From 1b06c6a30c8d6c0ee57f75f75ee6a436aa6c13a7 Mon Sep 17 00:00:00 2001
From: Mayuri Nehate <33225191+mayurinehate@users.noreply.github.com>
Date: Thu, 12 Oct 2023 00:31:42 +0530
Subject: [PATCH] fix(ingest/snowflake): fix sample fraction for very large
 tables (#8988)

---
 .../datahub/ingestion/source/snowflake/snowflake_profiler.py    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py
index 24275dcdff..8e18d85d6f 100644
--- a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py
+++ b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_profiler.py
@@ -86,7 +86,7 @@ class SnowflakeProfiler(GenericProfiler, SnowflakeCommonMixin):
             # Fixed-size sampling can be slower than equivalent fraction-based sampling
             # as per https://docs.snowflake.com/en/sql-reference/constructs/sample#performance-considerations
             sample_pc = 100 * self.config.profiling.sample_size / table.rows_count
-            custom_sql = f'select * from "{db_name}"."{schema_name}"."{table.name}" TABLESAMPLE ({sample_pc:.3f})'
+            custom_sql = f'select * from "{db_name}"."{schema_name}"."{table.name}" TABLESAMPLE ({sample_pc:.8f})'
         return {
             **super().get_batch_kwargs(table, schema_name, db_name),
             # Lowercase/Mixedcase table names in Snowflake do not work by default.