lecrapaud 0.19.3__py3-none-any.whl → 0.20.1__py3-none-any.whl

lecrapaud/api.py

@@ -165,6 +165,12 @@ class ExperimentEngine:
 
     def __init__(self, id: int = None, data: pd.DataFrame = None, **kwargs):
         """Initialize the experiment engine with either new or existing experiment."""
+        # Set all kwargs as instance attributes
+        if "models_idx" in kwargs:
+            kwargs["models_idx"] = normalize_models_idx(kwargs["models_idx"])
+        for key, value in kwargs.items():
+            setattr(self, key, value)
+
         if id:
             self.experiment = Experiment.get(id)
             kwargs.update(self.experiment.context)
@@ -180,12 +186,6 @@ class ExperimentEngine:
                 )
             self.experiment = create_experiment(data=data, **kwargs)
 
-        # Set all kwargs as instance attributes
-        for key, value in kwargs.items():
-            if key == "models_idx":
-                value = normalize_models_idx(value)
-            setattr(self, key, value)
-
     def train(self, data, best_params=None):
         logger.info("Running training...")
 
@@ -309,12 +309,8 @@ class ExperimentEngine:
     def feature_engineering(self, data, for_training=True):
         app = FeatureEngineeringEngine(
             data=data,
-            columns_drop=getattr(self, "columns_drop", []),
-            columns_boolean=getattr(self, "columns_boolean", []),
-            columns_date=getattr(self, "columns_date", []),
-            columns_te_groupby=getattr(self, "columns_te_groupby", []),
-            columns_te_target=getattr(self, "columns_te_target", []),
-            for_training=getattr(self, "for_training", True),
+            experiment=self.experiment,
+            for_training=for_training,
         )
         data = app.run()
         return data
@@ -322,21 +318,7 @@ class ExperimentEngine:
     def preprocess_feature(self, data, for_training=True):
         app = PreprocessFeature(
             data=data,
-            experiment=getattr(self, "experiment", None),
-            time_series=getattr(self, "time_series", False),
-            date_column=getattr(self, "date_column", None),
-            group_column=getattr(self, "group_column", None),
-            val_size=getattr(self, "val_size", 0.2),
-            test_size=getattr(self, "test_size", 0.2),
-            columns_pca=getattr(self, "columns_pca", []),
-            pca_temporal=getattr(self, "pca_temporal", []),
-            pca_cross_sectional=getattr(self, "pca_cross_sectional", []),
-            columns_onehot=getattr(self, "columns_onehot", []),
-            columns_binary=getattr(self, "columns_binary", []),
-            columns_ordinal=getattr(self, "columns_ordinal", []),
-            columns_frequency=getattr(self, "columns_frequency", []),
-            target_numbers=getattr(self, "target_numbers", []),
-            target_clf=getattr(self, "target_clf", []),
+            experiment=self.experiment,
         )
         if for_training:
             train, val, test = app.run()
@@ -351,7 +333,6 @@ class ExperimentEngine:
                 train=train,
                 target_number=target_number,
                 experiment=self.experiment,
-                target_clf=self.target_clf,
             )
             app.run()
         self.experiment = Experiment.get(self.experiment.id)
@@ -368,14 +349,7 @@ class ExperimentEngine:
             train=train,
             val=val,
             test=test,
-            experiment=getattr(self, "experiment", None),
-            target_numbers=getattr(self, "target_numbers", []),
-            target_clf=getattr(self, "target_clf", []),
-            models_idx=getattr(self, "models_idx", []),
-            time_series=getattr(self, "time_series", False),
-            max_timesteps=getattr(self, "max_timesteps", 120),
-            date_column=getattr(self, "date_column", None),
-            group_column=getattr(self, "group_column", None),
+            experiment=self.experiment,
         )
         if for_training:
             data, reshaped_data = app.run()
@@ -390,25 +364,13 @@ class ExperimentEngine:
                 data=data,
                 reshaped_data=reshaped_data,
                 target_number=target_number,
-                experiment=getattr(self, "experiment", None),
-                target_clf=getattr(self, "target_clf", []),
-                models_idx=getattr(self, "models_idx", []),
-                time_series=getattr(self, "time_series", False),
-                date_column=getattr(self, "date_column", None),
-                group_column=getattr(self, "group_column", None),
-                target_clf_thresholds=getattr(self, "target_clf_thresholds", {}),
+                experiment=self.experiment,
             )
             if best_params and target_number not in best_params.keys():
                 raise ValueError(
                     f"Target {target_number} not found in best_params passed as argument"
                 )
             app.run(
-                self.experiment_name,
-                perform_hyperopt=self.perform_hyperopt,
-                number_of_trials=self.number_of_trials,
-                perform_crossval=self.perform_crossval,
-                plot=self.plot,
-                preserve_model=self.preserve_model,
                 best_params=best_params[target_number] if best_params else None,
             )
 

lecrapaud/config.py

@@ -34,3 +34,4 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 LECRAPAUD_LOGFILE = os.getenv("LECRAPAUD_LOGFILE")
 LECRAPAUD_LOCAL = os.getenv("LECRAPAUD_LOCAL", False)
 LECRAPAUD_TABLE_PREFIX = os.getenv("LECRAPAUD_TABLE_PREFIX", "lecrapaud")
+LECRAPAUD_OPTIMIZATION_BACKEND = os.getenv("LECRAPAUD_OPTIMIZATION_BACKEND", "ray").lower()

lecrapaud/db/alembic/versions/2025_10_25_0635-07e303521594_add_unique_constraint_to_score.py

@@ -0,0 +1,39 @@
+"""add unique constraint to score
+
+Revision ID: 07e303521594
+Revises: 8b11c1ba982e
+Create Date: 2025-10-25 06:35:57.950929
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+
+# revision identifiers, used by Alembic.
+revision: str = "07e303521594"
+down_revision: Union[str, None] = "8b11c1ba982e"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_unique_constraint(
+        "unique_score_per_model_training",
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        ["model_training_id"],
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint(
+        "unique_score_per_model_training",
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        type_="unique",
+    )
+    # ### end Alembic commands ###

lecrapaud/db/alembic/versions/2025_10_26_1727-033e0f7eca4f_merge_score_and_model_trainings_into_.py

@@ -0,0 +1,264 @@
+"""merge score and model_trainings into model_selection_scores
+
+Revision ID: 033e0f7eca4f
+Revises: 07e303521594
+Create Date: 2025-10-26 17:27:30.400473
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+
+# revision identifiers, used by Alembic.
+revision: str = "033e0f7eca4f"
+down_revision: Union[str, None] = "07e303521594"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Check if table exists using inspector
+    from sqlalchemy import inspect
+    inspector = inspect(op.get_bind())
+    existing_tables = inspector.get_table_names()
+    
+    if f"{LECRAPAUD_TABLE_PREFIX}_model_selection_scores" not in existing_tables:
+        op.create_table(
+            f"{LECRAPAUD_TABLE_PREFIX}_model_selection_scores",
+            sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
+            sa.Column(
+                "created_at",
+                sa.TIMESTAMP(timezone=True),
+                server_default=sa.text("now()"),
+                nullable=False,
+            ),
+            sa.Column(
+                "updated_at",
+                sa.TIMESTAMP(timezone=True),
+                server_default=sa.text("now()"),
+                nullable=False,
+            ),
+            sa.Column("best_params", sa.JSON(), nullable=True),
+            sa.Column("model_path", sa.String(length=255), nullable=True),
+            sa.Column("training_time", sa.Integer(), nullable=True),
+            sa.Column("model_id", sa.BigInteger(), nullable=False),
+            sa.Column("model_selection_id", sa.BigInteger(), nullable=False),
+            sa.Column("eval_data_std", sa.Float(), nullable=True),
+            sa.Column("rmse", sa.Float(), nullable=True),
+            sa.Column("rmse_std_ratio", sa.Float(), nullable=True),
+            sa.Column("mae", sa.Float(), nullable=True),
+            sa.Column("mape", sa.Float(), nullable=True),
+            sa.Column("mam", sa.Float(), nullable=True),
+            sa.Column("mad", sa.Float(), nullable=True),
+            sa.Column("mae_mam_ratio", sa.Float(), nullable=True),
+            sa.Column("mae_mad_ratio", sa.Float(), nullable=True),
+            sa.Column("r2", sa.Float(), nullable=True),
+            sa.Column("logloss", sa.Float(), nullable=True),
+            sa.Column("accuracy", sa.Float(), nullable=True),
+            sa.Column("precision", sa.Float(), nullable=True),
+            sa.Column("recall", sa.Float(), nullable=True),
+            sa.Column("f1", sa.Float(), nullable=True),
+            sa.Column("roc_auc", sa.Float(), nullable=True),
+            sa.Column("avg_precision", sa.Float(), nullable=True),
+            sa.Column("thresholds", sa.JSON(), nullable=True),
+            sa.Column("precision_at_threshold", sa.Float(), nullable=True),
+            sa.Column("recall_at_threshold", sa.Float(), nullable=True),
+            sa.Column("f1_at_threshold", sa.Float(), nullable=True),
+            sa.ForeignKeyConstraint(
+                ["model_id"],
+                [f"{LECRAPAUD_TABLE_PREFIX}_models.id"],
+            ),
+            sa.ForeignKeyConstraint(
+                ["model_selection_id"],
+                [f"{LECRAPAUD_TABLE_PREFIX}_model_selections.id"],
+                ondelete="CASCADE",
+            ),
+            sa.PrimaryKeyConstraint("id"),
+            sa.UniqueConstraint(
+                "model_id",
+                "model_selection_id",
+                name="uq_model_selection_score_composite",
+            ),
+        )
+        op.create_index(
+            op.f("ix_model_selection_scores_id"),
+            f"{LECRAPAUD_TABLE_PREFIX}_model_selection_scores",
+            ["id"],
+            unique=False,
+        )
+
+    # Migrate existing data from model_trainings and scores to model_selection_scores
+    op.execute(
+        f"""
+        INSERT INTO {LECRAPAUD_TABLE_PREFIX}_model_selection_scores (
+            created_at, updated_at, best_params, model_path, training_time, 
+            model_id, model_selection_id,
+            eval_data_std, rmse, rmse_std_ratio, mae, mape, mam, mad, 
+            mae_mam_ratio, mae_mad_ratio, r2, logloss, accuracy, `precision`, 
+            recall, f1, roc_auc, avg_precision, thresholds, 
+            precision_at_threshold, recall_at_threshold, f1_at_threshold
+        )
+        SELECT 
+            mt.created_at, 
+            mt.updated_at, 
+            mt.best_params, 
+            mt.model_path, 
+            COALESCE(mt.training_time, s.training_time) as training_time,
+            mt.model_id, 
+            mt.model_selection_id,
+            s.eval_data_std, s.rmse, s.rmse_std_ratio, s.mae, s.mape, 
+            s.mam, s.mad, s.mae_mam_ratio, s.mae_mad_ratio, s.r2, 
+            s.logloss, s.accuracy, s.`precision`, s.recall, s.f1, 
+            s.roc_auc, s.avg_precision, s.thresholds,
+            s.precision_at_threshold, s.recall_at_threshold, s.f1_at_threshold
+        FROM {LECRAPAUD_TABLE_PREFIX}_model_trainings mt
+        LEFT JOIN {LECRAPAUD_TABLE_PREFIX}_scores s ON s.model_training_id = mt.id
+    """
+    )
+
+    # Drop the old tables
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_scores")
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_model_trainings")
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Recreate the old tables
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_model_trainings",
+        sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
+        sa.Column(
+            "created_at",
+            sa.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("best_params", sa.JSON(), nullable=True),
+        sa.Column("model_path", sa.String(length=255), nullable=True),
+        sa.Column("training_time", sa.Integer(), nullable=True),
+        sa.Column("model_id", sa.BigInteger(), nullable=False),
+        sa.Column("model_selection_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["model_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_models.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["model_selection_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_model_selections.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "model_id", "model_selection_id", name="uq_model_training_composite"
+        ),
+    )
+    op.create_index(
+        op.f("ix_model_trainings_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_model_trainings",
+        ["id"],
+        unique=False,
+    )
+
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        sa.Column("id", sa.BigInteger(), autoincrement=True, nullable=False),
+        sa.Column(
+            "created_at",
+            sa.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("type", sa.String(length=50), nullable=False),
+        sa.Column("training_time", sa.Integer(), nullable=True),
+        sa.Column("eval_data_std", sa.Float(), nullable=True),
+        sa.Column("rmse", sa.Float(), nullable=True),
+        sa.Column("rmse_std_ratio", sa.Float(), nullable=True),
+        sa.Column("mae", sa.Float(), nullable=True),
+        sa.Column("mape", sa.Float(), nullable=True),
+        sa.Column("mam", sa.Float(), nullable=True),
+        sa.Column("mad", sa.Float(), nullable=True),
+        sa.Column("mae_mam_ratio", sa.Float(), nullable=True),
+        sa.Column("mae_mad_ratio", sa.Float(), nullable=True),
+        sa.Column("r2", sa.Float(), nullable=True),
+        sa.Column("logloss", sa.Float(), nullable=True),
+        sa.Column("accuracy", sa.Float(), nullable=True),
+        sa.Column("precision", sa.Float(), nullable=True),
+        sa.Column("recall", sa.Float(), nullable=True),
+        sa.Column("f1", sa.Float(), nullable=True),
+        sa.Column("roc_auc", sa.Float(), nullable=True),
+        sa.Column("avg_precision", sa.Float(), nullable=True),
+        sa.Column("thresholds", sa.JSON(), nullable=True),
+        sa.Column("precision_at_threshold", sa.Float(), nullable=True),
+        sa.Column("recall_at_threshold", sa.Float(), nullable=True),
+        sa.Column("f1_at_threshold", sa.Float(), nullable=True),
+        sa.Column("model_training_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["model_training_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_model_trainings.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "model_training_id", name="unique_score_per_model_training"
+        ),
+    )
+    op.create_index(
+        op.f("ix_scores_id"), f"{LECRAPAUD_TABLE_PREFIX}_scores", ["id"], unique=False
+    )
+
+    # Migrate data back (note: we'll lose the type column data, defaulting to 'testset')
+    op.execute(
+        f"""
+        INSERT INTO {LECRAPAUD_TABLE_PREFIX}_model_trainings (
+            id, created_at, updated_at, best_params, model_path, 
+            training_time, model_id, model_selection_id
+        )
+        SELECT 
+            id, created_at, updated_at, best_params, model_path, 
+            training_time, model_id, model_selection_id
+        FROM {LECRAPAUD_TABLE_PREFIX}_model_selection_scores
+    """
+    )
+
+    op.execute(
+        f"""
+        INSERT INTO {LECRAPAUD_TABLE_PREFIX}_scores (
+            created_at, updated_at, type, training_time, eval_data_std, 
+            rmse, rmse_std_ratio, mae, mape, mam, mad, mae_mam_ratio, 
+            mae_mad_ratio, r2, logloss, accuracy, `precision`, recall, 
+            f1, roc_auc, avg_precision, thresholds, precision_at_threshold,
+            recall_at_threshold, f1_at_threshold, model_training_id
+        )
+        SELECT 
+            created_at, updated_at, 'testset', training_time, eval_data_std, 
+            rmse, rmse_std_ratio, mae, mape, mam, mad, mae_mam_ratio, 
+            mae_mad_ratio, r2, logloss, accuracy, precision, recall, 
+            f1, roc_auc, avg_precision, thresholds, precision_at_threshold,
+            recall_at_threshold, f1_at_threshold, id
+        FROM {LECRAPAUD_TABLE_PREFIX}_model_selection_scores
+    """
+    )
+
+    op.drop_index(
+        op.f("ix_model_selection_scores_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_model_selection_scores",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_model_selection_scores")
+    # ### end Alembic commands ###

lecrapaud/db/alembic/versions/2025_10_28_2006-0a8fb7826e9b_add_number_of_targets_and_remove_other_.py

@@ -0,0 +1,42 @@
+"""add number_of_targets and remove other fields from experiments
+
+Revision ID: 0a8fb7826e9b
+Revises: 033e0f7eca4f
+Create Date: 2025-10-28 20:06:54.792631
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import mysql
+
+# revision identifiers, used by Alembic.
+revision: str = '0a8fb7826e9b'
+down_revision: Union[str, None] = '033e0f7eca4f'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('lecrapaud_experiments', sa.Column('number_of_targets', sa.Integer(), nullable=True))
+    op.drop_column('lecrapaud_experiments', 'corr_threshold')
+    op.drop_column('lecrapaud_experiments', 'max_features')
+    op.drop_column('lecrapaud_experiments', 'percentile')
+    op.drop_column('lecrapaud_experiments', 'type')
+    op.drop_index(op.f('ix_model_selection_scores_id'), table_name='lecrapaud_model_selection_scores')
+    op.create_index(op.f('ix_lecrapaud_model_selection_scores_id'), 'lecrapaud_model_selection_scores', ['id'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_lecrapaud_model_selection_scores_id'), table_name='lecrapaud_model_selection_scores')
+    op.create_index(op.f('ix_model_selection_scores_id'), 'lecrapaud_model_selection_scores', ['id'], unique=False)
+    op.add_column('lecrapaud_experiments', sa.Column('type', mysql.VARCHAR(length=50), nullable=False))
+    op.add_column('lecrapaud_experiments', sa.Column('percentile', mysql.FLOAT(), nullable=False))
+    op.add_column('lecrapaud_experiments', sa.Column('max_features', mysql.INTEGER(), autoincrement=False, nullable=False))
+    op.add_column('lecrapaud_experiments', sa.Column('corr_threshold', mysql.FLOAT(), nullable=False))
+    op.drop_column('lecrapaud_experiments', 'number_of_targets')
+    # ### end Alembic commands ###

lecrapaud/db/models/__init__.py

@@ -4,9 +4,8 @@ from lecrapaud.db.models.feature_selection_rank import FeatureSelectionRank
 from lecrapaud.db.models.feature_selection import FeatureSelection
 from lecrapaud.db.models.feature import Feature
 from lecrapaud.db.models.model_selection import ModelSelection
-from lecrapaud.db.models.model_training import ModelTraining
 from lecrapaud.db.models.model import Model
-from lecrapaud.db.models.score import Score
+from lecrapaud.db.models.model_selection_score import ModelSelectionScore
 from lecrapaud.db.models.target import Target
 
 __all__ = [
@@ -16,8 +15,7 @@ __all__ = [
     'FeatureSelection',
     'Feature',
     'ModelSelection',
-    'ModelTraining',
     'Model',
-    'Score',
+    'ModelSelectionScore',
     'Target',
 ]