From c98563f5418f43a57c58a4619d2de700986d3f19 Mon Sep 17 00:00:00 2001
From: Erick Ahmed <engineering@erickahmed.com>
Date: Wed, 15 Jul 2026 00:48:30 +0200
Subject: [PATCH] Fix schema check and update import paths

- Use `collect_schema` for accurate column validation in Polars and
  correct
  relative import paths for statistical modules.
---
 parser.py            | 2 +-
 stats/correlation.py | 4 ++--
 stats/entropy.py     | 4 ++--
 stats/frequency.py   | 2 +-
 stats/id_viewer.py   | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/parser.py b/parser.py
index ad7fc32..1d84f6e 100644
--- a/parser.py
+++ b/parser.py
@@ -77,7 +77,7 @@ def parse_csv(csv_path: PathLike) -> pl.LazyFrame:
     """
     lf = pl.scan_csv(csv_path, schema_overrides={"ID": pl.String, "Data": pl.String})
 
-    if "Timestamp" not in lf.columns:
+    if "Timestamp" not in lf.collect_schema().names():
         lf = lf.with_row_index("Timestamp")
 
     byte_exprs = []
diff --git a/stats/correlation.py b/stats/correlation.py
index 1c232d7..d8a9811 100644
--- a/stats/correlation.py
+++ b/stats/correlation.py
@@ -9,8 +9,8 @@ import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from utils.extractor import load_data
-from utils.extractor import to_int
+from stats.utils.extractor import load_data
+from stats.utils.extractor import to_int
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
diff --git a/stats/entropy.py b/stats/entropy.py
index 51240e2..11d053b 100644
--- a/stats/entropy.py
+++ b/stats/entropy.py
@@ -9,8 +9,8 @@ import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
 
-from utils.extractor import load_data
-from utils.extractor import to_int
+from stats.utils.extractor import load_data
+from stats.utils.extractor import to_int
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
diff --git a/stats/frequency.py b/stats/frequency.py
index 1e8981b..0db6b30 100644
--- a/stats/frequency.py
+++ b/stats/frequency.py
@@ -7,7 +7,7 @@ from pathlib import Path
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from utils.extractor import load_data
+from stats.utils.extractor import load_data
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()
diff --git a/stats/id_viewer.py b/stats/id_viewer.py
index 273a041..59f00ac 100644
--- a/stats/id_viewer.py
+++ b/stats/id_viewer.py
@@ -7,7 +7,7 @@ from pathlib import Path
 import numpy as np
 import pandas as pd
 import plotly.graph_objects as go
-from utils.extractor import load_data
+from stats.utils.extractor import load_data
 
 def _format_can_id_vec(s: pd.Series) -> pd.Series:
     s = s.astype('string').str.strip()