LWPLSR as a documented class

docs/index.md

@@ -8,4 +8,7 @@ This workflow aims at ...
 
 ## Clustering
 [K-Means](Clustering.md#k-means-clustering)  
-[HDBSCAN](Clustering.md#hdbscan-clustering)
+[HDBSCAN](Clustering.md#hdbscan-clustering)
\ No newline at end of file
+
+## Models Creation
+[lwPlsR from Jchemo (Julia)](model_creation.md)
\ No newline at end of file

docs/model_creation.md

+# Models creation
+
+## PLSR from Pinard (scikit learn)
+::: src.Class_Mod.KMEANS_.Sk_Kmeans
+
+## lwPlsR from Jchemo (Julia)
+::: src.Class_Mod.LWPLSR_.LWPLSR
\ No newline at end of file

mkdocs.yml

@@ -4,6 +4,7 @@ nav:
   - Home: 'index.md'
   - Dimensionality Reduction: 'Dimensionality_Reduction.md'
   - Clustering Methods: 'Clustering.md'
+  - Models Creation: 'model_creation.md'
 
 
 theme:

src/Class_Mod/HDBSCAN_Clustering.py

@@ -132,7 +132,8 @@ class Hdbscan:
             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)
+        Returns:
+            mutual_reachability (float)
             mutual reachability between points i and j
 
         """

src/Class_Mod/LWPLSR_.py

 from Packages import *
 from Class_Mod.Miscellaneous import *
 
-def LWPLSR(x_train, x_test, y_train, y_test):
-    # prepare to send dataframes to julia and Jchemo
-    Main.x_train,Main.y_train,Main.x_test,Main.y_test = x_train, y_train, x_test, y_test
-    Main.eval("""
-    #convert python pd.dataframes to julia dataframes
-    x_train_j = Main.x_train |> Pandas.DataFrame|> DataFrames.DataFrame;
-    y_train_j = Main.y_train |> Pandas.DataFrame|> DataFrames.DataFrame;
-    x_test_j = Main.x_test |> Pandas.DataFrame|> DataFrames.DataFrame;
-    y_test_j = Main.y_test |> Pandas.DataFrame|> DataFrames.DataFrame;
-    # Compute model
-    nlvdis = 5 ; metric = :mah
-    h = 1 ; k = 200 ; nlv = 15 #; scal = true
-    mod = Main.Jchemo.model(Main.Jchemo.lwplsr; nlvdis, metric, h, k, nlv)
-    Main.Jchemo.fit!(mod, X_train_j, y_train_j)
-    # predictions on test data calculation
-    res = Main.Jchemo.predict(mod, X_test_j) ;
-    score = Main.Jchemo.rmsep(res.pred, y_test_j)
-    resjp = Pandas.DataFrame(res.pred);
-    """)
-    score = Main.score
-    predicted_results_on_test = pd.DataFrame(Main.resjp)
-    return score, predicted_results_on_test
+class LWPLSR:
+    """
+    The UMAP dimension reduction algorithm from scikit learn
+    """
+    def __init__(self, x_train, x_test, y_train, y_test):
+        """Initiate the LWPLSR and prepare data for Julia computing."""
+        self.x_train, self.y_train, self.x_test, self.y_test = x_train, x_test, y_train, y_test
+        # prepare to send dataframes to julia and Jchemo
+        self.Main.x_train,self.Main.y_train,self.Main.x_test,self.Main.y_test = self.x_train, self.y_train, self.x_test, self.y_test
+
+    def Jchemo_lwplsr(self):
+        """Send data to Julia to compute lwplsr.
+
+        Args:
+            self.Main.x_train (DataFrame):
+            self.Main.y_train (DataFrame):
+            self.Main.x_test (DataFrame):
+            self.Main.y_test (DataFrame):
+
+        Returns:
+            self.scores (DataFrame): various metrics and scores
+            self.predicted_results_on_test (DataFrame):
\ No newline at end of file
+        """
+        # launch Julia Jchemo lwplsr
+        Main.eval("""
+        #convert python pd.dataframes to julia dataframes
+        x_train_j = self.Main.x_train |> Pandas.DataFrame|> DataFrames.DataFrame;
+        y_train_j = self.Main.y_train |> Pandas.DataFrame|> DataFrames.DataFrame;
+        x_test_j = self.Main.x_test |> Pandas.DataFrame|> DataFrames.DataFrame;
+        y_test_j = self.Main.y_test |> Pandas.DataFrame|> DataFrames.DataFrame;
+        # Compute model
+        nlvdis = 5 ; metric = :mah
+        h = 1 ; k = 200 ; nlv = 15 #; scal = true
+        mod = Main.Jchemo.model(Main.Jchemo.lwplsr; nlvdis, metric, h, k, nlv)
+        Main.Jchemo.fit!(mod, X_train_j, y_train_j)
+        # predictions on test data calculation
+        res = Main.Jchemo.predict(mod, X_test_j) ;
+        scores = Main.Jchemo.mse(res.pred, y_test_j)
+        scoresjp = Pandas.DataFrame(scores);
+        resjp = Pandas.DataFrame(res.pred);
+        """)
+        self.scores = self.Main.scoresjp
+        self.predicted_results_on_test = pd.DataFrame(self.Main.resjp)
+
+    @property
+    def scores_(self):
+        return self.scores, self.predicted_results_on_test
\ No newline at end of file