Merge pull request #360 from ZJUEarthData/web

docs: rewrite the tutorial of framework.

README.md

@@ -59,6 +59,8 @@ Geochemistry π was selected for featuring as an Editor’s Highlight in EOS
 
 Eos Website: https://eos.org/editor-highlights/machine-learning-for-geochemists-who-dont-want-to-code.
 
+![Geochemistry pi news](https://github.com/ZJUEarthData/geochemistrypi/assets/47497750/bdd33a31-824a-492e-adcf-e660da4eaf1d)
+
 ## Quick Installation
 
 Our software is well tested on **macOS** and **Windows** system with **Python 3.9**. Other systems and Python version are not guranteed.

geochemistrypi/data_mining/model/_base.py

@@ -30,7 +30,7 @@ class WorkflowBase(metaclass=ABCMeta):
 
     @classmethod
     def show_info(cls) -> None:
-        """Display how many functions the algorithm will provide."""
+        """Display what application functions the algorithm will provide."""
         print("*-*" * 2, cls.name, "is running ...", "*-*" * 2)
         print("Expected Functionality:")
         function = cls.common_function + cls.special_function

geochemistrypi/data_mining/model/clustering.py

@@ -17,13 +17,14 @@
 from .func.algo_clustering._agglomerative import agglomerative_manual_hyper_parameters
 from .func.algo_clustering._common import plot_silhouette_diagram, plot_silhouette_value_diagram, scatter2d, scatter3d, score
 from .func.algo_clustering._dbscan import dbscan_manual_hyper_parameters
+from .func.algo_clustering._enum import ClusteringCommonFunction, KMeansSpecialFunction
 from .func.algo_clustering._kmeans import kmeans_manual_hyper_parameters
 
 
 class ClusteringWorkflowBase(WorkflowBase):
     """The base workflow class of clustering algorithms."""
 
-    common_function = ["Cluster Centers", "Cluster Labels", "Model Persistence"]
+    common_function = [func.value for func in ClusteringCommonFunction]
 
     def __init__(self):
         super().__init__()
@@ -58,12 +59,12 @@ def get_labels(self):
         save_data(self.clustering_result, f"{self.naming} Result", GEOPI_OUTPUT_ARTIFACTS_DATA_PATH, MLFLOW_ARTIFACT_DATA_PATH)
 
     @staticmethod
-    def _score(data: pd.DataFrame, labels: pd.DataFrame, algorithm_name: str, store_path: str) -> None:
+    def _score(data: pd.DataFrame, labels: pd.DataFrame, func_name: str, algorithm_name: str, store_path: str) -> None:
         """Calculate the score of the model."""
-        print("-----* Model Score *-----")
+        print(f"-----* {func_name} *-----")
         scores = score(data, labels)
         scores_str = json.dumps(scores, indent=4)
-        save_text(scores_str, f"Model Score - {algorithm_name}", store_path)
+        save_text(scores_str, f"{func_name}- {algorithm_name}", store_path)
         mlflow.log_metrics(scores)
 
     @staticmethod
@@ -112,6 +113,7 @@ def common_components(self) -> None:
         self._score(
             data=self.X,
             labels=self.clustering_result["clustering result"],
+            func_name=ClusteringCommonFunction.MODEL_SCORE.value,
             algorithm_name=self.naming,
             store_path=GEOPI_OUTPUT_METRICS_PATH,
         )
@@ -190,7 +192,7 @@ class KMeansClustering(ClusteringWorkflowBase):
     """The automation workflow of using KMeans algorithm to make insightful products."""
 
     name = "KMeans"
-    special_function = ["KMeans Score"]
+    special_function = [func.value for func in KMeansSpecialFunction]
 
     def __init__(
         self,
@@ -304,14 +306,15 @@ def __init__(
 
         self.naming = KMeansClustering.name
 
-    def _get_inertia_scores(self, algorithm_name: str, store_path: str) -> None:
+    @staticmethod
+    def _get_inertia_scores(func_name: str, algorithm_name: str, trained_model: object, store_path: str) -> None:
         """Get the scores of the clustering result."""
-        print("-----* KMeans Inertia Scores *-----")
-        print("Inertia Score: ", self.model.inertia_)
-        inertia_scores = {"Inertia Score": self.model.inertia_}
+        print(f"-----* {func_name} *-----")
+        print(f"{func_name}: ", trained_model.inertia_)
+        inertia_scores = {f"{func_name}": trained_model.inertia_}
         mlflow.log_metrics(inertia_scores)
         inertia_scores_str = json.dumps(inertia_scores, indent=4)
-        save_text(inertia_scores_str, f"KMeans Inertia Scores - {algorithm_name}", store_path)
+        save_text(inertia_scores_str, f"{func_name} - {algorithm_name}", store_path)
 
     @classmethod
     def manual_hyper_parameters(cls) -> Dict:
@@ -325,7 +328,9 @@ def special_components(self, **kwargs: Union[Dict, np.ndarray, int]) -> None:
         """Invoke all special application functions for this algorithms by Scikit-learn framework."""
         GEOPI_OUTPUT_METRICS_PATH = os.getenv("GEOPI_OUTPUT_METRICS_PATH")
         self._get_inertia_scores(
+            func_name=KMeansSpecialFunction.INERTIA_SCORE.value,
             algorithm_name=self.naming,
+            trained_model=self.model,
             store_path=GEOPI_OUTPUT_METRICS_PATH,
         )
 

geochemistrypi/data_mining/model/func/algo_clustering/_enum.py

@@ -0,0 +1,12 @@
+from enum import Enum
+
+
+class ClusteringCommonFunction(Enum):
+    CLUSTER_CENTERS = "Cluster Centers"
+    CLUSTER_LABELS = "Cluster Labels"
+    MODEL_PERSISTENCE = "Model Persistence"
+    MODEL_SCORE = "Model Score"
+
+
+class KMeansSpecialFunction(Enum):
+    INERTIA_SCORE = "Inertia Score"

geochemistrypi/data_mining/model/regression.py

@@ -200,7 +200,7 @@ def common_components(self) -> None:
         )
 
     @dispatch(bool)
-    def common_components(self, is_automl: bool) -> None:
+    def common_components(self, is_automl: bool = False) -> None:
         """Invoke all common application functions for regression algorithms by FLAML framework."""
         GEOPI_OUTPUT_METRICS_PATH = os.getenv("GEOPI_OUTPUT_METRICS_PATH")
         GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH = os.getenv("GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH")
@@ -904,7 +904,7 @@ def manual_hyper_parameters(cls) -> Dict:
         return hyper_parameters
 
     @dispatch()
-    def special_components(self):
+    def special_components(self, **kwargs):
         """Invoke all special application functions for this algorithms by Scikit-learn framework."""
         GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH = os.getenv("GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH")
         self._plot_feature_importance(

geochemistrypi/data_mining/process/classify.py

@@ -41,6 +41,7 @@ def activate(
     ) -> None:
         """Train by Scikit-learn framework."""
 
+        # Load the required data into the base class's attributes
         self.clf_workflow.data_upload(X=X, y=y, X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
 
         # Customize label
@@ -163,6 +164,7 @@ def activate(
                 validation_fraction=hyper_parameters["validation_fraction"],
                 n_iter_no_change=hyper_parameters["n_iter_no_change"],
             )
+        # Display what application functions the algorithm will provide
         self.clf_workflow.show_info()
 
         # Use Scikit-learn style API to process input data

geochemistrypi/data_mining/process/detect.py

@@ -16,7 +16,6 @@ def __init__(self, model_name: str) -> None:
         self.ad_workflow = AbnormalDetectionWorkflowBase()
         self.transformer_config = {}
 
-    # @dispatch(object, object, object, object, object, object)
     def activate(
         self,
         X: pd.DataFrame,