This is an automated email from the ASF dual-hosted git repository. skrawcz pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/hamilton.git
commit a9cfd66efce413886635cde39e701bc4f18d6310 Author: Josh Markovic <[email protected]> AuthorDate: Thu Jan 8 15:45:58 2026 +0000 Enforce Ruff B905 --- contrib/docs/compile_docs.py | 2 +- .../hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py | 2 +- contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py | 2 +- examples/LLM_Workflows/modular_llm_stack/lancedb_module.py | 4 +++- examples/LLM_Workflows/modular_llm_stack/marqo_module.py | 2 +- examples/LLM_Workflows/modular_llm_stack/pinecone_module.py | 2 +- examples/LLM_Workflows/modular_llm_stack/qdrant_module.py | 2 +- examples/LLM_Workflows/modular_llm_stack/weaviate_module.py | 2 +- .../LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py | 4 +++- examples/due_date_probabilities/probability_estimation.py | 3 ++- hamilton/async_driver.py | 2 +- hamilton/experimental/decorators/parameterize_frame.py | 4 ++-- hamilton/function_modifiers/expanders.py | 4 +++- hamilton/plugins/h_kedro.py | 4 ++-- hamilton/plugins/h_openlineage.py | 1 + scripts/update_blogs_in_learning_resources.py | 2 +- tests/resources/test_driver_serde_mapper.py | 2 +- ui/backend/server/trackingserver_run_tracking/api.py | 2 +- 18 files changed, 27 insertions(+), 19 deletions(-) diff --git a/contrib/docs/compile_docs.py b/contrib/docs/compile_docs.py index b5503ec6..dd492d89 100644 --- a/contrib/docs/compile_docs.py +++ b/contrib/docs/compile_docs.py @@ -344,7 +344,7 @@ def _create_commit_file(df_path, single_df): os.makedirs(commit_path, exist_ok=True) with open(os.path.join(commit_path, "commit.txt"), "w") as f: for commit, ts in zip( - single_df["__init__.py"]["commit"], single_df["__init__.py"]["timestamp"] + single_df["__init__.py"]["commit"], single_df["__init__.py"]["timestamp"], strict=False ): f.write(f"[commit::{commit}][ts::{ts}]\n") diff --git a/contrib/hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py b/contrib/hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py index a038698d..fed60ce6 100644 --- a/contrib/hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py +++ b/contrib/hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py @@ -409,7 +409,7 @@ def _accuracy_and_se( threshold = threshold_thousandths / 1000 total = 0 correct = 0 - for cs, ls in zip(cosine_similarity, labeled_similarity): + for cs, ls in zip(cosine_similarity, labeled_similarity, strict=False): total += 1 if cs > threshold: prediction = 1 diff --git a/contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py b/contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py index 406a2a3a..606520b5 100644 --- a/contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py +++ b/contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py @@ -657,7 +657,7 @@ def hold_out_set_predictions( ) predictions.append(prediction) questions.append(tokenizer.decode(sample["input_ids"], skip_special_tokens=True)) - return list(zip(questions, predictions)) + return list(zip(questions, predictions, strict=False)) if __name__ == "__main__": diff --git a/examples/LLM_Workflows/modular_llm_stack/lancedb_module.py b/examples/LLM_Workflows/modular_llm_stack/lancedb_module.py index 573db8b6..befb74f7 100644 --- a/examples/LLM_Workflows/modular_llm_stack/lancedb_module.py +++ b/examples/LLM_Workflows/modular_llm_stack/lancedb_module.py @@ -68,7 +68,9 @@ def data_objects( assert len(ids) == len(titles) == len(text_contents) == len(embeddings) return [ dict(squad_id=id_, title=title, context=context, vector=embedding, **metadata) - for id_, title, context, embedding in zip(ids, titles, text_contents, embeddings) + for id_, title, context, embedding in zip( + ids, titles, text_contents, embeddings, strict=False + ) ] diff --git a/examples/LLM_Workflows/modular_llm_stack/marqo_module.py b/examples/LLM_Workflows/modular_llm_stack/marqo_module.py index e186f781..2c1bea0c 100644 --- a/examples/LLM_Workflows/modular_llm_stack/marqo_module.py +++ b/examples/LLM_Workflows/modular_llm_stack/marqo_module.py @@ -58,7 +58,7 @@ def data_objects( assert len(ids) == len(titles) == len(text_contents) return [ dict(_id=id, title=title, Description=text_content) - for id, title, text_content in zip(ids, titles, text_contents) + for id, title, text_content in zip(ids, titles, text_contents, strict=False) if id is not None and title is not None or text_content is not None ] diff --git a/examples/LLM_Workflows/modular_llm_stack/pinecone_module.py b/examples/LLM_Workflows/modular_llm_stack/pinecone_module.py index 38f4d3bf..29f8bacb 100644 --- a/examples/LLM_Workflows/modular_llm_stack/pinecone_module.py +++ b/examples/LLM_Workflows/modular_llm_stack/pinecone_module.py @@ -62,7 +62,7 @@ def data_objects( assert len(ids) == len(titles) == len(embeddings) properties = [dict(title=title, **metadata) for title in titles] embeddings = [x.tolist() for x in embeddings] - return list(zip(ids, embeddings, properties)) + return list(zip(ids, embeddings, properties, strict=False)) def push_to_vector_db( diff --git a/examples/LLM_Workflows/modular_llm_stack/qdrant_module.py b/examples/LLM_Workflows/modular_llm_stack/qdrant_module.py index 9856cb17..a05fc26f 100644 --- a/examples/LLM_Workflows/modular_llm_stack/qdrant_module.py +++ b/examples/LLM_Workflows/modular_llm_stack/qdrant_module.py @@ -59,7 +59,7 @@ def data_objects( ids = list(range(len(ids))) payloads = [ dict(id=_id, text_content=text_content, title=title, **metadata) - for _id, title, text_content in zip(ids, titles, text_contents) + for _id, title, text_content in zip(ids, titles, text_contents, strict=False) ] embeddings = [x.tolist() for x in embeddings] return dict(ids=ids, vectors=embeddings, payload=payloads) diff --git a/examples/LLM_Workflows/modular_llm_stack/weaviate_module.py b/examples/LLM_Workflows/modular_llm_stack/weaviate_module.py index 3a723588..ed31145e 100644 --- a/examples/LLM_Workflows/modular_llm_stack/weaviate_module.py +++ b/examples/LLM_Workflows/modular_llm_stack/weaviate_module.py @@ -86,7 +86,7 @@ def data_objects( assert len(ids) == len(titles) == len(text_contents) return [ dict(squad_id=id_, title=title, context=context, **metadata) - for id_, title, context in zip(ids, titles, text_contents) + for id_, title, context in zip(ids, titles, text_contents, strict=False) ] diff --git a/examples/LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py b/examples/LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py index 14bfedd1..209debc2 100644 --- a/examples/LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py +++ b/examples/LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py @@ -212,7 +212,9 @@ def store_documents( uuid=document_uuid, ) - chunk_iterator = zip(pdf_obj["chunked_text"], pdf_obj["chunked_embeddings"]) + chunk_iterator = zip( + pdf_obj["chunked_text"], pdf_obj["chunked_embeddings"], strict=False + ) for chunk_idx, (chunk_text, chunk_embedding) in enumerate(chunk_iterator): chunk_object = dict(content=chunk_text, chunk_index=chunk_idx) chunk_uuid = generate_uuid5(chunk_object, "Chunk") diff --git a/examples/due_date_probabilities/probability_estimation.py b/examples/due_date_probabilities/probability_estimation.py index a3878750..8009cbb8 100644 --- a/examples/due_date_probabilities/probability_estimation.py +++ b/examples/due_date_probabilities/probability_estimation.py @@ -133,7 +133,8 @@ def raw_probabilities(raw_data: str) -> pd.DataFrame: days = [int(item.split(", ")[1].split()[0]) for item in raw_data] probability = [float(item.split()[5].replace("%", "")) / 100 for item in raw_data] probabilities_data = [ - (week * 7 + day, probability) for week, day, probability in zip(weeks, days, probability) + (week * 7 + day, probability) + for week, day, probability in zip(weeks, days, probability, strict=False) ] probabilities_df = pd.DataFrame(probabilities_data) probabilities_df.columns = ["days", "probability"] diff --git a/hamilton/async_driver.py b/hamilton/async_driver.py index aa6287fb..95a53a52 100644 --- a/hamilton/async_driver.py +++ b/hamilton/async_driver.py @@ -38,7 +38,7 @@ async def await_dict_of_tasks(task_dict: Dict[str, typing.Awaitable]) -> Dict[st keys = sorted(task_dict.keys()) coroutines = [task_dict[key] for key in keys] coroutines_gathered = await asyncio.gather(*coroutines) - return dict(zip(keys, coroutines_gathered)) + return dict(zip(keys, coroutines_gathered, strict=False)) async def process_value(val: Any) -> Any: diff --git a/hamilton/experimental/decorators/parameterize_frame.py b/hamilton/experimental/decorators/parameterize_frame.py index 30f9b331..10aee4a5 100644 --- a/hamilton/experimental/decorators/parameterize_frame.py +++ b/hamilton/experimental/decorators/parameterize_frame.py @@ -67,11 +67,11 @@ def _convert_params_from_df(parameterization: pd.DataFrame) -> List[Parameterize for _, column_set in parameterization.iterrows(): parameterization = { arg: dep_type(col_value) - for arg, col_value, dep_type in zip(args, column_set, dep_types_converted) + for arg, col_value, dep_type in zip(args, column_set, dep_types_converted, strict=False) if dep_type is not None } extracted_columns = [ - col for col, dep_type in zip(column_set, dep_types) if dep_type == "out" + col for col, dep_type in zip(column_set, dep_types, strict=False) if dep_type == "out" ] out.append(ParameterizedExtract(tuple(extracted_columns), parameterization)) return out diff --git a/hamilton/function_modifiers/expanders.py b/hamilton/function_modifiers/expanders.py index 9e16a945..a0074d35 100644 --- a/hamilton/function_modifiers/expanders.py +++ b/hamilton/function_modifiers/expanders.py @@ -1065,7 +1065,9 @@ class unpack_fields(base.SingleNodeNodeTransformer): output_nodes = [node_.copy_with(callabl=tuple_generator)] - for idx, (field_name, field_type) in enumerate(zip(self.fields, self.field_types)): + for idx, (field_name, field_type) in enumerate( + zip(self.fields, self.field_types, strict=False) + ): def extractor(field_index: int = idx, **kwargs) -> field_type: # type: ignore # This extractor is constructed to avoid closure issues. diff --git a/hamilton/plugins/h_kedro.py b/hamilton/plugins/h_kedro.py index b5e61723..a20557b8 100644 --- a/hamilton/plugins/h_kedro.py +++ b/hamilton/plugins/h_kedro.py @@ -35,7 +35,7 @@ def expand_k_node(base_node: HNode, outputs: List[str]) -> List[HNode]: """ def _convert_output_from_tuple_to_dict(node_result: Any, node_kwargs: Dict[str, Any]): - return {out: v for out, v in zip(outputs, node_result)} + return {out: v for out, v in zip(outputs, node_result, strict=False)} # NOTE isinstance(Any, type) is False for Python < 3.11 extractor = extract_fields(fields={out: Any for out in outputs}) @@ -91,7 +91,7 @@ def k_node_to_h_nodes(node: KNode) -> List[HNode]: # remap the function parameters to the node `inputs` and clean Kedro `parameters` name new_params = {} - for param, k_input in zip(params, node.inputs): + for param, k_input in zip(params, node.inputs, strict=False): if k_input.startswith("params:"): k_input = k_input.partition("params:")[-1] diff --git a/hamilton/plugins/h_openlineage.py b/hamilton/plugins/h_openlineage.py index 2554d568..a186b29e 100644 --- a/hamilton/plugins/h_openlineage.py +++ b/hamilton/plugins/h_openlineage.py @@ -61,6 +61,7 @@ def extract_schema_facet(metadata): for k, v in zip( metadata["dataframe_metadata"]["column_names"], metadata["dataframe_metadata"]["datatypes"], + strict=False, ) ] schema_facet = facet_v2.schema_dataset.SchemaDatasetFacet( diff --git a/scripts/update_blogs_in_learning_resources.py b/scripts/update_blogs_in_learning_resources.py index dd6601ca..3472d821 100644 --- a/scripts/update_blogs_in_learning_resources.py +++ b/scripts/update_blogs_in_learning_resources.py @@ -105,7 +105,7 @@ def fetch_articles(url, cutoff_date): None, ), ] - for _i, (anchor, time_el) in enumerate(zip(anchors, timeEls)): + for _i, (anchor, time_el) in enumerate(zip(anchors, timeEls, strict=False)): link = anchor["href"] text = anchor.get_text() diff --git a/tests/resources/test_driver_serde_mapper.py b/tests/resources/test_driver_serde_mapper.py index 7d71edf5..7b9f064d 100644 --- a/tests/resources/test_driver_serde_mapper.py +++ b/tests/resources/test_driver_serde_mapper.py @@ -27,7 +27,7 @@ def mapper( ) -> Parallelizable[dict]: if final_vars is None: final_vars = [] - for dr, input_ in zip(drivers, inputs): + for dr, input_ in zip(drivers, inputs, strict=False): yield { "dr": dr, "final_vars": final_vars or dr.list_available_variables(), diff --git a/ui/backend/server/trackingserver_run_tracking/api.py b/ui/backend/server/trackingserver_run_tracking/api.py index c216c3a6..a95e9c96 100644 --- a/ui/backend/server/trackingserver_run_tracking/api.py +++ b/ui/backend/server/trackingserver_run_tracking/api.py @@ -426,7 +426,7 @@ async def get_latest_template_runs( return CatalogZoomResponse( node_runs=[ NodeRunOutWithExtraData.from_orm(node_run, dag_template_id=dag_template_id) - for (node_run, dag_template_id) in zip(node_runs, all_dag_versions) + for (node_run, dag_template_id) in zip(node_runs, all_dag_versions, strict=False) ], node_templates=[ NodeTemplateOut.from_orm(node_template) for node_template in node_templates
