Refactor statistical analysis modules for performance

- Optimize data processing pipelines across files by replacing iterative
  pandas operations with vectorized NumPy routines

stat/correlation.py

@@ -12,75 +12,96 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
-def _format_can_id(x):
+def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    """Safely cleans CAN ID strings without altering their length or value."""
+    s = s.astype('string').str.strip()
-    if pd.isna(x):
+    s = s.str.replace(r'^0x', '', case=False, regex=True)
-        return "UNKNOWN"
+    s = s.str.upper()
+    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
 
-    s = str(x).strip()
+def _ensure_int_bytes(df: pd.DataFrame, cols: list) -> pd.DataFrame:
-    if not s:
+    needs = [c for c in cols if not pd.api.types.is_numeric_dtype(df[c])]
-        return "UNKNOWN"
+    if needs:
-
+        df = df.copy()
-    if s.lower().startswith('0x'):
+        for c in needs:
-        s = s[2:]
+            df[c] = df[c].apply(to_int)
-
+    return df
-    return s.upper()
 
 def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None = None) -> pd.DataFrame:
-    """Calculates inter-byte correlation grouped by identifier."""
+    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
-    byte_cols = [f"b{i}" for i in range(8)]
     available_cols = [col for col in byte_cols if col 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 = df[can_id_col].apply(_format_can_id)
+    identifiers = _format_can_id_vec(df[can_id_col]).to_numpy()
 
-    df_bytes = df[available_cols].copy()
+    df_bytes = _ensure_int_bytes(df, available_cols)[available_cols]
-    for col in available_cols:
+    data = df_bytes.to_numpy(dtype=np.float64, copy=False)
-        df_bytes[col] = df_bytes[col].apply(to_int)
 
     if target_id is not None:
-        target_id = _format_can_id(target_id)
+        target_id = _format_can_id_vec(pd.Series([target_id])).iloc[0]
-        group = df_bytes[identifiers == target_id]
+        mask = identifiers == target_id
-        if group.empty:
+        if not mask.any():
             raise ValueError(f"Identifier '{target_id}' not found in data")
-        return group[available_cols].corr(method=method).fillna(0.0)
+        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)
 
-    def max_abs_corr(group: pd.DataFrame) -> pd.Series:
+    unique_ids, inverse = np.unique(identifiers, return_inverse=True)
-        corr_arr = np.abs(group.corr(method=method).to_numpy().copy())
+    n_cols = len(available_cols)
-        np.fill_diagonal(corr_arr, 0.0)
-        return pd.Series(corr_arr.max(axis=0), index=group.columns).fillna(0.0)
 
-    result = df_bytes.groupby(identifiers)[available_cols].apply(max_abs_corr)
+    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 = []
+
+    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
+    for gi, sub in enumerate(groups):
+        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)
+            out[gi] = c.max(axis=0)
+
+    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:
-    """Generates an interactive heatmap of inter-byte correlation."""
     is_8x8 = target_id is not None
 
+    x = corr_df.columns.tolist()
+    y = corr_df.index.tolist()
+    z = corr_df.values
+
     if is_8x8:
-        x = corr_df.columns.tolist()
-        y = corr_df.index.tolist()
-        z = corr_df.values
         z_min, z_max = -1.0, 1.0
-        colorscale = [
+        colorscale = [[0.0, "#2c7bb6"], [0.25, "#abd9e9"], [0.5, "#ffffff"], [0.75, "#fdae61"], [1.0, "#d7191c"]]
-            [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:
-        x = corr_df.columns.tolist()
-        y = corr_df.index.tolist()
-        z = corr_df.values
         z_min, z_max = 0.0, 1.0
-        colorscale = [
+        colorscale = [[0.0, "#ffffff"], [0.2, "#fff5f0"], [0.4, "#fecc5c"], [0.6, "#fd8d3c"], [0.8, "#e31a1c"], [1.0, "#800026"]]
-            [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(
@@ -106,17 +127,17 @@ def plot_correlation_heatmap(corr_df: pd.DataFrame, target_id: str | None, title
 
     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) if not is_8x8 else 600,
+        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="top" if not is_8x8 else "bottom",
+            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="PGN or CAN ID" if not is_8x8 else "Byte Position", font=dict(size=13, color="#1a1a1a")),
+            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,
         ),
@@ -131,17 +152,15 @@ 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"), help="Path to the output HTML report")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("correlation_report.html"))
-    parser.add_argument("title", nargs="?", default="CAN Bus Inter-Byte Correlation", help="Title for the HTML report")
+    parser.add_argument("title", nargs="?", default="CAN Bus Inter-Byte Correlation")
-    parser.add_argument("--identifier", type=str, default=None, help="Specific PGN/CAN ID to analyze (e.g., 'PGN: 65331'). If omitted, shows max correlation per byte for all IDs.")
+    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,

stat/entropy.py

@@ -12,57 +12,76 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
-def _format_can_id(x):
+def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    """Safely cleans CAN ID strings without altering their length or value."""
+    s = s.astype('string').str.strip()
-    if pd.isna(x):
+    s = s.str.replace(r'^0x', '', case=False, regex=True)
-        return "UNKNOWN"
+    s = s.str.upper()
+    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
 
-    s = str(x).strip()
+def _entropy_col(a: np.ndarray) -> float:
-    if not s:
+    a = a[~np.isnan(a)]
-        return "UNKNOWN"
+    if a.size == 0:
-
+        return 0.0
-    if s.lower().startswith('0x'):
+    a = a.astype(np.int64)
-        s = s[2:]
+    lo, hi = a.min(), a.max()
-
+    span = hi - lo + 1
-    return s.upper()
+    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:
-    """Calculates Shannon entropy per byte position for each identifier."""
+    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in df.columns]
-    byte_cols = [f"b{i}" for i in range(8)]
+    available_cols = byte_cols
-    available_cols = [col for col in byte_cols if col 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 = df[can_id_col].apply(_format_can_id)
+    identifiers = _format_can_id_vec(df[can_id_col]).to_numpy()
 
-    df_bytes = df[available_cols].copy()
+    needs = [c for c in available_cols if not pd.api.types.is_numeric_dtype(df[c])]
-    for col in available_cols:
+    if needs:
-        df_bytes[col] = df_bytes[col].apply(to_int)
+        df = df.copy()
+        for c in needs:
+            df[c] = df[c].apply(to_int)
 
-    def entropy(s: pd.Series) -> float:
+    data = df[available_cols].to_numpy(dtype=np.float64, copy=False)
-        s = s.dropna()
+    unique_ids, inverse = np.unique(identifiers, return_inverse=True)
-        if s.empty:
+    n_cols = len(available_cols)
-            return 0.0
-        p = s.value_counts(normalize=True)
-        return -np.sum(p * np.log2(p))
 
-    result = df_bytes.groupby(identifiers)[available_cols].agg(entropy)
+    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 = []
+
+    out = np.zeros((len(unique_ids), n_cols), dtype=np.float64)
+    for gi, sub in enumerate(groups):
+        for ci in range(n_cols):
+            out[gi, ci] = _entropy_col(sub[:, ci])
+
+    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:
-    """Generates an interactive heatmap of byte-level Shannon entropy."""
     x = entropy_df.columns.tolist()
     y = entropy_df.index.tolist()
     z = entropy_df.values
 
     fig = go.Figure(
         data=go.Heatmap(
-            z=z,
+            z=z, x=x, y=y,
-            x=x,
-            y=y,
             colorscale=[
                 [0.0, "#ffffff"],
                 [0.15, "#fff7ec"],
@@ -71,112 +90,54 @@ def plot_entropy_heatmap(entropy_df: pd.DataFrame, title: str) -> go.Figure:
                 [0.75, "#fdbb84"],
                 [1.0, "#ef6548"],
             ],
-            xgap=3,
+            xgap=3, ygap=3,
-            ygap=3,
             text=np.round(z, 2),
             texttemplate="%{text}",
-            textfont={
+            textfont={"size": 11, "color": "#2a2a2a", "family": "Segoe UI, Arial, sans-serif"},
-                "size": 11,
-                "color": "#2a2a2a",
-                "family": "Segoe UI, Arial, sans-serif",
-            },
             hoverongaps=False,
-            hovertemplate=(
+            hovertemplate="<b>%{y}</b><br>Byte %{x}: %{z:.2f} bits<extra></extra>",
-                "<b>%{y}</b><br>"
-                "Byte %{x}: %{z:.2f} bits<extra></extra>"
-            ),
             colorbar=dict(
-                title=dict(
+                title=dict(text="Entropy (bits)", side="top", font=dict(size=13, color="#1a1a1a")),
-                    text="Entropy (bits)",
+                orientation="h", thickness=15, len=0.35,
-                    side="top",
+                x=1.0, xanchor="right", y=1.02, yanchor="bottom",
-                    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",
+                tickformat=".1f", outlinewidth=0.5, outlinecolor="#cccccc",
-                outlinewidth=0.5,
-                outlinecolor="#cccccc",
             ),
         )
     )
 
     fig.update_layout(
-        title=dict(
+        title=dict(text=title, font=dict(size=20, color="#1a1a1a"), x=0.5, xanchor="center", pad=dict(b=20)),
-            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",
+            side="top", dtick=1, showgrid=False, linecolor="#bdbdbd",
-            dtick=1,
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc",
-            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",
+            autorange="reversed", showgrid=False, linecolor="#bdbdbd",
-            showgrid=False,
+            tickfont=dict(size=12, color="#2a2a2a"), ticks="outside", ticklen=4, tickcolor="#cccccc", automargin=True,
-            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(
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor="#cccccc"),
-            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(
+    parser = argparse.ArgumentParser(description="Analyze CAN bus byte-level entropy")
-        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(
+    parser.add_argument("title", nargs="?", default="CAN Bus Byte-Level Entropy")
-        "input", type=Path, help="Path to the input CAN log file"
-    )
-    parser.add_argument(
-        "output",
-        type=Path,
-        nargs="?",
-        default=Path("entropy_report.html"),
-        help="Path to the output HTML report",
-    )
-    parser.add_argument(
-        "title",
-        nargs="?",
-        default="CAN Bus Byte-Level Entropy",
-        help="Title for the HTML report",
-    )
     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,

stat/frequency.py

@@ -4,52 +4,57 @@
 
 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 _format_can_id(x):
+def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    """Safely cleans CAN ID strings without altering their length or value."""
+    s = s.astype('string').str.strip()
-    if pd.isna(x):
+    s = s.str.replace(r'^0x', '', case=False, regex=True)
-        return "UNKNOWN"
+    s = s.str.upper()
-
+    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
-    s = str(x).strip()
-    if not s:
-        return "UNKNOWN"
-
-    if s.lower().startswith('0x'):
-        s = s[2:]
-
-    return s.upper()
 
 def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
-    """Calculates frequency counts and percentages for identifiers."""
     can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    formatted = _format_can_id_vec(df[can_id_col])
+    df['Formatted_ID'] = formatted
 
-    df['Formatted_ID'] = df[can_id_col].apply(_format_can_id)
+    counts = formatted.value_counts()
-
+    freq_df = pd.DataFrame({
-    freq_df = df['Formatted_ID'].value_counts().reset_index()
+        'Identifier': counts.index,
-    freq_df.columns = ['Identifier', 'Count']
+        'Count': counts.to_numpy(),
-
+    })
-    total = freq_df['Count'].sum()
+    total = counts.sum()
-    freq_df['Percentage'] = (freq_df['Count'] / total * 100).round(2)
+    freq_df['Percentage'] = np.round(freq_df['Count'] / total * 100, 2) if total else 0.0
-    return freq_df.sort_values('Count', ascending=True)
+    return freq_df.sort_values('Count', ascending=True).reset_index(drop=True)
 
 def plot_frequency(stats_df: pd.DataFrame, title: str) -> go.Figure:
-    """Generates interactive horizontal bar chart with log x-axis."""
+    n = len(stats_df)
-    fig = px.bar(
+    fig = go.Figure(go.Bar(
-        stats_df, y='Identifier', x='Count', orientation='h', title=title, log_x=True,
+        y=stats_df['Identifier'],
-        labels={'Identifier': 'PGN / CAN ID', 'Count': 'Message Count'},
+        x=stats_df['Count'],
-        color='Count', color_continuous_scale='Turbo',
+        orientation='h',
-        range_color=(stats_df['Count'].min(), stats_df['Count'].max()),
+        marker=dict(
-        hover_data={'Percentage': ':.2f', 'Count': ':,', 'Identifier': True}
+            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,
+    ))
+
     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,
@@ -69,11 +74,10 @@ def plot_frequency(stats_df: pd.DataFrame, title: str) -> go.Figure:
             ticklen=4,
             tickcolor="#cccccc",
             automargin=True,
-            type='category'
+            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(
@@ -87,39 +91,27 @@ def plot_frequency(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="Frequency", help="Title for the HTML report")
+    parser.add_argument("title", nargs="?", default="Frequency")
     args = parser.parse_args()
 
     df = load_data(args.input)
@@ -130,6 +122,6 @@ if __name__ == "__main__":
         '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)

stat/id_viewer.py

@@ -1,75 +1,64 @@
+# File: id_viewer.py
+# Copyright (C) 2026 Erick Ahmed
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
 import argparse
 from pathlib import Path
+import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 from utils.extractor import load_data
 
-def _format_can_id(x):
+def _format_can_id_vec(s: pd.Series) -> pd.Series:
-    if pd.isna(x):
+    s = s.astype('string').str.strip()
-        return "UNKNOWN"
+    s = s.str.replace(r'^0x', '', case=False, regex=True)
-    s = str(x).strip()
+    s = s.str.upper()
-    if not s:
+    return s.fillna('UNKNOWN').replace('', 'UNKNOWN')
-        return "UNKNOWN"
-    if s.lower().startswith('0x'):
-        s = s[2:]
-    return s.upper()
 
 def prepare_data(df, target_id):
     can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
-    df['Formatted_ID'] = df[can_id_col].apply(_format_can_id)
+    formatted = _format_can_id_vec(df[can_id_col])
-    target_id_clean = _format_can_id(target_id)
+    df = df.assign(Formatted_ID=formatted)
-    filtered = df[df['Formatted_ID'] == target_id_clean].copy()
+    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
 
-    byte_cols = [f"b{i}" for i in range(8)]
     for col in byte_cols:
-        filtered[col] = pd.to_numeric(
+        if not pd.api.types.is_numeric_dtype(filtered[col]):
-            filtered[col].apply(lambda x: int(x, 16) if pd.notna(x) else None),
+            filtered = filtered.assign(**{col: pd.to_numeric(filtered[col], errors='coerce').astype('float32')})
-            errors='coerce'
-        )
 
-    filtered = filtered.sort_values('Timestamp')
+    filtered = filtered.sort_values('Timestamp', kind='stable')
-    mask = (filtered[byte_cols] != filtered[byte_cols].shift()).any(axis=1)
+    arr = filtered[byte_cols].to_numpy(dtype=np.float32, copy=False)
-    filtered = filtered[mask]
+    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, byte_cols, can_id, title):
     fig = go.Figure()
-
     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):
-        fig.add_trace(go.Scatter(
+        y = df[col].to_numpy(dtype=np.float32, copy=False) if not df.empty else np.array([])
-            x=[None], y=[None],
+        fig.add_trace(go.Scattergl(
-            mode='markers',
+            x=x,
-            marker=dict(symbol='square', size=10, color=colors[i]),
+            y=y,
-            name=col.upper(),
-            showlegend=True,
-            legendgroup=col.upper(),
-            hoverinfo='skip'
-        ))
-        fig.add_trace(go.Scatter(
-            x=df['Timestamp'],
-            y=df[col],
             mode='lines',
-            line=dict(shape='hv', width=2, color=colors[i]),
+            line=dict(shape='hv', width=2, color=colors[i % len(colors)]),
             name=col.upper(),
-            showlegend=False,
             legendgroup=col.upper(),
-            hovertemplate=f"<b>{col.upper()}</b><br>Time: %{{x}}<br>Value: %{{y}}<extra></extra>"
+            hovertemplate=f"<b>{col.upper()}</b><br>Time: %{{x}}<br>Value: %{{y}}<extra></extra>",
         ))
 
-    all_button = dict(
+    all_button = dict(label='ALL', method='restyle', args=[{'visible': [True] * n}])
-        label='ALL',
+    none_button = dict(label='NONE', method='restyle', args=[{'visible': ['legendonly'] * n}])
-        method='restyle',
-        args=[{'visible': [True] * 16}]
-    )
-
-    none_button = dict(
-        label='NONE',
-        method='restyle',
-        args=[{'visible': ['legendonly'] * 16}]
-    )
 
     fig.update_layout(
         height=600,
@@ -79,19 +68,15 @@ def plot_bits(df, byte_cols, can_id, title):
             text=f"{title} - ID: {can_id}",
             font=dict(size=20, color='#1a1a1a'),
             x=0.5, xanchor='center',
-            pad=dict(b=20)
+            pad=dict(b=20),
         ),
         font=dict(family="Segoe UI, Arial, sans-serif", size=12, color='#2a2a2a'),
-        hoverlabel=dict(
+        hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI", bordercolor='#cccccc'),
-            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,
+            x=0.5, xanchor='center',
-            xanchor='center',
+            y=-0.18, yanchor='top',
-            y=-0.18,
-            yanchor='top',
             title=None,
             bgcolor='white',
             bordercolor='#cccccc',
@@ -99,7 +84,7 @@ def plot_bits(df, byte_cols, can_id, title):
             font=dict(size=12, color="#2a2a2a"),
             itemsizing='constant',
             itemclick='toggle',
-            itemdoubleclick='toggleothers'
+            itemdoubleclick='toggleothers',
         ),
         xaxis=dict(
             title=dict(text="Timestamp", font=dict(size=13, color="#1a1a1a")),
@@ -107,41 +92,38 @@ def plot_bits(df, byte_cols, can_id, title):
             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)
+            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"
+            ticks="outside", ticklen=4, tickcolor="#cccccc",
         ),
         updatemenus=[
             dict(
                 type='buttons',
                 direction='right',
-                x=0.5,
+                x=0.5, xanchor='center',
-                xanchor='center',
+                y=-0.06, yanchor='top',
-                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)
+                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"), help="Path to the output HTML report")
+    parser.add_argument("output", type=Path, nargs="?", default=Path("bits_report.html"))
-    parser.add_argument("title", nargs="?", default="Byte Visualization", help="Title for the HTML report")
+    parser.add_argument("title", nargs="?", default="Byte Visualization")
     args = parser.parse_args()
 
     df = load_data(args.input)
@@ -153,6 +135,6 @@ if __name__ == "__main__":
         '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)

stat/utils/extractor.py

@@ -7,9 +7,9 @@ from pathlib import Path
 
 import numpy as np
 import pandas as pd
+import polars as pl
 
 def to_int(x):
-    """Convert a hex string or integer to int, returning NaN on failure."""
     if isinstance(x, (int, np.integer)):
         return int(x)
     if isinstance(x, str):
@@ -20,7 +20,6 @@ def to_int(x):
     return np.nan
 
 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']}"
@@ -34,7 +33,31 @@ def extract_id(row: pd.Series) -> str:
     return f"ID: {row['ID']}"
 
 def load_data(file_path: Path) -> pd.DataFrame:
-    """Loads Parquet file and adds an Identifier column."""
+    lf = pl.scan_parquet(file_path)
-    df = pd.read_parquet(file_path)
+    schema = lf.collect_schema()
-    df['Identifier'] = df.apply(extract_id, axis=1)
+    names = schema.names()
-    return df
+
+    byte_cols = [f"b{i}" for i in range(8) if f"b{i}" in names]
+    if byte_cols:
+        lf = lf.with_columns([
+            pl.col(c).str.to_integer(base=16, strict=False).cast(pl.Int16).alias(c)
+            for c in byte_cols
+        ])
+
+    id_col = 'ID' if 'ID' in names else 'Identifier'
+    id_expr = pl.col(id_col).cast(pl.Utf8)
+
+    if 'j1939_metadata' in names:
+        try:
+            lf = lf.with_columns(
+                pl.when(pl.col('j1939_metadata').is_not_null())
+                .then(pl.lit('PGN: ') + pl.col('j1939_metadata').struct.field('PGN').cast(pl.Utf8))
+                .otherwise(pl.lit('ID: ') + id_expr)
+                .alias('Identifier')
+            )
+        except Exception:
+            lf = lf.with_columns((pl.lit('ID: ') + id_expr).alias('Identifier'))
+    else:
+        lf = lf.with_columns((pl.lit('ID: ') + id_expr).alias('Identifier'))
+
+    return lf.collect().to_pandas()