Beginning of Documentation via DocStrings

docs/Clustering.md

+# Clustering Methods
+
+## K-Means clustering
+::: src.Class_Mod.KMEANS_.Sk_Kmeans
+  
+## HDBSCAN clustering
+::: src.Class_Mod.HDBSCAN_Clustering.Hdbscan

docs/Dimensionality_Reduction.md

+# Dimensionality Reduction methods
+
+## PCA
+::: src.Class_Mod.PCA_
+
+## UMAP
+::: src.Class_Mod.UMAP_

docs/index.md

+# Welcome to NIRS Workflow documentation
+
+This workflow aims at ...
+
+## Samples Selection
+
+## Dimension Reduction
+
+## Clustering
+[K-Means](Clustering.md#k-means-clustering)  
+[HDBSCAN](Clustering.md#hdbscan-clustering)
\ No newline at end of file

mkdocs.yml

+site_name: NIRS Workflow
+
+nav:
+  - Home: 'index.md'
+  - Dimensionality Reduction: 'Dimensionality_Reduction.md'
+  - Clustering Methods: 'Clustering.md'
+
+
 theme:
-  name: NIRS Workflow
-  locale: en
-#  custom_dir: my_theme_customizations/
-  static_templates:
-    - sitemap.html
-  include_sidebar: false
+  name: material
+
+  features:
+    - navigation.tabs
+    - navigation.sections
+    - toc.integrate
\ No newline at end of file
+    - navigation.top
+    - search.suggest
+    - search.highlight
+    - content.tabs.link
+    - content.code.annotation
+    - content.code.copy
+  language: en
+  palette:
+    - scheme: default
+      toggle:
+        icon: material/toggle-switch-off-outline
+        name: switch to dark mode
+      primary: teal
+      accent: purple
+    - scheme: slate
+      toggle:
+        icon: material/toggle-switch
+        name: Switch to light mode
+      primary: teal
+      accent: lime
+
+plugins:
+  - mkdocstrings
+
+copyright:
+  <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">CNRS/UM CC BY 2024</a>
+extra:
+  social:
+    - icon: fontawesome/brands/gitlab
+      link: https://src.koda.cnrs.fr/cefe/pace/nirs_workflow
\ No newline at end of file

src/Class_Mod/HDBSCAN_Clustering.py

 from Packages import *
 
 class Hdbscan:
-    """Runs an automatic optimized sklearn.HDBSCAN clustering on Dimensionality reduced space.
-    Vars:
-        data: the Dimensionality reduced space, raw result of the UMAP.fit()
-        param_dist: the HDBSCAN optimization parameters to test
-        Density-Based Clustering Validation - DBCV (https://github.com/christopherjenness/DBCV/tree/master ;
-            Moulavi, Davoud, et al. "Density-based clustering validation." Proceedings of the 2014 SIAM
-            International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2014.)
-            is used as a metric to optimize HDBSCAN algorithm.
-            Functions DBCV, _core_dist, _mutual_reachability_dist, _mutual_reach_dist_graph, _mutual_reach_dist_graph,
-            _mutual_reach_dist_MST, _cluster_density_sparseness, _cluster_density_separation, _cluster_validity_index,
-            _clustering_validity_index and _get_label_members aim at DBCV computing.
-        _score is a dataframe with the DBCV value for each combination of param_dist. We search for the higher value and
-            compute an HDBSCAN with the best parameters.
-        The HDBSCAN_scores_ @property return the cluster number of each sample (_labels) and the DBCV best score.
+    """Runs an automatically optimized sklearn.HDBSCAN clustering on dimensionality reduced space.
+
+    The HDBSCAN_scores_ @Property returns the cluster number of each sample (_labels) and the DBCV best score.
+
+    Returns:
+        _labels (pd.DataFrame): DataFrame with the cluster belonging number for each sample
+        _hdbscan_score (float): a float with the best DBCV score after optimization
+
     Examples:
-        clustering = HDBSCAN((data)
-        scores = clustering.HDBSCAN_scores_
+        - clustering = HDBSCAN((data)
+        - scores = clustering.HDBSCAN_scores_
 
     """
     def __init__(self, data):
+        """Initiate the HDBSCAN calculation
+
+        Args:
+            data (pd.DataFrame): the Dimensionality reduced space, raw result of the UMAP.fit()
+            param_dist (dictionary): the HDBSCAN optimization parameters to test
+            _score (pd.DataFrame): is a dataframe with the DBCV value for each combination of param_dist. We search for the higher value to then compute an HDBSCAN with the best parameters.
+        """
         # Really fast
         # self._param_dist = {'min_samples': [1],
         #               'min_cluster_size':[5],
@@ -66,8 +67,7 @@ class Hdbscan:
         """
         Implimentation of Density-Based Clustering Validation "DBCV"
 
-        Citation:
-        Moulavi, Davoud, et al. "Density-based clustering validation."
+        Citation: Moulavi, Davoud, et al. "Density-based clustering validation."
         Proceedings of the 2014 SIAM International Conference on Data Mining.
         Society for Industrial and Applied Mathematics, 2014.
 
@@ -80,8 +80,8 @@ class Hdbscan:
             dist_dunction (func): function to determine distance between objects
                 func args must be [np.array, np.array] where each array is a point
 
-        Returns: cluster_validity (float)
-            score in range[-1, 1] indicating validity of clustering assignments
+        Returns:
+            cluster_validity (float): score in range[-1, 1] indicating validity of clustering assignments
         """
         graph = self._mutual_reach_dist_graph(X, labels, dist_function)
         mst = self._mutual_reach_dist_MST(graph)
@@ -129,7 +129,7 @@ class Hdbscan:
                 array of all other points in object class of point i
             neighbors_j (np.ndarray): array of dims (n_neighbors, n_features):
                 array of all other points in object class of point j
-            dist_dunction (func): function to determine distance between objects
+            dist_function (func): function to determine distance between objects
                 func args must be [np.array, np.array] where each array is a point
 
         Returns: mutual_reachability (float)

src/Class_Mod/KMEANS_.py

 from Packages import *
 class Sk_Kmeans:
+    """K-Means clustering for Samples selection.
+
+    Returns:
+        inertia_ (pd.DataFrame): DataFrame with ...
+        x (pd.DataFrame): Initial data
+        clu (pd.DataFrame): Cluster name for each sample
+        model.cluster_centers_ (pd.DataFrame): Coordinates of the center of each cluster
+    """
     def __init__(self, x, max_clusters):
+        """Initiate the KMeans class.
+
+        Args:
+            x (pd.DataFrame): the original reduced data to cluster
+            max_cluster (Int): the max number of desired clusters.
+        """
         self.x = x
         self.max_clusters = max_clusters
 

src/Class_Mod/__init__.py

+"""Here are all the classes to perform your analysis
+"""
 from .PCA_ import *
 from .KMEANS_ import Sk_Kmeans
 from .UMAP_ import Umap

src/__init__.py

@@ -3,6 +3,7 @@
 This is a webapp with Streamlit.
 GUI shows whatever is needed for Samples Selection based on NIRS spectra and then, to compute a model to predict
     chemical values on your samples.
+
 Examples:
     streamlit run ./app.py
 """
\ No newline at end of file