refactor: replace code with enum class

Dockerfile

@@ -1,39 +1,39 @@
-# Stage 1: Build the frontend
-FROM node:latest as frontend-builder
-
-# Set the working directory
-WORKDIR /app
-
-# Install frontent dependencies
-COPY geochemistrypi/frontend/package.json /app/
-RUN yarn install
-
-# Stage 2: Build the backend
-FROM python:3.9-slim AS backend-builder
-
-# Set the working directory
-WORKDIR /app
-
-# Install backend dependencies
-COPY requirements/production.txt /app/
-RUN pip install -r production.txt
-
-# Special case for Debian OS, update package lists and install Git and Node.js
-RUN apt-get update && apt-get install -y libgomp1 git
-RUN apt-get update && apt-get install -y nodejs
-RUN apt-get update && apt-get install -y npm
-
-# Install Yarn
-RUN npm install -g yarn
-
-# Copy the rest of the code
-COPY . .
-
-# Expose the port
-EXPOSE 8000 3001
-
-# Mount the volume
-VOLUME /app
-
-# Dummy CMD to prevent container from exiting immediately
-CMD ["tail", "-f", "/dev/null"]
+# Stage 1: Build the frontend
+FROM node:latest as frontend-builder
+
+# Set the working directory
+WORKDIR /app
+
+# Install frontent dependencies
+COPY geochemistrypi/frontend/package.json /app/
+RUN yarn install
+
+# Stage 2: Build the backend
+FROM python:3.9-slim AS backend-builder
+
+# Set the working directory
+WORKDIR /app
+
+# Install backend dependencies
+COPY requirements/production.txt /app/
+RUN pip install -r production.txt
+
+# Special case for Debian OS, update package lists and install Git and Node.js
+RUN apt-get update && apt-get install -y libgomp1 git
+RUN apt-get update && apt-get install -y nodejs
+RUN apt-get update && apt-get install -y npm
+
+# Install Yarn
+RUN npm install -g yarn
+
+# Copy the rest of the code
+COPY . .
+
+# Expose the port
+EXPOSE 8000 3001
+
+# Mount the volume
+VOLUME /app
+
+# Dummy CMD to prevent container from exiting immediately
+CMD ["tail", "-f", "/dev/null"]

geochemistrypi/data_mining/model/clustering.py

@@ -80,43 +80,45 @@ def _score(data: pd.DataFrame, labels: pd.Series, func_name: str, algorithm_name
         mlflow.log_metrics(scores)
 
     @staticmethod
-    def _scatter2d(data: pd.DataFrame, labels: pd.Series, name_column: str, cluster_centers_: pd.DataFrame, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _scatter2d(data: pd.DataFrame, labels: pd.Series, name_column: str, cluster_centers_: pd.DataFrame, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot the two-dimensional diagram of the clustering result."""
-        print("-----* Cluster Two-Dimensional Diagram *-----")
+        print(f"-----* {grah_name} *-----")
         scatter2d(data, labels, cluster_centers_, algorithm_name)
-        save_fig(f"Cluster Two-Dimensional Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
         data_with_labels = pd.concat([data, labels], axis=1)
-        save_data(data_with_labels, name_column, f"Cluster Two-Dimensional Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_data(data_with_labels, name_column, f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
 
     @staticmethod
-    def _scatter3d(data: pd.DataFrame, labels: pd.Series, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _scatter3d(data: pd.DataFrame, labels: pd.Series, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot the three-dimensional diagram of the clustering result."""
-        print("-----* Cluster Three-Dimensional Diagram *-----")
+        print(f"-----* {grah_name} *-----")
         scatter3d(data, labels, algorithm_name)
-        save_fig(f"Cluster Three-Dimensional Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
         data_with_labels = pd.concat([data, labels], axis=1)
-        save_data(data_with_labels, name_column, f"Cluster Two-Dimensional Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_data(data_with_labels, name_column, f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
 
     @staticmethod
-    def _plot_silhouette_diagram(data: pd.DataFrame, labels: pd.Series, name_column: str, model: object, cluster_centers_: np.ndarray, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _plot_silhouette_diagram(
+        data: pd.DataFrame, labels: pd.Series, name_column: str, model: object, cluster_centers_: np.ndarray, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str
+    ) -> None:
         """Plot the silhouette diagram of the clustering result."""
-        print("-----* Silhouette Diagram *-----")
+        print(f"-----* {grah_name} *-----")
         plot_silhouette_diagram(data, labels, cluster_centers_, model, algorithm_name)
-        save_fig(f"Silhouette Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
         data_with_labels = pd.concat([data, labels], axis=1)
-        save_data(data_with_labels, name_column, "Silhouette Diagram - Data With Labels", local_path, mlflow_path)
+        save_data(data_with_labels, name_column, f"{grah_name} - Data With Labels", local_path, mlflow_path)
         if not isinstance(cluster_centers_, str):
             cluster_center_data = pd.DataFrame(cluster_centers_, columns=data.columns)
-            save_data(cluster_center_data, name_column, "Silhouette Diagram - Cluster Centers", local_path, mlflow_path)
+            save_data(cluster_center_data, name_column, f"{grah_name} - Cluster Centers", local_path, mlflow_path)
 
     @staticmethod
-    def _plot_silhouette_value_diagram(data: pd.DataFrame, labels: pd.Series, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _plot_silhouette_value_diagram(data: pd.DataFrame, labels: pd.Series, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot the silhouette value diagram of the clustering result."""
-        print("-----* Silhouette value Diagram *-----")
+        print(f"-----* {grah_name} *-----")
         plot_silhouette_value_diagram(data, labels, algorithm_name)
-        save_fig(f"Silhouette value Diagram - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
         data_with_labels = pd.concat([data, labels], axis=1)
-        save_data(data_with_labels, name_column, "Silhouette value Diagram - Data With Labels", local_path, mlflow_path)
+        save_data(data_with_labels, name_column, f"{grah_name} - Data With Labels", local_path, mlflow_path)
 
     def common_components(self) -> None:
         """Invoke all common application functions for clustering algorithms."""
@@ -157,6 +159,7 @@ def common_components(self) -> None:
                 algorithm_name=self.naming,
                 local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
                 mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+                grah_name=ClusteringCommonFunction.CLUSTER_TWO_DIMENSIONAL_DIAGRAM.value,
             )
 
             # choose three of dimensions to draw
@@ -168,6 +171,7 @@ def common_components(self) -> None:
                 algorithm_name=self.naming,
                 local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
                 mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+                grah_name=ClusteringCommonFunction.CLUSTER_THREE_DIMENSIONAL_DIAGRAM.value,
             )
         elif self.X.shape[1] == 3:
             # choose two of dimensions to draw
@@ -180,6 +184,7 @@ def common_components(self) -> None:
                 algorithm_name=self.naming,
                 local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
                 mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+                grah_name=ClusteringCommonFunction.CLUSTER_TWO_DIMENSIONAL_DIAGRAM.value,
             )
 
             # no need to choose
@@ -190,6 +195,7 @@ def common_components(self) -> None:
                 algorithm_name=self.naming,
                 local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
                 mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+                grah_name=ClusteringCommonFunction.CLUSTER_THREE_DIMENSIONAL_DIAGRAM.value,
             )
         elif self.X.shape[1] == 2:
             self._scatter2d(
@@ -200,6 +206,7 @@ def common_components(self) -> None:
                 algorithm_name=self.naming,
                 local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
                 mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+                grah_name=ClusteringCommonFunction.CLUSTER_TWO_DIMENSIONAL_DIAGRAM.value,
             )
         else:
             pass
@@ -213,6 +220,7 @@ def common_components(self) -> None:
             algorithm_name=self.naming,
             local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
             mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+            grah_name=ClusteringCommonFunction.SILHOUETTE_DIAGRAM.value,
         )
         self._plot_silhouette_value_diagram(
             data=self.X,
@@ -221,6 +229,7 @@ def common_components(self) -> None:
             algorithm_name=self.naming,
             local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
             mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+            grah_name=ClusteringCommonFunction.SILHOUETTE_VALUE_DIAGRAM.value,
         )
 
 

geochemistrypi/data_mining/model/decomposition.py

@@ -67,28 +67,28 @@ def _reduced_data2pd(self, reduced_data: np.ndarray, components_num: int) -> Non
         self.X_reduced.columns = pa_name
 
     @staticmethod
-    def _plot_2d_scatter_diagram(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _plot_2d_scatter_diagram(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot the two-dimensional diagram of the decomposition result."""
-        print("-----* Decomposition Two-Dimensional Diagram *-----")
+        print(f"-----* {grah_name} *-----")
         plot_2d_scatter_diagram(data, algorithm_name)
-        save_fig(f"Decomposition Two-Dimensional Diagram - {algorithm_name}", local_path, mlflow_path)
-        save_data(data, name_column, f"Decomposition Two-Dimensional Data - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
+        save_data(data, name_column, f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
 
     @staticmethod
-    def _plot_heatmap(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _plot_heatmap(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot a heatmap for the decomposition result."""
-        print("-----* Decomposition Heatmap *-----")
+        print(f"-----* {grah_name} *-----")
         plot_heatmap(data, algorithm_name)
-        save_fig(f"Decomposition Heatmap - {algorithm_name}", local_path, mlflow_path)
-        save_data(data, name_column, f"Decomposition Heatmap Data - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
+        save_data(data, name_column, f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
 
     @staticmethod
-    def _plot_contour(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str) -> None:
+    def _plot_contour(data: pd.DataFrame, name_column: str, algorithm_name: str, local_path: str, mlflow_path: str, grah_name: str) -> None:
         """Plot a contour plot for dimensionality reduction results."""
-        print("-----* Dimensionality Reduction Contour Plot *-----")
+        print(f"-----* {grah_name} *-----")
         plot_contour(data, algorithm_name)
-        save_fig(f"Dimensionality Reduction Contour Plot - {algorithm_name}", local_path, mlflow_path)
-        save_data(data, name_column, f"Dimensionality Reduction Contour Plot Data - {algorithm_name}", local_path, mlflow_path)
+        save_fig(f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
+        save_data(data, name_column, f"{grah_name} - {algorithm_name}", local_path, mlflow_path)
 
     def common_components(self) -> None:
         """Invoke all common application functions for decomposition algorithms by Scikit-learn framework."""
@@ -100,20 +100,23 @@ def common_components(self) -> None:
             algorithm_name=self.naming,
             local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
             mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+            grah_name=DecompositionCommonFunction.DECOMPOSITION_TWO_DIMENSIONAL_DIAGRAM.value,
         )
         self._plot_heatmap(
             data=self.X,
             name_column=self.name_all,
             algorithm_name=self.naming,
             local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
             mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+            grah_name=DecompositionCommonFunction.DECOMPOSITION_HEATMAP.value,
         )
         self._plot_contour(
             data=self.X,
             name_column=self.name_all,
             algorithm_name=self.naming,
             local_path=GEOPI_OUTPUT_ARTIFACTS_IMAGE_MODEL_OUTPUT_PATH,
             mlflow_path=MLFLOW_ARTIFACT_IMAGE_MODEL_OUTPUT_PATH,
+            grah_name=DecompositionCommonFunction.DIMENSIONALITY_REDUCTION_CONTOUR_PLOT.value,
         )
 
 

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

@@ -6,6 +6,10 @@ class ClusteringCommonFunction(Enum):
     CLUSTER_LABELS = "Cluster Labels"
     MODEL_PERSISTENCE = "Model Persistence"
     MODEL_SCORE = "Model Score"
+    CLUSTER_TWO_DIMENSIONAL_DIAGRAM = "Cluster Two-Dimensional Diagram"
+    CLUSTER_THREE_DIMENSIONAL_DIAGRAM = "Cluster Three-Dimensional Diagram"
+    SILHOUETTE_DIAGRAM = "Silhouette Diagram"
+    SILHOUETTE_VALUE_DIAGRAM = "Silhouette value Diagram"
 
 
 class KMeansSpecialFunction(Enum):

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

@@ -3,6 +3,9 @@
 
 class DecompositionCommonFunction(Enum):
     MODEL_PERSISTENCE = "Model Persistence"
+    DECOMPOSITION_TWO_DIMENSIONAL = "Decomposition Two-Dimensional Diagram"
+    DECOMPOSITION_HEATMAP = "Decomposition Heatmap"
+    DIMENSIONALITY_REDUCTION_CONTOUR_PLOT = "Dimensionality Reduction Contour Plot"
 
 
 class PCASpecialFunction(Enum):