Cleanup package build

Author: akotyla

.gitlab-ci.yml

@@ -215,7 +215,7 @@ benchmark:
   stage: benchmark
   interruptible: true
   script:
-    - python src/dbally_benchmark/evaluate.py neptune.log=True
+    - PYTHONPATH=benchmark/ python benchmark/dbally_benchmark/evaluate.py neptune.log=True
   rules:
     - if: $CI_PIPELINE_SOURCE == "merge_request_event" || '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
       when: manual

src/dbally_benchmark/__init__.py benchmark/dbally_benchmark/__init__.py

@@ -1,6 +1,5 @@
-from pydantic.v1 import BaseSettings
-
 from dbally_benchmark.paths import PATH_PACKAGE
+from pydantic.v1 import BaseSettings
 
 
 class BenchmarkConfig(BaseSettings):

src/dbally_benchmark/config.py benchmark/dbally_benchmark/config.py

@@ -1,9 +1,10 @@
 from enum import Enum
 from typing import Dict, Type
 
-from dbally.views.sqlalchemy_base import SqlAlchemyBaseView
 from dbally_benchmark.views.superhero import SuperheroCountByPowerView, SuperheroView
 
+from dbally.views.sqlalchemy_base import SqlAlchemyBaseView
+
 
 class ViewName(Enum):
     """Enum representing the name of the view."""

src/dbally_benchmark/constants.py benchmark/dbally_benchmark/constants.py

@@ -4,10 +4,9 @@
 from pathlib import Path
 from typing import Iterator
 
+from dbally_benchmark.utils import load_data
 from pydantic import BaseModel, RootModel
 
-from dbally_benchmark.io import load_data
-
 
 class DifficultyLevel(str, enum.Enum):
     """Enum representing BIRD example difficulty level."""

src/dbally_benchmark/dataset/bird_dataset.py benchmark/dbally_benchmark/dataset/bird_dataset.py

@@ -7,6 +7,13 @@
 
 import hydra
 import neptune
+from dbally_benchmark.config import BenchmarkConfig
+from dbally_benchmark.constants import VIEW_REGISTRY, EvaluationType, ViewName
+from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
+from dbally_benchmark.paths import PATH_EXPERIMENTS
+from dbally_benchmark.text2sql.metrics import calculate_dataset_metrics
+from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
+from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 from hydra.utils import instantiate
 from loguru import logger
 from neptune.utils import stringify_unsupported
@@ -18,13 +25,6 @@
 from dbally.data_models.prompts.iql_prompt_template import default_iql_template
 from dbally.data_models.prompts.view_selector_prompt_template import default_view_selector_template
 from dbally.utils.errors import NoViewFoundError, UnsupportedQueryError
-from dbally_benchmark.config import BenchmarkConfig
-from dbally_benchmark.constants import VIEW_REGISTRY, EvaluationType, ViewName
-from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
-from dbally_benchmark.paths import PATH_EXPERIMENTS
-from dbally_benchmark.text2sql.metrics import calculate_dataset_metrics
-from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
-from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 
 
 async def _run_dbally_for_single_example(example: BIRDExample, collection: Collection) -> Text2SQLResult:

src/dbally_benchmark/e2e_benchmark.py benchmark/dbally_benchmark/e2e_benchmark.py

@@ -2,12 +2,11 @@
 from typing import Callable, Dict
 
 import hydra
-from omegaconf import DictConfig
-
 from dbally_benchmark.constants import EvaluationType
 from dbally_benchmark.e2e_benchmark import evaluate as e2e_evaluate
 from dbally_benchmark.iql_benchmark import evaluate as iql_evaluate
 from dbally_benchmark.text2sql_benchmark import evaluate as text2sql_evaluate
+from omegaconf import DictConfig
 
 
 async def evaluate(cfg: DictConfig) -> None:

src/dbally_benchmark/evaluate.py benchmark/dbally_benchmark/evaluate.py

@@ -1,13 +1,13 @@
 import ast
 from typing import Dict, List, Tuple
 
+from dbally_benchmark.iql.iql_result import IQLResult
+from dbally_benchmark.iql.method_call_visitor import MethodCallVisitor
 from loguru import logger
 
 from dbally.iql._exceptions import IQLError, IQLUnsupportedSyntaxError
 from dbally.iql._query import IQLQuery
 from dbally.views.base import ExposedFunction
-from dbally_benchmark.iql.iql_result import IQLResult
-from dbally_benchmark.iql.method_call_visitor import MethodCallVisitor
 
 
 def _count_hallucinated_methods_for_single_example(iql: str, allowed_methods: List[str]) -> Tuple[int, int]:

src/dbally_benchmark/experiment_config/config.yaml benchmark/dbally_benchmark/experiment_config/config.yaml

@@ -6,6 +6,13 @@
 
 import hydra
 import neptune
+from dbally_benchmark.config import BenchmarkConfig
+from dbally_benchmark.constants import VIEW_REGISTRY, EvaluationType, ViewName
+from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
+from dbally_benchmark.iql.iql_result import IQLResult
+from dbally_benchmark.iql.metrics import calculate_dataset_metrics
+from dbally_benchmark.paths import PATH_EXPERIMENTS
+from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 from hydra.utils import instantiate
 from loguru import logger
 from neptune.utils import stringify_unsupported
@@ -18,13 +25,6 @@
 from dbally.llm_client.openai_client import OpenAIClient
 from dbally.utils.errors import UnsupportedQueryError
 from dbally.views.base import AbstractBaseView
-from dbally_benchmark.config import BenchmarkConfig
-from dbally_benchmark.constants import VIEW_REGISTRY, EvaluationType, ViewName
-from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
-from dbally_benchmark.iql.iql_result import IQLResult
-from dbally_benchmark.iql.metrics import calculate_dataset_metrics
-from dbally_benchmark.paths import PATH_EXPERIMENTS
-from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 
 
 async def _run_iql_for_single_example(

src/dbally_benchmark/experiment_config/e2e/superhero.yaml benchmark/dbally_benchmark/experiment_config/e2e/superhero.yaml

@@ -2,11 +2,11 @@
 from typing import Dict, List
 
 import pandas as pd
+from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
+from dbally_benchmark.utils import batch
 from sqlalchemy import Engine, text
 
 from dbally.data_models.execution_result import ExecutionResult
-from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
-from dbally_benchmark.utils import batch
 
 
 def _run_query(query: str, engine: Engine) -> ExecutionResult:

src/dbally_benchmark/experiment_config/iql/superhero.yaml benchmark/dbally_benchmark/experiment_config/iql/superhero.yaml

@@ -6,6 +6,14 @@
 
 import hydra
 import neptune
+from dbally_benchmark.config import BenchmarkConfig
+from dbally_benchmark.constants import EvaluationType
+from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
+from dbally_benchmark.paths import PATH_EXPERIMENTS, PATH_SCHEMAS
+from dbally_benchmark.text2sql.metrics import calculate_dataset_metrics
+from dbally_benchmark.text2sql.prompt_template import TEXT2SQL_PROMPT_TEMPLATE
+from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
+from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 from hydra.utils import instantiate
 from loguru import logger
 from neptune.utils import stringify_unsupported
@@ -15,14 +23,6 @@
 from dbally.audit.event_tracker import EventTracker
 from dbally.llm_client.base import LLMClient
 from dbally.llm_client.openai_client import OpenAIClient
-from dbally_benchmark.config import BenchmarkConfig
-from dbally_benchmark.constants import EvaluationType
-from dbally_benchmark.dataset.bird_dataset import BIRDDataset, BIRDExample
-from dbally_benchmark.paths import PATH_EXPERIMENTS, PATH_SCHEMAS
-from dbally_benchmark.text2sql.metrics import calculate_dataset_metrics
-from dbally_benchmark.text2sql.prompt_template import TEXT2SQL_PROMPT_TEMPLATE
-from dbally_benchmark.text2sql.text2sql_result import Text2SQLResult
-from dbally_benchmark.utils import batch, get_datetime_str, set_up_gitlab_metadata
 
 
 def _load_db_schema(db_name: str, encoding: Optional[str] = None) -> str:

src/dbally_benchmark/experiment_config/text2sql/superhero.yaml benchmark/dbally_benchmark/experiment_config/text2sql/superhero.yaml

@@ -1,10 +1,30 @@
 import os
 from datetime import datetime
-from typing import Any, Iterator
+from pathlib import Path
+from typing import Any, Iterator, Optional, Union
 
 from neptune.metadata_containers import Run
 
 
+def load_data(
+    file_path: Union[str, Path],
+    encoding: Optional[str] = None,
+) -> str:
+    """
+    Load data from a file.
+
+    Args:
+        file_path: Path of the data.
+        encoding: Encoding of the input file.
+
+    Returns:
+        String read from the file.
+    """
+
+    with open(file_path, encoding=encoding) as file_handle:
+        return file_handle.read()
+
+
 def get_datetime_str() -> str:
     """
     Obtain a string representing current datetime.

src/dbally_benchmark/iql/iql_result.py benchmark/dbally_benchmark/iql/iql_result.py

@@ -1,13 +1,13 @@
 # pylint: disable=missing-docstring, missing-return-doc, missing-param-doc
 
 import sqlalchemy
+from dbally_benchmark.config import config
 from sqlalchemy import create_engine
 from sqlalchemy.dialects.postgresql import ARRAY
 from sqlalchemy.ext.automap import automap_base
 from sqlalchemy.orm import aliased
 
 from dbally import SqlAlchemyBaseView, decorators
-from dbally_benchmark.config import config
 
 engine = create_engine(config.pg_connection_string + "/superhero")
 SuperheroModel = automap_base()

src/dbally_benchmark/iql/method_call_visitor.py benchmark/dbally_benchmark/iql/method_call_visitor.py

@@ -1,4 +1,3 @@
-from dbally.views.base import ExposedFunction, MethodParamWithTyping
 from dbally_benchmark.iql.iql_result import IQLResult
 from dbally_benchmark.iql.metrics import (
     _count_hallucinated_methods_for_single_example,
@@ -7,6 +6,8 @@
     calculate_valid_iql,
 )
 
+from dbally.views.base import ExposedFunction, MethodParamWithTyping
+
 ALLOWED_METHODS = [
     ExposedFunction(
         name="filter_by_name",

src/dbally_benchmark/iql/metrics.py benchmark/dbally_benchmark/iql/metrics.py

@@ -1,9 +1,8 @@
 from unittest.mock import call, patch
 
 import pytest
-from omegaconf import DictConfig
-
 from dbally_benchmark.evaluate import evaluate
+from omegaconf import DictConfig
 
 
 @patch("dbally_benchmark.evaluate.e2e_evaluate")

src/dbally_benchmark/iql_benchmark.py benchmark/dbally_benchmark/iql_benchmark.py

@@ -1,7 +1,6 @@
 import ast
 
 import pytest
-
 from dbally_benchmark.iql.method_call_visitor import MethodCallVisitor
 
 

src/dbally_benchmark/paths.py benchmark/dbally_benchmark/paths.py

@@ -6,6 +6,7 @@ RUN python -m pip install --no-cache-dir --upgrade pip
 COPY pyproject.toml setup.cfg requirements-dev.txt check_licenses.sh ./
 COPY src/ src/
 COPY data/ data/
+COPY benchmark/ benchmark/
 
 RUN pip install build twine bump2version wheel==0.41.3
 RUN pip install --no-cache-dir --upgrade -e .[benchmark]

src/dbally_benchmark/text2sql/metrics.py benchmark/dbally_benchmark/text2sql/metrics.py

@@ -2,13 +2,14 @@
 from dataclasses import dataclass
 from typing import List
 
+from dbally_benchmark.text2sql.prompt_template import TEXT2SQL_PROMPT_TEMPLATE
+
 import dbally
 from dbally.audit.event_handlers.cli_event_handler import CLIEventHandler
 from dbally.audit.event_tracker import EventTracker
 from dbally.examples.db import ENGINE, fill_candidate_table, get_recruitment_db_description
 from dbally.examples.views import RecruitmentView
 from dbally.llm_client.openai_client import OpenAIClient
-from dbally_benchmark.text2sql.prompt_template import TEXT2SQL_PROMPT_TEMPLATE
 
 
 @dataclass