lecrapaud 0.20.0__py3-none-any.whl → 0.20.2__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

@@ -32,6 +32,7 @@ DB_URI: str = (
 )
 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_OPTIMIZATION_BACKEND = os.getenv(
+    "LECRAPAUD_OPTIMIZATION_BACKEND", "ray"
+).lower()

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/experiment.py

@@ -50,10 +50,43 @@ class Experiment(Base):
     )
     name = Column(String(255), nullable=False)
     path = Column(String(255))  # we do not have this at creation time
-    type = Column(String(50), nullable=False)
     size = Column(Integer, nullable=False)
     train_size = Column(Integer)
     val_size = Column(Integer)
+    test_size = Column(Integer)
+    number_of_groups = Column(Integer)
+    list_of_groups = Column(JSON)
+    number_of_targets = Column(Integer)
+    start_date = Column(DateTime)
+    end_date = Column(DateTime)
+    train_start_date = Column(DateTime)
+    train_end_date = Column(DateTime)
+    val_start_date = Column(DateTime)
+    val_end_date = Column(DateTime)
+    test_start_date = Column(DateTime)
+    test_end_date = Column(DateTime)
+    context = Column(JSON)
+
+    feature_selections = relationship(
+        "FeatureSelection",
+        back_populates="experiment",
+        cascade="all, delete-orphan",
+        lazy="selectin",
+    )
+
+    targets = relationship(
+        "Target",
+        secondary=lecrapaud_experiment_target_association,
+        back_populates="experiments",
+        lazy="selectin",
+    )
+
+    __table_args__ = (
+        UniqueConstraint(
+            "name",
+            name="uq_experiments_composite",
+        ),
+    )
 
     # Relationships
     model_selections = relationship(
@@ -68,16 +101,9 @@ class Experiment(Base):
         """Best RMSE score across all model selections and trainings."""
         # Get the minimum RMSE for each model selection
         min_scores = [
-            min(
-                mss.rmse
-                for mss in ms.model_selection_scores
-                if mss.rmse is not None
-            )
+            min(mss.rmse for mss in ms.model_selection_scores if mss.rmse is not None)
             for ms in self.model_selections
-            if any(
-                mss.rmse is not None
-                for mss in ms.model_selection_scores
-            )
+            if any(mss.rmse is not None for mss in ms.model_selection_scores)
         ]
         return min(min_scores) if min_scores else None
 
@@ -92,10 +118,7 @@ class Experiment(Base):
                 if mss.logloss is not None
             )
             for ms in self.model_selections
-            if any(
-                mss.logloss is not None
-                for mss in ms.model_selection_scores
-            )
+            if any(mss.logloss is not None for mss in ms.model_selection_scores)
         ]
         return min(min_scores) if min_scores else None
 
@@ -104,16 +127,9 @@ class Experiment(Base):
         """Average RMSE score across all model selections and trainings."""
         # Get the minimum RMSE for each model selection
         min_scores = [
-            min(
-                mss.rmse
-                for mss in ms.model_selection_scores
-                if mss.rmse is not None
-            )
+            min(mss.rmse for mss in ms.model_selection_scores if mss.rmse is not None)
             for ms in self.model_selections
-            if any(
-                mss.rmse is not None
-                for mss in ms.model_selection_scores
-            )
+            if any(mss.rmse is not None for mss in ms.model_selection_scores)
         ]
         return mean(min_scores) if min_scores else None
 
@@ -128,50 +144,10 @@ class Experiment(Base):
                 if mss.logloss is not None
             )
             for ms in self.model_selections
-            if any(
-                mss.logloss is not None
-                for mss in ms.model_selection_scores
-            )
+            if any(mss.logloss is not None for mss in ms.model_selection_scores)
         ]
         return mean(min_scores) if min_scores else None
 
-    test_size = Column(Integer)
-    corr_threshold = Column(Float, nullable=False)
-    max_features = Column(Integer, nullable=False)
-    percentile = Column(Float, nullable=False)
-    number_of_groups = Column(Integer)
-    list_of_groups = Column(JSON)
-    start_date = Column(DateTime)
-    end_date = Column(DateTime)
-    train_start_date = Column(DateTime)
-    train_end_date = Column(DateTime)
-    val_start_date = Column(DateTime)
-    val_end_date = Column(DateTime)
-    test_start_date = Column(DateTime)
-    test_end_date = Column(DateTime)
-    context = Column(JSON)
-
-    feature_selections = relationship(
-        "FeatureSelection",
-        back_populates="experiment",
-        cascade="all, delete-orphan",
-        lazy="selectin",
-    )
-
-    targets = relationship(
-        "Target",
-        secondary=lecrapaud_experiment_target_association,
-        back_populates="experiments",
-        lazy="selectin",
-    )
-
-    __table_args__ = (
-        UniqueConstraint(
-            "name",
-            name="uq_experiments_composite",
-        ),
-    )
-
     @classmethod
     @with_db
     def get_all_by_name(cls, name: str | None = None, limit: int = 1000, db=None):
@@ -354,19 +330,18 @@ class Experiment(Base):
 
         # Get the best model score based on lowest logloss or rmse
         model_scores = best_model_selection.model_selection_scores
-        
+
         # Determine if we should use logloss or rmse based on what's available
         if any(ms.logloss is not None for ms in model_scores):
             # Classification: find lowest logloss
             best_score = min(
                 (ms for ms in model_scores if ms.logloss is not None),
-                key=lambda x: x.logloss
+                key=lambda x: x.logloss,
             )
         elif any(ms.rmse is not None for ms in model_scores):
             # Regression: find lowest rmse
             best_score = min(
-                (ms for ms in model_scores if ms.rmse is not None),
-                key=lambda x: x.rmse
+                (ms for ms in model_scores if ms.rmse is not None), key=lambda x: x.rmse
             )
         else:
             return {
@@ -398,12 +373,8 @@ class Experiment(Base):
 
         # Get the model info
         model_info = {
-            "model_type": (
-                score.model.model_type if score.model else "unknown"
-            ),
-            "model_name": (
-                score.model.name if score.model else "unknown"
-            ),
+            "model_type": (score.model.model_type if score.model else "unknown"),
+            "model_name": (score.model.name if score.model else "unknown"),
             "training_time_seconds": score.training_time,
         }
 
@@ -434,7 +405,9 @@ class Experiment(Base):
         return features
 
     @with_db
-    def get_all_features(self, date_column: str = None, group_column: str = None, db=None):
+    def get_all_features(
+        self, date_column: str = None, group_column: str = None, db=None
+    ):
         # Ensure we have a fresh instance attached to the session
         self = db.merge(self)
         target_idx = [target.id for target in self.targets]

lecrapaud/experiment.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pandas as pd
 import joblib
+from datetime import datetime
 
 # Set up coverage file path
 os.environ["COVERAGE_FILE"] = str(Path(".coverage").resolve())
@@ -15,18 +16,18 @@ from lecrapaud.db.session import get_db
 
 def create_experiment(
     data: pd.DataFrame | str,
-    corr_threshold,
-    percentile,
-    max_features,
-    date_column,
-    group_column,
     experiment_name,
+    date_column=None,
+    group_column=None,
     **kwargs,
 ):
     if isinstance(data, str):
         path = f"{data}/data/full.pkl"
         data = joblib.load(path)
 
+    if kwargs.get("time_series") and not date_column:
+        raise ValueError("date_column must be provided for time series experiments")
+
     dates = {}
     if date_column:
         dates["start_date"] = pd.to_datetime(data[date_column].iat[0])
@@ -42,7 +43,10 @@ def create_experiment(
         targets = [
             target for target in all_targets if target.name in data.columns.str.upper()
         ]
-        experiment_name = f"{experiment_name}_{groups["number_of_groups"] if group_column else 'ng'}_{corr_threshold}_{percentile}_{max_features}_{dates['start_date'].date() if date_column else 'nd'}_{dates['end_date'].date() if date_column else 'nd'}"
+        experiment_name = (
+            f"{experiment_name}_{datetime.now().strftime('%Y%m%d_%H%M%S')}"
+        )
+        number_of_targets = len(targets)
 
         experiment_dir = f"{tmp_dir}/{experiment_name}"
         preprocessing_dir = f"{experiment_dir}/preprocessing"
@@ -55,26 +59,20 @@ def create_experiment(
             db=db,
             name=experiment_name,
             path=Path(experiment_dir).resolve(),
-            type="training",
             size=data.shape[0],
-            corr_threshold=corr_threshold,
-            percentile=percentile,
-            max_features=max_features,
+            number_of_targets=number_of_targets,
             **groups,
             **dates,
             context={
-                "corr_threshold": corr_threshold,
-                "percentile": percentile,
-                "max_features": max_features,
                 "date_column": date_column,
                 "group_column": group_column,
                 "experiment_name": experiment_name,
                 **kwargs,
             },
         )
-        
+
         # Set targets relationship after creation/update
         experiment.targets = targets
         experiment.save(db=db)
-        
+
         return experiment

lecrapaud/feature_engineering.py

@@ -87,21 +87,20 @@ class FeatureEngineeringEngine:
     def __init__(
         self,
         data: pd.DataFrame,
-        columns_drop: list[str] = [],
-        columns_boolean: list[str] = [],
-        columns_date: list[str] = [],
-        columns_te_groupby: list[str] = [],
-        columns_te_target: list[str] = [],
+        experiment,
         for_training: bool = True,
         **kwargs,
     ):
         self.data = data
-        self.columns_drop = columns_drop
-        self.columns_boolean = columns_boolean
-        self.columns_date = columns_date
-        self.columns_te_groupby = columns_te_groupby
-        self.columns_te_target = columns_te_target
+        self.experiment = experiment
         self.for_training = for_training
+        
+        # Get all parameters from experiment context
+        self.columns_drop = self.experiment.context.get("columns_drop", [])
+        self.columns_boolean = self.experiment.context.get("columns_boolean", [])
+        self.columns_date = self.experiment.context.get("columns_date", [])
+        self.columns_te_groupby = self.experiment.context.get("columns_te_groupby", [])
+        self.columns_te_target = self.experiment.context.get("columns_te_target", [])
 
     def run(self) -> pd.DataFrame:
         # drop columns
@@ -316,41 +315,30 @@ class PreprocessFeature:
         self,
         data: pd.DataFrame,
         experiment,
-        time_series: bool = False,
-        date_column: str | None = None,
-        group_column: str | None = None,
-        val_size: float = 0.2,
-        test_size: float = 0.2,
-        columns_pca: list[str] = [],
-        pca_temporal: list[dict[str, list[str]]] = [],
-        pca_cross_sectional: list[dict[str, list[str]]] = [],
-        columns_onehot: list[str] = [],
-        columns_binary: list[str] = [],
-        columns_ordinal: list[str] = [],
-        columns_frequency: list[str] = [],
-        target_numbers: list = [],
-        target_clf: list = [],
         **kwargs,
     ):
         self.data = data
         self.data.columns = self.data.columns.str.upper()
-
         self.experiment = experiment
-        self.columns_pca = [col.upper() for col in columns_pca]
-        self.pca_temporal = pca_temporal
-        self.pca_cross_sectional = pca_cross_sectional
-        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
-
-        self.time_series = time_series
-        self.date_column = date_column
-        self.group_column = group_column
-        self.val_size = val_size
-        self.test_size = test_size
+
+        # Get all parameters from experiment context
+        context = self.experiment.context
+        self.time_series = context.get("time_series", False)
+        self.date_column = context.get("date_column", None)
+        self.group_column = context.get("group_column", None)
+        self.val_size = context.get("val_size", 0.2)
+        self.test_size = context.get("test_size", 0.2)
+        self.target_numbers = context.get("target_numbers", [])
+        self.target_clf = context.get("target_clf", [])
+        
+        # Handle list parameters with uppercase conversion
+        self.columns_pca = [col.upper() for col in context.get("columns_pca", [])]
+        self.pca_temporal = context.get("pca_temporal", [])
+        self.pca_cross_sectional = context.get("pca_cross_sectional", [])
+        self.columns_onehot = [col.upper() for col in context.get("columns_onehot", [])]
+        self.columns_binary = [col.upper() for col in context.get("columns_binary", [])]
+        self.columns_ordinal = [col.upper() for col in context.get("columns_ordinal", [])]
+        self.columns_frequency = [col.upper() for col in context.get("columns_frequency", [])]
 
         self.experiment_dir = self.experiment.path
         self.experiment_id = self.experiment.id