LWPLSR CV can export results as a json back to streamlit

src/Class_Mod/LWPLSR_.py

@@ -16,15 +16,17 @@ class LWPLSR:
 
         # self.x_train, self.y_train, self.x_test, self.y_test = [dataset[i] for i in range(len(dataset))]
         self.x_train, self.y_train, self.x_test, self.y_test = [dataset[i] for i in range(4)]
-        nb_fold = int((len(dataset)-4)/4)
-        for i in range(nb_fold):
-            vars()["self.xtr_fold"+str(i+1)] = dataset[i+7]
-            vars()["self.ytr_fold"+str(i+1)] = dataset[i+13]
-            vars()["self.xte_fold"+str(i+1)] = dataset[i+4]
-            vars()["self.yte_fold"+str(i+1)] = dataset[i+10]
+        self.nb_fold = int((len(dataset)-4)/4)
+        for i in range(self.nb_fold):
+            setattr(self, "xtr_fold"+str(i+1), dataset[i+7])
+            setattr(self, "ytr_fold"+str(i+1), dataset[i+13])
+            setattr(self, "xte_fold"+str(i+1), dataset[i+4])
+            # setattr(self, "yte_fold"+str(i+1), dataset[i+10])
+            setattr(jl, "xtr_fold"+str(i+1), dataset[i+7])
+            setattr(jl, "ytr_fold"+str(i+1), dataset[i+13])
+            setattr(jl, "xte_fold"+str(i+1), dataset[i+4])
+            # setattr(jl, "yte_fold"+str(i+1), dataset[i+10])
 
-
-        print(self.xtr_fold1)
         # prepare to send dataframes to julia and Jchemo
         jl.x_train, jl.y_train, jl.x_test, jl.y_test = self.x_train, self.y_train, self.x_test, self.y_test
 
@@ -32,20 +34,20 @@ class LWPLSR:
         y_shape = self.y_test.shape
         self.predicted_results_on_test = pd.DataFrame
         self.predicted_results_on_train = pd.DataFrame
-        self.predicted_results_on_cv = pd.DataFrame
         self.pred_test = np.zeros(shape=(y_shape[0], 1))
         self.pred_train = np.zeros(shape=(y_shape[0], 1))
         self.mod = ""
         self.best_lwplsr_params = np.zeros(shape=(5, 1))
+        self.predicted_results = {}
 
     def Jchemo_lwplsr_fit(self):
         """Send data to Julia to fit lwplsr.
 
         Args:
-            self.jl.x_train (DataFrame):
-            self.jl.y_train (DataFrame):
-            self.jl.x_test (DataFrame):
-            self.jl.y_test (DataFrame):
+            self.x_train (DataFrame):
+            self.y_train (DataFrame):
+            self.x_test (DataFrame):
+            self.y_test (DataFrame):
 
         Returns:
             self.mod (Julia model): the prepared model
@@ -88,7 +90,7 @@ class LWPLSR:
         u = findall(res.y1 .== minimum(res.y1))[1] #best parameters combination
         """)
         self.best_lwplsr_params = {'nlvdis' : jl.res.nlvdis[jl.u], 'metric' : str(jl.res.metric[jl.u]), 'h' : jl.res.h[jl.u], 'k' : jl.res.k[jl.u], 'nlv' : jl.res.nlv[jl.u]}
-        print('best lwplsr params' + str(self.best_lwplsr_params))
+        print('best lwplsr params ' + str(self.best_lwplsr_params))
         print('LWPLSR - best params ok')
         # calculate LWPLSR model with best parameters
         jl.seval("""
@@ -103,15 +105,14 @@ class LWPLSR:
 
         Args:
             self.mod (Julia model): the prepared model
-            self.jl.x_train (DataFrame):
-            self.jl.y_train (DataFrame):
-            self.jl.x_test (DataFrame):
-            self.jl.y_test (DataFrame):
+            self.x_train (DataFrame):
+            self.y_train (DataFrame):
+            self.x_test (DataFrame):
+            self.y_test (DataFrame):
 
         Returns:
             self.pred_test (Julia DataFrame): predicted values on x_test
             self.pred_train (Julia DataFrame): predicted values on x_train
-            self.pred_cv (Julia DataFrame): predicted values on x_train with Cross-Validation
         """
         # Predictions on x_test and store in self.pred
         self.pred_test = jl.seval("""
@@ -126,13 +127,58 @@ class LWPLSR:
         """)
         print('LWPLSR - end')
 
+    def Jchemo_lwplsr_cv(self):
+        """Send data to Julia to predict with lwplsr.
+
+        Args:
+            self.mod (Julia model): the prepared model
+            self.xtr_fold1 (DataFrame):
+            self.ytr_fold1 (DataFrame):
+            self.xte_fold1 (DataFrame):
+            self.yte_fold1 (DataFrame):
+
+        Returns:
+            self.pred_cv (Julia DataFrame): predicted values on x_train with Cross-Validation
+        """
+        for i in range(self.nb_fold):
+            jl.Xtr = getattr(self, "xtr_fold"+str(i+1))
+            jl.Ytr = getattr(self, "ytr_fold"+str(i+1))
+            jl.Xte = getattr(self, "xte_fold"+str(i+1))
+            # jl.Yte = getattr(self, "yte_fold"+str(i+1))
+            jl.seval("""
+            using DataFrames
+            using Pandas
+            using Jchemo
+            Xtr |> Pandas.DataFrame |> DataFrames.DataFrame
+            Ytr |> Pandas.DataFrame |> DataFrames.DataFrame
+            Xte |> Pandas.DataFrame |> DataFrames.DataFrame
+            """)
+            jl.nlvdis = int(self.best_lwplsr_params['nlvdis'])
+            jl.metric = self.best_lwplsr_params['metric']
+            jl.h = self.best_lwplsr_params['h']
+            jl.k = int(self.best_lwplsr_params['k'])
+            jl.nlv = int(self.best_lwplsr_params['nlv'])
+            jl.seval("""
+            println("LWPLSR - start CV mod")
+            mod_cv = Jchemo.model(Jchemo.lwplsr; nlvdis = nlvdis, metric = Symbol(metric), h = h, k = k, nlv = nlv)
+            # Fit model
+            Jchemo.fit!(mod_cv, Xtr, Ytr)
+            """)
+            pred_cv = jl.seval("""
+            println("LWPLSR - start CV predict")
+            res = Jchemo.predict(mod_cv, Xte)
+            res.pred
+            """)
+            self.predicted_results["CV" + str(i+1)] = pd.DataFrame(pred_cv)
 
     @property
     def pred_data_(self):
         # convert predicted data from x_test to Pandas DataFrame
         self.predicted_results_on_test = pd.DataFrame(self.pred_test)
         self.predicted_results_on_train = pd.DataFrame(self.pred_train)
-        return self.predicted_results_on_train, self.predicted_results_on_test
+        self.predicted_results["pred_data_train"] = self.predicted_results_on_train
+        self.predicted_results["pred_data_test"] = self.predicted_results_on_test
+        return self.predicted_results
 
     @property
     def model_(self):

src/Class_Mod/LWPLSR_Call.py

@@ -8,9 +8,11 @@ import os
 temp_path = Path("temp/")
 data_to_work_with = ['x_train_np', 'y_train_np', 'x_test_np', 'y_test_np']
 temp_files_list = os.listdir(temp_path)
+nb_fold = 0
 for i in temp_files_list:
     if 'fold' in i:
         data_to_work_with.append(str(i)[:-4])
+        nb_fold += 1
 dataset = []
 for i in data_to_work_with:
     dataset.append(np.genfromtxt(temp_path / str(i + ".csv"), delimiter=','))
@@ -23,14 +25,16 @@ print('now predict')
 LWPLSR.Jchemo_lwplsr_predict(Reg)
 
 print('now CV')
-
+LWPLSR.Jchemo_lwplsr_cv(Reg)
 
 
 print('export to json')
 pred = ['pred_data_train', 'pred_data_test']
+for i in range(int(nb_fold/4)):
+    pred.append("CV" + str(i+1))
 json_export = {}
 for i in pred:
-    json_export[i] = Reg.pred_data_[pred.index(i)].to_dict()
+    json_export[i] = Reg.pred_data_[i].to_dict()
 json_export['model'] = str(Reg.model_)
 json_export['best_lwplsr_params'] = Reg.best_lwplsr_params_
 with open(temp_path / "lwplsr_outputs.json", "w+") as outfile: