ddi-fw 0.0.187__tar.gz → 0.0.188__tar.gz

{ddi_fw-0.0.187 → ddi_fw-0.0.188}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.187
+Version: 0.0.188
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.187 → ddi_fw-0.0.188}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.187"
+version = "0.0.188"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.187 → ddi_fw-0.0.188}/src/ddi_fw/datasets/core.py

@@ -222,8 +222,8 @@ class BaseDataset(BaseModel):
 
         X_train, X_test, y_train, y_test, X_train.index, X_test.index, train_idx_arr, val_idx_arr = self.dataset_splitter.split(
             X=X, y=y)
-        self.X_train = np.array(self.X_train)
-        self.X_test = np.array(self.X_test)
+        self.X_train = np.array(X_train)
+        self.X_test = np.array(X_test)
         self.y_train =  np.array(y_train.tolist())
         self.y_test = np.array(y_test.tolist())
         self.train_indexes = X_train.index

{ddi_fw-0.0.187 → ddi_fw-0.0.188}/src/ddi_fw/pipeline/pipeline.py

@@ -37,23 +37,24 @@ class Pipeline(BaseModel):
     model: Optional[Any] = None
     multi_modal:  Optional[Any] = None
     use_mlflow: bool = False
-    _items:List=[]
-    _train_idx_arr:List|None=[]
-    _val_idx_arr:List|None=[]
-    
+    _items: List = []
+    _train_idx_arr: List | None = []
+    _val_idx_arr: List | None = []
+
     @property
     def items(self) -> List:
         return self._items
+
     @property
-    def train_idx_arr(self) -> List|None:
+    def train_idx_arr(self) -> List | None:
         return self._train_idx_arr
+
     @property
-    def val_idx_arr(self) -> List|None:
+    def val_idx_arr(self) -> List | None:
         return self._val_idx_arr
 
     class Config:
         arbitrary_types_allowed = True
- 
 
     def __create_or_update_embeddings__(self, embedding_dict, vector_db_persist_directory, vector_db_collection_name, column=None):
         """
@@ -146,21 +147,22 @@ class Pipeline(BaseModel):
         #     filename=self.ner_data_file) if self.ner_data_file else None
 
         dataset_splitter = self.dataset_splitter_type()
-        
+
         if issubclass(self.dataset_type, TextDatasetMixin):
             key, value = next(iter(embedding_dict.items()))
             embedding_size = value[next(iter(value))][0].shape[0]
-            pooling_strategy = self.embedding_pooling_strategy_type() if self.embedding_pooling_strategy_type  else None
+            pooling_strategy = self.embedding_pooling_strategy_type(
+            ) if self.embedding_pooling_strategy_type else None
 
             dataset = self.dataset_type(
                 embedding_dict=embedding_dict,
                 embedding_size=embedding_size,
                 embeddings_pooling_strategy=pooling_strategy,
-                dataset_splitter_type = self.dataset_splitter_type,
+                dataset_splitter_type=self.dataset_splitter_type,
                 **kwargs)
         elif self.dataset_type == BaseDataset:
-             dataset = self.dataset_type(
-                dataset_splitter_type = self.dataset_splitter_type,
+            dataset = self.dataset_type(
+                dataset_splitter_type=self.dataset_splitter_type,
                 **kwargs)
         else:
             dataset = self.dataset_type(**kwargs)
@@ -168,15 +170,22 @@ class Pipeline(BaseModel):
         # 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
-        b = not( dataset.X_train and dataset.y_train and dataset.X_test and dataset.y_test)
-        c = dataframe is None or dataframe.empty 
 
-        if b or c:
+        # Check if any of the arrays are None or empty
+        is_data_valid = (dataset.X_train is not None and dataset.X_train.size > 0 and
+                         dataset.y_train is not None and dataset.y_train.size > 0 and
+                         dataset.X_test is not None and dataset.X_test.size > 0 and
+                         dataset.y_test is not None and dataset.y_test.size > 0)
+
+        # Check if the dataframe is None or empty
+        is_dataframe_valid = dataframe is not None and not dataframe.empty
+
+        if not (is_data_valid and is_dataframe_valid):
             raise ValueError("The dataset is not loaded")
- 
+
         # column name, train data, train label, test data, test label
         self._items = dataset.produce_inputs()
- 
+
         print("Building the experiment with the following settings:")
         print(
             f"Name: {self.experiment_name}, Dataset: {dataset}, Model: {self.model}")

{ddi_fw-0.0.187 → ddi_fw-0.0.188}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.187
+Version: 0.0.188
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>