рефакторинг блокнота research в части логирования в mlflow

research/research.py

@@ -51,6 +51,7 @@ mlflow_run_name: str = 'Baseline model'
 import os
 import pathlib
 import pickle
+import sys
 
 # %%
 import mlflow
@@ -66,6 +67,17 @@ import sklearn.preprocessing
 # %%
 BASE_PATH = pathlib.Path('..')
 
+# %%
+CODE_PATH = BASE_PATH
+sys.path.insert(0, str(CODE_PATH.resolve()))
+
+# %%
+from iis_project.sklearn_utils import filter_params
+from iis_project.sklearn_utils.compose import COLUMN_TRANSFORMER_PARAMS_COMMON_INCLUDE
+from iis_project.sklearn_utils.ensemble import RANDOM_FOREST_REGRESSOR_PARAMS_COMMON_EXCLUDE
+from iis_project.sklearn_utils.pipeline import PIPELINE_PARAMS_COMMON_INCLUDE
+from iis_project.sklearn_utils.preprocessing import STANDARD_SCALER_PARAMS_COMMON_EXCLUDE
+
 # %%
 MODEL_INOUT_EXAMPLE_SIZE = 0x10
 
@@ -196,6 +208,22 @@ tuple(map(len, (df_target_train, df_target_test)))
 mlflow_model_signature = mlflow.models.infer_signature(model_input=df_orig_features, model_output=df_target)
 mlflow_model_signature
 
+# %% [raw] vscode={"languageId": "raw"}
+# input_schema = mlflow.types.schema.Schema([
+#     mlflow.types.schema.ColSpec("double", "selling_price"),
+#     mlflow.types.schema.ColSpec("double", "driven_kms"),
+#     mlflow.types.schema.ColSpec("string", "fuel_type"),
+#     mlflow.types.schema.ColSpec("string", "selling_type"),
+#     mlflow.types.schema.ColSpec("string", "transmission"),
+#     mlflow.types.schema.ColSpec("double", "age"),
+# ])
+#
+# output_schema = mlflow.types.schema.Schema([
+#     mlflow.types.schema.ColSpec("double", "present_price"),
+# ])
+#
+# mlflow_model_signature = mlflow.models.ModelSignature(inputs=input_schema, outputs=output_schema)
+
 # %% [markdown]
 # Пайплайн предобработки признаков:
 
@@ -235,7 +263,25 @@ pipeline = sklearn.pipeline.Pipeline([
 pipeline
 
 # %%
-model_params = pipeline.get_params()
+model_params = filter_params(
+    pipeline.get_params(),
+    include={
+        **{k: True for k in PIPELINE_PARAMS_COMMON_INCLUDE},
+        'preprocess': (
+            False,
+            {
+                **{k: True for k in COLUMN_TRANSFORMER_PARAMS_COMMON_INCLUDE},
+                'scale_to_standard': True,
+                'encode_categorical_wrt_target': True,
+            },
+        ),
+        'regress': (False, True),
+    },
+    exclude={
+        'preprocess': {'scale_to_standard': STANDARD_SCALER_PARAMS_COMMON_EXCLUDE},
+        'regress': RANDOM_FOREST_REGRESSOR_PARAMS_COMMON_EXCLUDE,
+    },
+)
 model_params
 
 # %% [markdown]