Add custom plotting support for vehicle signal

- Plot pie chart for engine load state

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

@@ -8,9 +8,10 @@ from concurrent.futures import ThreadPoolExecutor
 
 import polars as pl
 import dash
-from dash import dcc, html, Input, Output
+from dash import dcc, html, Input, Output, State
 import dash_bootstrap_components as dbc
 import numpy as np
+import pandas as pd
 
 from parser import parse_log, parse_csv
 from decoder import decode_j1939_frames
@@ -19,56 +20,85 @@ from stats.id_viewer import _format_can_id_vec, plot_bits
 from stats.frequency import calculate_frequency, plot_frequency
 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 vehicle import get_vehicle_module
 
-RAW_LOG = "data/logs/rawlog.txt"
+RAW_LOG_DIR = "data/logs"
-BUS1_CSV = "data/csv/bus1.csv"
+PAGE_SIZE = 25000
-BUS2_CSV = "data/csv/bus2.csv"
+
-BUS1_PARQUET = "data/parquet/bus1.parquet"
+def parse_vehicle_from_filename(filename: str):
-BUS2_PARQUET = "data/parquet/bus2.parquet"
+    stem = Path(filename).stem
-BUS1_DECODED = "data/parquet/bus1_decoded.parquet"
+    if '-' in stem:
-BUS2_DECODED = "data/parquet/bus2_decoded.parquet"
+        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 run_pipeline():
-    os.makedirs("data/logs", exist_ok=True)
+    os.makedirs(RAW_LOG_DIR, exist_ok=True)
     os.makedirs("data/csv", exist_ok=True)
     os.makedirs("data/parquet", exist_ok=True)
-    if not Path(BUS1_DECODED).exists() or not Path(BUS2_DECODED).exists():
+
-        print("Parsing raw log...")
+    for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
-        parse_log(RAW_LOG, BUS1_CSV, BUS2_CSV)
+        vehicle, brand, model = parse_vehicle_from_filename(log_file.name)
+
+        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"
+
+        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(bus1_csv).sink_parquet(bus1_parquet)
-        parse_csv(BUS2_CSV).sink_parquet(BUS2_PARQUET)
+            parse_csv(bus2_csv).sink_parquet(bus2_parquet)
 
             print("Decoding J1939...")
-        df1 = pl.read_parquet(BUS1_PARQUET)
+            df1 = pl.read_parquet(bus1_parquet)
-        df2 = pl.read_parquet(BUS2_PARQUET)
+            df2 = pl.read_parquet(bus2_parquet)
             dec1 = decode_j1939_frames(df1)
             dec2 = decode_j1939_frames(df2)
-        dec1.write_parquet(BUS1_DECODED)
+            dec1.write_parquet(bus1_decoded)
-        dec2.write_parquet(BUS2_DECODED)
+            dec2.write_parquet(bus2_decoded)
 
 run_pipeline()
 
 print("Loading data into memory...")
-DATA = {
+DATA = {}
-    "Bus 1": load_data(BUS1_DECODED),
+VEHICLE_META = {}
-    "Bus 2": load_data(BUS2_DECODED)
+
-}
+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_decoded = f"data/parquet/{vehicle}_bus1_decoded.parquet"
+    bus2_decoded = f"data/parquet/{vehicle}_bus2_decoded.parquet"
+
+    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(bus, df):
+def process_bus_data(vehicle, bus, df):
     precomp = {}
-    precomp[f"{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{bus} Frequency")
+    precomp[f"{vehicle}_{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{vehicle} {bus} Frequency")
-    precomp[f"{bus}_entropy"] = plot_entropy_heatmap(calculate_byte_entropy(df), title=f"{bus} Byte-Level Entropy")
+    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 = {}
@@ -82,15 +112,17 @@ def process_bus_data(bus, df):
                 group = group.iloc[keep]
         grouped[can_id] = (group, byte_cols)
 
-    return precomp, grouped
+    return vehicle, bus, precomp, grouped
 
 with ThreadPoolExecutor() as executor:
-    futures = {executor.submit(process_bus_data, bus, df): bus for bus, df in DATA.items()}
+    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:
-        bus = futures[future]
+        v, b, precomp, grouped = future.result()
-        precomp, grouped = future.result()
         PRECOMPUTED_FIGURES.update(precomp)
-        DATA_BY_ID[bus] = grouped
+        DATA_BY_ID[(v, b)] = grouped
 
 app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
 app.config.suppress_callback_exceptions = True
@@ -101,16 +133,54 @@ app.layout = dbc.Container([
         dbc.Tab(label="Overview", tab_id="overview", children=[
             html.Div(id="overview-content")
         ]),
-        dbc.Tab(label="Statistics", tab_id="statistics", children=[
+        dbc.Tab(label="Vehicles", tab_id="vehicles", children=[
             dbc.Row([
-                dbc.Col(html.Label("Select Bus:"), width=1, className="mt-2"),
+                dbc.Col(html.Label("Vehicle:", className="mt-2"), width="auto"),
                 dbc.Col(dcc.Dropdown(
-                    id='bus-selector',
+                    id='vehicles-vehicle-selector',
-                    options=[{'label': k, 'value': k} for k in DATA.keys()],
+                    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"),
+            ], 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(html.Label("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("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"),
+            ], 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("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("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"),
@@ -122,21 +192,136 @@ app.layout = dbc.Container([
     ], id="main-tabs", active_tab="statistics")
 ], fluid=True)
 
+def get_prepared_logs(vehicle, bus):
+    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)
+    return PREPARED_LOGS_CACHE[cache_key]
+
+def build_page_buttons(current_page: int, total_pages: int, max_buttons: int = 15) -> list:
+    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": 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_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, bus):
+def render_content(tab, vehicle, bus):
-    df = DATA[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"{bus}_freq"], style={'height': '80vh'})
+        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{vehicle}_{bus}_freq"], style={'height': '80vh'})
 
     elif tab == 'id_viewer':
-        ids = sorted(DATA_BY_ID[bus].keys())
+        ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
         return html.Div([
-            html.Label("Select CAN ID:"),
+            html.Label("CAN ID:"),
             dcc.Dropdown(
                 id='id-selector',
                 options=[{'label': i, 'value': i} for i in ids],
@@ -148,7 +333,7 @@ def render_content(tab, bus):
         ])
 
     elif tab == 'corr':
-        ids = sorted(DATA_BY_ID[bus].keys())
+        ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
         return html.Div([
             dbc.Row([
                 dbc.Col(html.Label("Method:"), width=1, className="mt-2"),
@@ -170,53 +355,115 @@ def render_content(tab, bus):
         ])
 
     elif tab == 'entropy':
-        return dcc.Graph(figure=PRECOMPUTED_FIGURES[f"{bus}_entropy"], style={'height': '80vh'})
+        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, bus, tab):
+def update_id_viewer(selected_id, vehicle, bus, tab):
-    if tab != 'id_viewer' or not selected_id:
+    if tab != 'id_viewer' or not selected_id or not vehicle or not bus:
         return dash.no_update
 
-    grouped_data = DATA_BY_ID.get(bus, {})
+    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"{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'),
 )
-def update_corr(method, target, bus, tab):
+def update_corr(method, target, vehicle, bus, tab):
-    if tab != 'corr':
+    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 = (bus, method, target_id)
+    cache_key = (vehicle, bus, method, target_id)
 
     if cache_key not in CORR_CACHE:
-        df = DATA[bus]
+        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]
 
-    title = f"{bus} Correlation"
+    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 = []
+    for bus_df in DATA[vehicle].values():
+        dfs.append(bus_df)
+
+    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"{frame_def.can_id} - {sig.name}{unit_str}"
+                fig = vehicle_module.plot_signal(decoded, sig.name, title=title, color=frame_def.color)
+
+            card = dbc.Card([
+                dbc.CardBody([
+                    dcc.Graph(figure=fig, config={'displayModeBar': False},
+                              style={'height': '280px'})
+                ], className="p-2"),
+            ], className="shadow-sm border-0 h-100")
+
+            cards.append(
+                dbc.Col(card, 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=True)
+    app.run(debug=False)

stats/correlation.py

@@ -83,8 +83,12 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
             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:
-        out = np.array(list(executor.map(_process_group, groups)))
+            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'

stats/entropy.py

@@ -70,8 +70,12 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
             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:
-        out = np.array(list(executor.map(_process_group, groups)))
+            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'

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 +1,139 @@
+# File: vehicle/base.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+from dataclasses import dataclass, field
+from typing import List
+import numpy as np
+import pandas as pd
+import plotly.graph_objects as go
+
+@dataclass
+class SignalDef:
+    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:
+    can_id: str
+    description: str = ""
+    color: str = "#377eb8"
+    signals: List[SignalDef] = field(default_factory=list)
+
+def normalize_id(can_id: str) -> str:
+    s = str(can_id).strip().upper()
+    if s.startswith("0X"):
+        s = s[2:]
+    return s.lstrip("0") or "0"
+
+def _extract_signal(bytes_arr: np.ndarray, sig: SignalDef) -> np.ndarray:
+    if bytes_arr.size == 0:
+        return np.zeros(0, dtype=np.float64)
+
+    byte_lo = sig.bit_start // 8
+    byte_hi = (sig.bit_start + sig.bit_length - 1) // 8
+    byte_indices = [i for i in range(byte_lo, byte_hi + 1) if 0 <= i < 8]
+
+    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)
+
+    intra_byte_shift = sig.bit_start % 8
+    raw = raw >> intra_byte_shift
+
+    mask = (1 << sig.bit_length) - 1
+    raw = raw & mask
+
+    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) -> pd.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)
+    mask = df_ids == norm
+    sub = df.loc[mask].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:
+    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>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 +1,146 @@
+# File: vehicle/komatsu.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+import plotly.express as px
+import pandas as pd
+from dataclasses import dataclass
+from typing import Callable
+from copy import deepcopy
+from vehicle.base import (
+    SignalDef, FrameDef, normalize_id, decode_dataframe as _decode_dataframe, plot_signal
+)
+
+@dataclass
+class CustomPlotDef:
+    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 = {
+    normalize_id("0x011F"): FrameDef(
+        can_id="0x011F",
+        description="Engine ECM Main Broadcast",
+        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="Pressure / 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 temperature and load state block",
+        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 State",
+                plot_func=lambda decoded, color: plot_load_state_pie(decoded, color)
+            ),
+        ],
+    ),
+}
+
+LOAD_STATE_MAP = {
+    0: "Boot up",
+    16: "Normal load",
+    32: "High load"
+}
+
+def plot_load_state_pie(decoded_df, color):
+    if decoded_df is None or decoded_df.empty or "Engine Load State" not in decoded_df.columns:
+        return px.pie(title="No data for Engine Load State")
+
+    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',
+        title='Engine Load State Distribution',
+        color_discrete_map={
+            "Boot up": "#ff9900",
+            "Normal load": "#00cc00",
+            "High load": "#cc0000",
+            "Unknown": "#808080"
+        }
+    )
+
+    fig.update_traces(
+        textinfo='none',
+        hoverinfo='label+percent+value',
+        domain={'x': [0.05, 0.55], 'y': [0.05, 0.95]}
+    )
+    fig.update_layout(
+        margin=dict(l=0, r=10, t=40, b=0),
+        legend=dict(x=0.6, y=0.5)
+    )
+    return fig
+
+def decode_dataframe(df, can_id):
+    filtered_rules = {}
+    for nid, frame in DECODER_RULES.items():
+        filtered_signals = [sig for sig in frame.signals if isinstance(sig, SignalDef)]
+        new_frame = deepcopy(frame)
+        new_frame.signals = filtered_signals
+        filtered_rules[nid] = new_frame
+
+    return _decode_dataframe(df, can_id, filtered_rules)