ddi-fw 0.0.187__py3-none-any.whl → 0.0.189__py3-none-any.whl

ddi_fw/datasets/core.py

@@ -158,9 +158,11 @@ class BaseDataset(BaseModel):
         y_test = test[self.class_column]
         
         self.X_train = np.array(X_train)
-        self.y_train = np.array(y_train)
+        # self.y_train = np.array(y_train)
+        self.y_train = np.array(y_train.tolist())
         self.X_test = np.array(X_test)
-        self.y_test = np.array(y_test)
+        # self.y_test = np.array(y_test)
+        self.y_test = np.array(y_test.tolist())
 
         self.train_indexes = X_train.index
         self.test_indexes = X_test.index
@@ -222,8 +224,8 @@ 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/ml/ml_helper.py

@@ -57,7 +57,7 @@ class MultiModalRunner:
             raise ValueError(
                 "Unsupported library type. Choose 'tensorflow' or 'pytorch'.")
 
-    def __predict(self,single_results):
+    def __predict(self, single_results):
         item_dict = {t[0]: t for t in self.items}
         print("multi_modal")
         print(self.multi_modal)
@@ -71,7 +71,8 @@ class MultiModalRunner:
             model_type = get_import(m.get("model_type"))
             kwargs = m.get('params')
             T = self.__create_model(self.library)
-            single_modal = T(self.date, name, model_type, **kwargs)
+            single_modal = T(self.date, name, model_type,
+                             use_mlflow=self.use_mlflow,  **kwargs)
             if input_type == '1D':
                 item = item_dict[input]
                 single_modal.set_data(
@@ -79,7 +80,7 @@ class MultiModalRunner:
             elif input_type == '2D':
                 # check keys
                 filtered_dict = {k: item_dict[k]
-                                    for k in inputs if k in item_dict}
+                                 for k in inputs if k in item_dict}
                 print(filtered_dict.keys())
                 first_input = next(iter(filtered_dict.values()))
                 train_data_list = [f[1] for f in filtered_dict.values()]

ddi_fw/ml/tensorflow_wrapper.py

@@ -64,7 +64,7 @@ def convert_to_categorical(arr, num_classes):
 
 class TFModelWrapper(ModelWrapper):
 
-    def __init__(self, date, descriptor, model_func, use_mlflow=True, **kwargs):
+    def __init__(self, date, descriptor, model_func, use_mlflow=False, **kwargs):
         super().__init__(date, descriptor, model_func, **kwargs)
         self.batch_size = kwargs.get('batch_size', 128)
         self.epochs = kwargs.get('epochs', 100)

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.dist-info → ddi_fw-0.0.189.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.187
+Version: 0.0.189
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.187.dist-info → ddi_fw-0.0.189.dist-info}/RECORD

@@ -1,5 +1,5 @@
 ddi_fw/datasets/__init__.py,sha256=_I3iDHARwzmg7_EL5XKtB_TgG1yAkLSOVTujLL9Wz9Q,280
-ddi_fw/datasets/core.py,sha256=mZcGqP3Ukx5FbYSMi08uq4vYDr7jbHR3xg1qOPJmU0s,10640
+ddi_fw/datasets/core.py,sha256=WWWd5SGHVUpJn-IJF1p1PScSWpb7VfQdcMTroufkgUk,10734
 ddi_fw/datasets/dataset_splitter.py,sha256=8H8uZTAf8N9LUZeSeHOMawtJFJhnDgUUqFcnl7dquBQ,1672
 ddi_fw/datasets/db_utils.py,sha256=OTsa3d-Iic7z3HmzSQK9UigedRbHDxYChJk0s4GfLnw,6191
 ddi_fw/datasets/setup_._py,sha256=khYVJuW5PlOY_i_A16F3UbSZ6s6o_ljw33Byw3C-A8E,1047
@@ -74,10 +74,10 @@ ddi_fw/langchain/sentence_splitter.py,sha256=h_bYElx4Ud1mwDNJfL7mUwvgadwKX3GKlSz
 ddi_fw/langchain/storage.py,sha256=OizKyWm74Js7T6Q9kez-ulUoBGzIMFo4R46h4kjUyIM,11200
 ddi_fw/ml/__init__.py,sha256=tIxiW0g6q1VsmDYVXR_ovvHQR3SCir8g2bKxx_CrS7s,221
 ddi_fw/ml/evaluation_helper.py,sha256=2-7CLSgGTqLEk4HkgCVIOt-GxfLAn6SBozJghAtHb5M,11581
-ddi_fw/ml/ml_helper.py,sha256=l1ZLYL3x5bHxD2bh2ezEgWDlV0ni8zGZGgj07x7KR40,6310
+ddi_fw/ml/ml_helper.py,sha256=xbIg0fAJeJuB7rlgUMzCFhQ4WLBXS35x5N5gCcs6-so,6367
 ddi_fw/ml/model_wrapper.py,sha256=kabPXuo7S8tGkp9a00V04n4rXDmv7dD8wYGMjotISRc,1050
 ddi_fw/ml/pytorch_wrapper.py,sha256=pe6UsjP2XeTgLxDnIUiodoyhJTGCxV27wD4Cjxysu2Q,8553
-ddi_fw/ml/tensorflow_wrapper.py,sha256=-zcbd0LBg9QNMF9K1I-JC379cS3rTO7ibgsDIOnMsoc,12951
+ddi_fw/ml/tensorflow_wrapper.py,sha256=lNJvg3odqMKmILecOMdcOCAOrwzWZDzxB0DWGcYWsPg,12952
 ddi_fw/ner/__init__.py,sha256=JwhGXrepomxPSsGsg2b_xPRC72AjvxOIn2CW5Mvscn0,26
 ddi_fw/ner/mmlrestclient.py,sha256=NZta7m2Qm6I_qtVguMZhqtAUjVBmmXn0-TMnsNp0jpg,6859
 ddi_fw/ner/ner.py,sha256=FHyyX53Xwpdw8Hec261dyN88yD7Z9LmJua2mIrQLguI,17967
@@ -85,7 +85,7 @@ ddi_fw/pipeline/__init__.py,sha256=tKDM_rW4vPjlYTeOkNgi9PujDzb4e9O3LK1w5wqnebw,2
 ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=JSyuP71b1I1yuk0s2ecCJZTtCED85jBtkpwTUxibJvI,1706
 ddi_fw/pipeline/multi_pipeline.py,sha256=NfcH4Ze5U-JRiH3lrxEDWj-VPxYQYtp7tq6bLCImBzs,5550
 ddi_fw/pipeline/ner_pipeline.py,sha256=Bp6BA6nozfWFaMHH6jKlzesnCGO6qiMkzdGy_ed6nh0,5947
-ddi_fw/pipeline/pipeline.py,sha256=VSILkxot_O1DJMWPavzFUH3le4zVKQydcH32SbuHZlQ,9355
+ddi_fw/pipeline/pipeline.py,sha256=dCXZuXOlW74ZO0e_OhS9OX0dqI9abj7CQz_lkKrDIWY,9787
 ddi_fw/utils/__init__.py,sha256=bqIC0YjbD0YSHtO0nWUkRs4w5nu7qBV0yU72sRzwCj8,475
 ddi_fw/utils/categorical_data_encoding_checker.py,sha256=gzb_vUDBrCMUhBxY1fBYTe8hmK72p0_uw3DTga8cqP8,1580
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
@@ -98,7 +98,7 @@ ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,55
 ddi_fw/vectorization/__init__.py,sha256=LcJOpLVoLvHPDw9phGFlUQGeNcST_zKV-Oi1Pm5h_nE,110
 ddi_fw/vectorization/feature_vector_generation.py,sha256=Z1A_DOBqDFPqLN4YB-3oYlOQWJK-X6Oes6UFjpzR47Q,4760
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.187.dist-info/METADATA,sha256=dzH9YAqsPxQcvuS9h0JRNx5qtd8vGNr-1c5f0uE3c7M,2542
-ddi_fw-0.0.187.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.187.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.187.dist-info/RECORD,,
+ddi_fw-0.0.189.dist-info/METADATA,sha256=y3hik68p2UsqKr7ur8R2ix8TyPfGsveDbKWboSaRkzA,2542
+ddi_fw-0.0.189.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.189.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.189.dist-info/RECORD,,