Normalize CAN IDs number of bits

stat/frequency.py

@@ -9,10 +9,29 @@ import plotly.express as px
 import plotly.graph_objects as go
 from utils.extractor import load_data
 
+def _format_can_id(x):
+    """Safely cleans CAN ID strings without altering their length or value."""
+    if pd.isna(x):
+        return "UNKNOWN"
+
+    s = str(x).strip()
+    if not s:
+        return "UNKNOWN"
+
+    if s.lower().startswith('0x'):
+        s = s[2:]
+
+    return s.upper()
+
 def calc_freq(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'
+
+    df['Formatted_ID'] = df[can_id_col].apply(_format_can_id)
+
+    freq_df = df['Formatted_ID'].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)
@@ -43,7 +62,6 @@ 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 +69,7 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
             ticklen=4,
             tickcolor="#cccccc",
             automargin=True,
+            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",