pandas_profiling_extractor | ♻️ Refactoring code.

Signed-off-by: mgorsk1 <gorskimariusz13@gmail.com>
amundsen-io · May 18, 2021 · 60274d0 · 60274d0
1 parent ee55930
commit 60274d0
Showing 1 changed file with 7 additions and 4 deletions.
diff --git a/databuilder/README.md b/databuilder/README.md
@@ -1229,12 +1229,15 @@ from databuilder.job.job import DefaultJob
 from databuilder.loader.file_system_neo4j_csv_loader import FsNeo4jCSVLoader
 from databuilder.task.task import DefaultTask
 
+table_name = 'video_game_sales'
+schema_name = 'superset'
+
 # Load table contents to pandas dataframe
-db_uri = 'postgresql://superset:superset@localhost:5432/superset'
+db_uri = f'postgresql://superset:superset@localhost:5432/{schema_name}'
 engine = create_engine(db_uri, echo=True)
 
 df = pd.read_sql_table(
-    'video_game_sales',
+    table_name,
     con=engine
 )
 
@@ -1251,8 +1254,8 @@ dict_config = {
     f'loader.filesystem_csv_neo4j.{FsNeo4jCSVLoader.NODE_DIR_PATH}': f'{tmp_folder}/nodes',
     f'loader.filesystem_csv_neo4j.{FsNeo4jCSVLoader.RELATION_DIR_PATH}': f'{tmp_folder}/relationships',
     f'loader.filesystem_csv_neo4j.{FsNeo4jCSVLoader.SHOULD_DELETE_CREATED_DIR}': False,
-    'extractor.pandas_profiling.table_name': 'video_game_sales',
-    'extractor.pandas_profiling.schema_name': 'superset',
+    'extractor.pandas_profiling.table_name': table_name,
+    'extractor.pandas_profiling.schema_name': schema_name,
     'extractor.pandas_profiling.database_name': 'postgres',
     'extractor.pandas_profiling.cluster_name': 'dev',
     'extractor.pandas_profiling.file_path': report_file