Normalize CAN IDs to strictly match same number of bit

stat/correlation.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
 import argparse
+import numbers
 from pathlib import Path
 
 import numpy as np
@@ -12,6 +13,21 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
+def _format_can_id(x):
+    if pd.isna(x):
+        return "UNKNOWN"
+    if isinstance(x, numbers.Number):
+        return f"{int(x):08X}"
+    s = str(x).strip()
+    if s.lower().startswith('0x'):
+        s = s[2:]
+    if s.isdigit():
+        return f"{int(s):08X}"
+    try:
+        return f"{int(s, 16):08X}"
+    except ValueError:
+        return s
+
 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)]
@@ -20,12 +36,18 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
     if not available_cols:
         raise ValueError("No byte columns (b0-b7) found in the DataFrame")
 
-    df_bytes = df[["Identifier"] + available_cols].copy()
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    identifiers = df[can_id_col].apply(_format_can_id)
+
+    if target_id is not None:
+        target_id = _format_can_id(target_id)
+
+    df_bytes = df[available_cols].copy()
     for col in available_cols:
         df_bytes[col] = df_bytes[col].apply(to_int)
 
-    if target_id:
-        group = df_bytes[df_bytes["Identifier"] == target_id]
+    if target_id is not None:
+        group = df_bytes[identifiers == target_id]
         if group.empty:
             raise ValueError(f"Identifier '{target_id}' not found in data")
         return group[available_cols].corr(method=method).fillna(0.0)
@@ -35,7 +57,9 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
         np.fill_diagonal(corr_arr, 0.0)
         return pd.Series(corr_arr.max(axis=0), index=group.columns).fillna(0.0)
 
-    return df_bytes.groupby("Identifier")[available_cols].apply(max_abs_corr)
+    result = df_bytes.groupby(identifiers)[available_cols].apply(max_abs_corr)
+    result.index.name = 'Identifier'
+    return result
 
 
 def plot_correlation_heatmap(corr_df: pd.DataFrame, target_id: str | None, title: str) -> go.Figure:

stat/entropy.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
 import argparse
+import numbers
 from pathlib import Path
 
 import numpy as np
@@ -12,6 +13,21 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
+def _format_can_id(x):
+    if pd.isna(x):
+        return "UNKNOWN"
+    if isinstance(x, numbers.Number):
+        return f"{int(x):08X}"
+    s = str(x).strip()
+    if s.lower().startswith('0x'):
+        s = s[2:]
+    if s.isdigit():
+        return f"{int(s):08X}"
+    try:
+        return f"{int(s, 16):08X}"
+    except ValueError:
+        return s
+
 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)]
@@ -19,6 +35,9 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     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)
+
     df_bytes = df[available_cols].copy()
     for col in available_cols:
         df_bytes[col] = df_bytes[col].apply(to_int)
@@ -30,8 +49,9 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
         p = s.value_counts(normalize=True)
         return -np.sum(p * np.log2(p))
 
-    return df.groupby("Identifier")[available_cols].agg(entropy)
-
+    result = df_bytes.groupby(identifiers).agg(entropy)
+    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."""
@@ -131,7 +151,6 @@ def plot_entropy_heatmap(entropy_df: pd.DataFrame, title: str) -> go.Figure:
     )
     return fig
 
-
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="Analyze CAN bus byte-level entropy"

stat/frequency.py

@@ -3,21 +3,46 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
 import argparse
+import numbers
 from pathlib import Path
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
 from utils.extractor import load_data
 
-def calc_freq(df: pd.DataFrame) -> pd.DataFrame:
+def calculate_frequency(df: pd.DataFrame) -> pd.DataFrame:
     """Calculates frequency counts and percentages for identifiers."""
-    freq_df = df['Identifier'].value_counts().reset_index()
+
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+
+    def format_can_id(x):
+        if pd.isna(x):
+            return "UNKNOWN"
+        if isinstance(x, numbers.Number):
+            return f"{int(x):08X}"
+        s = str(x).strip()
+        if s.lower().startswith('0x'):
+            s = s[2:]
+        if s.isdigit():
+            return f"{int(s):08X}"
+        try:
+            return f"{int(s, 16):08X}"
+        except ValueError:
+            return s
+
+    raw_ids = df[can_id_col]
+    formatted_ids = raw_ids.apply(format_can_id)
+
+    freq_df = formatted_ids.value_counts().reset_index()
+
     freq_df.columns = ['Identifier', 'Count']
+
     total = freq_df['Count'].sum()
     freq_df['Percentage'] = (freq_df['Count'] / total * 100).round(2)
+
     return freq_df.sort_values('Count', ascending=True)
 
-def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
+def plot_frequency(stats_df: pd.DataFrame, title: str) -> go.Figure:
     """Generates interactive horizontal bar chart with log x-axis."""
     fig = px.bar(
         stats_df, y='Identifier', x='Count', orientation='h', title=title, log_x=True,
@@ -43,7 +68,6 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
         ),
         yaxis=dict(
             title=dict(text="PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
-            #autorange="",
             showgrid=False,
             linecolor="#bdbdbd",
             tickfont=dict(size=12, color="#2a2a2a"),
@@ -51,6 +75,7 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
             ticklen=4,
             tickcolor="#cccccc",
             automargin=True,
+            type='category' # Force categorical axis to ensure every ID gets a tick
         ),
         font=dict(family="Segoe UI, Arial, sans-serif", size=12, color='#2a2a2a'),
         hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI",
@@ -104,8 +129,8 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     df = load_data(args.input)
-    stats = calc_freq(df)
-    fig = plot_freq(stats, title=args.title)
+    stats = calculate_frequency(df)
+    fig = plot_frequency(stats, title=args.title)
     config = {
         'responsive': True,
         'displaylogo': False,