Minor fixes

aligned/retrival_job.py

@@ -654,6 +654,8 @@ def fill_missing_columns(self) -> RetrivalJob:
         return FillMissingColumnsJob(self)
 
     def rename(self, mappings: dict[str, str]) -> RetrivalJob:
+        if not mappings:
+            return self
         return RenameJob(self, mappings)
 
     def drop_duplicate_entities(self) -> RetrivalJob:

aligned/schemas/feature_view.py

@@ -316,6 +316,7 @@ def __hash__(self) -> int:
 class FeatureViewReferenceSource(BatchDataSource):
 
     view: CompiledFeatureView
+    renames: dict[str, str] = field(default_factory=dict)
 
     type_name = 'view_ref'
 
@@ -373,7 +374,7 @@ def multi_source_features_for(
         else:
             available_features = sub_job.derive_features([request])
 
-        return FileFactualJob(available_features, [request], facts)
+        return FileFactualJob(available_features, [request], facts).rename(source.renames)
 
     def all_data(self, request: RetrivalRequest, limit: int | None) -> RetrivalJob:
         sub_source = self.view.materialized_source or self.view.source
@@ -382,9 +383,11 @@ def all_data(self, request: RetrivalRequest, limit: int | None) -> RetrivalJob:
 
         core_job = sub_source.all_data(sub_req, limit=limit)
         if request.aggregated_features:
-            return core_job.aggregate(request).derive_features([request])
+            job = core_job.aggregate(request)
         else:
-            return core_job.derive_features().derive_features([request])
+            job = core_job.derive_features()
+
+        return job.derive_features([request]).rename(self.renames)
 
     def all_between_dates(
         self, request: RetrivalRequest, start_date: datetime, end_date: datetime
@@ -395,9 +398,10 @@ def all_between_dates(
 
         core_job = sub_source.all_between_dates(sub_req, start_date, end_date)
         if request.aggregated_features:
-            return core_job.aggregate(request).derive_features([request])
+            job = core_job.aggregate(request)
         else:
-            return core_job.derive_features().derive_features([request])
+            job = core_job.derive_features()
+        return job.derive_features([request]).rename(self.renames)
 
     def depends_on(self) -> set[FeatureLocation]:
         return {FeatureLocation.feature_view(self.view.name)}

aligned/schemas/text_vectoriser.py

@@ -275,11 +275,9 @@ async def load_model(self):
     async def vectorise_polars(self, texts: pl.LazyFrame, text_key: str, output_key: str) -> pl.LazyFrame:
         if self.loaded_model is None:
             await self.load_model()
-        return texts.with_columns(
-            pl.Series(
-                self.loaded_model.encode(texts.select(pl.col(text_key)).collect().to_series().to_list())
-            ).alias(output_key)
-        )
+        return pl.Series(
+            self.loaded_model.encode(texts.select(pl.col(text_key)).collect().to_series().to_list())
+        ).alias(output_key)
 
     async def vectorise_pandas(self, texts: pd.Series) -> pd.Series:
         if self.loaded_model is None:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "aligned"
-version = "0.0.63"
+version = "0.0.64"
 description = "A data managment and lineage tool for ML applications."
 authors = ["Mats E. Mollestad <mats@mollestad.no>"]
 license = "Apache-2.0"

test_data/titanic-sets.json

@@ -1 +1 @@
-{"raw_data": [], "train_test": [], "train_test_validation": [{"id": "titanic_test", "name": null, "request_result": {"entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}, {"name": "in_domain", "values": ["male", "female"]}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 20.0}, {"name": "optional"}, {"name": "lower_bound_inc", "value": 0.0}]}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "upper_bound_inc", "value": 100.0}, {"name": "lower_bound_inc", "value": 0.0}]}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}], "event_timestamp": null}, "train_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-train.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "test_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-test.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "validation_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-validate.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "train_size_fraction": 0.6, "test_size_fraction": 0.20000000000000007, "validate_size_fraction": 0.19999999999999996, "target": ["survived"], "description": null, "tags": null}], "active_learning": []}
+{"raw_data": [], "train_test": [], "train_test_validation": [{"id": "titanic_test", "name": null, "request_result": {"entities": [{"name": "passenger_id", "dtype": {"name": "int32"}, "description": null, "tags": null, "constraints": null}], "features": [{"name": "has_siblings", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sibsp", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "int32"}}], "transformation": {"name": "not-equals", "dtype": {"name": "bool"}, "key": "sibsp", "value": {"name": "int", "value": 0}}, "depth": 1}, {"name": "is_female", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "female"}}, "depth": 1}, {"name": "is_male", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "sex", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "equals", "dtype": {"name": "bool"}, "key": "sex", "value": {"name": "string", "value": "male"}}, "depth": 1}, {"name": "name", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "sibsp", "dtype": {"name": "int32"}, "description": "Number of siblings on titanic", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 20.0}, {"name": "optional"}]}, {"name": "sex", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}, {"name": "in_domain", "values": ["male", "female"]}]}, {"name": "cabin", "dtype": {"name": "string"}, "description": null, "tags": null, "constraints": [{"name": "optional"}]}, {"name": "survived", "dtype": {"name": "bool"}, "description": "If the passenger survived", "tags": null, "constraints": null}, {"name": "is_mr", "dtype": {"name": "bool"}, "description": null, "tags": null, "constraints": null, "depending_on": [{"name": "name", "location": {"name": "titanic", "location": "feature_view"}, "dtype": {"name": "string"}}], "transformation": {"name": "contains", "dtype": {"name": "bool"}, "key": "name", "value": "Mr."}, "depth": 1}, {"name": "age", "dtype": {"name": "float"}, "description": "A float as some have decimals", "tags": null, "constraints": [{"name": "lower_bound_inc", "value": 0.0}, {"name": "upper_bound_inc", "value": 100.0}]}], "event_timestamp": null}, "train_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-train.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "test_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-test.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "validation_dataset": {"mapping_keys": {}, "type_name": "csv", "path": "test_data/titanic-validate.csv", "csv_config": {"seperator": ",", "compression": "infer", "should_write_index": false}}, "train_size_fraction": 0.6, "test_size_fraction": 0.20000000000000007, "validate_size_fraction": 0.19999999999999996, "target": ["survived"], "description": null, "tags": null}], "active_learning": []}

test_data/titanic-test.csv

@@ -1,21 +1,21 @@
-survived,has_siblings,sex,sibsp,is_male,name,passenger_id,is_mr,age,is_female,cabin
-False,False,male,0,True,"Sirayanian, Mr. Orsen",61,True,22.0,False,
-True,False,female,0,False,"Icard, Miss. Amelie",62,False,38.0,True,B28
-False,True,male,1,True,"Harris, Mr. Henry Birkhardt",63,True,45.0,False,C83
-False,True,male,3,True,"Skoog, Master. Harald",64,False,4.0,False,
-False,False,male,0,True,"Stewart, Mr. Albert A",65,True,,False,
-True,True,male,1,True,"Moubarek, Master. Gerios",66,False,,False,
-True,False,female,0,False,"Nye, Mrs. (Elizabeth Ramell)",67,True,29.0,True,F33
-False,False,male,0,True,"Crease, Mr. Ernest James",68,True,19.0,False,
-True,True,female,4,False,"Andersson, Miss. Erna Alexandra",69,False,17.0,True,
-False,True,male,2,True,"Kink, Mr. Vincenz",70,True,26.0,False,
-False,False,male,0,True,"Jenkin, Mr. Stephen Curnow",71,True,32.0,False,
-False,True,female,5,False,"Goodwin, Miss. Lillian Amy",72,False,16.0,True,
-False,False,male,0,True,"Hood, Mr. Ambrose Jr",73,True,21.0,False,
-False,True,male,1,True,"Chronopoulos, Mr. Apostolos",74,True,26.0,False,
-True,False,male,0,True,"Bing, Mr. Lee",75,True,32.0,False,
-False,False,male,0,True,"Moen, Mr. Sigurd Hansen",76,True,25.0,False,F G73
-False,False,male,0,True,"Staneff, Mr. Ivan",77,True,,False,
-False,False,male,0,True,"Moutal, Mr. Rahamin Haim",78,True,,False,
-True,False,male,0,True,"Caldwell, Master. Alden Gates",79,False,0.83,False,
-True,False,female,0,False,"Dowdell, Miss. Elizabeth",80,False,30.0,True,
+has_siblings,is_female,is_male,name,sibsp,sex,cabin,survived,is_mr,passenger_id,age
+False,False,True,"Sirayanian, Mr. Orsen",0,male,,False,True,61,22.0
+False,True,False,"Icard, Miss. Amelie",0,female,B28,True,False,62,38.0
+True,False,True,"Harris, Mr. Henry Birkhardt",1,male,C83,False,True,63,45.0
+True,False,True,"Skoog, Master. Harald",3,male,,False,False,64,4.0
+False,False,True,"Stewart, Mr. Albert A",0,male,,False,True,65,
+True,False,True,"Moubarek, Master. Gerios",1,male,,True,False,66,
+False,True,False,"Nye, Mrs. (Elizabeth Ramell)",0,female,F33,True,True,67,29.0
+False,False,True,"Crease, Mr. Ernest James",0,male,,False,True,68,19.0
+True,True,False,"Andersson, Miss. Erna Alexandra",4,female,,True,False,69,17.0
+True,False,True,"Kink, Mr. Vincenz",2,male,,False,True,70,26.0
+False,False,True,"Jenkin, Mr. Stephen Curnow",0,male,,False,True,71,32.0
+True,True,False,"Goodwin, Miss. Lillian Amy",5,female,,False,False,72,16.0
+False,False,True,"Hood, Mr. Ambrose Jr",0,male,,False,True,73,21.0
+True,False,True,"Chronopoulos, Mr. Apostolos",1,male,,False,True,74,26.0
+False,False,True,"Bing, Mr. Lee",0,male,,True,True,75,32.0
+False,False,True,"Moen, Mr. Sigurd Hansen",0,male,F G73,False,True,76,25.0
+False,False,True,"Staneff, Mr. Ivan",0,male,,False,True,77,
+False,False,True,"Moutal, Mr. Rahamin Haim",0,male,,False,True,78,
+False,False,True,"Caldwell, Master. Alden Gates",0,male,,True,False,79,0.83
+False,True,False,"Dowdell, Miss. Elizabeth",0,female,,True,False,80,30.0