ddi-fw 0.0.222__py3-none-any.whl → 0.0.224__py3-none-any.whl

ddi_fw/datasets/ddi_mdl/base.py

@@ -65,8 +65,8 @@ class DDIMDLDataset(BaseDataset,TextDatasetMixin):
     def __init__(self, **kwargs):
 
         super().__init__(**kwargs)
-        self.index_path: str = Field(default_factory=lambda: str(
-        pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
+        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/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,
@@ -88,7 +88,7 @@ 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')))
@@ -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
 
@@ -119,9 +119,9 @@ class MDFSADDIDataset(BaseDataset,TextDatasetMixin):
     def __init__(self, **kwargs):
 
         super().__init__(**kwargs)
-        self.index_path: str = Field(default_factory=lambda: str(
-        pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
-         
+        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', {})
@@ -130,10 +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 = []
@@ -148,13 +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):
@@ -166,8 +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__ = []
@@ -217,11 +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:
@@ -246,7 +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
@@ -272,7 +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/pipeline/pipeline.py

@@ -105,8 +105,10 @@ 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()
-
+        
         self._dataset = dataset
+        self._train_idx_arr = dataset.train_idx_arr
+        self._val_idx_arr = dataset.val_idx_arr
 
         dataframe = dataset.dataframe
 

{ddi_fw-0.0.222.dist-info → ddi_fw-0.0.224.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.222
+Version: 0.0.224
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.222.dist-info → ddi_fw-0.0.224.dist-info}/RECORD

@@ -3,7 +3,7 @@ ddi_fw/datasets/core.py,sha256=PX6MX4hmeYxIWAKAx7NnJr1fpzR11xA8g8vAjYcQNN8,16936
 ddi_fw/datasets/dataset_splitter.py,sha256=8H8uZTAf8N9LUZeSeHOMawtJFJhnDgUUqFcnl7dquBQ,1672
 ddi_fw/datasets/db_utils.py,sha256=xRj28U_uXTRPHcz3yIICczFUHXUPiAOZtAj5BM6kH44,6465
 ddi_fw/datasets/setup_._py,sha256=khYVJuW5PlOY_i_A16F3UbSZ6s6o_ljw33Byw3C-A8E,1047
-ddi_fw/datasets/ddi_mdl/base.py,sha256=0fHiKtnbYrcucBRcR6fMOD1WZnZFeJ-uQXFtqJ7xnfg,11379
+ddi_fw/datasets/ddi_mdl/base.py,sha256=1bFubHRi5idP6SYGyB3tXZPV8aUzETbrzGqnXsQFbJU,11347
 ddi_fw/datasets/ddi_mdl/debug.log,sha256=eWz05j8RFqZuHFDTCF7Rck5w4rvtTanFN21iZsgxO7Y,115
 ddi_fw/datasets/ddi_mdl/readme.md,sha256=WC6lpmsEKvIISnZqENY7TWtzCQr98HPpE3oRsBl8pIw,625
 ddi_fw/datasets/ddi_mdl/data/event.db,sha256=cmlSsf9MYjRzqR-mw3cUDnTnfT6FkpOG2yCl2mMwwew,30580736
@@ -46,7 +46,7 @@ ddi_fw/datasets/ddi_mdl_text/indexes/validation_fold_2.txt,sha256=fFJbN0DbKH4mve
 ddi_fw/datasets/ddi_mdl_text/indexes/validation_fold_3.txt,sha256=NhiLF_5INQCpjOlE-RIxDKy7rYwksLdx60L6HCmDKoY,81247
 ddi_fw/datasets/ddi_mdl_text/indexes/validation_fold_4.txt,sha256=bPvMCJVy7jtcaYbR-5bmdB6s7gT8NSfK2wDC7iJ0O10,81308
 ddi_fw/datasets/mdf_sa_ddi/__init__.py,sha256=UEFBM92y2aJjlMJw4Jx405tOAwJ88r_nHAVgAszSjuo,68
-ddi_fw/datasets/mdf_sa_ddi/base.py,sha256=rMfHf3pg-XL2zgGuwByDI5354udJ98xuZTj4_wufoGM,16050
+ddi_fw/datasets/mdf_sa_ddi/base.py,sha256=27TwErhK7mjd4YzVhQgjWjlVgX4PpNq54zoNJLXp-bE,15993
 ddi_fw/datasets/mdf_sa_ddi/df_extraction_cleanxiaoyu50.csv,sha256=EOOLF_0vVVzShoofcGYlOzpztlM1m9jJdftepHicix4,25787699
 ddi_fw/datasets/mdf_sa_ddi/drug_information_del_noDDIxiaoyu50.csv,sha256=lpuMz5KxPsG6MKNuIIUmT5cZquWHQiIao8tXlmOHzq8,381321
 ddi_fw/datasets/mdf_sa_ddi/mdf-sa-ddi.zip,sha256=DfN8mczGvWba2y45cPqtWtXjUDXy49VOtRfpcb0tn8c,4382827
@@ -87,7 +87,7 @@ ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=JSyuP71b1I1yuk0s2ecCJ
 ddi_fw/pipeline/multi_pipeline.py,sha256=npJUXYT31fxD6kpJKSeixjbH5jNfPUwIVG7lRdBszRg,9852
 ddi_fw/pipeline/multi_pipeline_org.py,sha256=AbErwu05-3YIPnCcXRsj-jxPJG8HG2H7cMZlGjzaYa8,9037
 ddi_fw/pipeline/ner_pipeline.py,sha256=yp-Met2794EKcgr8_3gqt03l4v2efOdaZuAcIXTubvQ,5780
-ddi_fw/pipeline/pipeline.py,sha256=mCEiFwM80Gs6Uo7QFJNioFHwLTZcwoSVmc52Xos81XY,6133
+ddi_fw/pipeline/pipeline.py,sha256=q1kMkW9-fOlrA4BOGUku40U_PuEYfcbtH2EvlRM4uTM,6243
 ddi_fw/utils/__init__.py,sha256=WNxkQXk-694roG50D355TGLXstfdWVb_tUyr-PM-8rg,537
 ddi_fw/utils/categorical_data_encoding_checker.py,sha256=T1X70Rh4atucAuqyUZmz-iFULllY9dY0NRyV9-jTjJ0,3438
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
@@ -101,7 +101,7 @@ 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=EBf-XAiwQwr68az91erEYNegfeqssBR29kVgrliIyac,4765
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.222.dist-info/METADATA,sha256=WC33zHRr1ONe_rAX-dG4wf_LSc8L7qUOoEeki9PwvYY,2631
-ddi_fw-0.0.222.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.222.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.222.dist-info/RECORD,,
+ddi_fw-0.0.224.dist-info/METADATA,sha256=5dFfDc76jiVD68bVFOsMw8lUXIaklRzuWIA6HB781Ls,2631
+ddi_fw-0.0.224.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.224.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.224.dist-info/RECORD,,