sklearn Pls

Table that was written in a message was incorporated

src/Class_Mod/SK_PLSR_.py

-from Packages  import *
+from Packages import *
+from Class_Mod.Miscellaneous import *
+from Class_Mod.Regression_metrics import metrics
+
+
+
+
 class PlsR:
     def __init__(self, x_train, y_train, x_test, y_test):
         self.x_train = x_train
@@ -6,12 +12,53 @@ class PlsR:
         self.y_train = y_train
         self.y_test = y_test
     
-    def fit_(self):
-        nlv = 20
-        rmse = []
-        for i in range(nlv):
-            m = PLSRegression(n_components= 20)
+        self.trained = PLSRegression(n_components= self._optimize(), scale = False)
+        self.trained.fit(self.x_train, self.y_train)
+
+        self.yc = pd.DataFrame(self.trained.predict(self.x_train)) # make predictions on test data and assign to Y_preds variable
+        self.ycv = pd.DataFrame(cross_val_predict(self.trained, self.x_train, self.y_train, cv = 3)) # make predictions on test data and assign to Y_preds variable
+        self.yt = pd.DataFrame(self.trained.predict(self.x_test)) # make predictions on test data and assign to Y_preds variable
+
+
+    def _optimize(self):
+        nlv = 21
+        rmse = np.ones(21)
+        rmse[0] = 0.002
+        lv = {}
+        ratio = []
+        for i in range(1,nlv):
+            m = PLSRegression(n_components= i, scale = False)
             ycv = cross_val_predict(m, self.x_train, self.y_train, cv = 5)
-            rmse.append(mean_squared_error(self.y_train, ycv))
-            print(rmse)
+            rmse[i] = mean_squared_error(self.y_train, ycv)
+
+            ratio.append(((rmse[i-1]-rmse[i])/rmse[i-1])*100)
+        return np.argmax(ratio)+1
+
+        ################################################################################################################
+        
+
+        ################################################################################################################
+
+    @property
+    def model_(self):
+        return self.trained
+    
+    @property
+    def metrics_(self):
+        metc = metrics(self.y_train, self.yc)
+        metc = metc.evaluate_
+
+        metcv = metrics(self.y_train, self.ycv)
+        metcv = metcv.evaluate_
+
+        mett = metrics( self.y_test, self.yt)
+        mett = mett.evaluate_
+        
+        met = pd.concat([metc, metcv, mett], axis = 0)
+        met.index = ['calib','cv','test']
+        return met
 
+    @property
+    def pred_data_(self):
+        
+        return self.yc, self.ycv, self.yt
\ No newline at end of file

src/Class_Mod/__init__.py

@@ -11,4 +11,4 @@ from .VarSel import TpeIpls
 from .Miscellaneous import resid_plot, reg_plot
 from .DxReader import DxRead, read_dx
 from .HDBSCAN_Clustering import Hdbscan
-
+from .SK_PLSR_ import PlsR
\ No newline at end of file

src/Modules.py

-from Class_Mod import LinearPCA, Umap, find_col_index, PinardPlsr, LWPLSR, list_files, metrics, TpeIpls, reg_plot, resid_plot, Sk_Kmeans, DxRead, Hdbscan, read_dx
+from Class_Mod import PlsR, LinearPCA, Umap, find_col_index, PinardPlsr 
+from Class_Mod import LWPLSR, list_files, metrics, TpeIpls, reg_plot, resid_plot, Sk_Kmeans, DxRead, Hdbscan, read_dx
 # find_col_index
 
 from Class_Mod.Miscellaneous import prediction, download_results, plot_spectra

src/Packages.py

@@ -11,6 +11,7 @@ from os import listdir
 from os.path import isfile, join
 from sklearn.preprocessing import StandardScaler, MinMaxScaler, LabelEncoder
 import time
+from scipy.stats import skew, kurtosis
 
 ### Exploratory data analysis-Dimensionality reduction
 from umap.umap_ import UMAP
@@ -24,7 +25,7 @@ from scipy.sparse import csgraph
 
 # Modelling
 # import julia
-from julia import Main, Jchemo, DataFrames, Base, Pandas
+#from julia import Main, Jchemo, DataFrames, Base, Pandas
 
 from pinard import utils
 from pinard import preprocessing as pp

src/pages/2-model_creation.py

@@ -2,6 +2,8 @@ from Packages import *
 st.set_page_config(page_title="NIRS Utils", page_icon=":goat:", layout="wide")
 from Modules import *
 from Class_Mod.DATA_HANDLING import *
+
+
 # HTML pour le bandeau "CEFE - CNRS"
 bandeau_html = """
 <div style="width: 100%; background-color: #4682B4; padding: 10px; margin-bottom: 10px;">
@@ -19,7 +21,7 @@ if st.session_state["interface"] == 'simple':
 def nn(x):
     return x is not None
 ########################################################################################
-reg_algo = ["","Full-PLSR", "Locally Weighted PLSR", "Interval-PLSR"]
+reg_algo = ["","Full-PLSR", "Locally Weighted PLSR", "Interval-PLSR", "Full-PLSR-sklearn"]
 
 # page Design
 st.header("Calibration Model Development", divider='blue')
@@ -94,7 +96,22 @@ if not spectra.empty and not y.empty:
     # Assign data to training and test sets
     X_train, y_train = pd.DataFrame(spectra.iloc[train_index,:]), y.iloc[train_index]
     X_test, y_test = pd.DataFrame(spectra.iloc[test_index,:]), y.iloc[test_index]
-    M2.write("ADD HERE A TABLE WITH SHAPE OF THE DATA: SAMPLES NUMBER AND WAVELENGTHS OR CHEMICAL VALUES NUMBER FOR TRAIN AND TEST")
+    
+    sk = lambda x: skew(x, axis=0, bias=True)
+    ku = lambda x:kurtosis(x, axis=0, bias=True)
+    cv = lambda x: x.std()*100/x.mean()
+
+    M2.write('Loaded data summary')
+    M2.write(f'The loaded spectra consist of {spectra.shape[1]} wavelengths')
+    datainf = pd.DataFrame()
+    datainf['N samples'] = [X_train.shape[0], X_test.shape[0], spectra.shape[0] ]
+    datainf['Mean'] = [y_train.mean(), y_test.mean(), y.mean()]
+    datainf['SD'] = [y_train.std(), y_test.std(), y.std()]
+    datainf['CV(%)'] = [cv(y_train), cv(y_test), cv(y)]
+    datainf['Skewness'] = [sk(y_train), sk(y_test), sk(y)]
+    datainf['Kurtosis'] = [ku(y_train), ku(y_test), ku(y)]
+    datainf.index = ['Train', 'Test', 'Total']
+    M2.write(datainf.round(3))
 
 #######################################
     regression_algo = M1.selectbox("Choose the algorithm for regression", options=reg_algo, key = 12)
@@ -121,6 +138,10 @@ if not spectra.empty and not y.empty:
         M2.write('-- Table of selected wavelengths --')
         M2.table(rega[0])
         
+    elif regression_algo == reg_algo[4]:
+        Reg = PlsR(x_train = X_train, x_test = X_test, y_train = y_train, y_test = y_test)
+        reg_model = Reg.model_
+
         ################# Model analysis ############
     if regression_algo in reg_algo[1:]:
         yc = Reg.pred_data_[0]