From 96de1f540269f5595b2a2e10469dbdcc1c755fa7 Mon Sep 17 00:00:00 2001 From: Mayur Singal <39544459+ulixius9@users.noreply.github.com> Date: Fri, 9 Feb 2024 11:25:53 +0530 Subject: [PATCH] MINOR: Fix Sample Data Deserialization (#15079) --- .../metadata/profiler/processor/sample_data_handler.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/ingestion/src/metadata/profiler/processor/sample_data_handler.py b/ingestion/src/metadata/profiler/processor/sample_data_handler.py index 2536682a5d0..33bd65aca60 100644 --- a/ingestion/src/metadata/profiler/processor/sample_data_handler.py +++ b/ingestion/src/metadata/profiler/processor/sample_data_handler.py @@ -11,7 +11,7 @@ """ Profiler Processor Step """ - +import json import traceback from datetime import datetime from functools import singledispatch @@ -48,7 +48,11 @@ def upload_sample_data(data: TableData, profiler_interface: ProfilerInterface) - sample_storage_config = profiler_interface.storage_config if not sample_storage_config: return - df = pd.DataFrame(data=data.rows, columns=[i.__root__ for i in data.columns]) + deserialized_data = json.loads(data.json()) + df = pd.DataFrame( + data=deserialized_data.get("rows", []), + columns=[i.__root__ for i in data.columns], + ) pq_buffer = BytesIO() df.to_parquet(pq_buffer) object_key = _get_object_key(