Merge branch 'dev' into feat/logreg-retrieval

Author: Darinochka

CONTRIBUTING.md

@@ -50,41 +50,6 @@ make lint
 
 ![](assets/dependency-graph.png)
 
-## Настройка логгера
-Чтобы видеть debug строчки у вас есть несколько опций:
-
-1. Включить весь debug output через опцию коммандной строки: 
-```bash 
-autointent hydra.verbose=true
-```
-2. Включить debug output только для определенных модулей, пример для autointent.pipeline.optimization.cli_endpoint и самой hydra: 
-```bash
-autointent hydra.verbose=[hydra,autointent/pipeline/optimization/cli_endpoint] hydra.job_logging.root.level=DEBUG
-```
-
-Само конфигурирование логгера сделано в autointent.configs.optimization_cli.logger_config. Вы можете изменить любой параметр логгера через коммандную строку. Вот пример, как поменять уровень логгера на ERROR:
-```bash
-autointent hydra.job_logging.root.level=ERROR
-```
-
-Еще можно изменить параметры логгера через yaml файлы:
-1. Создадим папку с конфиг. файлами: test_config
-2. test_config/config.yaml:
-```yaml
-defaults:
-  - optimization_config
-  - _self_
-  - override hydra/job_logging: custom
-  
-# set your config params for optimization here
-embedder_batch_size: 32
-```
-3. Поместите конфигурацию логгера в test_config/hydra/job_logging/custom.yaml (параметры см. [здесь](https://docs.python.org/3/howto/logging.html))
-4. Запускаем с конфиг файлом config.yaml:
-```bash
-autointent --config-path FULL_PATH/test_config --config-name config
-```
-
 ## Построение документации
 
 Построить html версию в папке `docs/build`:

Makefile

@@ -24,7 +24,7 @@ lint:
 
 .PHONY: sync
 sync:
-	poetry sync
+	poetry sync --with dev,test,typing,docs
 
 .PHONY: docs
 docs:

autointent/__init__.py

@@ -1,5 +1,6 @@
 """This is AutoIntent API reference."""
 
+from ._logging import setup_logging
 from ._ranker import Ranker
 from ._embedder import Embedder
 from ._vector_index import VectorIndex
@@ -8,5 +9,4 @@
 from .context import Context
 from ._pipeline import Pipeline
 
-
-__all__ = ["Context", "Dataset", "Embedder", "Hasher", "Pipeline", "Ranker", "VectorIndex"]
+__all__ = ["Context", "Dataset", "Embedder", "Hasher", "Pipeline", "Ranker", "VectorIndex", "setup_logging"]

autointent/_logging/__init__.py

@@ -0,0 +1,3 @@
+from .setup import setup_logging
+
+__all__ = ["setup_logging"]

autointent/_logging/config.yaml

@@ -0,0 +1,27 @@
+version: 1
+disable_existing_loggers: false
+formatters:
+  simple:
+    format: '%(levelname)s: %(message)s'
+    datefmt: '%Y-%m-%dT%H:%M:%S%z'
+  json:
+    (): autointent._logging.formatter.JSONFormatter
+    fmt_keys:
+      level: levelname
+      message: message
+      timestamp: timestamp
+      logger: name
+      module: module
+      function: funcName
+      line: lineno
+      thread_name: threadName
+handlers:
+  stdout:
+    class: logging.StreamHandler
+    formatter: simple
+    stream: ext://sys.stdout
+loggers:
+  root:
+    level: DEBUG
+    handlers:
+    - stdout

autointent/_logging/formatter.py

@@ -0,0 +1,68 @@
+import datetime as dt
+import json
+import logging
+from typing import Any
+
+LOG_RECORD_BUILTIN_ATTRS = {
+    "args",
+    "asctime",
+    "created",
+    "exc_info",
+    "exc_text",
+    "filename",
+    "funcName",
+    "levelname",
+    "levelno",
+    "lineno",
+    "module",
+    "msecs",
+    "message",
+    "msg",
+    "name",
+    "pathname",
+    "process",
+    "processName",
+    "relativeCreated",
+    "stack_info",
+    "thread",
+    "threadName",
+    "taskName",
+}
+
+
+class JSONFormatter(logging.Formatter):
+    """This is a custom formatter for saving logging records as a json."""
+
+    def __init__(
+        self,
+        *,
+        fmt_keys: dict[str, str] | None = None,
+    ) -> None:
+        super().__init__()
+        self.fmt_keys = fmt_keys if fmt_keys is not None else {}
+
+    def format(self, record: logging.LogRecord) -> str:
+        message = self._prepare_log_dict(record)
+        return json.dumps(message, default=str)
+
+    def _prepare_log_dict(self, record: logging.LogRecord) -> dict[str, Any]:
+        always_fields = {
+            "message": record.getMessage(),
+            "timestamp": dt.datetime.fromtimestamp(record.created, tz=dt.timezone.utc).isoformat(),
+        }
+        if record.exc_info is not None:
+            always_fields["exc_info"] = self.formatException(record.exc_info)
+
+        if record.stack_info is not None:
+            always_fields["stack_info"] = self.formatStack(record.stack_info)
+
+        message = {
+            key: msg_val if (msg_val := always_fields.pop(val, None)) is not None else getattr(record, val)
+            for key, val in self.fmt_keys.items()
+        }
+        message.update(always_fields)
+
+        extra_fields = {key: val for key, val in record.__dict__.items() if key not in LOG_RECORD_BUILTIN_ATTRS}
+        message.update(extra_fields)
+
+        return message

autointent/_logging/setup.py

@@ -0,0 +1,41 @@
+import importlib.resources as ires
+import logging.config
+import logging.handlers
+from pathlib import Path
+
+import yaml
+
+from autointent.custom_types import LogLevel
+
+
+def setup_logging(level: LogLevel | str, log_filename: Path | str | None = None) -> None:
+    """
+    Set stdout and file handlers for logging autointent internal actions.
+
+    The first parameter affects the logs to the standard output stream. The second parameter is optional.
+    If it is specified, then the "DEBUG" messages are logged to the file,
+    regardless of what is specified by the first parameter.
+
+    :param level: one of "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"
+    :param log_to_filepath: specify location of logfile, omit extension as suffix ``.log.jsonl`` will be appended.
+    """
+    config_file = ires.files("autointent._logging").joinpath("config.yaml")
+    with config_file.open() as f_in:
+        config = yaml.safe_load(f_in)
+
+    level = LogLevel(level)
+    config["handlers"]["stdout"]["level"] = level.value
+
+    if log_filename is not None:
+        config["loggers"]["root"]["handlers"].append("file")
+
+        filename = str(log_filename) + ".log.jsonl"
+        config["handlers"]["file"] = {
+            "class": "logging.FileHandler",
+            "level": "DEBUG",
+            "formatter": "json",
+            "filename": filename,
+        }
+        Path(filename).parent.mkdir(parents=True, exist_ok=True)
+
+    logging.config.dictConfig(config)

autointent/_pipeline/_cli_endpoint.py

@@ -25,14 +25,17 @@ class Pipeline:
     def __init__(
         self,
         nodes: list[NodeOptimizer] | list[InferenceNode],
+        seed: int = 42,
     ) -> None:
         """
         Initialize the pipeline optimizer.
 
         :param nodes: list of nodes
+        :param seed: random seed
         """
         self._logger = logging.getLogger(__name__)
         self.nodes = {node.node_type: node for node in nodes}
+        self.seed = seed
 
         if isinstance(nodes[0], NodeOptimizer):
             self.logging_config = LoggingConfig(dump_dir=None)
@@ -62,7 +65,7 @@ def set_config(self, config: LoggingConfig | VectorIndexConfig | EmbedderConfig
             raise TypeError(msg)
 
     @classmethod
-    def from_search_space(cls, search_space: list[dict[str, Any]] | Path | str) -> "Pipeline":
+    def from_search_space(cls, search_space: list[dict[str, Any]] | Path | str, seed: int = 42) -> "Pipeline":
         """
         Create pipeline optimizer from dictionary search space.
 
@@ -71,16 +74,16 @@ def from_search_space(cls, search_space: list[dict[str, Any]] | Path | str) -> "
         if isinstance(search_space, Path | str):
             search_space = load_search_space(search_space)
         nodes = [NodeOptimizer(**node) for node in search_space]
-        return cls(nodes)
+        return cls(nodes=nodes, seed=seed)
 
     @classmethod
-    def default_optimizer(cls, multilabel: bool) -> "Pipeline":
+    def default_optimizer(cls, multilabel: bool, seed: int = 42) -> "Pipeline":
         """
         Create pipeline optimizer with default search space for given classification task.
 
         :param multilabel: Whether the task multi-label, or single-label.
         """
-        return cls.from_search_space(load_default_search_space(multilabel))
+        return cls.from_search_space(search_space=load_default_search_space(multilabel), seed=seed)
 
     def _fit(self, context: Context) -> None:
         """
@@ -91,8 +94,8 @@ def _fit(self, context: Context) -> None:
         self.context = context
         self._logger.info("starting pipeline optimization...")
         self.context.callback_handler.start_run(
-            run_name=self.context.logging_config.get_run_name(),
-            dirpath=self.context.logging_config.get_dirpath(),
+            run_name=self.context.logging_config.run_name,
+            dirpath=self.context.logging_config.dirpath,
         )
         for node_type in NodeType:
             node_optimizer = self.nodes.get(node_type, None)
@@ -111,20 +114,19 @@ def _is_inference(self) -> bool:
         """
         return isinstance(self.nodes[NodeType.scoring], InferenceNode)
 
-    def fit(self, dataset: Dataset, force_multilabel: bool = False) -> Context:
+    def fit(self, dataset: Dataset) -> Context:
         """
         Optimize the pipeline from dataset.
 
         :param dataset: Dataset for optimization
-        :param force_multilabel: Whether to force multilabel or not
         :return: Context
         """
         if self._is_inference():
             msg = "Pipeline in inference mode cannot be fitted"
             raise RuntimeError(msg)
 
         context = Context()
-        context.set_dataset(dataset, force_multilabel)
+        context.set_dataset(dataset)
         context.configure_logging(self.logging_config)
         context.configure_vector_index(self.vector_index_config, self.embedder_config)
         context.configure_cross_encoder(self.cross_encoder_config)

autointent/_pipeline/_pipeline.py

@@ -1,12 +1,11 @@
 """Dataclasses for the configuration of the :class:`autointent.Embedder` and other objects."""
 
 from ._inference_node import InferenceNodeConfig
-from ._optimization_cli import (
+from ._optimization import (
     CrossEncoderConfig,
     DataConfig,
     EmbedderConfig,
     LoggingConfig,
-    OptimizationConfig,
     TaskConfig,
     VectorIndexConfig,
 )
@@ -18,7 +17,6 @@
     "InferenceNodeConfig",
     "InferenceNodeConfig",
     "LoggingConfig",
-    "OptimizationConfig",
     "TaskConfig",
     "VectorIndexConfig",
 ]