lecrapaud 0.14.0__tar.gz → 0.14.2__tar.gz

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.14.0
+Version: 0.14.2
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet
@@ -177,13 +177,13 @@ experiment.model_selection(std_data, reshaped_data)
 
 ## ⚠️ Using Alembic in Your Project (Important for Integrators)
 
-If you use Alembic for migrations in your own project and you share the same database with LeCrapaud, you must ensure that Alembic does **not** attempt to drop or modify LeCrapaud tables (those prefixed with `lecrapaud_`).
+If you use Alembic for migrations in your own project and you share the same database with LeCrapaud, you must ensure that Alembic does **not** attempt to drop or modify LeCrapaud tables (those prefixed with `{LECRAPAUD_TABLE_PREFIX}_`).
 
 By default, Alembic's autogenerate feature will propose to drop any table that exists in the database but is not present in your project's models. To prevent this, add the following filter to your `env.py`:
 
 ```python
 def include_object(object, name, type_, reflected, compare_to):
-    if type_ == "table" and name.startswith("lecrapaud_"):
+    if type_ == "table" and name.startswith(f"{LECRAPAUD_TABLE_PREFIX}_"):
         return False  # Ignore LeCrapaud tables
     return True
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/README.md

@@ -144,13 +144,13 @@ experiment.model_selection(std_data, reshaped_data)
 
 ## ⚠️ Using Alembic in Your Project (Important for Integrators)
 
-If you use Alembic for migrations in your own project and you share the same database with LeCrapaud, you must ensure that Alembic does **not** attempt to drop or modify LeCrapaud tables (those prefixed with `lecrapaud_`).
+If you use Alembic for migrations in your own project and you share the same database with LeCrapaud, you must ensure that Alembic does **not** attempt to drop or modify LeCrapaud tables (those prefixed with `{LECRAPAUD_TABLE_PREFIX}_`).
 
 By default, Alembic's autogenerate feature will propose to drop any table that exists in the database but is not present in your project's models. To prevent this, add the following filter to your `env.py`:
 
 ```python
 def include_object(object, name, type_, reflected, compare_to):
-    if type_ == "table" and name.startswith("lecrapaud_"):
+    if type_ == "table" and name.startswith(f"{LECRAPAUD_TABLE_PREFIX}_"):
         return False  # Ignore LeCrapaud tables
     return True
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/api.py

@@ -298,6 +298,9 @@ class ExperimentEngine:
         all_features = self.experiment.get_all_features(
             date_column=self.date_column, group_column=self.group_column
         )
+        joblib.dump(
+            all_features, f"{self.experiment.path}/preprocessing/all_features.pkl"
+        )
         return all_features
 
     def preprocess_model(self, train, val=None, test=None, for_training=True):

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/alembic/env.py

@@ -6,6 +6,7 @@ from sqlalchemy import pool
 from alembic import context
 from lecrapaud.db.session import DATABASE_URL
 from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
@@ -46,7 +47,7 @@ def run_migrations_offline() -> None:
         target_metadata=target_metadata,
         literal_binds=True,
         dialect_opts={"paramstyle": "named"},
-        version_table="lecrapaud_alembic_version",
+        version_table=f"{LECRAPAUD_TABLE_PREFIX}_alembic_version",
     )
 
     with context.begin_transaction():
@@ -70,7 +71,7 @@ def run_migrations_online() -> None:
         context.configure(
             connection=connection,
             target_metadata=target_metadata,
-            version_table="lecrapaud_alembic_version",
+            version_table=f"{LECRAPAUD_TABLE_PREFIX}_alembic_version",
         )
 
         with context.begin_transaction():

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/experiment.py

@@ -18,21 +18,22 @@ from sqlalchemy import (
 from sqlalchemy.orm import relationship
 
 from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 # jointures
 lecrapaud_experiment_target_association = Table(
-    "lecrapaud_experiment_target_association",
+    f"{LECRAPAUD_TABLE_PREFIX}_experiment_target_association",
     Base.metadata,
     Column(
         "experiment_id",
         BigInteger,
-        ForeignKey("lecrapaud_experiments.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_experiments.id", ondelete="CASCADE"),
         primary_key=True,
     ),
     Column(
         "target_id",
         BigInteger,
-        ForeignKey("lecrapaud_targets.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_targets.id", ondelete="CASCADE"),
         primary_key=True,
     ),
 )

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/feature_selection.py

@@ -26,21 +26,24 @@ 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
 
 # jointures
 lecrapaud_feature_selection_association = Table(
-    "lecrapaud_feature_selection_association",
+    f"{LECRAPAUD_TABLE_PREFIX}_feature_selection_association",
     Base.metadata,
     Column(
         "feature_selection_id",
         BigInteger,
-        ForeignKey("lecrapaud_feature_selections.id", ondelete="CASCADE"),
+        ForeignKey(
+            f"{LECRAPAUD_TABLE_PREFIX}_feature_selections.id", ondelete="CASCADE"
+        ),
         primary_key=True,
     ),
     Column(
         "feature_id",
         BigInteger,
-        ForeignKey("lecrapaud_features.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_features.id", ondelete="CASCADE"),
         primary_key=True,
     ),
 )
@@ -62,12 +65,12 @@ class FeatureSelection(Base):
     best_features_path = Column(String(255))
     experiment_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_experiments.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_experiments.id", ondelete="CASCADE"),
         nullable=False,
     )
     target_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_targets.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_targets.id", ondelete="CASCADE"),
         nullable=False,
     )
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/feature_selection_rank.py

@@ -20,6 +20,7 @@ from sqlalchemy.dialects.mysql import insert
 
 from lecrapaud.db.session import get_db
 from lecrapaud.db.models.base import Base, with_db
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 
 class FeatureSelectionRank(Base):
@@ -41,10 +42,14 @@ class FeatureSelectionRank(Base):
     method = Column(String(50))
     training_time = Column(Integer)
     feature_id = Column(
-        BigInteger, ForeignKey("lecrapaud_features.id", ondelete="CASCADE")
+        BigInteger,
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_features.id", ondelete="CASCADE"),
     )
     feature_selection_id = Column(
-        BigInteger, ForeignKey("lecrapaud_feature_selections.id", ondelete="CASCADE")
+        BigInteger,
+        ForeignKey(
+            f"{LECRAPAUD_TABLE_PREFIX}_feature_selections.id", ondelete="CASCADE"
+        ),
     )
 
     feature = relationship("Feature", lazy="selectin")

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/model_selection.py

@@ -19,6 +19,7 @@ from sqlalchemy.orm import relationship, Mapped, mapped_column, DeclarativeBase
 
 from lecrapaud.db.session import get_db
 from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 
 class ModelSelection(Base):
@@ -37,16 +38,17 @@ class ModelSelection(Base):
     best_thresholds = Column(JSON)
     best_model_path = Column(String(255))
     best_model_id = Column(
-        BigInteger, ForeignKey("lecrapaud_models.id", ondelete="CASCADE")
+        BigInteger,
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_models.id", ondelete="CASCADE"),
     )
     target_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_targets.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_targets.id", ondelete="CASCADE"),
         nullable=False,
     )
     experiment_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_experiments.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_experiments.id", ondelete="CASCADE"),
         nullable=False,
     )
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/model_training.py

@@ -19,6 +19,7 @@ from sqlalchemy.orm import relationship, Mapped, mapped_column, DeclarativeBase
 
 from lecrapaud.db.session import get_db
 from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 
 class ModelTraining(Base):
@@ -36,10 +37,12 @@ class ModelTraining(Base):
     best_params = Column(JSON)
     model_path = Column(String(255))
     training_time = Column(Integer)
-    model_id = Column(BigInteger, ForeignKey("lecrapaud_models.id"), nullable=False)
+    model_id = Column(
+        BigInteger, ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_models.id"), nullable=False
+    )
     model_selection_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_model_selections.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_model_selections.id", ondelete="CASCADE"),
         nullable=False,
     )
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/db/models/score.py

@@ -11,6 +11,7 @@ from sqlalchemy import (
 from sqlalchemy import func
 from sqlalchemy.orm import relationship
 from lecrapaud.db.models.base import Base
+from lecrapaud.config import LECRAPAUD_TABLE_PREFIX
 
 
 class Score(Base):
@@ -50,7 +51,7 @@ class Score(Base):
     f1_at_threshold = Column(Float)
     model_training_id = Column(
         BigInteger,
-        ForeignKey("lecrapaud_model_trainings.id", ondelete="CASCADE"),
+        ForeignKey(f"{LECRAPAUD_TABLE_PREFIX}_model_trainings.id", ondelete="CASCADE"),
         nullable=False,
     )
 

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/experiment.py

@@ -24,7 +24,7 @@ def create_experiment(
     **kwargs,
 ):
     if isinstance(data, str):
-        path = f"{data}/data/full.pkl" if "data" not in data else f"{data}/full.pkl"
+        path = f"{data}/data/full.pkl"
         data = joblib.load(path)
 
     dates = {}

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/lecrapaud/feature_engineering.py

@@ -327,11 +327,11 @@ class PreprocessFeature:
         self.data.columns = self.data.columns.str.upper()
 
         self.experiment = experiment
-        self.columns_pca = columns_pca
-        self.columns_onehot = columns_onehot
-        self.columns_binary = columns_binary
-        self.columns_ordinal = columns_ordinal
-        self.columns_frequency = columns_frequency
+        self.columns_pca = [col.upper() for col in columns_pca]
+        self.columns_onehot = [col.upper() for col in columns_onehot]
+        self.columns_binary = [col.upper() for col in columns_binary]
+        self.columns_ordinal = [col.upper() for col in columns_ordinal]
+        self.columns_frequency = [col.upper() for col in columns_frequency]
         self.target_numbers = target_numbers
         self.target_clf = target_clf
 
@@ -526,7 +526,6 @@ class PreprocessFeature:
 
         pcas_dict = {}
         for column in columns:
-            column = column.upper()
             # Convert text to embeddings if necessary
             if not isinstance(df[column].iloc[0], (np.ndarray, list)):
                 sentences = df[column].astype(str).tolist()
@@ -582,10 +581,10 @@ class PreprocessFeature:
         Returns:
             tuple: (transformed DataFrame, ColumnTransformer)
         """
-        columns_onehot: list[str] = [col.upper() for col in self.columns_onehot]
-        columns_binary: list[str] = [col.upper() for col in self.columns_binary]
-        columns_ordinal: list[str] = [col.upper() for col in self.columns_ordinal]
-        columns_frequency: list[str] = [col.upper() for col in self.columns_frequency]
+        columns_onehot: list[str] = self.columns_onehot
+        columns_binary: list[str] = self.columns_binary
+        columns_ordinal: list[str] = self.columns_ordinal
+        columns_frequency: list[str] = self.columns_frequency
 
         X = df.loc[:, ~df.columns.str.contains("^TARGET_")]
         y = df.loc[:, df.columns.str.contains("^TARGET_")]

{lecrapaud-0.14.0 → lecrapaud-0.14.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.14.0"
+version = "0.14.2"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}