Merge pull request 'Implement Pearson and Spearman per-bit correleration' (#3) from dev-inter-byte-correlation into main
Reviewed-on: erickahmed/CANveyor#3
This commit was merged in pull request #3.
This commit is contained in:
@@ -0,0 +1,144 @@
|
||||
# File: correlation.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_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)]
|
||||
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[["Identifier"] + 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 group.empty:
|
||||
raise ValueError(f"Identifier '{target_id}' not found in data")
|
||||
return group[available_cols].corr(method=method).fillna(0.0)
|
||||
|
||||
def max_abs_corr(group: pd.DataFrame) -> pd.Series:
|
||||
corr_arr = np.abs(group.corr(method=method).to_numpy().copy())
|
||||
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)
|
||||
|
||||
|
||||
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
|
||||
|
||||
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 = [
|
||||
[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 = [
|
||||
[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(
|
||||
data=go.Heatmap(
|
||||
z=z, x=x, y=y,
|
||||
zmin=z_min, zmax=z_max,
|
||||
colorscale=colorscale,
|
||||
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=hover_template,
|
||||
colorbar=dict(
|
||||
title=dict(text="Correlation", 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) if not is_8x8 else 600,
|
||||
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",
|
||||
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")),
|
||||
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 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("title", nargs="?", default="CAN Bus Inter-Byte Correlation", help="Title for the HTML report")
|
||||
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.")
|
||||
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,
|
||||
"scrollZoom": True,
|
||||
"modeBarButtonsToAdd": ["toggleSpikelines"],
|
||||
"toImageButtonOptions": {"format": "png", "scale": 2},
|
||||
}
|
||||
fig.write_html(str(args.output), include_plotlyjs="cdn", config=config)
|
||||
+13
-4
@@ -1,11 +1,20 @@
|
||||
# File: extractor.py
|
||||
# Copyright (C) 2026 Erick Ahmed
|
||||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
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 extract_id(row: pd.Series) -> str:
|
||||
"""Extracts PGN from metadata or falls back to CAN ID."""
|
||||
meta = row.get('j1939_metadata')
|
||||
|
||||
Reference in New Issue
Block a user