Merge pull request 'Implement multi-vehicle support and CAN log viewing options' (#7) from dev-dash into main

Reviewed-on: erickahmed/CANveyor#7

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

@@ -2,50 +2,394 @@
 # Copyright (C) 2026 Erick Ahmed
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
-import diskcache
-import flask_caching
+import os
+from pathlib import Path
+from concurrent.futures import ThreadPoolExecutor
+
+import polars as pl
 import dash
-from dash import Input, Output, State, dcc, html, no_update
+from dash import dcc, html, Input, Output, State
 import dash_bootstrap_components as dbc
+import numpy as np
 
-CACHE_DATA_DIR = ".cache_data"
-background_callback_manager = dash.DiskcacheManager(cache_dir=CACHE_DATA_DIR)
-data_cache = flask_caching.Cache(config={'CACHE_TYPE': 'FileSystemCache', 'CACHE_DIR': CACHE_DATA_DIR})
+from parser import parse_log, parse_csv
+from decoder import decode_j1939_frames
+from stats.utils.extractor import load_data
+from stats.id_viewer import _format_can_id_vec, plot_bits
+from stats.frequency import calculate_frequency, plot_frequency
+from stats.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
 
-app = dash.Dash(
-    __name__,
-    external_stylesheets=[dbc.themes.BOOTSTRAP],
-    background_callback_manager=background_callback_manager
-)
-data_cache.init_app(app.server)
+RAW_LOG_DIR = "data/logs"
+PAGE_SIZE = 25000
 
-def _get_df(session_data):
-    if not session_data or "token" not in session_data:
-        return None
-    return data_cache.get(session_data["token"])
+def parse_vehicle_from_filename(filename: str):
+    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 run_pipeline():
+    os.makedirs(RAW_LOG_DIR, exist_ok=True)
+    os.makedirs("data/csv", exist_ok=True)
+    os.makedirs("data/parquet", exist_ok=True)
+
+    for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
+        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(bus2_csv).sink_parquet(bus2_parquet)
+
+            print("Decoding J1939...")
+            df1 = pl.read_parquet(bus1_parquet)
+            df2 = pl.read_parquet(bus2_parquet)
+            dec1 = decode_j1939_frames(df1)
+            dec2 = decode_j1939_frames(df2)
+            dec1.write_parquet(bus1_decoded)
+            dec2.write_parquet(bus2_decoded)
+
+run_pipeline()
+
+print("Loading data into memory...")
+DATA = {}
+VEHICLE_META = {}
+
+for log_file in Path(RAW_LOG_DIR).glob("*.txt"):
+    vehicle, brand, model = parse_vehicle_from_filename(log_file.name)
+    VEHICLE_META[vehicle] = {"brand": brand, "model": model}
+
+    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(vehicle, bus, df):
+    precomp = {}
+    precomp[f"{vehicle}_{bus}_freq"] = plot_frequency(calculate_frequency(df), title=f"{vehicle} {bus} Frequency")
+    precomp[f"{vehicle}_{bus}_entropy"] = plot_entropy_heatmap(calculate_byte_entropy(df), title=f"{vehicle} {bus} Byte-Level Entropy")
+
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    formatted = _format_can_id_vec(df[can_id_col])
+    df = df.assign(Formatted_ID=formatted)
+    df = df.sort_values(['Formatted_ID', 'Timestamp'], kind='stable')
+
+    grouped = {}
+    for can_id, group in df.groupby(by='Formatted_ID'):
+        byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in group.columns]
+        if not group.empty and len(byte_cols) > 0:
+            arr = group[byte_cols].to_numpy(dtype=np.float32, copy=False)
+            if len(arr) > 1:
+                changed = np.any(arr[1:] != arr[:-1], axis=1)
+                keep = np.concatenate(([True], changed))
+                group = group.iloc[keep]
+        grouped[can_id] = (group, byte_cols)
+
+    return vehicle, bus, precomp, grouped
+
+with ThreadPoolExecutor() as executor:
+    futures = []
+    for vehicle, buses in DATA.items():
+        for bus, df in buses.items():
+            futures.append(executor.submit(process_bus_data, vehicle, bus, df))
+    for future in futures:
+        v, b, precomp, grouped = future.result()
+        PRECOMPUTED_FIGURES.update(precomp)
+        DATA_BY_ID[(v, b)] = grouped
+
+app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
+app.config.suppress_callback_exceptions = True
+
+app.layout = dbc.Container([
+    html.H1("CANveyor", className="my-4"),
+    dbc.Tabs([
+        dbc.Tab(label="Overview", tab_id="overview", children=[
+            html.Div(id="overview-content")
+        ]),
+        dbc.Tab(label="Logs", tab_id="logs", children=[
+            dbc.Row([
+                dbc.Col(html.Label("Select Vehicle:", className="mt-2"), width="auto"),
+                dbc.Col(dcc.Dropdown(
+                    id='logs-vehicle-selector',
+                    options=[{'label': v, 'value': v} for v in DATA.keys()],
+                    value=list(DATA.keys())[0] if DATA else None,
+                    clearable=False
+                ), width=3, className="me-4"),
+                dbc.Col(html.Label("Select Bus:", className="mt-2"), width="auto"),
+                dbc.Col(dcc.Dropdown(
+                    id='logs-bus-selector',
+                    options=[{'label': 'Bus 1', 'value': 'Bus 1'}, {'label': 'Bus 2', 'value': 'Bus 2'}],
+                    value='Bus 1',
+                    clearable=False
+                ), width=2),
+            ], className="mb-3 mt-3", align="end"),
+            get_logs_table_component()
+        ]),
+        dbc.Tab(label="Statistics", tab_id="statistics", children=[
+            dbc.Row([
+                dbc.Col(html.Label("Select Vehicle:", className="mt-2"), width="auto"),
+                dbc.Col(dcc.Dropdown(
+                    id='vehicle-selector',
+                    options=[{'label': v, 'value': v} for v in DATA.keys()],
+                    value=list(DATA.keys())[0] if DATA else None,
+                    clearable=False
+                ), width=3, className="me-4"),
+                dbc.Col(html.Label("Select Bus:", className="mt-2"), width="auto"),
+                dbc.Col(dcc.Dropdown(
+                    id='bus-selector',
+                    options=[{'label': 'Bus 1', 'value': 'Bus 1'}, {'label': 'Bus 2', 'value': 'Bus 2'}],
+                    value='Bus 1',
+                    clearable=False
+                ), width=2),
+            ], className="mb-3 mt-3", align="end"),
+            dbc.Tabs([
+                dbc.Tab(label="Frequency", tab_id="freq"),
+                dbc.Tab(label="ID Viewer", tab_id="id_viewer"),
+                dbc.Tab(label="Correlation", tab_id="corr"),
+                dbc.Tab(label="Entropy", tab_id="entropy"),
+            ], id="tabs", active_tab="freq"),
+            html.Div(id="tab-content", className="mt-3")
+        ])
+    ], id="main-tabs", active_tab="statistics")
+], fluid=True)
+
+def get_prepared_logs(vehicle, bus):
+    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("graph-correlation", "figure"),
-    Input("corr-method", "value"),
-    Input("corr-target", "value"),
-    Input("session-store", "data"),
-
-    background=True,
-    prevent_initial_call=True,
+    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_correlation(method, target, session_data):
-    df = _get_df(session_data)
-    if df is None or not method:
-        return no_update
+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
 
-    target_id = None if target == "all" else target
-    try:
+    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, 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'})
+
+    elif tab == 'id_viewer':
+        ids = sorted(DATA_BY_ID.get((vehicle, bus), {}).keys())
+        return html.Div([
+            html.Label("Select CAN ID:"),
+            dcc.Dropdown(
+                id='id-selector',
+                options=[{'label': i, 'value': i} for i in ids],
+                value=ids[0] if ids else None,
+                clearable=False,
+                style={'width': '50%', 'marginBottom': '10px'}
+            ),
+            dcc.Graph(id='id-viewer-graph', style={'height': '70vh'})
+        ])
+
+    elif 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'})
+        ])
+
+    elif 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_df = calculate_correlation(df, method=method, target_id=target_id)
-        title = f"Inter-Byte Correlation ({method.capitalize()})"
-        if target_id:
-            title += f" - {target_id}"
-        return plot_correlation_heatmap(corr_df, target_id=target_id, title=title)
-    except Exception as exc:
-        fig = dash.go.Figure()
-        fig.update_layout(title=f"Error: {exc}")
-        return fig
+        CORR_CACHE[cache_key] = corr_df
+    else:
+        corr_df = CORR_CACHE[cache_key]
+
+    title = f"{vehicle} {bus} Correlation"
+    if target_id:
+        title += f" ({target_id})"
+
+    return plot_correlation_heatmap(corr_df, target_id=target_id, title=title)
+
+if __name__ == '__main__':
+    app.run(debug=False)

parser.py

@@ -77,7 +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 = []

pyproject.toml

@@ -1,7 +1,15 @@
 [project]
 name = "CANveyor"
-version = "0.0.4"
+version = "0.1.0"
 description = "J1939 CAN bus parser that works in pair with CANdigger"
 readme = "README.md"
-requires-python = ">=3.14"
-dependencies = ["polars", "pathlib", "typing"]
+requires-python = ">=3.10"
+dependencies = [
+    "polars",
+    "dash",
+    "dash-bootstrap-components",
+    "numpy",
+    "pandas",
+    "plotly",
+    "plotly-resampler"
+]

stats/correlation.py

@@ -4,13 +4,14 @@
 
 import argparse
 from pathlib import Path
+from concurrent.futures import ThreadPoolExecutor
 
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from utils.extractor import load_data
-from utils.extractor import to_int
+from stats.utils.extractor import load_data
+from stats.utils.extractor import to_int
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
@@ -27,8 +28,7 @@ def _ensure_int_bytes(df: pd.DataFrame, cols: list) -> pd.DataFrame:
     return df
 
 def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None = None) -> pd.DataFrame:
-    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
-    available_cols = [col for col in byte_cols if col in df.columns]
+    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")
@@ -70,8 +70,7 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
     else:
         groups = []
 
-    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
-    for gi, sub in enumerate(groups):
+    def _process_group(sub):
         mask = ~np.isnan(sub).any(axis=1)
         sub = sub[mask]
         if len(sub) > 1:
@@ -81,7 +80,15 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
                 c = np.abs(np.corrcoef(sub, rowvar=False))
             np.nan_to_num(c, copy=False, nan=0.0)
             np.fill_diagonal(c, 0.0)
-            out[gi] = c.max(axis=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'

stats/entropy.py

@@ -4,13 +4,14 @@
 
 import argparse
 from pathlib import Path
+from concurrent.futures import ThreadPoolExecutor
 
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from utils.extractor import load_data
-from utils.extractor import to_int
+from stats.utils.extractor import load_data
+from stats.utils.extractor import to_int
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
@@ -36,8 +37,7 @@ def _entropy_col(a: np.ndarray) -> float:
     return float(-np.sum(p * np.log2(p)))
 
 def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
-    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
-    available_cols = byte_cols
+    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")
 
@@ -64,10 +64,18 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     else:
         groups = []
 
-    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
-    for gi, sub in enumerate(groups):
+    def _process_group(sub):
+        res = np.zeros(n_cols, dtype=np.float64)
         for ci in range(n_cols):
-            out[gi, ci] = _entropy_col(sub[:, ci])
+            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'

stats/frequency.py

@@ -7,7 +7,7 @@ from pathlib import Path
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from utils.extractor import load_data
+from stats.utils.extractor import load_data
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
@@ -18,7 +18,6 @@ def _format_can_id_vec(s: pd.Series) -> pd.Series:
 def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
     can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
     formatted = _format_can_id_vec(df[can_id_col])
-    df['Formatted_ID'] = formatted
 
     counts = formatted.value_counts()
     freq_df = pd.DataFrame({

stats/id_viewer.py

@@ -7,7 +7,8 @@ from pathlib import Path
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from utils.extractor import load_data
+from plotly_resampler import FigureResampler
+from stats.utils.extractor import load_data
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
@@ -40,22 +41,24 @@ def prepare_data(df, target_id):
     return filtered, byte_cols
 
 def plot_bits(df, byte_cols, can_id, title):
-    fig = go.Figure()
+    fig = FigureResampler(
+        resampled_trace_prefix_suffix=("", ""),
+        show_mean_aggregation_size=False
+    )
     colors = ['#e41a1c', '#377eb8', '#4daf4a', '#984ea3', '#ff7f00', '#ffff33', '#a65628', '#f781bf']
     n = len(byte_cols)
 
     x = df['Timestamp'].to_numpy() if not df.empty else np.array([])
     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.Scattergl(
-            x=x,
-            y=y,
+
+        fig.add_trace(go.Scatter(
             mode='lines',
             line=dict(shape='hv', width=2, color=colors[i % len(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}])