ddi-fw 0.0.198__tar.gz → 0.0.200__tar.gz

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.198
+Version: 0.0.200
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.198"
+version = "0.0.200"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw/datasets/core.py

@@ -144,8 +144,8 @@ class BaseDataset(BaseModel, abc.ABC):
         Load the dataset. If X_train, y_train, X_test, and y_test are already provided,
         skip deriving them. Otherwise, derive them from the dataframe and indices.
         """
-        self.prep()  # Prepare the dataset
         self.handle_mixins()  # Centralized mixin handling
+        self.prep()  # Prepare the dataset
 
         if self.X_train is not None or self.y_train is not None or self.X_test is not None or self.y_test is not None:
             # Data is already provided, no need to calculate
@@ -169,8 +169,9 @@ class BaseDataset(BaseModel, abc.ABC):
         
         # train = self.dataframe[self.dataframe.index.isin(train_idx_all)]
         # test = self.dataframe[self.dataframe.index.isin(test_idx_all)]
-        train = self.dataframe.loc[self.dataframe.index.isin(train_idx_all), self.columns]
-        test = self.dataframe.loc[self.dataframe.index.isin(test_idx_all), self.columns]
+        columns = self.columns + [self.class_column] 
+        train = self.dataframe.loc[self.dataframe.index.isin(train_idx_all), columns]
+        test = self.dataframe.loc[self.dataframe.index.isin(test_idx_all), columns]
         X_train = train.drop(self.class_column, axis=1)
         X_train = train.drop(self.class_column, axis=1)
         y_train = train[self.class_column]

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw/datasets/ddi_mdl/base.py

@@ -81,6 +81,7 @@ class DDIMDLDataset(BaseDataset,TextDatasetMixin):
             self.chemical_property_columns = chemical_property_columns
             self.embedding_columns = embedding_columns 
             self.ner_columns = ner_columns 
+            self.columns = [] # these variable is modified in prep method
         
         self.class_column = 'event_category'
         _db_path = HERE.joinpath('data/event.db')

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw/ml/ml_helper.py

@@ -32,9 +32,10 @@ import ddi_fw.utils as utils
 
 class MultiModalRunner:
     # todo model related parameters to config
-    def __init__(self, library, multi_modal, use_mlflow=False):
+    def __init__(self, library, multi_modal, default_model, use_mlflow=False):
         self.library = library
         self.multi_modal = multi_modal
+        self.default_model = default_model
         self.use_mlflow = use_mlflow
         self.result = Result()
 
@@ -60,14 +61,13 @@ class MultiModalRunner:
     # TODO check single_results, 1d,2d ...
     def __predict(self, single_results):
         item_dict = {t[0]: t for t in self.items}
-        print("multi_modal")
-        print(self.multi_modal)
-        print(item_dict.keys())
+        if self.default_model is None and not self.multi_modal:
+            raise Exception("Default model and multi modal cannot be None at the same time")
 
         if self.multi_modal:
             for m in self.multi_modal:
                 name = m.get('name')
-                input_type = m.get('input_type')
+                # input_type = m.get('input_type')
                 input = m.get('input')
                 inputs = m.get('inputs')
                 model_type = get_import(m.get("model_type"))
@@ -99,14 +99,25 @@ class MultiModalRunner:
                         self.train_idx_arr, self.val_idx_arr, train_data, train_label, test_data, test_label)
                 else:
                     raise Exception("check configurations")
-            else: # TODO default model maybe?
-                item = self.items[0]
+                logs, metrics, prediction = single_modal.fit_and_evaluate()
+                self.result.add_metric(name, metrics)
+                single_results[name] = prediction
+        else: # TODO default model maybe?
+            print("Default model will be used")
+            name = self.default_model.get('name')
+            # input_type = m.get('input_type')
+            model_type = get_import(self.default_model.get("model_type"))
+            kwargs = self.default_model.get('params')
+            for item in self.items:
+                T = self.__create_model(self.library)
+                single_modal = T(self.date, name, model_type,
+                                use_mlflow=self.use_mlflow,  **kwargs)
                 single_modal.set_data(
                         self.train_idx_arr, self.val_idx_arr, item[1], item[2], item[3], item[4])
 
-            logs, metrics, prediction = single_modal.fit_and_evaluate()
-            self.result.add_metric(name, metrics)
-            single_results[name] = prediction
+                logs, metrics, prediction = single_modal.fit_and_evaluate()
+                self.result.add_metric(name, metrics)
+                single_results[name] = prediction
 
     def predict(self, combinations: list = [], generate_combinations=False):
         self.prefix = utils.utc_time_as_string()

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw/pipeline/multi_pipeline.py

@@ -57,6 +57,7 @@ class MultiPipeline():
         tracking_uri = config.get("tracking_uri")
         artifact_location = config.get("artifact_location")
         #new
+        default_model = config.get("default_model"),
         multi_modal = config.get("multi_modal")
         columns = config.get("columns")
         ner_data_file = config.get("ner_data_file")
@@ -101,6 +102,7 @@ class MultiPipeline():
                 ner_data_file=ner_data_file,
                 ner_threshold=ner_threshold,
                 combinations=combinations,
+                default_model=default_model,
                 multi_modal= multi_modal)
         elif type== "ner_search":
             pipeline = NerParameterSearch(

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw/pipeline/pipeline.py

@@ -35,6 +35,7 @@ class Pipeline(BaseModel):
     ner_threshold: Optional[dict] = None
     combinations: Optional[List[str]] = None
     model: Optional[Any] = None
+    default_model:  Optional[Any] = None
     multi_modal:  Optional[Any] = None
     use_mlflow: bool = False
     _dataset: BaseDataset = []
@@ -193,7 +194,7 @@ class Pipeline(BaseModel):
 
         y_test_label = self.items[0][4]
         multi_modal_runner = MultiModalRunner(
-            library=self.library, multi_modal=self.multi_modal, use_mlflow=self.use_mlflow)
+            library=self.library, multi_modal=self.multi_modal, default_model= self.default_model , use_mlflow=self.use_mlflow)
         # multi_modal_runner = MultiModalRunner(
         #     library=self.library, model_func=model_func, batch_size=batch_size,  epochs=epochs)
         # multi_modal = TFMultiModal(

{ddi_fw-0.0.198 → ddi_fw-0.0.200}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.198
+Version: 0.0.200
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>