добавить логирование прогонов в MLFlow

mlflow/.gitignore

@@ -0,0 +1,2 @@
+mlruns.sqlite
+mlartifacts/

requirements.txt

@@ -2,6 +2,7 @@ bokeh >=3.7.2,<4
 ipykernel >=6.30.1,<7
 ipympl ~=0.9.6
 matplotlib >=3.10.1,<4
+mlflow>=2.16,<2.22
 numpy >=2.2.6,<3
 pandas >=2.3.1,<3
 scipy >=1.15.3,<2

research/research.py

@@ -1,7 +1,7 @@
 # ---
 # jupyter:
 #   jupytext:
-#     formats: ipynb,py:percent
+#     formats: py:percent,ipynb
 #     text_representation:
 #       extension: .py
 #       format_name: percent
@@ -16,19 +16,6 @@
 # %%
 from typing import Optional
 
-# %%
-import os
-import pathlib
-import pickle
-
-# %%
-import sklearn.compose
-import sklearn.ensemble
-import sklearn.metrics
-import sklearn.model_selection
-import sklearn.pipeline
-import sklearn.preprocessing
-
 # %%
 # %% tags=["parameters"]
 data_path: Optional[str] = None
@@ -41,9 +28,37 @@ data_aug_pickle_path: Optional[str] = None
 data_aug_pickle_relpath: str = 'cars.aug.pickle'
 # Путь к файлу (pickle) для сохранения очищенного датасета относительно директории данных `data`. Игнорируется, если установлен data_aug_pickle_path.
 
+mlflow_tracking_server_uri: str = 'http://localhost:5000'
+mlflow_registry_uri: Optional[str] = None
+
+mlflow_experiment_name: str = 'Current price predicion for used cars'
+mlflow_experiment_new: bool = False
+mlflow_run_name: str = 'Baseline model'
+
+# %%
+import os
+import pathlib
+import pickle
+
+# %%
+import mlflow
+import mlflow.models
+import mlflow.sklearn
+import sklearn.compose
+import sklearn.ensemble
+import sklearn.metrics
+import sklearn.model_selection
+import sklearn.pipeline
+import sklearn.preprocessing
+
 # %%
 BASE_PATH = pathlib.Path('..')
 
+# %%
+mlflow.set_tracking_uri(mlflow_tracking_server_uri)
+if mlflow_registry_uri is not None:
+    mlflow.set_registry_uri(mlflow_registry_uri)
+
 # %%
 DATA_PATH = (
     pathlib.Path(os.path.dirname(data_path))
@@ -171,3 +186,45 @@ metrics = {
 
 # %%
 metrics
+
+# %%
+MODEL_PIP_REQUIREMENTS_PATH = BASE_PATH / 'requirements.txt'
+MODEL_COMMENTS_FILE_PATH = BASE_PATH / 'comment.txt'
+
+# %%
+MODEL_INOUT_EXAMPLE_SIZE = 0x10
+
+# %%
+model_inout_example = (df_orig_features.head(MODEL_INOUT_EXAMPLE_SIZE), df_target.head(MODEL_INOUT_EXAMPLE_SIZE))
+
+# %%
+mlflow_model_signature = mlflow.models.infer_signature(model_input=model_inout_example[0], model_output=model_inout_example[1])
+
+# %%
+mlflow_model_signature
+
+# %%
+model_params = pipeline.get_params()
+
+# %%
+model_params
+
+# %%
+if mlflow_experiment_new:
+    experiment = mlflow.get_experiment(mlflow.create_experiment(mlflow_experiment_name))
+else:
+    experiment = mlflow.set_experiment(experiment_name=mlflow_experiment_name)
+
+# %%
+with mlflow.start_run(experiment_id=experiment.experiment_id, run_name=mlflow_run_name):
+    _ = mlflow.sklearn.log_model(
+        pipeline,
+        'model',
+        signature=mlflow_model_signature,
+        input_example=model_inout_example[0],
+        pip_requirements=str(MODEL_PIP_REQUIREMENTS_PATH),
+    )
+    _ = mlflow.log_params(model_params)
+    _ = mlflow.log_metrics({k: float(v) for k, v in metrics.items()})
+    if MODEL_COMMENTS_FILE_PATH.exists():
+        mlflow.log_artifact(str(MODEL_COMMENTS_FILE_PATH))

run_mlflow_server.sh

@@ -0,0 +1,13 @@
+# Must be a relative path to be used in an option for mlflow server.
+BACKEND_STORE_DB_PATH="./mlflow/mlruns.sqlite"
+DEFAULT_ARTIFACTS_ROOT="./mlflow/"
+
+if [ ! -e "$BACKEND_STORE_DB_PATH" ]; then
+    printf '%s\n' "Error: '$BACKEND_STORE_DB_PATH' does not exist." >&2
+    exit 1
+fi
+
+mlflow server \
+    --backend-store-uri="sqlite:///$BACKEND_STORE_DB_PATH"  \
+    --default-artifacts-root="$DEFAULT_ARTIFACTS_ROOT" \
+    -p 5000