Minor title changes

Reviewed-on: erickahmed/CANveyor#8

logs/view.py

@@ -0,0 +1,83 @@
+# File: logs/view.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+import pandas as pd
+from dash import html, dash_table, dcc
+import dash_bootstrap_components as dbc
+
+PAGE_SIZE = 25000
+
+def prepare_logs_data(df: pd.DataFrame) -> pd.DataFrame:
+    if df is None or df.empty:
+        return pd.DataFrame()
+
+    df = df.copy()
+
+    if 'j1939_metadata' in df.columns:
+        df['Priority'] = df['j1939_metadata'].apply(lambda x: x.get('Priority') if isinstance(x, dict) else None)
+        df['PF'] = df['j1939_metadata'].apply(lambda x: x.get('PF') if isinstance(x, dict) else None)
+        df['PS'] = df['j1939_metadata'].apply(lambda x: x.get('PS') if isinstance(x, dict) else None)
+        df['SA'] = df['j1939_metadata'].apply(lambda x: x.get('SA') if isinstance(x, dict) else None)
+        df['DA'] = df['j1939_metadata'].apply(lambda x: x.get('DA') if isinstance(x, dict) else None)
+        df['PGN'] = df['j1939_metadata'].apply(lambda x: x.get('PGN') if isinstance(x, dict) else None)
+    else:
+        for col in ['Priority', 'PF', 'PS', 'SA', 'DA', 'PGN']:
+            df[col] = None
+
+    for i in range(8):
+        col = f'b{i}'
+        if col in df.columns:
+            df[col] = df[col].apply(lambda x: f"{int(x):02X}" if pd.notna(x) else "")
+        else:
+            df[col] = ""
+
+    if 'ID' in df.columns:
+        df['ID'] = df['ID'].astype(str)
+
+    display_cols = ['Timestamp', 'ID', 'DLC', 'b0', 'b1', 'b2', 'b3', 'b4', 'b5', 'b6', 'b7', 'Priority', 'PF', 'PS', 'SA', 'DA', 'PGN']
+    display_df = df[[c for c in display_cols if c in df.columns]]
+
+    return display_df.fillna("")
+
+def get_logs_table_component():
+    return html.Div([
+        html.Div(id='logs-info-text', className="text-muted mb-2"),
+        dash_table.DataTable(
+            id='logs-table',
+            virtualization=True,
+            page_action='none',
+            style_table={'overflowX': 'auto', 'height': '70vh', 'overflowY': 'auto'},
+            style_header={
+                'backgroundColor': '#1a1a1a',
+                'color': 'white',
+                'fontWeight': 'bold',
+                'textAlign': 'center',
+                'position': 'sticky',
+                'top': 0
+            },
+            style_data={
+                'backgroundColor': '#f8f9fa',
+                'color': '#2a2a2a',
+                'textAlign': 'center'
+            },
+            style_data_conditional=[
+                {
+                    'if': {'row_index': 'odd'},
+                    'backgroundColor': 'rgb(240, 240, 240)'
+                }
+            ],
+            style_cell={
+                'minWidth': '80px',
+                'padding': '5px',
+                'textAlign': 'center',
+                'fontFamily': 'Segoe UI, Arial, sans-serif'
+            }
+        ),
+        html.Div([
+            dbc.Button("Prev", id='logs-prev-btn', color="secondary", outline=True, size="sm", className="me-2"),
+            html.Div(id='logs-page-nav', className="d-inline-block", style={'verticalAlign': 'middle'}),
+            dbc.Button("Next", id='logs-next-btn', color="secondary", outline=True, size="sm", className="ms-2"),
+        ], className="d-flex justify-content-center align-items-center mt-3"),
+        dcc.Store(id='logs-current-page', data=0),
+    ])

main.py

@@ -1,3 +1,597 @@
 # File: main.py
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""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 dash
+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 decoder import decode_j1939_frames
+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 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"
+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"},
+]
+
+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)
+    else:
+        brand, model_part = stem, "Unknown"
+    model = model_part.replace("_", " ")
+    vehicle = f"{brand} {model}".strip()
+    return vehicle, brand, model
+
+
+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}
+
+        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"]),
+            }
+
+
+def _can_id_column(df: pd.DataFrame) -> str:
+    return "ID" if "ID" in df.columns else "Identifier"
+
+
+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]
+
+
+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"
+        ),
+    }
+
+    df = df.assign(Formatted_ID=_format_can_id_vec(df[_can_id_column(df)]))
+    df = df.sort_values(["Formatted_ID", "Timestamp"], kind="stable")
+
+    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
+
+
+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
+
+
+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:
+        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:
+    """Build the pagination button list with ellipses where appropriate."""
+    buttons: List = []
+    if total_pages <= 1:
+        return buttons
+
+    half = max_buttons // 2
+    start = max(0, current_page - half)
+    end = min(total_pages, start + max_buttons)
+    if end - start < max_buttons:
+        start = max(0, end - max_buttons)
+
+    if start > 0:
+        buttons.append(
+            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
+        buttons.append(
+            dbc.Button(
+                str(i + 1),
+                id={"type": "page-btn", "index": i},
+                size="sm",
+                color="primary" if is_current else "secondary",
+                outline=not is_current,
+                className="me-1",
+                disabled=is_current,
+            )
+        )
+
+    if end < total_pages:
+        if end < total_pages - 1:
+            buttons.append(html.Span("…", className="mx-1 align-middle"))
+        buttons.append(
+            dbc.Button(
+                str(total_pages),
+                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"),
+)
+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]:
+        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
+
+    total_pages = max(1, (total_rows + PAGE_SIZE - 1) // PAGE_SIZE)
+
+    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"):
+        current_page = 0
+    elif triggered_id == "logs-prev-btn":
+        current_page = max(0, current_page - 1)
+    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"]
+
+    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": 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"),
+)
+def render_content(tab, vehicle, bus):
+    if not vehicle or not bus or vehicle not in DATA or bus not in DATA[vehicle]:
+        return html.Div("No data available")
+
+    df = DATA[vehicle][bus]
+
+    if tab == "freq":
+        return dcc.Graph(
+            figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_freq"],
+            style={"height": "80vh"},
+        )
+
+    if tab == "id_viewer":
+        ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
+        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"}),
+            ]
+        )
+
+    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"}),
+            ]
+        )
+
+    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"),
+)
+def update_id_viewer(selected_id, vehicle, bus, tab):
+    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), {})
+    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"{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"),
+)
+def update_corr(method, target, vehicle, bus, tab):
+    if tab != "corr" or not vehicle or not bus:
+        return dash.no_update
+
+    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_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)
+
+@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)

parser.py

@@ -19,7 +19,7 @@ def parse_log(input_path: PathLike, out_bus1: PathLike, out_bus2: PathLike) -> N
     out1_file = Path(out_bus1)
     out2_file = Path(out_bus2)
 
-    start_pattern = re.compile(r'(C[12]):([0-9A-Fa-f]{1,8})\s+([0-9A-Fa-f]{1,2})\s+')
+    start_pattern = re.compile(r'(C[12]):([0-9A-Fa-f]{7,8})\s+([0-9A-Fa-f]{1,2})\s+')
     byte_pattern = re.compile(r'^[0-9A-Fa-f]{2}$')
 
     with input_file.open('r', encoding='utf-8') as f_in, \
@@ -35,7 +35,12 @@ def parse_log(input_path: PathLike, out_bus1: PathLike, out_bus2: PathLike) -> N
         for line in f_in:
             for match in start_pattern.finditer(line):
                 bus = match.group(1)
-                can_id = match.group(2).upper()
+
+                can_id = match.group(2).upper().zfill(8)
+
+                if int(can_id, 16) > 0x1FFFFFFF:
+                    continue
+
                 dlc_str = match.group(3)
 
                 try:
@@ -72,7 +77,7 @@ def parse_csv(csv_path: PathLike) -> pl.LazyFrame:
     """
     lf = pl.scan_csv(csv_path, schema_overrides={"ID": pl.String, "Data": pl.String})
 
-    if "Timestamp" not in lf.columns:
+    if "Timestamp" not in lf.collect_schema().names():
         lf = lf.with_row_index("Timestamp")
 
     byte_exprs = []
@@ -116,4 +121,3 @@ if __name__ == '__main__':
         print(f"[*] Processing {args.input_csv}...")
         lf = parse_csv(args.input_csv)
         lf.sink_parquet(args.output_parquet)
-        print(f"[+] Saved parquet file to {args.output_parquet}")

pyproject.toml

@@ -1,7 +1,15 @@
 [project]
 name = "CANveyor"
-version = "0.0.1"
+version = "0.1.0"
 description = "J1939 CAN bus parser that works in pair with CANdigger"
 readme = "README.md"
-requires-python = ">=3.14"
+requires-python = ">=3.10"
-dependencies = ["polars", "pathlib", "typing"]
+dependencies = [
+    "polars",
+    "dash",
+    "dash-bootstrap-components",
+    "numpy",
+    "pandas",
+    "plotly",
+    "plotly-resampler"
+]

stat/utils/extractor.py

@@ -1,27 +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 pandas as pd
-
-def extract_id(row: pd.Series) -> str:
-    """Extracts PGN from metadata or falls back to CAN ID."""
-    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:
-    """Loads Parquet file and adds an Identifier column."""
-    df = pd.read_parquet(file_path)
-    df['Identifier'] = df.apply(extract_id, axis=1)
-    return df

stats/correlation.py

@@ -0,0 +1,177 @@
+# 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.converter import format_can_id_vec as _format_can_id_vec, to_int
+from stats.utils.loader import load_data
+
+
+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()
+        for c in needs:
+            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]
+
+    if not available_cols:
+        raise ValueError("No byte columns (b0-b7) found in the DataFrame")
+
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    identifiers = _format_can_id_vec(df[can_id_col]).to_numpy()
+
+    df_bytes = _ensure_int_bytes(df, available_cols)[available_cols]
+    data = df_bytes.to_numpy(dtype=np.float64, copy=False)
+
+    if target_id is not None:
+        target_id = _format_can_id_vec(pd.Series([target_id])).iloc[0]
+        mask = identifiers == target_id
+        if not mask.any():
+            raise ValueError(f"Identifier '{target_id}' not found in data")
+        sub = data[mask]
+        mask = ~np.isnan(sub).any(axis=1)
+        sub = sub[mask]
+        if method == 'spearman' and sub.shape[0] > 1:
+            sub = pd.DataFrame(sub).rank().to_numpy()
+        if sub.shape[0] > 1:
+            with np.errstate(divide='ignore', invalid='ignore'):
+                c = np.corrcoef(sub, rowvar=False)
+            np.nan_to_num(c, copy=False, nan=0.0)
+        else:
+            c = np.zeros((len(available_cols), len(available_cols)))
+        return pd.DataFrame(c, index=available_cols, columns=available_cols)
+
+    unique_ids, inverse = np.unique(identifiers, return_inverse=True)
+    n_cols = len(available_cols)
+
+    sort_idx = np.argsort(inverse, kind='stable')
+    data_sorted = data[sort_idx]
+    inverse_sorted = inverse[sort_idx]
+
+    if len(inverse_sorted) > 0:
+        split_points = np.flatnonzero(np.diff(inverse_sorted)) + 1
+        groups = np.split(data_sorted, split_points)
+    else:
+        groups = []
+
+    def _process_group(sub: np.ndarray) -> np.ndarray:
+        mask = ~np.isnan(sub).any(axis=1)
+        sub = sub[mask]
+        if len(sub) > 1:
+            if method == 'spearman':
+                sub = pd.DataFrame(sub).rank().to_numpy()
+            with np.errstate(divide='ignore', invalid='ignore'):
+                c = np.abs(np.corrcoef(sub, rowvar=False))
+            np.nan_to_num(c, copy=False, nan=0.0)
+            np.fill_diagonal(c, 0.0)
+            return c.max(axis=0)
+        return np.zeros(n_cols, dtype=np.float64)
+
+    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
+    if len(groups) > 0:
+        with ThreadPoolExecutor() as executor:
+            results = list(executor.map(_process_group, groups))
+            for i, res in enumerate(results):
+                out[i] = res
+
+    result = pd.DataFrame(out, index=unique_ids, columns=available_cols)
+    result.index.name = 'Identifier'
+    return result
+
+
+def plot_correlation_heatmap(corr_df: pd.DataFrame, target_id: str | None, title: str) -> go.Figure:
+    is_8x8 = target_id is not None
+
+    x = corr_df.columns.tolist()
+    y = corr_df.index.tolist()
+    z = corr_df.values
+
+    if is_8x8:
+        z_min, z_max = -1.0, 1.0
+        colorscale = [[0.0, "#2c7bb6"], [0.25, "#abd9e9"], [0.5, "#ffffff"], [0.75, "#fdae61"], [1.0, "#d7191c"]]
+        hover_template = "<b>%{y}</b> vs <b>%{x}</b><br>Correlation: %{z:.2f}<extra></extra>"
+    else:
+        z_min, z_max = 0.0, 1.0
+        colorscale = [[0.0, "#ffffff"], [0.2, "#fff5f0"], [0.4, "#fecc5c"], [0.6, "#fd8d3c"], [0.8, "#e31a1c"], [1.0, "#800026"]]
+        hover_template = "<b>%{y}</b><br>Byte %{x} max correlation: %{z:.2f}<extra></extra>"
+
+    fig = go.Figure(
+        data=go.Heatmap(
+            z=z, x=x, y=y,
+            zmin=z_min, zmax=z_max,
+            colorscale=colorscale,
+            xgap=3, ygap=3,
+            text=np.round(z, 2),
+            texttemplate="%{text}",
+            textfont={"size": 11, "color": "#2a2a2a", "family": "Segoe UI, Arial, sans-serif"},
+            hoverongaps=False,
+            hovertemplate=hover_template,
+            colorbar=dict(
+                title=dict(text="Correlation", side="top", font=dict(size=13, color="#1a1a1a")),
+                orientation="h", thickness=15, len=0.35,
+                x=1.0, xanchor="right", y=1.02, yanchor="bottom",
+                tickfont=dict(size=11, color="#2a2a2a"),
+                tickformat=".1f", outlinewidth=0.5, outlinecolor="#cccccc",
+            ),
+        )
+    )
+
+    fig.update_layout(
+        title=dict(text=title, font=dict(size=20, color="#1a1a1a"), x=0.5, xanchor="center", pad=dict(b=20)),
+        height=600 if is_8x8 else max(600, len(y) * 28 + 150),
+        autosize=True,
+        template="plotly_white",
+        xaxis=dict(
+            title=dict(text="Byte Position", font=dict(size=13, color="#1a1a1a")),
+            side="bottom" if is_8x8 else "top",
+            dtick=1, showgrid=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc",
+        ),
+        yaxis=dict(
+            title=dict(text="Byte Position" if is_8x8 else "PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
+            autorange="reversed", showgrid=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc", automargin=True,
+        ),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=12, color="#2a2a2a"),
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor="#cccccc"),
+        margin=dict(l=200, r=40, t=120, b=60),
+    )
+    return fig
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Analyze CAN bus inter-byte correlation")
+    parser.add_argument("method", choices=["pearson", "spearman"], help="Correlation method to use")
+    parser.add_argument("input", type=Path, help="Path to the input CAN log file")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("correlation_report.html"))
+    parser.add_argument("title", nargs="?", default="CAN Bus Inter-Byte Correlation")
+    parser.add_argument("--identifier", type=str, default=None)
+    args = parser.parse_args()
+
+    df = load_data(args.input)
+    corr_df = calculate_correlation(df, method=args.method, target_id=args.identifier)
+    display_title = f"{args.title} ({args.identifier})" if args.identifier else args.title
+    fig = plot_correlation_heatmap(corr_df, target_id=args.identifier, title=display_title)
+    config = {
+        "responsive": True,
+        "displaylogo": False,
+        "scrollZoom": True,
+        "modeBarButtonsToAdd": ["toggleSpikelines"],
+        "toImageButtonOptions": {"format": "png", "scale": 2},
+    }
+    fig.write_html(str(args.output), include_plotlyjs="cdn", config=config)

stats/entropy.py

@@ -0,0 +1,155 @@
+# 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.converter import format_can_id_vec as _format_can_id_vec, to_int
+from stats.utils.loader import load_data
+
+
+def _entropy_col(a: np.ndarray) -> float:
+    a = a[~np.isnan(a)]
+    if a.size == 0:
+        return 0.0
+    a = a.astype(np.int64)
+    lo, hi = a.min(), a.max()
+    span = hi - lo + 1
+    if span <= 0:
+        return 0.0
+    if span > 1 << 20:
+        _, counts = np.unique(a, return_counts=True)
+    else:
+        counts = np.bincount(a - lo, minlength=span)
+        counts = counts[counts > 0]
+    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:
+        raise ValueError("No byte columns (b0-b7) found in the DataFrame")
+
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    identifiers = _format_can_id_vec(df[can_id_col]).to_numpy()
+
+    needs = [c for c in available_cols if not pd.api.types.is_numeric_dtype(df[c])]
+    if needs:
+        df = df.copy()
+        for c in needs:
+            df[c] = df[c].apply(to_int)
+
+    data = df[available_cols].to_numpy(dtype=np.float64, copy=False)
+    unique_ids, inverse = np.unique(identifiers, return_inverse=True)
+    n_cols = len(available_cols)
+
+    sort_idx = np.argsort(inverse, kind='stable')
+    data_sorted = data[sort_idx]
+    inverse_sorted = inverse[sort_idx]
+
+    if len(inverse_sorted) > 0:
+        split_points = np.flatnonzero(np.diff(inverse_sorted)) + 1
+        groups = np.split(data_sorted, split_points)
+    else:
+        groups = []
+
+    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])
+        return res
+
+    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
+    if len(groups) > 0:
+        with ThreadPoolExecutor() as executor:
+            results = list(executor.map(_process_group, groups))
+            for i, res in enumerate(results):
+                out[i] = res
+
+    result = pd.DataFrame(out, index=unique_ids, columns=available_cols)
+    result.index.name = 'Identifier'
+    return result
+
+
+def plot_entropy_heatmap(entropy_df: pd.DataFrame, title: str) -> go.Figure:
+    x = entropy_df.columns.tolist()
+    y = entropy_df.index.tolist()
+    z = entropy_df.values
+
+    fig = go.Figure(
+        data=go.Heatmap(
+            z=z, x=x, y=y,
+            colorscale=[
+                [0.0, "#ffffff"],
+                [0.15, "#fff7ec"],
+                [0.35, "#fee8c8"],
+                [0.55, "#fdd49e"],
+                [0.75, "#fdbb84"],
+                [1.0, "#ef6548"],
+            ],
+            xgap=3, ygap=3,
+            text=np.round(z, 2),
+            texttemplate="%{text}",
+            textfont={"size": 11, "color": "#2a2a2a", "family": "Segoe UI, Arial, sans-serif"},
+            hoverongaps=False,
+            hovertemplate="<b>%{y}</b><br>Byte %{x}: %{z:.2f} bits<extra></extra>",
+            colorbar=dict(
+                title=dict(text="Entropy (bits)", side="top", font=dict(size=13, color="#1a1a1a")),
+                orientation="h", thickness=15, len=0.35,
+                x=1.0, xanchor="right", y=1.02, yanchor="bottom",
+                tickfont=dict(size=11, color="#2a2a2a"),
+                tickformat=".1f", outlinewidth=0.5, outlinecolor="#cccccc",
+            ),
+        )
+    )
+
+    fig.update_layout(
+        title=dict(text=title, font=dict(size=20, color="#1a1a1a"), x=0.5, xanchor="center", pad=dict(b=20)),
+        height=max(600, len(y) * 28 + 150),
+        autosize=True,
+        template="plotly_white",
+        xaxis=dict(
+            title=dict(text="Byte Position", font=dict(size=13, color="#1a1a1a")),
+            side="top", dtick=1, showgrid=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc",
+        ),
+        yaxis=dict(
+            title=dict(text="PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
+            autorange="reversed", showgrid=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc", automargin=True,
+        ),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=12, color="#2a2a2a"),
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor="#cccccc"),
+        margin=dict(l=200, r=40, t=120, b=60),
+    )
+    return fig
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Analyze CAN bus byte-level entropy")
+    parser.add_argument("input", type=Path, help="Path to the input CAN log file")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("entropy_report.html"))
+    parser.add_argument("title", nargs="?", default="CAN Bus Byte-Level Entropy")
+    args = parser.parse_args()
+
+    df = load_data(args.input)
+    entropy_df = calculate_byte_entropy(df)
+    fig = plot_entropy_heatmap(entropy_df, title=args.title)
+    config = {
+        "responsive": True,
+        "displaylogo": False,
+        "scrollZoom": True,
+        "modeBarButtonsToAdd": ["toggleSpikelines"],
+        "toImageButtonOptions": {"format": "png", "scale": 2},
+    }
+    fig.write_html(str(args.output), include_plotlyjs="cdn", config=config)

stats/frequency.py

@@ -1,36 +1,60 @@
-# 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.express as px
 import plotly.graph_objects as go
-from utils.extractor import load_data
 
-def calc_freq(df: pd.DataFrame) -> pd.DataFrame:
+from stats.utils.converter import format_can_id_vec as _format_can_id_vec
-    """Calculates frequency counts and percentages for identifiers."""
+from stats.utils.loader import load_data
-    freq_df = df['Identifier'].value_counts().reset_index()
+
-    freq_df.columns = ['Identifier', 'Count']
+
-    total = freq_df['Count'].sum()
+def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
-    freq_df['Percentage'] = (freq_df['Count'] / total * 100).round(2)
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
-    return freq_df.sort_values('Count', ascending=True)
+    formatted = _format_can_id_vec(df[can_id_col])
+
+    counts = formatted.value_counts()
+    freq_df = pd.DataFrame({
+        'Identifier': counts.index,
+        'Count': counts.to_numpy(),
+    })
+    total = counts.sum()
+    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(
+        y=stats_df['Identifier'],
+        x=stats_df['Count'],
+        orientation='h',
+        marker=dict(
+            color=stats_df['Count'],
+            colorscale='Turbo',
+            cmin=int(stats_df['Count'].min()) if n else 0,
+            cmax=int(stats_df['Count'].max()) if n else 1,
+            line_width=0,
+        ),
+        customdata=stats_df[['Percentage']].to_numpy(),
+        hovertemplate="<b>%{y}</b><br>Count: %{x:,}<br>Share: %{customdata[0]}%<extra></extra>",
+        texttemplate='%{x:,}',
+        textposition='outside',
+        cliponaxis=False,
+    ))
 
-def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
-    """Generates interactive horizontal bar chart with log x-axis."""
-    fig = px.bar(
-        stats_df, y='Identifier', x='Count', orientation='h', title=title, log_x=True,
-        labels={'Identifier': 'PGN / CAN ID', 'Count': 'Message Count'},
-        color='Count', color_continuous_scale='Turbo',
-        range_color=(stats_df['Count'].min(), stats_df['Count'].max()),
-        hover_data={'Percentage': ':.2f', 'Count': ':,', 'Identifier': True}
-    )
     fig.update_layout(
-        height=max(600, len(stats_df) * 18),
+        height=max(600, n * 18),
         autosize=True,
         template='plotly_white',
         xaxis=dict(
+            type='log',
             title=dict(text="Message count [log scale]", font=dict(size=13, color="#1a1a1a")),
             side="top",
             dtick=1,
@@ -43,7 +67,6 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
         ),
         yaxis=dict(
             title=dict(text="PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
-            #autorange="",
             showgrid=False,
             linecolor="#bdbdbd",
             tickfont=dict(size=12, color="#2a2a2a"),
@@ -51,10 +74,10 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
             ticklen=4,
             tickcolor="#cccccc",
             automargin=True,
+            type='category',
         ),
         font=dict(family="Segoe UI, Arial, sans-serif", size=12, color='#2a2a2a'),
-        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI",
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor='#cccccc'),
-                        bordercolor='#cccccc'),
         margin=dict(l=200, r=40, t=120, b=60),
         bargap=0.35,
         coloraxis_colorbar=dict(
@@ -68,49 +91,38 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
             yanchor='bottom',
             tickformat=',',
             outlinecolor='#cccccc',
-            outlinewidth=0.5
+            outlinewidth=0.5,
         ),
-        title=dict(font=dict(size=20, color='#1a1a1a'), x=0.5, xanchor='center',
+        title=dict(text=title, font=dict(size=20, color='#1a1a1a'), x=0.5, xanchor='center', pad=dict(b=20)),
-                   pad=dict(b=20))
     )
     fig.update_xaxes(
         showgrid=True, gridwidth=0.5, gridcolor='#e8e8e8',
         zeroline=False, linecolor='#bdbdbd', mirror=False,
         tickformat=',',
-        minor=dict(showgrid=True, gridcolor='#f4f4f4', gridwidth=0.5)
+        minor=dict(showgrid=True, gridcolor='#f4f4f4', gridwidth=0.5),
     )
     fig.update_yaxes(
         showgrid=False, zeroline=False, linecolor='#bdbdbd',
-        ticks='outside', ticklen=4, tickcolor='#cccccc',
+        ticks='outside', ticklen=4, tickcolor='#cccccc', automargin=True,
-        automargin=True
-    )
-    fig.update_traces(
-        hovertemplate="<b>%{y}</b><br>Count: %{x:,}<br>Share: %{customdata[0]}%<extra></extra>",
-        marker_line_width=0,
-        texttemplate='%{x:,}',
-        textposition='outside',
-        textfont=dict(size=10, color='#666666'),
-        cliponaxis=False,
-        selected=dict(marker=dict(opacity=0.6)),
-        unselected=dict(marker=dict(opacity=0.2))
     )
     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")
-    parser.add_argument("output", type=Path, nargs="?", default=Path("freq_report.html"), help="Path to the output HTML report")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("freq_report.html"))
-    parser.add_argument("title", nargs="?", default="CAN Bus Message Frequency", help="Title for the HTML report")
+    parser.add_argument("title", nargs="?", default="Frequency")
     args = parser.parse_args()
 
     df = load_data(args.input)
-    stats = calc_freq(df)
+    stats = calculate_frequency(df)
-    fig = plot_freq(stats, title=args.title)
+    fig = plot_frequency(stats, title=args.title)
     config = {
         'responsive': True,
         'displaylogo': False,
         'scrollZoom': True,
         'modeBarButtonsToAdd': ['toggleSpikelines'],
-        'toImageButtonOptions': {'format': 'png', 'scale': 2}
+        'toImageButtonOptions': {'format': 'png', 'scale': 2},
     }
     fig.write_html(str(args.output), include_plotlyjs='cdn', config=config)

stats/id_viewer.py

@@ -0,0 +1,151 @@
+# 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.converter import format_can_id_vec as _format_can_id_vec
+from stats.utils.loader import load_data
+
+_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'
+    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]
+
+    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in filtered.columns]
+    if filtered.empty:
+        return filtered, byte_cols
+
+    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.sort_values('Timestamp', kind='stable')
+    arr = filtered[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))
+        filtered = filtered.iloc[keep]
+
+    return filtered, byte_cols
+
+
+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
+    )
+    n = len(byte_cols)
+
+    x = df['Timestamp'].to_numpy() if not df.empty else np.array([])
+    for i, col in enumerate(byte_cols):
+        y = df[col].to_numpy(dtype=np.float32, copy=False) if not df.empty else np.array([])
+
+        fig.add_trace(go.Scatter(
+            mode='lines',
+            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>",
+        ), hf_x=x, hf_y=y)
+
+    all_button = dict(label='ALL', method='restyle', args=[{'visible': [True] * n}])
+    none_button = dict(label='NONE', method='restyle', args=[{'visible': ['legendonly'] * n}])
+
+    fig.update_layout(
+        height=600,
+        autosize=True,
+        template='plotly_white',
+        title=dict(
+            text=f"{title} - ID: {can_id}",
+            font=dict(size=20, color='#1a1a1a'),
+            x=0.5, xanchor='center',
+            pad=dict(b=20),
+        ),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=12, color='#2a2a2a'),
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor='#cccccc'),
+        margin=dict(l=60, r=40, t=120, b=140),
+        legend=dict(
+            orientation='h',
+            x=0.5, xanchor='center',
+            y=-0.18, yanchor='top',
+            title=None,
+            bgcolor='white',
+            bordercolor='#cccccc',
+            borderwidth=1,
+            font=dict(size=12, color="#2a2a2a"),
+            itemsizing='constant',
+            itemclick='toggle',
+            itemdoubleclick='toggleothers',
+        ),
+        xaxis=dict(
+            title=dict(text="Timestamp", font=dict(size=13, color="#1a1a1a")),
+            showgrid=True, gridwidth=0.5, gridcolor='#e8e8e8',
+            zeroline=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"),
+            ticks="outside", ticklen=4, tickcolor="#cccccc",
+            minor=dict(showgrid=True, gridcolor='#f4f4f4', gridwidth=0.5),
+        ),
+        yaxis=dict(
+            title=dict(text="Byte Value", font=dict(size=13, color="#1a1a1a")),
+            showgrid=True, gridwidth=0.5, gridcolor='#e8e8e8',
+            zeroline=False, linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"),
+            ticks="outside", ticklen=4, tickcolor="#cccccc",
+        ),
+        updatemenus=[
+            dict(
+                type='buttons',
+                direction='right',
+                x=0.5, xanchor='center',
+                y=-0.06, yanchor='top',
+                buttons=[all_button, none_button],
+                bgcolor='white',
+                bordercolor='#cccccc',
+                borderwidth=1,
+                font=dict(size=11, color='#2a2a2a'),
+                pad=dict(l=5, r=5, t=5, b=5),
+            )
+        ],
+    )
+    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")
+    parser.add_argument("can_id", type=str, help="CAN ID to visualize")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("bits_report.html"))
+    parser.add_argument("title", nargs="?", default="Byte Visualization")
+    args = parser.parse_args()
+
+    df = load_data(args.input)
+    filtered_df, byte_cols = prepare_data(df, args.can_id)
+    fig = plot_bits(filtered_df, byte_cols, args.can_id, title=args.title)
+
+    config = {
+        'responsive': True,
+        'displaylogo': False,
+        'scrollZoom': True,
+        'modeBarButtonsToAdd': ['toggleSpikelines'],
+        'toImageButtonOptions': {'format': 'png', 'scale': 2},
+    }
+    fig.write_html(str(args.output), include_plotlyjs='cdn', config=config)

utils/extractor.py

@@ -1,27 +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 pandas as pd
-
-def extract_id(row: pd.Series) -> str:
-    """Extracts PGN from metadata or falls back to CAN ID."""
-    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:
-    """Loads Parquet file and adds an Identifier column."""
-    df = pd.read_parquet(file_path)
-    df['Identifier'] = df.apply(extract_id, axis=1)
-    return df

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)