chore: autopublish 2024-04-05T18:46:33Z

Author: github-actions[bot]

src/energy_forcasting_model/pipelines/lightgbm_training_pipeline/nodes.py

@@ -1,6 +1,3 @@
-import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
 import lightgbm as lgb
 import logging
 
@@ -50,4 +47,4 @@ def train_lightgbm_model(X_train, y_train, params):
     # Log the completion of the training process
     logger.info("LightGBM model training completed successfully.")
 
-    return lgbm_model
+    return lgbm_model

src/energy_forcasting_model/pipelines/lightgbm_training_pipeline/pipeline.py

@@ -1,6 +1,5 @@
 from kedro.pipeline import Pipeline, node, pipeline
 
-from kedro.pipeline import Pipeline, pipeline
 
 from .nodes import train_lightgbm_model
 
@@ -51,14 +50,14 @@ def create_pipeline(**kwargs) -> Pipeline:
         tags="model_training",
         namespace="lightgbm_training_pipeline",
         inputs=[
-                        "X_train",
-                        "y_train",
-                        "X_test",
-                        "y_test",
+            "X_train",
+            "y_train",
+            "X_test",
+            "y_test",
         ],
         outputs=[
-"lightgbm_model",
-"lightgbm_feature_importance_plot",
-"real_data_and_lightgbm_predictions_plot",
+            "lightgbm_model",
+            "lightgbm_feature_importance_plot",
+            "real_data_and_lightgbm_predictions_plot",
         ],
     )

src/energy_forcasting_model/pipelines/xgboost_training_pipeline/nodes.py

@@ -1,7 +1,4 @@
-import pandas as pd
-import matplotlib.pyplot as plt
 import xgboost as xgb
-import seaborn as sns
 import logging
 
 
@@ -49,13 +46,13 @@ def train_xgboost_model(X_train, y_train, params):
     # Training the model with verbosity based on the provided configuration
     logger.info("Training the XGBoost model...")
     xgb_model.fit(
-        X_train_clean, 
-        y_train_clean, 
+        X_train_clean,
+        y_train_clean,
         eval_set=[(X_train_clean, y_train_clean)],
-        verbose=params["verbose_eval"]
+        verbose=params["verbose_eval"],
     )
 
     # Log the completion of the training process
     logger.info("XGBoost model training completed successfully.")
 
-    return xgb_model
+    return xgb_model