lecrapaud 0.6.2__tar.gz → 0.7.1__tar.gz

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lecrapaud
-Version: 0.6.2
+Version: 0.7.1
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
 Author: Pierre H. Gallet

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/api.py

@@ -48,13 +48,13 @@ class LeCrapaud:
         init_db(uri=uri)
 
     def create_experiment(self, data: pd.DataFrame, **kwargs):
-        return App(data=data, **kwargs)
+        return ExperimentEngine(data=data, **kwargs)
 
     def get_experiment(self, id: int, **kwargs):
-        return App(id=id, **kwargs)
+        return ExperimentEngine(id=id, **kwargs)
 
 
-class App:
+class ExperimentEngine:
     def __init__(self, id=None, data=None, **kwargs):
         if id:
             self.experiment = Experiment.get(id)
@@ -285,3 +285,16 @@ class App:
                 plot=self.plot,
                 preserve_model=self.preserve_model,
             )
+
+    def get_scores(self, target_number: int):
+        return pd.read_csv(
+            f"{self.experiment.path}/TARGET_{target_number}/scores_tracking.csv"
+        )
+
+    def get_prediction(self, target_number: int, model_name: str):
+        return pd.read_csv(
+            f"{self.experiment.path}/TARGET_{target_number}/{model_name}/prediction.csv"
+        )
+
+    def get_feature_summary(self):
+        return pd.read_csv(f"{self.experiment.path}/feature_summary.csv")

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/config.py

@@ -5,7 +5,7 @@ load_dotenv(override=False)
 
 PYTHON_ENV = os.getenv("PYTHON_ENV")
 REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")
-DATASET_ID = os.getenv("DATASET_ID")
+EXPERIMENT_ID = os.getenv("EXPERIMENT_ID")
 LOGGING_LEVEL = os.getenv("LOGGING_LEVEL", "INFO")
 
 DB_USER = (

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/feature_engineering.py

@@ -358,8 +358,8 @@ class PreprocessFeature:
 
         # PCA
         train, pcas = self.add_pca_features(train)
-        val, _ = self.add_pca_features(test, pcas=pcas)
-        test, _ = self.add_pca_features(val, pcas=pcas)
+        val, _ = self.add_pca_features(val, pcas=pcas)
+        test, _ = self.add_pca_features(test, pcas=pcas)
 
         joblib.dump(pcas, f"{self.preprocessing_dir}/pcas.pkl")
 

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/feature_selection.py

@@ -1140,6 +1140,7 @@ def get_features_by_types(df: pd.DataFrame, sample_categorical_threshold: int =
         for col in df.columns
         if df[col].nunique() <= sample_categorical_threshold
         and df[col].dtype in ["int64", "Int64"]
+        and (df[col] >= 0).all()
     ]
     df_categorical = df[categorical_features]
     logger.info(f"Number of categorical features: {len(categorical_features)}")

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/jobs/tasks.py

@@ -2,7 +2,7 @@ from lecrapaud.jobs import app
 
 # from honeybadger import honeybadger
 from lecrapaud.send_daily_emails import send_daily_emails
-from lecrapaud.config import DATASET_ID, RECEIVER_EMAIL
+from lecrapaud.config import EXPERIMENT_ID, RECEIVER_EMAIL
 from lecrapaud.training import run_training
 from lecrapaud.constants import stock_list_3
 from lecrapaud.search_space import get_models_idx
@@ -18,7 +18,7 @@ from lecrapaud.search_space import get_models_idx
 def task_send_daily_emails(self):
     try:
         print(f"[Attempt #{self.request.retries}] task_send_daily_emails")
-        experiment_id = int(DATASET_ID)
+        experiment_id = int(EXPERIMENT_ID)
         email = RECEIVER_EMAIL
         return send_daily_emails(email, experiment_id)
     except Exception as e:

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/lecrapaud/model_selection.py

@@ -1015,7 +1015,7 @@ class ModelSelectionEngine:
 
             # Save validation predictions
             best_pred.to_csv(
-                f"{self.results_dir}/pred_val.csv",
+                f"{self.results_dir}/prediction.csv",
                 index=True,
                 header=True,
                 index_label="ID",
@@ -1636,7 +1636,7 @@ def get_pred_distribution(training_target_dir: str, model_name="linear"):
     Look at prediction distributions
     """
     prediction = pd.read_csv(
-        f"{training_target_dir}/{model_name}/pred_val.csv",
+        f"{training_target_dir}/{model_name}/prediction.csv",
         index_col="ID",
     )
     prediction.describe()

{lecrapaud-0.6.2 → lecrapaud-0.7.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.6.2"
+version = "0.7.1"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}