lecrapaud 0.14.4__tar.gz → 0.14.6__tar.gz

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.14.4
+Version: 0.14.6
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet

lecrapaud-0.14.6/lecrapaud/db/alembic/versions/2025_06_23_1748-f089dfb7e3ba_.py

@@ -0,0 +1,449 @@
+"""
+
+Revision ID: f089dfb7e3ba
+Revises:
+Create Date: 2025-06-23 17:48:32.842030
+
+"""
+
+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 = "f089dfb7e3ba"
+down_revision: Union[str, None] = None
+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_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_experiments",
+        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("name", sa.String(length=50), nullable=False),
+        sa.Column("path", sa.String(length=255), nullable=True),
+        sa.Column("type", sa.String(length=50), nullable=False),
+        sa.Column("size", sa.Integer(), nullable=False),
+        sa.Column("train_size", sa.Integer(), nullable=True),
+        sa.Column("val_size", sa.Integer(), nullable=True),
+        sa.Column("test_size", sa.Integer(), nullable=True),
+        sa.Column("corr_threshold", sa.Float(), nullable=False),
+        sa.Column("max_features", sa.Integer(), nullable=False),
+        sa.Column("percentile", sa.Float(), nullable=False),
+        sa.Column("number_of_groups", sa.Integer(), nullable=True),
+        sa.Column("list_of_groups", sa.JSON(), nullable=True),
+        sa.Column("start_date", sa.DateTime(), nullable=True),
+        sa.Column("end_date", sa.DateTime(), nullable=True),
+        sa.Column("train_start_date", sa.DateTime(), nullable=True),
+        sa.Column("train_end_date", sa.DateTime(), nullable=True),
+        sa.Column("val_start_date", sa.DateTime(), nullable=True),
+        sa.Column("val_end_date", sa.DateTime(), nullable=True),
+        sa.Column("test_start_date", sa.DateTime(), nullable=True),
+        sa.Column("test_end_date", sa.DateTime(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name", name="uq_experiments_composite"),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_experiments_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_experiments",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_features",
+        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("name", sa.String(length=50), nullable=False),
+        sa.Column("type", sa.String(length=50), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_features_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_features",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_models",
+        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("name", sa.String(length=50), nullable=False),
+        sa.Column("type", sa.String(length=50), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name", "type", name="uq_model_composite"),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_models_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_models",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_targets",
+        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("name", sa.String(length=50), nullable=False),
+        sa.Column("type", sa.String(length=50), nullable=False),
+        sa.Column("description", sa.String(length=255), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name", "type", name="uq_target_composite"),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_targets_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_targets",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_experiment_target_association",
+        sa.Column("experiment_id", sa.BigInteger(), nullable=False),
+        sa.Column("target_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["experiment_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_experiments.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["target_id"], [f"{LECRAPAUD_TABLE_PREFIX}_targets.id"], ondelete="CASCADE"
+        ),
+        sa.PrimaryKeyConstraint("experiment_id", "target_id"),
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_feature_selections",
+        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("training_time", sa.Integer(), nullable=True),
+        sa.Column("best_features_path", sa.String(length=255), nullable=True),
+        sa.Column("experiment_id", sa.BigInteger(), nullable=False),
+        sa.Column("target_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["experiment_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_experiments.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["target_id"], [f"{LECRAPAUD_TABLE_PREFIX}_targets.id"], ondelete="CASCADE"
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "experiment_id", "target_id", name="uq_feature_selection_composite"
+        ),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_feature_selections_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_feature_selections",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_model_selections",
+        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_model_params", sa.JSON(), nullable=True),
+        sa.Column("best_model_path", sa.String(length=255), nullable=True),
+        sa.Column("best_model_id", sa.BigInteger(), nullable=True),
+        sa.Column("target_id", sa.BigInteger(), nullable=False),
+        sa.Column("experiment_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["best_model_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_models.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["experiment_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_experiments.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["target_id"], [f"{LECRAPAUD_TABLE_PREFIX}_targets.id"], ondelete="CASCADE"
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "target_id", "experiment_id", name="uq_model_selection_composite"
+        ),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_model_selections_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_model_selections",
+        ["id"],
+        unique=False,
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_association",
+        sa.Column("feature_selection_id", sa.BigInteger(), nullable=False),
+        sa.Column("feature_id", sa.BigInteger(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["feature_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_features.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["feature_selection_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_feature_selections.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("feature_selection_id", "feature_id"),
+    )
+    op.create_table(
+        f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks",
+        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("score", sa.Float(), nullable=True),
+        sa.Column("pvalue", sa.Float(), nullable=True),
+        sa.Column("support", sa.Integer(), nullable=True),
+        sa.Column("rank", sa.Integer(), nullable=True),
+        sa.Column("method", sa.String(length=50), nullable=True),
+        sa.Column("training_time", sa.Integer(), nullable=True),
+        sa.Column("feature_id", sa.BigInteger(), nullable=True),
+        sa.Column("feature_selection_id", sa.BigInteger(), nullable=True),
+        sa.ForeignKeyConstraint(
+            ["feature_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_features.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["feature_selection_id"],
+            [f"{LECRAPAUD_TABLE_PREFIX}_feature_selections.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "feature_id",
+            "feature_selection_id",
+            "method",
+            name="uq_feature_selection_rank_composite",
+        ),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks",
+        ["id"],
+        unique=False,
+    )
+    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(f"ix_{LECRAPAUD_TABLE_PREFIX}_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("threshold", sa.Float(), nullable=True),
+        sa.Column("precision_at_threshold", sa.Float(), nullable=True),
+        sa.Column("recall_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"),
+    )
+    op.create_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_scores_id"),
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        ["id"],
+        unique=False,
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_scores_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_scores",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_scores")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_model_trainings_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_model_trainings",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_model_trainings")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_ranks")
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_association")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_model_selections_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_model_selections",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_model_selections")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_feature_selections_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_feature_selections",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_feature_selections")
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_experiment_target_association")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_targets_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_targets",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_targets")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_models_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_models",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_models")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_features_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_features",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_features")
+    op.drop_index(
+        op.f(f"ix_{LECRAPAUD_TABLE_PREFIX}_experiments_id"),
+        table_name=f"{LECRAPAUD_TABLE_PREFIX}_experiments",
+    )
+    op.drop_table(f"{LECRAPAUD_TABLE_PREFIX}_experiments")
+    # ### end Alembic commands ###

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/db/alembic/versions/2025_06_24_1216-c62251b129ed_.py

@@ -5,26 +5,31 @@ Revises: f089dfb7e3ba
 Create Date: 2025-06-24 12:16:21.949079
 
 """
+
 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 = 'c62251b129ed'
-down_revision: Union[str, None] = 'f089dfb7e3ba'
+revision: str = "c62251b129ed"
+down_revision: Union[str, None] = "f089dfb7e3ba"
 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('context', sa.JSON(), nullable=True))
+    op.add_column(
+        f"{LECRAPAUD_TABLE_PREFIX}_experiments",
+        sa.Column("context", sa.JSON(), nullable=True),
+    )
     # ### end Alembic commands ###
 
 
 def downgrade() -> None:
     # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_column('lecrapaud_experiments', 'context')
+    op.drop_column(f"{LECRAPAUD_TABLE_PREFIX}_experiments", "context")
     # ### end Alembic commands ###

lecrapaud-0.14.6/lecrapaud/db/alembic/versions/2025_06_24_1711-86457e2f333f_.py

@@ -0,0 +1,45 @@
+"""
+
+Revision ID: 86457e2f333f
+Revises: c62251b129ed
+Create Date: 2025-06-24 17:11:25.187876
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import mysql
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+
+# revision identifiers, used by Alembic.
+revision: str = "86457e2f333f"
+down_revision: Union[str, None] = "c62251b129ed"
+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(
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        sa.Column("thresholds", sa.JSON(), nullable=True),
+    )
+    op.add_column(
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        sa.Column("f1_at_threshold", sa.Float(), nullable=True),
+    )
+    op.drop_column(f"{LECRAPAUD_TABLE_PREFIX}_scores", "threshold")
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        f"{LECRAPAUD_TABLE_PREFIX}_scores",
+        sa.Column("threshold", mysql.FLOAT(), nullable=True),
+    )
+    op.drop_column(f"{LECRAPAUD_TABLE_PREFIX}_scores", "f1_at_threshold")
+    op.drop_column(f"{LECRAPAUD_TABLE_PREFIX}_scores", "thresholds")
+    # ### end Alembic commands ###

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/db/alembic/versions/2025_06_25_1759-72aa496ca65b_.py

@@ -5,26 +5,31 @@ Revises: 86457e2f333f
 Create Date: 2025-06-25 17:59:28.544283
 
 """
+
 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 = '72aa496ca65b'
-down_revision: Union[str, None] = '86457e2f333f'
+revision: str = "72aa496ca65b"
+down_revision: Union[str, None] = "86457e2f333f"
 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_model_selections', sa.Column('best_thresholds', sa.JSON(), nullable=True))
+    op.add_column(
+        f"{LECRAPAUD_TABLE_PREFIX}_model_selections",
+        sa.Column("best_thresholds", sa.JSON(), nullable=True),
+    )
     # ### end Alembic commands ###
 
 
 def downgrade() -> None:
     # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_column('lecrapaud_model_selections', 'best_thresholds')
+    op.drop_column(f"{LECRAPAUD_TABLE_PREFIX}_model_selections", "best_thresholds")
     # ### end Alembic commands ###

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/db/models/experiment.py

@@ -18,24 +18,15 @@ from sqlalchemy import (
 from sqlalchemy.orm import relationship
 
 from lecrapaud.db.models.base import Base
-from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+from lecrapaud.db.models.utils import create_association_table
 
 # jointures
-lecrapaud_experiment_target_association = Table(
-    f"{LECRAPAUD_TABLE_PREFIX}_experiment_target_association",
-    Base.metadata,
-    Column(
-        "experiment_id",
-        BigInteger,
-        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_experiments.id", ondelete="CASCADE"),
-        primary_key=True,
-    ),
-    Column(
-        "target_id",
-        BigInteger,
-        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_targets.id", ondelete="CASCADE"),
-        primary_key=True,
-    ),
+lecrapaud_experiment_target_association = create_association_table(
+    name="experiment_target_association",
+    table1="experiments",
+    column1="experiment",
+    table2="targets",
+    column2="target"
 )
 
 

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/db/models/feature_selection.py

@@ -26,26 +26,15 @@ from collections.abc import Iterable
 
 from lecrapaud.db.session import get_db
 from lecrapaud.db.models.base import Base, with_db
-from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+from lecrapaud.db.models.utils import create_association_table
 
 # jointures
-lecrapaud_feature_selection_association = Table(
-    f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_association",
-    Base.metadata,
-    Column(
-        "feature_selection_id",
-        BigInteger,
-        ForeignKey(
-            f"{LECRAPAUD_TABLE_PREFIX}_feature_selections.id", ondelete="CASCADE"
-        ),
-        primary_key=True,
-    ),
-    Column(
-        "feature_id",
-        BigInteger,
-        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_features.id", ondelete="CASCADE"),
-        primary_key=True,
-    ),
+lecrapaud_feature_selection_association = create_association_table(
+    name="feature_selection_association",
+    table1="feature_selections",
+    column1="feature_selection",
+    table2="features",
+    column2="feature"
 )
 
 

lecrapaud-0.14.6/lecrapaud/db/models/utils.py

@@ -0,0 +1,32 @@
+from sqlalchemy import Table, Column, BigInteger, ForeignKey
+
+from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
+
+
+def create_association_table(name, table1, column1, table2, column2):
+    """Create an association table with the LECRAPAUD_TABLE_PREFIX.
+
+    Args:
+        name: The base name for the association table (will be prefixed)
+        table1: First table name (without prefix)
+        column1: First column name (will be used as f"{column1}_id")
+        table2: Second table name (without prefix)
+        column2: Second column name (will be used as f"{column2}_id")
+    """
+    return Table(
+        f"{LECRAPAUD_TABLE_PREFIX}_{name}",
+        Base.metadata,
+        Column(
+            f"{column1}_id",
+            BigInteger,
+            ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_{table1}.id", ondelete="CASCADE"),
+            primary_key=True,
+        ),
+        Column(
+            f"{column2}_id",
+            BigInteger,
+            ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_{table2}.id", ondelete="CASCADE"),
+            primary_key=True,
+        ),
+    )

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/feature_engineering.py

@@ -380,10 +380,16 @@ class PreprocessFeature:
         summary = summarize_dataframe(train)
         summary.to_csv(f"{self.experiment_dir}/feature_summary.csv", index=False)
 
+        # Save all features before selection
+        joblib.dump(
+            train, f"{self.preprocessing_dir}/all_features_before_selection.pkl"
+        )
+
         return train, val, test
 
     def inference(self):
         data = self.data
+
         # PCA
         if os.path.exists(f"{self.preprocessing_dir}/pcas.pkl"):
             pcas = joblib.load(f"{self.preprocessing_dir}/pcas.pkl")
@@ -652,7 +658,7 @@ class PreprocessFeature:
         X_transformed = pd.DataFrame(transformed, columns=column_names, index=df.index)
 
         # Try to convert columns to best possible dtypes
-        X_transformed = X_transformed.convert_dtypes()
+        X_transformed = X_transformed.convert_ups()
 
         # Insert features in db
         if save_in_db:

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/lecrapaud/model_selection.py

@@ -570,11 +570,13 @@ class ModelEngine:
         self.target_type = self._model.target_type
 
         # Load threshold
-        self.threshold = (
-            joblib.load(f"{self.path}/thresholds.pkl")
-            if self.target_type == "classification"
-            else None
-        )
+        if (
+            os.path.exists(f"{self.path}/thresholds.pkl")
+            and self.target_type == "classification"
+        ):
+            self.threshold = joblib.load(f"{self.path}/thresholds.pkl")
+        else:
+            self.threshold = None
 
         logger.info(
             f"Loaded model {self._model.model_name} and threshold {self.threshold}"

{lecrapaud-0.14.4 → lecrapaud-0.14.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.14.4"
+version = "0.14.6"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}

lecrapaud-0.14.4/lecrapaud/db/alembic/versions/2025_06_23_1748-f089dfb7e3ba_.py

@@ -1,214 +0,0 @@
-"""
-
-Revision ID: f089dfb7e3ba
-Revises: 
-Create Date: 2025-06-23 17:48:32.842030
-
-"""
-from typing import Sequence, Union
-
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision: str = 'f089dfb7e3ba'
-down_revision: Union[str, None] = None
-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_table('lecrapaud_experiments',
-    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('name', sa.String(length=50), nullable=False),
-    sa.Column('path', sa.String(length=255), nullable=True),
-    sa.Column('type', sa.String(length=50), nullable=False),
-    sa.Column('size', sa.Integer(), nullable=False),
-    sa.Column('train_size', sa.Integer(), nullable=True),
-    sa.Column('val_size', sa.Integer(), nullable=True),
-    sa.Column('test_size', sa.Integer(), nullable=True),
-    sa.Column('corr_threshold', sa.Float(), nullable=False),
-    sa.Column('max_features', sa.Integer(), nullable=False),
-    sa.Column('percentile', sa.Float(), nullable=False),
-    sa.Column('number_of_groups', sa.Integer(), nullable=True),
-    sa.Column('list_of_groups', sa.JSON(), nullable=True),
-    sa.Column('start_date', sa.DateTime(), nullable=True),
-    sa.Column('end_date', sa.DateTime(), nullable=True),
-    sa.Column('train_start_date', sa.DateTime(), nullable=True),
-    sa.Column('train_end_date', sa.DateTime(), nullable=True),
-    sa.Column('val_start_date', sa.DateTime(), nullable=True),
-    sa.Column('val_end_date', sa.DateTime(), nullable=True),
-    sa.Column('test_start_date', sa.DateTime(), nullable=True),
-    sa.Column('test_end_date', sa.DateTime(), nullable=True),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('name', name='uq_experiments_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_experiments_id'), 'lecrapaud_experiments', ['id'], unique=False)
-    op.create_table('lecrapaud_features',
-    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('name', sa.String(length=50), nullable=False),
-    sa.Column('type', sa.String(length=50), nullable=True),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('name')
-    )
-    op.create_index(op.f('ix_lecrapaud_features_id'), 'lecrapaud_features', ['id'], unique=False)
-    op.create_table('lecrapaud_models',
-    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('name', sa.String(length=50), nullable=False),
-    sa.Column('type', sa.String(length=50), nullable=False),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('name', 'type', name='uq_model_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_models_id'), 'lecrapaud_models', ['id'], unique=False)
-    op.create_table('lecrapaud_targets',
-    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('name', sa.String(length=50), nullable=False),
-    sa.Column('type', sa.String(length=50), nullable=False),
-    sa.Column('description', sa.String(length=255), nullable=True),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('name', 'type', name='uq_target_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_targets_id'), 'lecrapaud_targets', ['id'], unique=False)
-    op.create_table('lecrapaud_experiment_target_association',
-    sa.Column('experiment_id', sa.BigInteger(), nullable=False),
-    sa.Column('target_id', sa.BigInteger(), nullable=False),
-    sa.ForeignKeyConstraint(['experiment_id'], ['lecrapaud_experiments.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['target_id'], ['lecrapaud_targets.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('experiment_id', 'target_id')
-    )
-    op.create_table('lecrapaud_feature_selections',
-    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('training_time', sa.Integer(), nullable=True),
-    sa.Column('best_features_path', sa.String(length=255), nullable=True),
-    sa.Column('experiment_id', sa.BigInteger(), nullable=False),
-    sa.Column('target_id', sa.BigInteger(), nullable=False),
-    sa.ForeignKeyConstraint(['experiment_id'], ['lecrapaud_experiments.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['target_id'], ['lecrapaud_targets.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('experiment_id', 'target_id', name='uq_feature_selection_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_feature_selections_id'), 'lecrapaud_feature_selections', ['id'], unique=False)
-    op.create_table('lecrapaud_model_selections',
-    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_model_params', sa.JSON(), nullable=True),
-    sa.Column('best_model_path', sa.String(length=255), nullable=True),
-    sa.Column('best_model_id', sa.BigInteger(), nullable=True),
-    sa.Column('target_id', sa.BigInteger(), nullable=False),
-    sa.Column('experiment_id', sa.BigInteger(), nullable=False),
-    sa.ForeignKeyConstraint(['best_model_id'], ['lecrapaud_models.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['experiment_id'], ['lecrapaud_experiments.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['target_id'], ['lecrapaud_targets.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('target_id', 'experiment_id', name='uq_model_selection_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_model_selections_id'), 'lecrapaud_model_selections', ['id'], unique=False)
-    op.create_table('lecrapaud_feature_selection_association',
-    sa.Column('feature_selection_id', sa.BigInteger(), nullable=False),
-    sa.Column('feature_id', sa.BigInteger(), nullable=False),
-    sa.ForeignKeyConstraint(['feature_id'], ['lecrapaud_features.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['feature_selection_id'], ['lecrapaud_feature_selections.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('feature_selection_id', 'feature_id')
-    )
-    op.create_table('lecrapaud_feature_selection_ranks',
-    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('score', sa.Float(), nullable=True),
-    sa.Column('pvalue', sa.Float(), nullable=True),
-    sa.Column('support', sa.Integer(), nullable=True),
-    sa.Column('rank', sa.Integer(), nullable=True),
-    sa.Column('method', sa.String(length=50), nullable=True),
-    sa.Column('training_time', sa.Integer(), nullable=True),
-    sa.Column('feature_id', sa.BigInteger(), nullable=True),
-    sa.Column('feature_selection_id', sa.BigInteger(), nullable=True),
-    sa.ForeignKeyConstraint(['feature_id'], ['lecrapaud_features.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['feature_selection_id'], ['lecrapaud_feature_selections.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('feature_id', 'feature_selection_id', 'method', name='uq_feature_selection_rank_composite')
-    )
-    op.create_index(op.f('ix_lecrapaud_feature_selection_ranks_id'), 'lecrapaud_feature_selection_ranks', ['id'], unique=False)
-    op.create_table('lecrapaud_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'], ['lecrapaud_models.id'], ),
-    sa.ForeignKeyConstraint(['model_selection_id'], ['lecrapaud_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_lecrapaud_model_trainings_id'), 'lecrapaud_model_trainings', ['id'], unique=False)
-    op.create_table('lecrapaud_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('threshold', sa.Float(), nullable=True),
-    sa.Column('precision_at_threshold', sa.Float(), nullable=True),
-    sa.Column('recall_at_threshold', sa.Float(), nullable=True),
-    sa.Column('model_training_id', sa.BigInteger(), nullable=False),
-    sa.ForeignKeyConstraint(['model_training_id'], ['lecrapaud_model_trainings.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index(op.f('ix_lecrapaud_scores_id'), 'lecrapaud_scores', ['id'], unique=False)
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index(op.f('ix_lecrapaud_scores_id'), table_name='lecrapaud_scores')
-    op.drop_table('lecrapaud_scores')
-    op.drop_index(op.f('ix_lecrapaud_model_trainings_id'), table_name='lecrapaud_model_trainings')
-    op.drop_table('lecrapaud_model_trainings')
-    op.drop_index(op.f('ix_lecrapaud_feature_selection_ranks_id'), table_name='lecrapaud_feature_selection_ranks')
-    op.drop_table('lecrapaud_feature_selection_ranks')
-    op.drop_table('lecrapaud_feature_selection_association')
-    op.drop_index(op.f('ix_lecrapaud_model_selections_id'), table_name='lecrapaud_model_selections')
-    op.drop_table('lecrapaud_model_selections')
-    op.drop_index(op.f('ix_lecrapaud_feature_selections_id'), table_name='lecrapaud_feature_selections')
-    op.drop_table('lecrapaud_feature_selections')
-    op.drop_table('lecrapaud_experiment_target_association')
-    op.drop_index(op.f('ix_lecrapaud_targets_id'), table_name='lecrapaud_targets')
-    op.drop_table('lecrapaud_targets')
-    op.drop_index(op.f('ix_lecrapaud_models_id'), table_name='lecrapaud_models')
-    op.drop_table('lecrapaud_models')
-    op.drop_index(op.f('ix_lecrapaud_features_id'), table_name='lecrapaud_features')
-    op.drop_table('lecrapaud_features')
-    op.drop_index(op.f('ix_lecrapaud_experiments_id'), table_name='lecrapaud_experiments')
-    op.drop_table('lecrapaud_experiments')
-    # ### end Alembic commands ###

lecrapaud-0.14.4/lecrapaud/db/alembic/versions/2025_06_24_1711-86457e2f333f_.py

@@ -1,34 +0,0 @@
-"""
-
-Revision ID: 86457e2f333f
-Revises: c62251b129ed
-Create Date: 2025-06-24 17:11:25.187876
-
-"""
-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 = '86457e2f333f'
-down_revision: Union[str, None] = 'c62251b129ed'
-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_scores', sa.Column('thresholds', sa.JSON(), nullable=True))
-    op.add_column('lecrapaud_scores', sa.Column('f1_at_threshold', sa.Float(), nullable=True))
-    op.drop_column('lecrapaud_scores', 'threshold')
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.add_column('lecrapaud_scores', sa.Column('threshold', mysql.FLOAT(), nullable=True))
-    op.drop_column('lecrapaud_scores', 'f1_at_threshold')
-    op.drop_column('lecrapaud_scores', 'thresholds')
-    # ### end Alembic commands ###