ddi-fw 0.0.221__tar.gz → 0.0.223__tar.gz

{ddi_fw-0.0.221 → ddi_fw-0.0.223}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.221
+Version: 0.0.223
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.221 → ddi_fw-0.0.223}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.221"
+version = "0.0.223"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.221 → ddi_fw-0.0.223}/src/ddi_fw/datasets/ddi_mdl/base.py

@@ -36,8 +36,8 @@ HERE = pathlib.Path(__file__).resolve().parent
 
 class DDIMDLDataset(BaseDataset,TextDatasetMixin):
     dataset_name: str = "DDIMDLDataset"
-    index_path: str = Field(default_factory=lambda: str(
-        pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
+    # index_path: str = Field(default_factory=lambda: str(
+    #     pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
     # drugs_df: pd.DataFrame = Field(default_factory=pd.DataFrame)
     # ddis_df: pd.DataFrame = Field(default_factory=pd.DataFrame)
     drugs_df: Optional[pd.DataFrame] = None
@@ -65,7 +65,8 @@ class DDIMDLDataset(BaseDataset,TextDatasetMixin):
     def __init__(self, **kwargs):
 
         super().__init__(**kwargs)
-        
+        self.index_path = str(
+            pathlib.Path(__file__).resolve().parent.joinpath('indexes'))
         # self.additional_config = kwargs.get('dataset_additional_config', {})
         if self.additional_config:
             ner = self.additional_config.get('ner', {})

{ddi_fw-0.0.221 → ddi_fw-0.0.223}/src/ddi_fw/datasets/mdf_sa_ddi/base.py

@@ -35,7 +35,8 @@ LIST_OF_NER_COLUMNS = ['tui', 'cui', 'entities']
 
 HERE = pathlib.Path(__file__).resolve().parent
 
-class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
+
+class MDFSADDIDataset(BaseDataset, TextDatasetMixin):
     # def __init__(self, embedding_size,
     #              embedding_dict,
     #              embeddings_pooling_strategy: PoolingStrategy,
@@ -64,7 +65,6 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
     #             else:
     #                 raise Exception(f"{column} is not related this dataset")
 
-
     #     super().__init__(embedding_size=embedding_size,
     #                      embedding_dict=embedding_dict,
     #                      embeddings_pooling_strategy=embeddings_pooling_strategy,
@@ -88,10 +88,10 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
     #     kwargs['index_path'] = str(HERE.joinpath('indexes'))
 
     #     self.index_path = kwargs.get('index_path')
-    
+
     dataset_name: str = "MDFSADDIDataset"
-    index_path: str = Field(default_factory=lambda: str(
-        pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
+    # index_path: str = Field(default_factory=lambda: str(
+    #     pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
     # drugs_df: pd.DataFrame = Field(default_factory=pd.DataFrame)
     # ddis_df: pd.DataFrame = Field(default_factory=pd.DataFrame)
     drugs_df: Optional[pd.DataFrame] = None
@@ -105,7 +105,7 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
     tui_threshold: float | None = None
     cui_threshold: float | None = None
     entities_threshold: float | None = None
-    _ner_threshold: dict[str,Any] |None= None
+    _ner_threshold: dict[str, Any] | None = None
 
     # @model_validator
 
@@ -119,7 +119,9 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
     def __init__(self, **kwargs):
 
         super().__init__(**kwargs)
-        
+        self.index_path = str(
+            pathlib.Path(__file__).resolve().parent.joinpath('indexes'))
+
         # self.additional_config = kwargs.get('dataset_additional_config', {})
         if self.additional_config:
             ner = self.additional_config.get('ner', {})
@@ -128,10 +130,10 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
             # if self.ner_threshold:
             #     for k, v in self.ner_threshold.items():
             #         kwargs[k] = v
-        
+
             self.ner_df = CTakesNER(df=None).load(
                 filename=ner_data_file) if ner_data_file else None
-        
+
         columns = kwargs['columns']
         if columns:
             chemical_property_columns = []
@@ -146,13 +148,12 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
                     ner_columns.append(column)
                 else:
                     raise Exception(f"{column} is not related this dataset")
-        
+
             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.embedding_columns = embedding_columns
+            self.ner_columns = ner_columns
+            self.columns = []  # these variable is modified in prep method
+
         db_zip_path = HERE.joinpath('mdf-sa-ddi.zip')
         db_path = HERE.joinpath('mdf-sa-ddi.db')
         if not os.path.exists(db_zip_path):
@@ -164,8 +165,7 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
             self.drugs_df = select_all_drugs_as_dataframe(conn)
             self.ddis_df = select_all_events_as_dataframe(conn)
         # kwargs = {'index_path': str(HERE.joinpath('indexes'))}
-        
-        
+
         self.class_column = 'event_category'
 
         self.__similarity_related_columns__ = []
@@ -215,11 +215,13 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
         self.ddis_df['id2'] = self.ddis_df['name2'].apply(
             lambda_fnc1)  # , axis=1
         if conn:
-            self.drugs_df.to_sql('drug', conn, if_exists='replace', index=False)
-            self.ddis_df.to_sql('event', conn, if_exists='replace', index=False)
+            self.drugs_df.to_sql(
+                'drug', conn, if_exists='replace', index=False)
+            self.ddis_df.to_sql(
+                'event', conn, if_exists='replace', index=False)
             ZipHelper().zip_single_file(
                 file_path=db_path, output_path=HERE, zip_name='mdf-sa-ddi')
-            
+
     def prep(self):
         # self.load_drugs_and_events()
         if self.drugs_df is None or self.ddis_df is None:
@@ -244,7 +246,8 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
 
             # for key in filtered_ner_df.keys():
             for key in self.ner_columns:
-                threshold = self._ner_threshold.get(key, 0) if self._ner_threshold else 0
+                threshold = self._ner_threshold.get(
+                    key, 0) if self._ner_threshold else 0
                 # threshold = 0
                 # if key.startswith('tui'):
                 #     threshold = self.tui_threshold
@@ -270,7 +273,7 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
         generated_vectors = generate_vectors(
             chemical_properties_df, self.__similarity_related_columns__)
 
-        # TODO if necessary 
+        # TODO if necessary
         similarity_matrices = generate_sim_matrices_new(
             chemical_properties_df, generated_vectors,  self.__similarity_related_columns__, key_column="id")
 

{ddi_fw-0.0.221 → ddi_fw-0.0.223}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.221
+Version: 0.0.223
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>