feathr-ai · hangfei · Jun 14, 2022 · Jun 11, 2022 · Jun 11, 2022 · Jun 11, 2022
diff --git a/docs/images/product_recommendation.jpg b/docs/images/product_recommendation.jpg
diff --git a/docs/images/product_recommendation_advanced.jpg b/docs/images/product_recommendation_advanced.jpg
diff --git a/feathr_project/feathr/udf/_preprocessing_pyudf_manager.py b/feathr_project/feathr/udf/_preprocessing_pyudf_manager.py
@@ -52,7 +52,7 @@ def build_anchor_preprocessing_metadata(anchor_list, local_workspace_dir):
                     feature_names_to_func_mapping[string_feature_list] = _PreprocessingPyudfManager._parse_function_str_for_name(anchor.source.preprocessing)
                 else:
                     # it's a callable function
-                    feature_names_to_func_mapping[string_feature_list] = anchor.source.preprocessing.__name__ 
+                    feature_names_to_func_mapping[string_feature_list] = anchor.source.preprocessing.__name__
 
         if not features_with_preprocessing:
             return
@@ -87,9 +87,9 @@ def _parse_function_str_for_name(source: str) -> str:
 
     @staticmethod
     def persist_pyspark_udf_to_file(user_func, local_workspace_dir):
-        """persist the pyspark UDF to a file in `local_workspace_dir` for later usage. 
-        The user_func could be either a string that represents a function body, or a callable object. 
-        The reason being - if we are defining a regular Python function, it will be a callable object; 
+        """persist the pyspark UDF to a file in `local_workspace_dir` for later usage.
+        The user_func could be either a string that represents a function body, or a callable object.
+        The reason being - if we are defining a regular Python function, it will be a callable object;
         however if we reterive features from registry, the current implementation is to use plain strings to store the function body. In that case, the user_fuc will be string.
         """
         if isinstance(user_func, str):

diff --git a/...t3storage.dfs.core.windows.net/product_recommendation_sample/product_detail_mock_data.csv b/...t3storage.dfs.core.windows.net/product_recommendation_sample/product_detail_mock_data.csv
@@ -0,0 +1,11 @@
+product_id,category,price,quantity,recent_sold,made_in_state,discount
+1,1,22,100,0,CA,7.5
+2,2,17,300,1,CA,7.5
+3,1,40,0,2,WA,7.5
+4,1,25,100,3,WA,7.5
+5,1,33,0,2,PA,0
+6,2,19,0,2,CA,7.5
+7,2,22,200,1,WA,7.5
+8,2,59,300,0,PA,8.5
+9,0,80,100,1,WA,8.5
+10,0,39,100,0,WA,7.5
diff --git a/...storage.dfs.core.windows.net/product_recommendation_sample/user_observation_mock_data.csv b/...storage.dfs.core.windows.net/product_recommendation_sample/user_observation_mock_data.csv
@@ -1,11 +1,35 @@
-user_id,event_timestamp,product_rating
-1,2021-04-01,4
-2,2021-04-01,5
-3,2021-04-01,5
-4,2021-04-01,1
-5,2021-04-01,5
-6,2021-04-01,2
-7,2021-04-01,5
-8,2021-04-01,2
-9,2021-04-01,5
-10,2021-04-01,3
+user_id,product_id,event_timestamp,product_rating
+1,1,2021-04-01,4
+1,2,2021-04-01,4
+1,3,2021-04-01,4
+1,4,2021-04-01,4
+1,5,2021-04-01,4
+2,1,2021-04-01,5
+2,2,2021-04-01,5
+2,3,2021-04-01,5
+2,4,2021-04-01,5
+2,5,2021-04-01,5
+3,1,2021-04-01,5
+3,2,2021-04-01,5
+3,3,2021-04-01,5
+3,4,2021-04-01,5
+3,5,2021-04-01,5
+4,1,2021-04-01,1
+4,2,2021-04-01,1
+4,3,2021-04-01,1
+4,4,2021-04-01,1
+4,5,2021-04-01,1
+5,1,2021-04-01,5
+5,2,2021-04-01,5
+6,1,2021-04-01,2
+7,1,2021-04-01,5
+7,2,2021-04-01,5
+7,3,2021-04-01,5
+8,1,2021-04-01,2
+8,2,2021-04-01,2
+8,3,2021-04-01,2
+9,1,2021-04-01,5
+9,2,2021-04-01,5
+9,3,2021-04-01,5
+9,4,2021-04-01,5
+10,1,2021-04-01,3