str, object], Dict[str, Tuple[pd.DataFrame, List[str]]]]:
+    """Compute per-bus figures and ID-grouped, downsampled frames."""
+    precomp = {
+        f"{vehicle}_{bus}_freq": plot_frequency(
+            calculate_frequency(df), title=f"{vehicle} {bus} Frequency"
+        ),
+        f"{vehicle}_{bus}_entropy": plot_entropy_heatmap(
+            calculate_byte_entropy(df), title=f"{vehicle} {bus} Byte-Level Entropy"
+        ),
+    }
 
-    bus1_decoded = f"data/parquet/{vehicle}_bus1_decoded.parquet"
-    bus2_decoded = f"data/parquet/{vehicle}_bus2_decoded.parquet"
+    df = df.assign(Formatted_ID=_format_can_id_vec(df[_can_id_column(df)]))
+    df = df.sort_values(["Formatted_ID", "Timestamp"], kind="stable")
 
-    if Path(bus1_decoded).exists() and Path(bus2_decoded).exists():
-        DATA[vehicle] = {
-            "Bus 1": load_data(bus1_decoded),
-            "Bus 2": load_data(bus2_decoded)
-        }
-
-PRECOMPUTED_FIGURES = {}
-DATA_BY_ID = {}
-CORR_CACHE = {}
-PREPARED_LOGS_CACHE = {}
-
-def process_bus_data(vehicle, bus, df):
-    precomp = {}
-    precomp[f"{vehicle}_{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{vehicle} {bus} Frequency")
-    precomp[f"{vehicle}_{bus}_entropy"] = plot_entropy_heatmap(calculate_byte_entropy(df), title=f"{vehicle} {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(by='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: Dict[str, Tuple[pd.DataFrame, List[str]]] = {}
+    for can_id, group in df.groupby(by="Formatted_ID"):
+        byte_cols = [c for c in BYTE_COLS if c in group.columns]
+        group = _downsample_unchanged(group, byte_cols)
         grouped[can_id] = (group, byte_cols)
 
     return vehicle, bus, precomp, grouped
 
-with ThreadPoolExecutor() as executor:
-    futures = []
-    for vehicle, buses in DATA.items():
-        for bus, df in buses.items():
-            futures.append(executor.submit(process_bus_data, vehicle, bus, df))
-    for future in futures:
-        v, b, precomp, grouped = future.result()
-        PRECOMPUTED_FIGURES.update(precomp)
-        DATA_BY_ID[(v, b)] = grouped
+
+def precompute_all() -> None:
+    """Run :func:`process_bus_data` across every vehicle/bus pair in parallel."""
+    with ThreadPoolExecutor() as executor:
+        futures = [
+            executor.submit(process_bus_data, vehicle, bus, df)
+            for vehicle, buses in DATA.items()
+            for bus, df in buses.items()
+        ]
+        for future in futures:
+            v, b, precomp, grouped = future.result()
+            PRECOMPUTED_FIGURES.update(precomp)
+            DATA_BY_ID[(v, b)] = grouped
+
+run_pipeline()
+
+print("Loading data into memory...")
+load_vehicle_data()
+precompute_all()
 
 app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
 app.config.suppress_callback_exceptions = True
 
-app.layout = dbc.Container([
-    html.H1("CANveyor", className="my-4"),
-    dbc.Tabs([
-        dbc.Tab(label="Overview", tab_id="overview", children=[
-            html.Div(id="overview-content")
-        ]),
-        dbc.Tab(label="Logs", tab_id="logs", children=[
-            dbc.Row([
-                dbc.Col(html.Label("Select Vehicle:", className="mt-2"), width="auto"),
-                dbc.Col(dcc.Dropdown(
-                    id='logs-vehicle-selector',
-                    options=[{'label': v, 'value': v} for v in DATA.keys()],
-                    value=list(DATA.keys())[0] if DATA else None,
-                    clearable=False
-                ), width=3, className="me-4"),
-                dbc.Col(html.Label("Select Bus:", className="mt-2"), width="auto"),
-                dbc.Col(dcc.Dropdown(
-                    id='logs-bus-selector',
-                    options=[{'label': 'Bus 1', 'value': 'Bus 1'}, {'label': 'Bus 2', 'value': 'Bus 2'}],
-                    value='Bus 1',
-                    clearable=False
-                ), width=2),
-            ], className="mb-3 mt-3", align="end"),
-            get_logs_table_component()
-        ]),
-        dbc.Tab(label="Statistics", tab_id="statistics", children=[
-            dbc.Row([
-                dbc.Col(html.Label("Select Vehicle:", className="mt-2"), width="auto"),
-                dbc.Col(dcc.Dropdown(
-                    id='vehicle-selector',
-                    options=[{'label': v, 'value': v} for v in DATA.keys()],
-                    value=list(DATA.keys())[0] if DATA else None,
-                    clearable=False
-                ), width=3, className="me-4"),
-                dbc.Col(html.Label("Select Bus:", className="mt-2"), width="auto"),
-                dbc.Col(dcc.Dropdown(
-                    id='bus-selector',
-                    options=[{'label': 'Bus 1', 'value': 'Bus 1'}, {'label': 'Bus 2', 'value': 'Bus 2'}],
-                    value='Bus 1',
-                    clearable=False
-                ), width=2),
-            ], className="mb-3 mt-3", align="end"),
-            dbc.Tabs([
-                dbc.Tab(label="Frequency", tab_id="freq"),
-                dbc.Tab(label="ID Viewer", tab_id="id_viewer"),
-                dbc.Tab(label="Correlation", tab_id="corr"),
-                dbc.Tab(label="Entropy", tab_id="entropy"),
-            ], id="tabs", active_tab="freq"),
-            html.Div(id="tab-content", className="mt-3")
-        ])
-    ], id="main-tabs", active_tab="statistics")
-], fluid=True)
 
-def get_prepared_logs(vehicle, bus):
+def _vehicle_dropdown(dropdown_id: str) -> dcc.Dropdown:
+    return dcc.Dropdown(
+        id=dropdown_id,
+        options=[{"label": v, "value": v} for v in DATA.keys()],
+        value=list(DATA.keys())[0] if DATA else None,
+        clearable=False,
+    )
+
+
+def _bus_dropdown(dropdown_id: str) -> dcc.Dropdown:
+    return dcc.Dropdown(
+        id=dropdown_id,
+        options=BUS_OPTIONS,
+        value="Bus 1",
+        clearable=False,
+    )
+
+
+def _label(text: str) -> html.Label:
+    return html.Label(text, className="mt-2")
+
+
+app.layout = dbc.Container(
+    [
+        html.H1("CANveyor", className="my-4"),
+        dbc.Tabs(
+            [
+                dbc.Tab(
+                    label="Overview",
+                    tab_id="overview",
+                    children=[html.Div(id="overview-content")],
+                ),
+                dbc.Tab(
+                    label="Vehicles",
+                    tab_id="vehicles",
+                    children=[
+                        dbc.Row(
+                            [
+                                dbc.Col(_label("Vehicle:"), width="auto"),
+                                dbc.Col(
+                                    _vehicle_dropdown("vehicles-vehicle-selector"),
+                                    width=3, className="me-4",
+                                ),
+                            ],
+                            className="mb-3 mt-3", align="end",
+                        ),
+                        html.Div(id="vehicles-content", className="mt-3"),
+                    ],
+                ),
+                dbc.Tab(
+                    label="Logs",
+                    tab_id="logs",
+                    children=[
+                        dbc.Row(
+                            [
+                                dbc.Col(_label("Vehicle:"), width="auto"),
+                                dbc.Col(
+                                    _vehicle_dropdown("logs-vehicle-selector"),
+                                    width=3, className="me-4",
+                                ),
+                                dbc.Col(_label("Bus:"), width="auto"),
+                                dbc.Col(
+                                    _bus_dropdown("logs-bus-selector"),
+                                    width=2,
+                                ),
+                            ],
+                            className="mb-3 mt-3", align="end",
+                        ),
+                        get_logs_table_component(),
+                    ],
+                ),
+                dbc.Tab(
+                    label="Statistics",
+                    tab_id="statistics",
+                    children=[
+                        dbc.Row(
+                            [
+                                dbc.Col(_label("Vehicle:"), width="auto"),
+                                dbc.Col(
+                                    _vehicle_dropdown("vehicle-selector"),
+                                    width=3, className="me-4",
+                                ),
+                                dbc.Col(_label("Bus:"), width="auto"),
+                                dbc.Col(
+                                    _bus_dropdown("bus-selector"),
+                                    width=2,
+                                ),
+                            ],
+                            className="mb-3 mt-3", align="end",
+                        ),
+                        dbc.Tabs(
+                            [
+                                dbc.Tab(label="Frequency", tab_id="freq"),
+                                dbc.Tab(label="ID Viewer", tab_id="id_viewer"),
+                                dbc.Tab(label="Correlation", tab_id="corr"),
+                                dbc.Tab(label="Entropy", tab_id="entropy"),
+                            ],
+                            id="tabs",
+                            active_tab="freq",
+                        ),
+                        html.Div(id="tab-content", className="mt-3"),
+                    ],
+                ),
+            ],
+            id="main-tabs",
+            active_tab="statistics",
+        ),
+    ],
+    fluid=True,
+)
+
+
+def get_prepared_logs(vehicle: str, bus: str) -> pd.DataFrame:
+    """Lazily prepare and cache log table data for a vehicle/bus pair."""
     cache_key = (vehicle, bus)
     if cache_key not in PREPARED_LOGS_CACHE:
-        df = DATA[vehicle][bus]
-        PREPARED_LOGS_CACHE[cache_key] = prepare_logs_data(df)
+        PREPARED_LOGS_CACHE[cache_key] = prepare_logs_data(DATA[vehicle][bus])
     return PREPARED_LOGS_CACHE[cache_key]
 
-def build_page_buttons(current_page: int, total_pages: int, max_buttons: int = 15) -> list:
-    buttons: list = []
+
+def build_page_buttons(
+    current_page: int, total_pages: int, max_buttons: int = 15
+) -> List:
+    """Build the pagination button list with ellipses where appropriate."""
+    buttons: List = []
     if total_pages <= 1:
         return buttons
 
@@ -198,17 +313,21 @@ def build_page_buttons(current_page: int, total_pages: int, max_buttons: int = 1
 
     if start > 0:
         buttons.append(
-            dbc.Button("1", id={'type': 'page-btn', 'index': 0}, color="secondary", outline=True, size="sm", className="me-1")
+            dbc.Button(
+                "1",
+                id={"type": "page-btn", "index": 0},
+                color="secondary", outline=True, size="sm", className="me-1",
+            )
         )
         if start > 1:
             buttons.append(html.Span("…", className="mx-1 align-middle"))
 
     for i in range(start, end):
-        is_current = (i == current_page)
+        is_current = i == current_page
         buttons.append(
             dbc.Button(
                 str(i + 1),
-                id={'type': 'page-btn', 'index': i},
+                id={"type": "page-btn", "index": i},
                 size="sm",
                 color="primary" if is_current else "secondary",
                 outline=not is_current,
@@ -223,33 +342,33 @@ def build_page_buttons(current_page: int, total_pages: int, max_buttons: int = 1
         buttons.append(
             dbc.Button(
                 str(total_pages),
-                id={'type': 'page-btn', 'index': total_pages - 1},
+                id={"type": "page-btn", "index": total_pages - 1},
                 color="secondary", outline=True, size="sm", className="me-1",
             )
         )
 
     return buttons
 
+
 @app.callback(
-    Output('logs-table', 'data'),
-    Output('logs-table', 'columns'),
-    Output('logs-info-text', 'children'),
-    Output('logs-page-nav', 'children'),
-    Output('logs-current-page', 'data'),
-    Input('logs-vehicle-selector', 'value'),
-    Input('logs-bus-selector', 'value'),
-    Input('logs-prev-btn', 'n_clicks'),
-    Input('logs-next-btn', 'n_clicks'),
-    Input({'type': 'page-btn', 'index': dash.ALL}, 'n_clicks'),
-    State('logs-current-page', 'data'),
+    Output("logs-table", "data"),
+    Output("logs-table", "columns"),
+    Output("logs-info-text", "children"),
+    Output("logs-page-nav", "children"),
+    Output("logs-current-page", "data"),
+    Input("logs-vehicle-selector", "value"),
+    Input("logs-bus-selector", "value"),
+    Input("logs-prev-btn", "n_clicks"),
+    Input("logs-next-btn", "n_clicks"),
+    Input({"type": "page-btn", "index": dash.ALL}, "n_clicks"),
+    State("logs-current-page", "data"),
 )
 def update_logs_table(vehicle, bus, prev_clicks, next_clicks, page_btn_clicks, current_page):
-    if (not vehicle or not bus or vehicle not in DATA or bus not in DATA[vehicle]):
+    if not vehicle or not bus or vehicle not in DATA or bus not in DATA[vehicle]:
         return [], [], "No data available", [], 0
 
     prepared_df = get_prepared_logs(vehicle, bus)
     total_rows = len(prepared_df)
-
     if total_rows == 0:
         return [], [], "No data available", [], 0
 
@@ -257,43 +376,37 @@ def update_logs_table(vehicle, bus, prev_clicks, next_clicks, page_btn_clicks, c
 
     ctx = dash.callback_context
     triggered_id = ctx.triggered_id
-
     current_page = current_page if current_page is not None else 0
 
-    if triggered_id in ('logs-vehicle-selector', 'logs-bus-selector'):
+    if triggered_id in ("logs-vehicle-selector", "logs-bus-selector"):
         current_page = 0
-
-    elif triggered_id == 'logs-prev-btn':
+    elif triggered_id == "logs-prev-btn":
         current_page = max(0, current_page - 1)
-
-    elif triggered_id == 'logs-next-btn':
+    elif triggered_id == "logs-next-btn":
         current_page = current_page + 1
-
-    elif isinstance(triggered_id, dict) and triggered_id.get('type') == 'page-btn':
-        if ctx.triggered and ctx.triggered[0]['value']:
-            current_page = triggered_id['index']
+    elif isinstance(triggered_id, dict) and triggered_id.get("type") == "page-btn":
+        if ctx.triggered and ctx.triggered[0]["value"]:
+            current_page = triggered_id["index"]
 
     current_page = max(0, min(current_page, total_pages - 1))
 
     start_idx = current_page * PAGE_SIZE
     end_idx = min(start_idx + PAGE_SIZE, total_rows)
-    page_data = prepared_df.iloc[start_idx:end_idx].to_dict('records')
-
-    columns = [{"name": i, "id": i} for i in prepared_df.columns]
-
-    info_text = (f"Page {current_page + 1} of {total_pages} | "
-                 f"Showing rows {start_idx + 1:,}–{end_idx:,} "
-                 f"of {total_rows:,} total frames")
-
+    page_data = prepared_df.iloc[start_idx:end_idx].to_dict("records")
+    columns = [{"name": c, "id": c} for c in prepared_df.columns]
+    info_text = (
+        f"Page {current_page + 1} of {total_pages} | "
+        f"Showing rows {start_idx + 1:,}–{end_idx:,} "
+        f"of {total_rows:,} total frames"
+    )
     page_buttons = build_page_buttons(current_page, total_pages)
-
     return page_data, columns, info_text, page_buttons, current_page
 
 @app.callback(
-    Output('tab-content', 'children'),
-    Input('tabs', 'active_tab'),
-    Input('vehicle-selector', 'value'),
-    Input('bus-selector', 'value')
+    Output("tab-content", "children"),
+    Input("tabs", "active_tab"),
+    Input("vehicle-selector", "value"),
+    Input("bus-selector", "value"),
 )
 def render_content(tab, vehicle, bus):
     if not vehicle or not bus or vehicle not in DATA or bus not in DATA[vehicle]:
@@ -301,59 +414,82 @@ def render_content(tab, vehicle, bus):
 
     df = DATA[vehicle][bus]
 
-    if tab == 'freq':
-        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_freq"], style={'height': '80vh'})
+    if tab == "freq":
+        return dcc.Graph(
+            figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_freq"],
+            style={"height": "80vh"},
+        )
 
-    elif tab == 'id_viewer':
+    if tab == "id_viewer":
         ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
-        return html.Div([
-            html.Label("Select CAN ID:"),
-            dcc.Dropdown(
-                id='id-selector',
-                options=[{'label': i, 'value': i} for i in ids],
-                value=ids[0] if ids else None,
-                clearable=False,
-                style={'width': '50%', 'marginBottom': '10px'}
-            ),
-            dcc.Graph(id='id-viewer-graph', style={'height': '70vh'})
-        ])
+        return html.Div(
+            [
+                html.Label("CAN ID:"),
+                dcc.Dropdown(
+                    id="id-selector",
+                    options=[{"label": i, "value": i} for i in ids],
+                    value=ids[0] if ids else None,
+                    clearable=False,
+                    style={"width": "50%", "marginBottom": "10px"},
+                ),
+                dcc.Graph(id="id-viewer-graph", style={"height": "70vh"}),
+            ]
+        )
 
-    elif tab == 'corr':
+    if tab == "corr":
         ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
-        return html.Div([
-            dbc.Row([
-                dbc.Col(html.Label("Method:"), width=1, className="mt-2"),
-                dbc.Col(dcc.Dropdown(
-                    id='corr-method',
-                    options=[{'label': 'Pearson', 'value': 'pearson'}, {'label': 'Spearman', 'value': 'spearman'}],
-                    value='pearson',
-                    clearable=False
-                ), width=2),
-                dbc.Col(html.Label("Target ID:"), width=1, className="mt-2"),
-                dbc.Col(dcc.Dropdown(
-                    id='corr-target',
-                    options=[{'label': 'All IDs (Max Corr)', 'value': 'all'}] + [{'label': i, 'value': i} for i in ids],
-                    value='all',
-                    clearable=True
-                ), width=4),
-            ], className="mb-3"),
-            dcc.Graph(id='corr-graph', style={'height': '80vh'})
-        ])
+        return html.Div(
+            [
+                dbc.Row(
+                    [
+                        dbc.Col(html.Label("Method:"), width=1, className="mt-2"),
+                        dbc.Col(
+                            dcc.Dropdown(
+                                id="corr-method",
+                                options=[
+                                    {"label": "Pearson", "value": "pearson"},
+                                    {"label": "Spearman", "value": "spearman"},
+                                ],
+                                value="pearson",
+                                clearable=False,
+                            ),
+                            width=2,
+                        ),
+                        dbc.Col(html.Label("Target ID:"), width=1, className="mt-2"),
+                        dbc.Col(
+                            dcc.Dropdown(
+                                id="corr-target",
+                                options=[{"label": "All IDs (Max Corr)", "value": "all"}]
+                                + [{"label": i, "value": i} for i in ids],
+                                value="all",
+                                clearable=True,
+                            ),
+                            width=4,
+                        ),
+                    ],
+                    className="mb-3",
+                ),
+                dcc.Graph(id="corr-graph", style={"height": "80vh"}),
+            ]
+        )
 
-    elif tab == 'entropy':
-        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_entropy"], style={'height': '80vh'})
+    if tab == "entropy":
+        return dcc.Graph(
+            figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_entropy"],
+            style={"height": "80vh"},
+        )
 
     return html.Div("Tab not found")
 
 @app.callback(
-    Output('id-viewer-graph', 'figure'),
-    Input('id-selector', 'value'),
-    Input('vehicle-selector', 'value'),
-    Input('bus-selector', 'value'),
-    Input('tabs', 'active_tab'),
+    Output("id-viewer-graph", "figure"),
+    Input("id-selector", "value"),
+    Input("vehicle-selector", "value"),
+    Input("bus-selector", "value"),
+    Input("tabs", "active_tab"),
 )
 def update_id_viewer(selected_id, vehicle, bus, tab):
-    if tab != 'id_viewer' or not selected_id or not vehicle or not bus:
+    if tab != "id_viewer" or not selected_id or not vehicle or not bus:
         return dash.no_update
 
     grouped_data = DATA_BY_ID.get((vehicle, bus), {})
@@ -361,35 +497,101 @@ def update_id_viewer(selected_id, vehicle, bus, tab):
         return dash.no_update
 
     filtered_df, byte_cols = grouped_data[selected_id]
-    return plot_bits(filtered_df, byte_cols, selected_id, title=f"{vehicle} {bus} Byte Visualization")
+    return plot_bits(
+        filtered_df, byte_cols, selected_id,
+        title=f"{vehicle} {bus} Byte Visualization",
+    )
 
 @app.callback(
-    Output('corr-graph', 'figure'),
-    Input('corr-method', 'value'),
-    Input('corr-target', 'value'),
-    Input('vehicle-selector', 'value'),
-    Input('bus-selector', 'value'),
-    Input('tabs', 'active_tab'),
+    Output("corr-graph", "figure"),
+    Input("corr-method", "value"),
+    Input("corr-target", "value"),
+    Input("vehicle-selector", "value"),
+    Input("bus-selector", "value"),
+    Input("tabs", "active_tab"),
 )
 def update_corr(method, target, vehicle, bus, tab):
-    if tab != 'corr' or not vehicle or not bus:
+    if tab != "corr" or not vehicle or not bus:
         return dash.no_update
 
-    target_id = None if target == 'all' or not target else target
+    target_id = None if target == "all" or not target else target
     cache_key = (vehicle, bus, method, target_id)
 
     if cache_key not in CORR_CACHE:
         df = DATA[vehicle][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]
+        CORR_CACHE[cache_key] = calculate_correlation(
+            df, method=method, target_id=target_id
+        )
+    corr_df = CORR_CACHE[cache_key]
 
     title = f"{vehicle} {bus} Correlation"
     if target_id:
         title += f" ({target_id})"
-
     return plot_correlation_heatmap(corr_df, target_id=target_id, title=title)
 
-if __name__ == '__main__':
+@app.callback(
+    Output("vehicles-content", "children"),
+    Input("vehicles-vehicle-selector", "value"),
+)
+def render_vehicles(vehicle):
+    if not vehicle or vehicle not in DATA:
+        return html.Div("No data available", className="text-muted")
+
+    brand = VEHICLE_META.get(vehicle, {}).get("brand", "")
+    vehicle_module = get_vehicle_module(brand)
+
+    dfs = list(DATA[vehicle].values())
+    if not dfs:
+        return html.Div("No data available", className="text-muted")
+
+    df = pd.concat(dfs, ignore_index=True)
+    if "Timestamp" in df.columns:
+        df = df.sort_values("Timestamp", kind="stable").reset_index(drop=True)
+
+    cards = []
+    for nid, frame_def in vehicle_module.DECODER_RULES.items():
+        decoded = vehicle_module.decode_dataframe(df, frame_def.can_id)
+        for item in frame_def.signals:
+            if hasattr(item, "plot_func") and callable(item.plot_func):
+                title = f"{frame_def.can_id} - {item.name}"
+                fig = item.plot_func(decoded, frame_def.color)
+            else:
+                sig = item
+                if getattr(sig, "skip_plot", False):
+                    continue
+                unit_str = f" ({sig.unit})" if sig.unit else ""
+                title = f"{sig.name}{unit_str}"
+                fig = vehicle_module.plot_signal(
+                    decoded, sig.name, title=title, color=frame_def.color
+                )
+
+            cards.append(
+                dbc.Col(
+                    dbc.Card(
+                        [
+                            dbc.CardBody(
+                                [
+                                    dcc.Graph(
+                                        figure=fig,
+                                        config={"displayModeBar": False},
+                                        style={"height": "280px"},
+                                    )
+                                ],
+                                className="p-2",
+                            ),
+                        ],
+                        className="shadow-sm border-0 h-100",
+                    ),
+                    xs=12, sm=6, md=4, lg=3, className="mb-3",
+                )
+            )
+
+    if not cards:
+        return html.Div(
+            "No decoded signals available. Add rules in the vehicle module.",
+            className="text-muted",
+        )
+    return dbc.Row(cards)
+
+if __name__ == "__main__":
     app.run(debug=False)

stats/correlation.py

@@ -1,25 +1,23 @@
-# File: correlation.py
+# File: stats/correlation.py
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
+"""CAN bus inter-byte correlation analyzer and plotter."""
+
 import argparse
 from pathlib import Path
 from concurrent.futures import ThreadPoolExecutor
+from typing import List
 
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from stats.utils.extractor import load_data
-from stats.utils.extractor import to_int
+from stats.utils.converter import format_can_id_vec as _format_can_id_vec, to_int
+from stats.utils.loader import load_data
 
-def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    s = s.astype('string').str.strip()
-    s = s.str.replace(r'^0x', '', case=False, regex=True)
-    s = s.str.upper()
-    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
 
-def _ensure_int_bytes(df: pd.DataFrame, cols: list) -> pd.DataFrame:
+def _ensure_int_bytes(df: pd.DataFrame, cols: List[str]) -> pd.DataFrame:
     needs = [c for c in cols if not pd.api.types.is_numeric_dtype(df[c])]
     if needs:
         df = df.copy()
@@ -27,6 +25,7 @@ def _ensure_int_bytes(df: pd.DataFrame, cols: list) -> pd.DataFrame:
             df[c] = df[c].apply(to_int)
     return df
 
+
 def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None = None) -> pd.DataFrame:
     available_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
 
@@ -70,7 +69,7 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
     else:
         groups = []
 
-    def _process_group(sub):
+    def _process_group(sub: np.ndarray) -> np.ndarray:
         mask = ~np.isnan(sub).any(axis=1)
         sub = sub[mask]
         if len(sub) > 1:

stats/entropy.py

@@ -1,23 +1,21 @@
-# File: entropy.py
+# File: stats/entropy.py
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
+"""CAN bus byte-level entropy analyzer and plotter."""
+
 import argparse
 from pathlib import Path
 from concurrent.futures import ThreadPoolExecutor
+from typing import List
 
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from stats.utils.extractor import load_data
-from stats.utils.extractor import to_int
+from stats.utils.converter import format_can_id_vec as _format_can_id_vec, to_int
+from stats.utils.loader import load_data
 
-def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    s = s.astype('string').str.strip()
-    s = s.str.replace(r'^0x', '', case=False, regex=True)
-    s = s.str.upper()
-    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
 
 def _entropy_col(a: np.ndarray) -> float:
     a = a[~np.isnan(a)]
@@ -36,6 +34,7 @@ def _entropy_col(a: np.ndarray) -> float:
     p = counts / counts.sum()
     return float(-np.sum(p * np.log2(p)))
 
+
 def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     available_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
     if not available_cols:
@@ -64,7 +63,7 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     else:
         groups = []
 
-    def _process_group(sub):
+    def _process_group(sub: np.ndarray) -> np.ndarray:
         res = np.zeros(n_cols, dtype=np.float64)
         for ci in range(n_cols):
             res[ci] = _entropy_col(sub[:, ci])

stats/frequency.py

@@ -1,19 +1,19 @@
-# File: frequency.py
+# File: stats/frequency.py
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
+"""CAN bus message frequency analyzer and plotter."""
+
 import argparse
 from pathlib import Path
+
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from stats.utils.extractor import load_data
 
-def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    s = s.astype('string').str.strip()
-    s = s.str.replace(r'^0x', '', case=False, regex=True)
-    s = s.str.upper()
-    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
+from stats.utils.converter import format_can_id_vec as _format_can_id_vec
+from stats.utils.loader import load_data
+
 
 def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
     can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
@@ -28,6 +28,7 @@ def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
     freq_df['Percentage'] = np.round(freq_df['Count'] / total * 100, 2) if total else 0.0
     return freq_df.sort_values('Count', ascending=True).reset_index(drop=True)
 
+
 def plot_frequency(stats_df: pd.DataFrame, title: str) -> go.Figure:
     n = len(stats_df)
     fig = go.Figure(go.Bar(
@@ -106,6 +107,7 @@ def plot_frequency(stats_df: pd.DataFrame, title: str) -> go.Figure:
     )
     return fig
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Analyze CAN bus message frequency")
     parser.add_argument("input", type=Path, help="Path to the input CAN log file")

stats/id_viewer.py

@@ -1,25 +1,30 @@
-# File: id_viewer.py
+# File: stats/id_viewer.py
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
+"""Interactive CAN bus byte-change visualizer."""
+
 import argparse
 from pathlib import Path
+from typing import List, Tuple
+
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 from plotly_resampler import FigureResampler
-from stats.utils.extractor import load_data
 
-def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    s = s.astype('string').str.strip()
-    s = s.str.replace(r'^0x', '', case=False, regex=True)
-    s = s.str.upper()
-    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
+from stats.utils.converter import format_can_id_vec as _format_can_id_vec
+from stats.utils.loader import load_data
 
-def prepare_data(df, target_id):
+_BYTE_COLORS = [
+    '#e41a1c', '#377eb8', '#4daf4a', '#984ea3',
+    '#ff7f00', '#ffff33', '#a65628', '#f781bf',
+]
+
+
+def prepare_data(df: pd.DataFrame, target_id: str) -> Tuple[pd.DataFrame, List[str]]:
     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.assign(Formatted_ID=_format_can_id_vec(df[can_id_col]))
     target_id_clean = _format_can_id_vec(pd.Series([target_id])).iloc[0]
     filtered = df[df['Formatted_ID'] == target_id_clean]
 
@@ -29,7 +34,9 @@ def prepare_data(df, target_id):
 
     for col in byte_cols:
         if not pd.api.types.is_numeric_dtype(filtered[col]):
-            filtered = filtered.assign(**{col: pd.to_numeric(filtered[col], errors='coerce').astype('float32')})
+            filtered = filtered.assign(
+                **{col: pd.to_numeric(filtered[col], errors='coerce').astype('float32')}
+            )
 
     filtered = filtered.sort_values('Timestamp', kind='stable')
     arr = filtered[byte_cols].to_numpy(dtype=np.float32, copy=False)
@@ -40,12 +47,12 @@ def prepare_data(df, target_id):
 
     return filtered, byte_cols
 
-def plot_bits(df, byte_cols, can_id, title):
+
+def plot_bits(df: pd.DataFrame, byte_cols: List[str], can_id: str, title: str) -> FigureResampler:
     fig = FigureResampler(
         resampled_trace_prefix_suffix=("", ""),
         show_mean_aggregation_size=False
     )
-    colors = ['#e41a1c', '#377eb8', '#4daf4a', '#984ea3', '#ff7f00', '#ffff33', '#a65628', '#f781bf']
     n = len(byte_cols)
 
     x = df['Timestamp'].to_numpy() if not df.empty else np.array([])
@@ -54,7 +61,7 @@ def plot_bits(df, byte_cols, can_id, title):
 
         fig.add_trace(go.Scatter(
             mode='lines',
-            line=dict(shape='hv', width=2, color=colors[i % len(colors)]),
+            line=dict(shape='hv', width=2, color=_BYTE_COLORS[i % len(_BYTE_COLORS)]),
             name=col.upper(),
             legendgroup=col.upper(),
             hovertemplate=f"<b>{col.upper()}</b><br>Time: %{{x}}<br>Value: %{{y}}<extra></extra>",
@@ -121,6 +128,7 @@ def plot_bits(df, byte_cols, can_id, title):
     )
     return fig
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Visualize CAN bus byte changes over time")
     parser.add_argument("input", type=Path, help="Path to the input CAN log file")

stats/utils/extractor.py

@@ -1,63 +0,0 @@
-# File: extractor.py
-# Copyright (C) 2026 Erick Ahmed
-# SPDX-License-Identifier: AGPL-3.0-or-later
-
-import json
-from pathlib import Path
-
-import numpy as np
-import pandas as pd
-import polars as pl
-
-def to_int(x):
-    if isinstance(x, (int, np.integer)):
-        return int(x)
-    if isinstance(x, str):
-        try:
-            return int(x, 16)
-        except ValueError:
-            return np.nan
-    return np.nan
-
-def extract_id(row: pd.Series) -> str:
-    meta = row.get('j1939_metadata')
-    if pd.isna(meta):
-        return f"ID: {row['ID']}"
-    if isinstance(meta, str):
-        try:
-            meta = json.loads(meta)
-        except json.JSONDecodeError:
-            return f"ID: {row['ID']}"
-    if isinstance(meta, dict) and 'PGN' in meta:
-        return f"PGN: {meta['PGN']}"
-    return f"ID: {row['ID']}"
-
-def load_data(file_path: Path) -> pd.DataFrame:
-    lf = pl.scan_parquet(file_path)
-    schema = lf.collect_schema()
-    names = schema.names()
-
-    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in names]
-    if byte_cols:
-        lf = lf.with_columns([
-            pl.col(c).str.to_integer(base=16, strict=False).cast(pl.Int16).alias(c)
-            for c in byte_cols
-        ])
-
-    id_col = 'ID' if 'ID' in names else 'Identifier'
-    id_expr = pl.col(id_col).cast(pl.Utf8)
-
-    if 'j1939_metadata' in names:
-        try:
-            lf = lf.with_columns(
-                pl.when(pl.col('j1939_metadata').is_not_null())
-                .then(pl.lit('PGN: ') + pl.col('j1939_metadata').struct.field('PGN').cast(pl.Utf8))
-                .otherwise(pl.lit('ID: ') + id_expr)
-                .alias('Identifier')
-            )
-        except Exception:
-            lf = lf.with_columns((pl.lit('ID: ') + id_expr).alias('Identifier'))
-    else:
-        lf = lf.with_columns((pl.lit('ID: ') + id_expr).alias('Identifier'))
-
-    return lf.collect().to_pandas()

vehicle/__init__.py

@@ -0,0 +1,19 @@
+# File: vehicle/__init__.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+import importlib
+
+def get_vehicle_module(brand: str):
+    """
+    Dynamically imports the correct decoder module based on the vehicle brand.
+    Falls back to 'vehicle.generic' if a specific brand module is not found.
+    """
+    if not brand:
+        return importlib.import_module("vehicle.generic")
+
+    module_name = f"vehicle.{brand.lower().replace(' ', '_')}"
+    try:
+        return importlib.import_module(module_name)
+    except ModuleNotFoundError:
+        return importlib.import_module("vehicle.generic")

vehicle/base.py

@@ -0,0 +1,186 @@
+# File: vehicle/base.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""Core data structures and helpers for J1939/CAN signal decoding."""
+
+from dataclasses import dataclass, field
+from typing import Dict, List
+
+import numpy as np
+import pandas as pd
+import plotly.graph_objects as go
+
+
+@dataclass
+class SignalDef:
+    """Definition of a single signal within a CAN frame."""
+
+    name: str
+    bit_start: int
+    bit_length: int
+    factor: float = 1.0
+    offset: float = 0.0
+    is_signed: bool = False
+    byte_order: str = "little"
+    unit: str = ""
+
+
+@dataclass
+class FrameDef:
+    """Definition of a CAN frame and its contained signals."""
+
+    can_id: str
+    description: str = ""
+    color: str = "#377eb8"
+    signals: List[SignalDef] = field(default_factory=list)
+
+
+def normalize_id(can_id: str) -> str:
+    """Normalize a CAN ID string to uppercase hex without leading zeros/0x."""
+    s = str(can_id).strip().upper()
+    if s.startswith("0X"):
+        s = s[2:]
+    return s.lstrip("0") or "0"
+
+
+def _byte_indices(sig: SignalDef) -> List[int]:
+    """Return the in-range byte positions spanned by *sig*."""
+    byte_lo = sig.bit_start // 8
+    byte_hi = (sig.bit_start + sig.bit_length - 1) // 8
+    return [i for i in range(byte_lo, byte_hi + 1) if 0 <= i < 8]
+
+
+def _extract_signal(bytes_arr: np.ndarray, sig: SignalDef) -> np.ndarray:
+    """Extract raw signal values from an (N, 8) byte array and apply scaling."""
+    if bytes_arr.size == 0:
+        return np.zeros(0, dtype=np.float64)
+
+    byte_indices = _byte_indices(sig)
+    if not byte_indices:
+        return np.full(bytes_arr.shape[0], np.nan, dtype=np.float64)
+
+    raw = np.zeros(bytes_arr.shape[0], dtype=np.int64)
+    if sig.byte_order == "little":
+        for shift, bi in enumerate(byte_indices):
+            raw += bytes_arr[:, bi].astype(np.int64) << (shift * 8)
+    else:
+        for shift, bi in enumerate(reversed(byte_indices)):
+            raw += bytes_arr[:, bi].astype(np.int64) << (shift * 8)
+
+    raw = raw >> (sig.bit_start % 8)
+    raw = raw & ((1 << sig.bit_length) - 1)
+
+    if sig.is_signed and sig.bit_length < 64:
+        sign_bit = 1 << (sig.bit_length - 1)
+        raw = (raw ^ sign_bit) - sign_bit
+
+    return raw.astype(np.float64) * sig.factor + sig.offset
+
+
+def decode_dataframe(
+    df: pd.DataFrame, can_id: str, decoder_rules: Dict[str, FrameDef]
+) -> pd.DataFrame:
+    """Decode all signals for *can_id* from *df* into a new DataFrame."""
+    norm = normalize_id(can_id)
+    if norm not in decoder_rules:
+        return pd.DataFrame()
+
+    frame_def = decoder_rules[norm]
+
+    id_col = "ID" if "ID" in df.columns else "Identifier"
+    df_ids = df[id_col].astype(str).map(normalize_id)
+    sub = df.loc[df_ids == norm].copy()
+    if sub.empty:
+        return pd.DataFrame()
+
+    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in sub.columns]
+    if not byte_cols:
+        return pd.DataFrame()
+
+    arr = np.zeros((len(sub), 8), dtype=np.int64)
+    for i, c in enumerate(byte_cols):
+        arr[:, i] = (
+            pd.to_numeric(sub[c], errors="coerce")
+            .fillna(0)
+            .astype(np.int64)
+            .to_numpy()
+        )
+
+    out = pd.DataFrame()
+    out["Timestamp"] = (
+        sub["Timestamp"].to_numpy()
+        if "Timestamp" in sub.columns
+        else np.arange(len(sub))
+    )
+
+    for sig in frame_def.signals:
+        out[sig.name] = _extract_signal(arr, sig)
+
+    return out
+
+
+def plot_signal(
+    df: pd.DataFrame,
+    signal_name: str,
+    title: str,
+    color: str = "#377eb8",
+    height: int = 280,
+) -> go.Figure:
+    """Plot a single signal over time as a line chart."""
+    fig = go.Figure()
+
+    if df.empty or signal_name not in df.columns:
+        fig.update_layout(
+            title=dict(text=title, font=dict(size=14)),
+            annotations=[
+                dict(
+                    text="No data", showarrow=False, x=0.5, y=0.5,
+                    font=dict(size=13, color="#888"),
+                )
+            ],
+            height=height,
+            template="plotly_white",
+        )
+        return fig
+
+    fig.add_trace(
+        go.Scatter(
+            x=df["Timestamp"],
+            y=df[signal_name],
+            mode="lines",
+            line=dict(width=2, color=color),
+            name=signal_name,
+            hovertemplate=(
+                f"<b>{signal_name}</b><br>Time: %{{x}}<br>"
+                f"Value: %{{y:.2f}}<extra></extra>"
+            ),
+        )
+    )
+
+    fig.update_layout(
+        title=dict(
+            text=title, font=dict(size=14, color="#1a1a1a"),
+            x=0.5, xanchor="center", pad=dict(b=10),
+        ),
+        height=height,
+        autosize=True,
+        template="plotly_white",
+        margin=dict(l=55, r=20, t=55, b=45),
+        xaxis=dict(
+            title=dict(text="Time", font=dict(size=11)),
+            showgrid=True, gridwidth=0.5, gridcolor="#eee",
+            zeroline=False, linecolor="#bdbdbd",
+        ),
+        yaxis=dict(
+            title=dict(text=signal_name, font=dict(size=11)),
+            showgrid=True, gridwidth=0.5, gridcolor="#eee",
+            zeroline=False, linecolor="#bdbdbd",
+        ),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=11, color="#2a2a2a"),
+        hoverlabel=dict(
+            bgcolor="white", font_size=12,
+            font_family="Segoe UI", bordercolor="#cccccc",
+        ),
+    )
+    return fig

vehicle/komatsu.py

@@ -0,0 +1,180 @@
+# File: vehicle/komatsu.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""Komatsu-specific CAN frame decoder rules and custom plot definitions."""
+
+from copy import deepcopy
+from dataclasses import dataclass
+from typing import Callable, Dict
+
+import pandas as pd
+import plotly.express as px
+
+from vehicle.base import (
+    FrameDef,
+    SignalDef,
+    decode_dataframe as _decode_dataframe,
+    normalize_id,
+    plot_signal,
+)
+
+
+@dataclass
+class CustomPlotDef:
+    """A non-signal entry in a FrameDef that carries its own plotting function."""
+
+    name: str
+    plot_func: Callable
+
+load_state_sig = SignalDef(
+    name="Engine Load State",
+    bit_start=24,
+    bit_length=8,
+    factor=1,
+    offset=0.0,
+    is_signed=False,
+    byte_order="big",
+    unit="",
+)
+load_state_sig.skip_plot = True
+
+DECODER_RULES: Dict[str, FrameDef] = {
+    normalize_id("0x011F"): FrameDef(
+        can_id="0x011F",
+        description="ECM",
+        color="#e41a1c",
+        signals=[
+            SignalDef(
+                name="Engine",
+                bit_start=0,
+                bit_length=16,
+                factor=0.125,
+                offset=0.0,
+                is_signed=False,
+                byte_order="big",
+                unit="RPM",
+            ),
+            SignalDef(
+                name="Engine Load",
+                bit_start=16,
+                bit_length=16,
+                factor=0.05,
+                offset=0,
+                is_signed=False,
+                byte_order="little",
+                unit="%",
+            ),
+        ],
+    ),
+    normalize_id("0x0CFF3300"): FrameDef(
+        can_id="0x0CFF3300",
+        description="Engine temperatures",
+        color="#0080fe",
+        signals=[
+            SignalDef(
+                name="Engine coolant temp",
+                bit_start=8,
+                bit_length=8,
+                factor=1,
+                offset=0.0,
+                is_signed=False,
+                byte_order="big",
+                unit="℃",
+            ),
+            SignalDef(
+                name="Engine oil temp",
+                bit_start=40,
+                bit_length=8,
+                factor=1,
+                offset=0.0,
+                is_signed=False,
+                byte_order="big",
+                unit="℃",
+            ),
+            load_state_sig,
+            CustomPlotDef(
+                name="Engine Load",
+                plot_func=lambda decoded, color: plot_load_state_pie(decoded, color),
+            ),
+        ],
+    ),
+}
+
+LOAD_STATE_MAP = {
+    0: "Boot up",
+    16: "Normal load",
+    32: "High load",
+}
+
+_LOAD_STATE_COLORS = {
+    "Boot up": "#ff9900",
+    "Normal load": "#00cc00",
+    "High load": "#cc0000",
+    "Unknown": "#808080",
+}
+
+
+def plot_load_state_pie(decoded_df, color):
+    """Render a pie chart showing the distribution of engine load states."""
+    if decoded_df is None or decoded_df.empty or "Engine Load State" not in decoded_df.columns:
+        fig = px.pie()
+        fig.update_layout(
+            title=dict(
+                text="Engine Load State",
+                font=dict(size=14, color="#1a1a1a"),
+                x=0.5, xanchor="center", pad=dict(b=10)
+            ),
+            height=280,
+            template="plotly_white",
+            annotations=[dict(text="No data", showarrow=False, x=0.5, y=0.5, font=dict(size=13, color="#888"))]
+        )
+        return fig
+
+    states = pd.to_numeric(decoded_df["Engine Load State"], errors="coerce").dropna().astype(int)
+
+    labels = states.map(LOAD_STATE_MAP).fillna("Unknown")
+    counts = labels.value_counts().reset_index()
+    counts.columns = ["State", "Count"]
+
+    total = counts["Count"].sum()
+    counts["Percentage"] = (counts["Count"] / total * 100).round(1)
+    counts["Legend"] = counts["State"] + " (" + counts["Percentage"].astype(str) + "%)"
+
+    fig = px.pie(
+        counts,
+        values="Count",
+        names="Legend",
+        color="State",
+        color_discrete_map=_LOAD_STATE_COLORS,
+    )
+
+    fig.update_traces(
+        textinfo="none",
+        hoverinfo="label+percent+value",
+        domain={"x": [0.05, 0.55], "y": [0.05, 0.95]},
+    )
+    fig.update_layout(
+        title=dict(
+            text="Engine Load State",
+            font=dict(size=14, color="#1a1a1a"),
+            x=0.5, xanchor="center", pad=dict(b=10)
+        ),
+        height=280,
+        autosize=True,
+        template="plotly_white",
+        margin=dict(l=20, r=20, t=55, b=45),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=11, color="#2a2a2a"),
+        legend=dict(x=0.6, y=0.5),
+    )
+    return fig
+
+def decode_dataframe(df, can_id):
+    """Decode *can_id* from *df*, filtering out non-SignalDef entries first."""
+    filtered_rules: Dict[str, FrameDef] = {}
+    for nid, frame in DECODER_RULES.items():
+        new_frame = deepcopy(frame)
+        new_frame.signals = [s for s in frame.signals if isinstance(s, SignalDef)]
+        filtered_rules[nid] = new_frame
+
+    return _decode_dataframe(df, can_id, filtered_rules)