perf: optimze the loading of built-in application data.

ZJUEarthData · Feb 27, 2024 · bc56c7e · bc56c7e
1 parent 2872da2
commit bc56c7e
Show file tree

Hide file tree

Showing 6 changed files with 8 additions and 7 deletions.
diff --git a/geochemistrypi/data_mining/cli_pipeline.py b/geochemistrypi/data_mining/cli_pipeline.py
@@ -202,20 +202,21 @@ def cli_pipeline(training_data_path: str, application_data_path: Optional[str] =
     logger.debug("Built-in Application Data Loading")
     # If the user doesn't provide training data path and inference data path, then use the built-in inference data.
     if is_built_in_inference_data and built_in_training_data_num == 1:
-        application_data_path = "InferenceData_Regression.xlsx"
+        application_data_path = "ApplicationData_Regression.xlsx"
         inference_data = read_data(file_path=application_data_path)
-        print(f"Successfully loading the built-in inference data set '{application_data_path}'.")
+        print(f"Successfully loading the built-in application data set '{application_data_path}'.")
         show_data_columns(inference_data.columns)
+        clear_output()
     elif is_built_in_inference_data and built_in_training_data_num == 2:
-        application_data_path = "InferenceData_Classification.xlsx"
+        application_data_path = "ApplicationData_Classification.xlsx"
         inference_data = read_data(file_path=application_data_path)
-        print(f"Successfully loading the built-in inference data set '{application_data_path}'.")
+        print(f"Successfully loading the built-in application data set '{application_data_path}'.")
         show_data_columns(inference_data.columns)
+        clear_output()
     elif is_built_in_inference_data and built_in_training_data_num == 3:
         inference_data = None
     elif is_built_in_inference_data and built_in_training_data_num == 4:
         inference_data = None
-    clear_output()
 
     # <--- World Map Projection --->
     logger.debug("World Map Projection")

diff --git a/...dataset/InferenceData_Classification.xlsx → ...taset/ApplicationData_Classification.xlsx b/...dataset/InferenceData_Classification.xlsx → ...taset/ApplicationData_Classification.xlsx
diff --git a/...ata/dataset/InferenceData_Regression.xlsx → ...a/dataset/ApplicationData_Regression.xlsx b/...ata/dataset/InferenceData_Regression.xlsx → ...a/dataset/ApplicationData_Regression.xlsx
diff --git a/geochemistrypi/data_mining/data/dataset/InferenceData_Clustering.xlsx b/geochemistrypi/data_mining/data/dataset/InferenceData_Clustering.xlsx
diff --git a/geochemistrypi/data_mining/data/dataset/InferenceData_Decomposition.xlsx b/geochemistrypi/data_mining/data/dataset/InferenceData_Decomposition.xlsx
diff --git a/geochemistrypi/data_mining/model/regression.py b/geochemistrypi/data_mining/model/regression.py
@@ -4115,7 +4115,7 @@ def __init__(
 
     @property
     def settings(self) -> Dict:
-        """The configuration of Lasso to implement AutoML by FLAML framework."""
+        """The configuration of Ridge to implement AutoML by FLAML framework."""
         configuration = {
             "time_budget": 10,  # total running time in seconds
             "metric": "r2",
@@ -4128,7 +4128,7 @@ def settings(self) -> Dict:
 
     @property
     def customization(self) -> object:
-        """The customized Lasso of FLAML framework."""
+        """The customized Ridge of FLAML framework."""
         from flaml import tune
         from flaml.data import REGRESSION
         from flaml.model import SKLearnEstimator