ddi-fw 0.0.182__tar.gz → 0.0.184__tar.gz

{ddi_fw-0.0.182 → ddi_fw-0.0.184}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.182
+Version: 0.0.184
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.182 → ddi_fw-0.0.184}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.182"
+version = "0.0.184"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.182 → ddi_fw-0.0.184}/src/ddi_fw/datasets/core.py

@@ -77,17 +77,23 @@ class BaseDataset(BaseModel):
         items = []
         if self.X_train is None or self.X_test is None:
             raise Exception("There is no data to produce inputs")
-        y_train_label, y_test_label = np.array(self.y_train), np.array(self.y_test)
-
-        for index,column in enumerate(self.columns):
-            train_data, test_data =  self.X_train[:,index], self.X_test[:,index]
-            items.append([f'{column}', np.nan_to_num(train_data),
-                          y_train_label, np.nan_to_num(test_data), y_test_label])
-
-            # items.append([f'{column}_embedding', train_data,
-            #             y_train_label, test_data, y_test_label])
+        y_train_label, y_test_label = np.array(
+            self.y_train), np.array(self.y_test)
+
+        if self.columns is None or len(self.columns) == 0:
+            items.append([f'defaukt', np.nan_to_num(self.X_train),
+                          y_train_label, np.nan_to_num(self.X_test), y_test_label])
+        else:
+            for index, column in enumerate(self.columns):
+                train_data, test_data = self.X_train[:,
+                                                     index], self.X_test[:, index]
+                items.append([f'{column}', np.nan_to_num(train_data),
+                              y_train_label, np.nan_to_num(test_data), y_test_label])
+
+                # items.append([f'{column}_embedding', train_data,
+                #             y_train_label, test_data, y_test_label])
         return items
-    
+
     def produce_inputs_ex(self):
         items = []
         if self.X_train is None or self.X_test is None:
@@ -127,6 +133,8 @@ class BaseDataset(BaseModel):
                 "X_train, y_train, X_test, and y_test are already provided. Skipping calculation.")
             return self.X_train, self.X_test, self.y_train, self.y_test, self.train_indexes, self.test_indexes, self.train_idx_arr, self.val_idx_arr
 
+        self.prep()
+
         if self.index_path is None:
             raise Exception(
                 "There is no index path. Please call split_dataset or provide indices.")
@@ -140,21 +148,19 @@ class BaseDataset(BaseModel):
         except FileNotFoundError as e:
             raise FileNotFoundError(f"Index files not found: {e.filename}")
 
-        self.prep()
-
         train = self.dataframe[self.dataframe.index.isin(train_idx_all)]
         test = self.dataframe[self.dataframe.index.isin(test_idx_all)]
 
-        self.X_train =  train.drop(self.class_column, axis=1)
+        self.X_train = train.drop(self.class_column, axis=1)
         self.y_train = train[self.class_column]
         self.X_test = test.drop(self.class_column, axis=1)
         self.y_test = test[self.class_column]
- 
+
         self.train_indexes = self.X_train.index
         self.test_indexes = self.X_test.index
         self.train_idx_arr = train_idx_arr
         self.val_idx_arr = val_idx_arr
-        
+
         # Dataframe to numpy array conversion
         self.X_train = np.array(self.X_train)
         self.y_train = np.array(self.y_train)
@@ -201,13 +207,12 @@ class BaseDataset(BaseModel):
         if self.X_train is not None or self.X_test is not None:
             raise Exception(
                 "X_train and X_test are already present. Splitting is not allowed.")
-            
+
         self.prep()
         if self.dataframe is None:
             raise Exception("There is no dataframe to split.")
 
         save_path = self.index_path
-        
 
         X = self.dataframe.drop(self.class_column, axis=1)
         y = self.dataframe[self.class_column]
@@ -222,7 +227,7 @@ class BaseDataset(BaseModel):
         self.test_indexes = X_test.index
         self.train_idx_arr = train_idx_arr
         self.val_idx_arr = val_idx_arr
-        
+
         # Dataframe to numpy array conversion
         self.X_train = np.array(self.X_train)
         self.y_train = np.array(self.y_train.tolist())

{ddi_fw-0.0.182 → ddi_fw-0.0.184}/src/ddi_fw/pipeline/pipeline.py

@@ -199,7 +199,8 @@ class Pipeline(BaseModel):
         else:
             dataset = self.dataset_type(**kwargs)
 
-        X_train, X_test, y_train, y_test, X_train.index, X_test.index, train_idx_arr, val_idx_arr = dataset.load()
+        # X_train, X_test, y_train, y_test, train_indexes, test_indexes, train_idx_arr, val_idx_arr = dataset.load()
+        dataset.load()
 
         dataframe = dataset.dataframe
 
@@ -207,12 +208,12 @@ class Pipeline(BaseModel):
             raise ValueError("The dataset is not loaded")
 
         # dataframe.dropna()
-        X_train = dataset.X_train
-        X_test = dataset.X_test
-        y_train = dataset.y_train
-        y_test = dataset.y_test
-        self._train_idx_arr = dataset.train_idx_arr
-        self._val_idx_arr = dataset.val_idx_arr
+        # X_train = dataset.X_train
+        # X_test = dataset.X_test
+        # y_train = dataset.y_train
+        # y_test = dataset.y_test
+        # self._train_idx_arr = dataset.train_idx_arr
+        # self._val_idx_arr = dataset.val_idx_arr
         # Logic to set up the experiment
         # column name, train data, train label, test data, test label
         self._items = dataset.produce_inputs()

{ddi_fw-0.0.182 → ddi_fw-0.0.184}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.182
+Version: 0.0.184
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>