[SPARK-48650][PYTHON] Display correct call site from IPython Notebook

python/pyspark/errors/utils.py

@@ -165,8 +165,34 @@ def _capture_call_site(spark_session: "SparkSession", depth: int) -> str:
     in the user code that led to the error.
     """
     stack = list(reversed(inspect.stack()))
+    ipython = None
+
+    # We try import here since IPython is not a required dependency
+    try:
+        from IPython import get_ipython
+
+        ipython = get_ipython()
+    except ImportError:
+        pass
+
+    if ipython:
+        import pyspark
+
+        # Filtering out PySpark code and keeping user code only
+        pyspark_root = os.path.dirname(pyspark.__file__)
+        stack = [
+            frame_info for frame_info in inspect.stack() if pyspark_root not in frame_info.filename
+        ]
+
     selected_frames = stack[:depth]
-    call_sites = [f"{frame.filename}:{frame.lineno}" for frame in selected_frames]
+
+    # Identifying the cell is useful when the error is generated from IPython Notebook
+    if ipython:
+        call_sites = [
+            f"line {frame.lineno} in cell [{ipython.execution_count}]" for frame in selected_frames
+        ]
+    else:
+        call_sites = [f"{frame.filename}:{frame.lineno}" for frame in selected_frames]
     call_sites_str = "\n".join(call_sites)
 
     return call_sites_str