Remove leftovers

Reviewed-on: erickahmed/CANveyor#2

stat/entropy.py

@@ -0,0 +1,180 @@
+# File: entropy.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 _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):
+        try:
+            return int(x, 16)
+        except ValueError:
+            return np.nan
+    return np.nan
+
+
+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)]
+    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")
+
+    df_bytes = df[available_cols].copy()
+    for col in available_cols:
+        df_bytes[col] = df_bytes[col].apply(_to_int)
+
+    def entropy(s: pd.Series) -> float:
+        s = s.dropna()
+        if s.empty:
+            return 0.0
+        p = s.value_counts(normalize=True)
+        return -np.sum(p * np.log2(p))
+
+    return df.groupby("Identifier")[available_cols].agg(entropy)
+
+
+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,
+            x=x,
+            y=y,
+            colorscale=[
+                [0.0, "#ffffff"],
+                [0.15, "#fff7ec"],
+                [0.35, "#fee8c8"],
+                [0.55, "#fdd49e"],
+                [0.75, "#fdbb84"],
+                [1.0, "#ef6548"],
+            ],
+            xgap=3,
+            ygap=3,
+            text=np.round(z, 2),
+            texttemplate="%{text}",
+            textfont={
+                "size": 11,
+                "color": "#2a2a2a",
+                "family": "Segoe UI, Arial, sans-serif",
+            },
+            hoverongaps=False,
+            hovertemplate=(
+                "<b>%{y}</b><br>"
+                "Byte %{x}: %{z:.2f} bits<extra></extra>"
+            ),
+            colorbar=dict(
+                title=dict(
+                    text="Entropy (bits)",
+                    side="top",
+                    font=dict(size=13, color="#1a1a1a"),
+                ),
+                orientation="h",
+                thickness=15,
+                len=0.35,
+                x=1.0,
+                xanchor="right",
+                y=1.02,
+                yanchor="bottom",
+                tickfont=dict(size=11, color="#2a2a2a"),
+                tickformat=".1f",
+                outlinewidth=0.5,
+                outlinecolor="#cccccc",
+            ),
+        )
+    )
+
+    fig.update_layout(
+        title=dict(
+            text=title,
+            font=dict(size=20, color="#1a1a1a"),
+            x=0.5,
+            xanchor="center",
+            pad=dict(b=20),
+        ),
+        height=max(600, len(y) * 28 + 150),
+        autosize=True,
+        template="plotly_white",
+        xaxis=dict(
+            title=dict(text="Byte Position", font=dict(size=13, color="#1a1a1a")),
+            side="top",
+            dtick=1,
+            showgrid=False,
+            linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"),
+            ticks="outside",
+            ticklen=4,
+            tickcolor="#cccccc",
+        ),
+        yaxis=dict(
+            title=dict(text="PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
+            autorange="reversed",
+            showgrid=False,
+            linecolor="#bdbdbd",
+            tickfont=dict(size=12, color="#2a2a2a"),
+            ticks="outside",
+            ticklen=4,
+            tickcolor="#cccccc",
+            automargin=True,
+        ),
+        font=dict(family="Segoe UI, Arial, sans-serif", size=12, color="#2a2a2a"),
+        hoverlabel=dict(
+            bgcolor="white",
+            font_size=13,
+            font_family="Segoe UI",
+            bordercolor="#cccccc",
+        ),
+        margin=dict(l=200, r=40, t=120, b=60),
+    )
+    return fig
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Analyze CAN bus byte-level entropy"
+    )
+    parser.add_argument(
+        "input", type=Path, help="Path to the input CAN log file"
+    )
+    parser.add_argument(
+        "output",
+        type=Path,
+        nargs="?",
+        default=Path("entropy_report.html"),
+        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,
+        "scrollZoom": True,
+        "modeBarButtonsToAdd": ["toggleSpikelines"],
+        "toImageButtonOptions": {"format": "png", "scale": 2},
+    }
+    fig.write_html(str(args.output), include_plotlyjs="cdn", config=config)

utils/extractor.py

@@ -1,27 +0,0 @@
-# File: extractor.py
-# Copyright (C) 2026 Erick Ahmed
-# SPDX-License-Identifier: AGPL-3.0-or-later
-
-import json
-from pathlib import Path
-import pandas as pd
-
-def extract_id(row: pd.Series) -> str:
-    """Extracts PGN from metadata or falls back to CAN ID."""
-    meta = row.get('j1939_metadata')
-    if pd.isna(meta):
-        return f"ID: {row['ID']}"
-    if isinstance(meta, str):
-        try:
-            meta = json.loads(meta)
-        except json.JSONDecodeError:
-            return f"ID: {row['ID']}"
-    if isinstance(meta, dict) and 'PGN' in meta:
-        return f"PGN: {meta['PGN']}"
-    return f"ID: {row['ID']}"
-
-def load_data(file_path: Path) -> pd.DataFrame:
-    """Loads Parquet file and adds an Identifier column."""
-    df = pd.read_parquet(file_path)
-    df['Identifier'] = df.apply(extract_id, axis=1)
-    return df