lecrapaud 0.21.1__py3-none-any.whl → 0.21.2__py3-none-any.whl

lecrapaud/config.py

@@ -34,5 +34,5 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 LECRAPAUD_LOGFILE = os.getenv("LECRAPAUD_LOGFILE")
 LECRAPAUD_TABLE_PREFIX = os.getenv("LECRAPAUD_TABLE_PREFIX", "lecrapaud")
 LECRAPAUD_OPTIMIZATION_BACKEND = os.getenv(
-    "LECRAPAUD_OPTIMIZATION_BACKEND", "ray"
+    "LECRAPAUD_OPTIMIZATION_BACKEND", "hyperopt"
 ).lower()

lecrapaud/feature_selection.py

@@ -278,24 +278,32 @@ class FeatureSelectionEngine:
 
         features_selected_list = features_selected["features"].values.tolist()
         
-        # Save ensemble features before correlation (aggregated features)
-        logger.info("Saving ensemble features before correlation...")
-        all_features_in_data = self.X.columns.tolist()
+        # Save ensemble features for all numerical features with global ranking
+        logger.info("Saving ensemble features with global ranking for all numerical features...")
+        numerical_features_in_data = self.X_numerical.columns.tolist()
         ensemble_rows = []
         
-        # Add global rank for selected features
-        features_selected_with_global_rank = features_selected.copy()
-        features_selected_with_global_rank["global_rank"] = range(1, len(features_selected_with_global_rank) + 1)
+        # Create global ranking for ALL numerical features (1 to n, no null values)
+        all_numerical_scores = pd.concat(results, axis=0)
+        all_numerical_scores = all_numerical_scores.groupby("features").agg({
+            "rank": "mean"  # Average rank across all methods
+        }).reset_index()
+        all_numerical_scores.sort_values("rank", inplace=True)
+        all_numerical_scores["global_rank"] = range(1, len(all_numerical_scores) + 1)
         
-        for feature in all_features_in_data:
+        for feature in numerical_features_in_data:
             feature_id = feature_map.get(feature)
             if feature_id:
                 is_selected = feature in features_selected_list
-                global_rank = None
-                if is_selected:
-                    global_rank = features_selected_with_global_rank[
-                        features_selected_with_global_rank["features"] == feature
+                
+                # Get global rank (no null values - all features get a rank)
+                if feature in all_numerical_scores["features"].values:
+                    global_rank = all_numerical_scores[
+                        all_numerical_scores["features"] == feature
                     ]["global_rank"].values[0]
+                else:
+                    # Fallback: assign last rank + position for features not in results
+                    global_rank = len(all_numerical_scores) + numerical_features_in_data.index(feature) + 1
                 
                 ensemble_rows.append({
                     "feature_selection_id": feature_selection.id,
@@ -353,28 +361,12 @@ class FeatureSelectionEngine:
         )
         
         # Final update for features after max limitation (final selection)
-        logger.info("Finalizing ensemble features with categorical features...")
+        logger.info("Finalizing ensemble features...")
         for row in ensemble_rows:
             feature = Feature.get(row["feature_id"]).name
             if feature in features and row["support"] == 1:
                 row["support"] = 2  # 2 = in final selection
         
-        # Add categorical features to ensemble if not already present
-        if target_type == "classification":
-            for cat_feature in categorical_features_selected:
-                feature_id = feature_map.get(cat_feature)
-                if feature_id and not any(row["feature_id"] == feature_id for row in ensemble_rows):
-                    ensemble_rows.append({
-                        "feature_selection_id": feature_selection.id,
-                        "feature_id": feature_id,
-                        "method": "ensemble",
-                        "score": None,
-                        "pvalue": None,
-                        "support": 2,  # 2 = in final selection (categorical)
-                        "rank": None,  # No rank for categorical features added at the end
-                        "training_time": 0,
-                    })
-        
         # Re-save all ensemble data with updated support values
         FeatureSelectionRank.bulk_upsert(rows=ensemble_rows)
         logger.debug(

lecrapaud/model_selection.py

@@ -55,8 +55,7 @@ from tensorboardX import SummaryWriter
 
 # Optimization
 import ray
-from ray.tune import Tuner, TuneConfig, with_parameters
-from ray.train import RunConfig
+from ray.tune import Tuner, TuneConfig, with_parameters, RunConfig
 from ray.tune.search.hyperopt import HyperOptSearch
 from ray.tune.search.bayesopt import BayesOptSearch
 from ray.tune.logger import TBXLoggerCallback
@@ -1357,8 +1356,12 @@ class ModelSelectionEngine:
         """Choose between Ray Tune and HyperOpt standalone based on configuration."""
         if LECRAPAUD_OPTIMIZATION_BACKEND == "hyperopt":
             return self.hyperoptimize_hyperopt(x_train, y_train, x_val, y_val, model)
-        else:
+        elif LECRAPAUD_OPTIMIZATION_BACKEND == "ray":
             return self.hyperoptimize_ray(x_train, y_train, x_val, y_val, model)
+        else:
+            raise ValueError(
+                f"Invalid optimization backend: {LECRAPAUD_OPTIMIZATION_BACKEND}."
+            )
 
     def hyperoptimize_hyperopt(
         self, x_train, y_train, x_val, y_val, model: ModelEngine
@@ -1746,11 +1749,11 @@ def evaluate(
         y_pred_proba = (
             prediction[1] if num_classes == 2 else prediction.iloc[:, 2:].values
         )
-        if num_classes > 2:
-            lb = LabelBinarizer(sparse_output=False)  # Change to True for sparse matrix
-            lb.fit(labels)
-            y_true_onhot = lb.transform(y_true)
-            y_pred_onehot = lb.transform(y_pred)
+        # if num_classes > 2:
+        #     lb = LabelBinarizer(sparse_output=False)  # Change to True for sparse matrix
+        #     lb.fit(labels)
+        #     y_true_onhot = lb.transform(y_true)
+        #     y_pred_onehot = lb.transform(y_pred)
 
         score["LOGLOSS"] = log_loss(y_true, y_pred_proba)
         score["ACCURACY"] = accuracy_score(y_true, y_pred)

{lecrapaud-0.21.1.dist-info → lecrapaud-0.21.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lecrapaud
-Version: 0.21.1
+Version: 0.21.2
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 License-File: LICENSE
@@ -218,7 +218,11 @@ context = {
     "val_size": 0.2,
     "test_size": 0.2,
     "pca_temporal": [
-        {"name": "LAST_20_RET", "columns": [f"RET_-{i}" for i in range(1, 21)]},
+        # Old format (still supported)
+        # {"name": "LAST_20_RET", "columns": [f"RET_-{i}" for i in range(1, 21)]},
+        # New simplified format - automatically creates lag columns
+        {"name": "LAST_20_RET", "column": "RET", "lags": 20},
+        {"name": "LAST_10_VOL", "column": "VOLUME", "lags": 10},
     ],
     "pca_cross_sectional": [
         {
@@ -255,11 +259,20 @@ experiment = app.create_experiment(data=your_dataframe, **context)
 
 2. **Parameter Precedence**: When loading an existing experiment, the stored context takes precedence over any parameters passed to the constructor.
 
-3. **PCA Time Series**: For time series data with `pca_cross_sectional` where index equals `date_column`, the system automatically uses an expanding window approach to prevent data leakage.
+3. **PCA Time Series**: 
+   - For time series data, both `pca_cross_sectional` and `pca_temporal` automatically use an expanding window approach with periodic refresh (default: every 90 days) to prevent data leakage.
+   - The system fits PCA only on historical data (lookback window of 365 days by default) and avoids look-ahead bias.
+   - For panel data (e.g., multiple stocks), lag features are created per group when using the simplified `pca_temporal` format.
+   - Missing PCA values are handled with forward-fill followed by zero-fill to ensure compatibility with downstream models.
 
-4. **OpenAI Embeddings**: If using `columns_pca` with text columns, ensure `OPENAI_API_KEY` is set as an environment variable.
+4. **PCA Temporal Simplified Format**: 
+   - Instead of manually listing lag columns: `{"name": "LAST_20_RET", "columns": ["RET_-1", "RET_-2", ..., "RET_-20"]}`
+   - Use the simplified format: `{"name": "LAST_20_RET", "column": "RET", "lags": 20}`
+   - The system automatically creates the lag columns, handling panel data correctly with `group_column`.
 
-5. **Model Indices**: The `models_idx` parameter accepts both integer indices and string names (e.g., `'xgb'`, `'lgb'`, `'catboost'`).
+5. **OpenAI Embeddings**: If using `columns_pca` with text columns, ensure `OPENAI_API_KEY` is set as an environment variable.
+
+6. **Model Indices**: The `models_idx` parameter accepts both integer indices and string names (e.g., `'xgb'`, `'lgb'`, `'catboost'`).
 
 
 

{lecrapaud-0.21.1.dist-info → lecrapaud-0.21.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
 lecrapaud/__init__.py,sha256=7Wp_VF08UZP8o-GkpB4_yRjP4twQmpcTc3202OkPmHs,176
 lecrapaud/api.py,sha256=7OL_wbg9hCmlZ0WI6eCDkublntES3f320OZlpuKu8f4,22376
-lecrapaud/config.py,sha256=0NEg61QdLxQ97bVFDDXa6OwlWFEo_z8VIhX5KrD1ik0,1170
+lecrapaud/config.py,sha256=7kwV9kpglFX79YC3fKcANawWJMYYi7SGaVShNsmO4EQ,1175
 lecrapaud/db/__init__.py,sha256=82o9fMfaqKXPh2_rt44EzNRVZV1R4LScEnQYvj_TjK0,34
 lecrapaud/db/alembic/README,sha256=MVlc9TYmr57RbhXET6QxgyCcwWP7w-vLkEsirENqiIQ,38
 lecrapaud/db/alembic/env.py,sha256=RvTTBa3bDVBxmDtapAfzUoeWBgmVQU3s9U6HmQCAP84,2421
@@ -31,7 +31,7 @@ lecrapaud/db/session.py,sha256=u9NCwUoV5VbtScRb6HOSQr4oTEjIwj0waP5mGlc1qJg,3735
 lecrapaud/directories.py,sha256=0LrANuDgbuneSLker60c6q2hmGnQ3mKHIztTGzTx6Gw,826
 lecrapaud/experiment.py,sha256=LiecZS3P4igO_3nJ4IB-2b25CttQS2RePDnhBNucvdE,2478
 lecrapaud/feature_engineering.py,sha256=SvGrJXv24rVgH0QE5mRwJITcCLfUqgbV2Ep68bBVnJs,58794
-lecrapaud/feature_selection.py,sha256=Q9xWVmZsvRjX9mJHB_PY_KLXsEAYNLX7txSe0cniY4A,47529
+lecrapaud/feature_selection.py,sha256=vzL-eklVZl-tHIwqTy4Yg9kYpwOTCoM72IrFoJyDmg8,47203
 lecrapaud/integrations/openai_integration.py,sha256=hHLF3fk5Bps8KNbNrEL3NUFa945jwClE6LrLpuMZOd4,7459
 lecrapaud/jobs/__init__.py,sha256=ZkrsyTOR21c_wN7RY8jPhm8jCrL1oCEtTsf3VFIlQiE,292
 lecrapaud/jobs/config.py,sha256=AmO0j3RFjx8H66dfKw_7vnshaOJb9Ox5BAZ9cwwLFMY,377
@@ -41,10 +41,10 @@ lecrapaud/misc/tabpfn_tests.ipynb,sha256=VkgsCUJ30d8jaL2VaWtQAgb8ngHPNtPgnXLs7QQ
 lecrapaud/misc/test-gpu-bilstm.ipynb,sha256=4nLuZRJVe2kn6kEmauhRiz5wkWT9AVrYhI9CEk_dYUY,9608
 lecrapaud/misc/test-gpu-resnet.ipynb,sha256=27Vu7nYwujYeh3fOxBNCnKJn3MXNPKZU-U8oDDUbymg,4944
 lecrapaud/misc/test-gpu-transformers.ipynb,sha256=k6MBSs_Um1h4PykvE-LTBcdpbWLbIFST_xl_AFW2jgI,8444
-lecrapaud/model_selection.py,sha256=o4_hOEp91_33HtMatVHU7YPc71KZ2hK7wucN63xqWkA,88017
+lecrapaud/model_selection.py,sha256=VL-JQGY-dRsFgfuRob_-lt9bFyex_PyAUJsPHqr453c,88187
 lecrapaud/search_space.py,sha256=caCehJklD3-sgmlisJj_GmuB7LJiVvTF71gEjPGDvV4,36336
 lecrapaud/utils.py,sha256=0k76HFETO0_NgCYUv8b3RTBLgry6MsDBaHJfpAplxCY,8855
-lecrapaud-0.21.1.dist-info/METADATA,sha256=rKls8xvjhu9f72jTw2sjBYCmQPw-N02RSScSOjJ1E2g,14348
-lecrapaud-0.21.1.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-lecrapaud-0.21.1.dist-info/licenses/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.21.1.dist-info/RECORD,,
+lecrapaud-0.21.2.dist-info/METADATA,sha256=5e2V3i21uDdh9fnrdc5MZUQ7EZMJgR8mRKnvGzqwmZw,15337
+lecrapaud-0.21.2.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+lecrapaud-0.21.2.dist-info/licenses/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.21.2.dist-info/RECORD,,