lecrapaud 0.18.1__py3-none-any.whl → 0.18.3__py3-none-any.whl

lecrapaud/feature_engineering.py

@@ -220,7 +220,7 @@ class FeatureEngineeringEngine:
         Returns:
             pd.DataFrame: Original dataframe with new encoded columns added
         """
-
+        # TODO: target encoding needs to be fit / transform based at inference time.
         df: pd.DataFrame = self.data
         columns_te_groupby: list[list[str]] = self.columns_te_groupby
         columns_te_target: list[str] = self.columns_te_target
@@ -231,6 +231,9 @@ class FeatureEngineeringEngine:
         for group_cols, stat, target_col in product(
             columns_te_groupby, statistics, columns_te_target
         ):
+            df[target_col] = pd.to_numeric(
+                df[target_col].replace("", "0"), errors="coerce"
+            ).fillna(0)
             col_name = f"{target_col}_{'_'.join(group_cols)}_{stat.upper()}"
             new_feature_cols[col_name] = df.groupby(group_cols)[target_col].transform(
                 stat

lecrapaud/model_selection.py

@@ -12,6 +12,7 @@ import glob
 from pathlib import Path
 import pickle
 from pydantic import BaseModel
+import ast
 
 os.environ["COVERAGE_FILE"] = str(Path(".coverage").resolve())
 
@@ -122,6 +123,7 @@ class ModelEngine:
         plot: bool = False,
         log_dir: str = None,
     ):
+        self.threshold = None
         self.path = path
         if path:
             self.load()
@@ -152,8 +154,6 @@ class ModelEngine:
         else:
             self.scaler_y = None
 
-        self.threshold = None
-
     def fit(self, *args):
         if self.recurrent:
             fit = self.fit_recurrent
@@ -1070,7 +1070,7 @@ class ModelSelectionEngine:
         best_score_overall = scores_tracking.iloc[0, :]
         best_model_name = best_score_overall["MODEL_NAME"]
         if self.target_type == "classification":
-            best_thresholds = best_score_overall["THRESHOLDS"]
+            best_thresholds = ast.literal_eval(best_score_overall["THRESHOLDS"])
             joblib.dump(best_thresholds, f"{self.target_dir}/thresholds.pkl")
         else:
             best_thresholds = None
@@ -1852,7 +1852,9 @@ def apply_thresholds(
     """
 
     # Case 1: Per-class thresholds
-    if isinstance(threshold, dict):
+    if not isinstance(threshold, int):
+        if isinstance(threshold, str):
+            threshold = ast.literal_eval(threshold)
         class_predictions = []
         class_probabilities = []
 
@@ -1862,6 +1864,7 @@ def apply_thresholds(
                 metrics.get("threshold") if isinstance(metrics, dict) else metrics[0]
             )
             if _threshold is not None:
+                class_label = int(class_label)
                 if class_label not in pred_proba.columns:
                     continue  # skip missing class
                 col = pred_proba[class_label]

lecrapaud/utils.py

@@ -10,21 +10,27 @@ import unicodedata
 import re
 import string
 import sys
+import tomllib
+
 from lecrapaud.directories import logger_dir
 from lecrapaud.config import LOGGING_LEVEL, PYTHON_ENV, LECRAPAUD_LOCAL
 
+
 _LECRAPAUD_LOGGER_ALREADY_CONFIGURED = False
 
 
 def setup_logger():
 
+    with open("pyproject.toml", "rb") as f:
+        pyproject_data = tomllib.load(f)
+    name = pyproject_data["project"]["name"]
+
     global _LECRAPAUD_LOGGER_ALREADY_CONFIGURED
     if _LECRAPAUD_LOGGER_ALREADY_CONFIGURED:  # ← bail out if done before
-
-        return logging.getLogger("lecrapaud" if PYTHON_ENV != "Worker" else "")
+        return logging.getLogger(name if PYTHON_ENV != "Worker" else "")
 
     print(
-        f"Setting up logger lecrapaud with PYTHON_ENV {PYTHON_ENV} and LOGGING_LEVEL {LOGGING_LEVEL}"
+        f"Setting up logger for {name} with PYTHON_ENV {PYTHON_ENV} and LOGGING_LEVEL {LOGGING_LEVEL}"
     )
     # ------------------------------------------------------------------ #
     #  Real configuration happens only on the FIRST call                 #

{lecrapaud-0.18.1.dist-info → lecrapaud-0.18.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.18.1
+Version: 0.18.3
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet

{lecrapaud-0.18.1.dist-info → lecrapaud-0.18.3.dist-info}/RECORD

@@ -26,7 +26,7 @@ lecrapaud/db/models/utils.py,sha256=-a-nWWmpJ2XzidIxo2COVUTrGZIPYCfBzjhcszJj_bM,
 lecrapaud/db/session.py,sha256=E93WXcFFILFAIeH61ft2Egs7D-6caqs0oi4zCkO5Lq4,2822
 lecrapaud/directories.py,sha256=0LrANuDgbuneSLker60c6q2hmGnQ3mKHIztTGzTx6Gw,826
 lecrapaud/experiment.py,sha256=1xLWjOrqAxJh9CdXOx9ppQuRFRRj0GH-xYZqg-ty9hI,2463
-lecrapaud/feature_engineering.py,sha256=ey46MqXBC-c-BS6nRA7zo8uafxmDABy5ThIyTfmXoSo,38982
+lecrapaud/feature_engineering.py,sha256=ib1afBrwqePiXUaw0Cpe6hY3VNl5afg8YVntb88SCT4,39199
 lecrapaud/feature_selection.py,sha256=6ry-oVPQHbipm1XSE5YsH7AY0lQFt4CFbWiHiRs1nxg,43593
 lecrapaud/integrations/openai_integration.py,sha256=hHLF3fk5Bps8KNbNrEL3NUFa945jwClE6LrLpuMZOd4,7459
 lecrapaud/jobs/__init__.py,sha256=ZkrsyTOR21c_wN7RY8jPhm8jCrL1oCEtTsf3VFIlQiE,292
@@ -37,10 +37,10 @@ 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=QOwOsn1WEBzR-2ZpHvhzv9Qz47delkBdNziHy-auY3o,72302
+lecrapaud/model_selection.py,sha256=WbFn4wiykD8DOJ_7OsZLoocp-q4GDzW0dXCf-hHhl74,72471
 lecrapaud/search_space.py,sha256=-JkzuMhaomdwiWi4HvVQY5hiw3-oREemJA16tbwEIp4,34854
-lecrapaud/utils.py,sha256=g5ZbULUpgUqmKHO4vqjIS6BYlZ9MjQn5cts0GHqiejM,8234
-lecrapaud-0.18.1.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
-lecrapaud-0.18.1.dist-info/METADATA,sha256=wNG11NG_K0VHJbu4T47Zlh0eam6bxR0JqLc40d_QIjI,11081
-lecrapaud-0.18.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-lecrapaud-0.18.1.dist-info/RECORD,,
+lecrapaud/utils.py,sha256=eMnNVKWTqzXCLaaxSbKLBrThkOWoJrieifr9PNqFD5Y,8375
+lecrapaud-0.18.3.dist-info/LICENSE,sha256=MImCryu0AnqhJE_uAZD-PIDKXDKb8sT7v0i1NOYeHTM,11350
+lecrapaud-0.18.3.dist-info/METADATA,sha256=RYBX8NxcLXMDYU4FDkkZW9iIynfLqmpkQd9FozyFPzQ,11081
+lecrapaud-0.18.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+lecrapaud-0.18.3.dist-info/RECORD,,