ddi-fw 0.0.194__tar.gz → 0.0.196__tar.gz

{ddi_fw-0.0.194 → ddi_fw-0.0.196}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.194
+Version: 0.0.196
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.194 → ddi_fw-0.0.196}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.194"
+version = "0.0.196"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.194 → ddi_fw-0.0.196}/src/ddi_fw/datasets/core.py

@@ -258,7 +258,7 @@ class BaseDataset(BaseModel):
         # return X_train, X_test, y_train, y_test, folds
 
 
-class TextDatasetMixin(BaseDataset):
+class TextDatasetMixin(BaseModel):
     embedding_size: Optional[int] = None
     embedding_dict: Dict[str, Any] | None = Field(
         default_factory=dict, description="Dictionary for embeddings")
@@ -346,9 +346,10 @@ class TextDatasetMixin(BaseDataset):
             else:
                 print(
                     f"There is no configuration of Embeddings")
+            self.embedding_dict = embedding_dict
 
-        else:
-            embedding_dict = self.embedding_dict
+        # else:
+        #     embedding_dict = self.embedding_dict
             # TODO make generic
             # embedding_size = list(embedding_dict['all_text'].values())[
             #     0][0].shape

{ddi_fw-0.0.194 → ddi_fw-0.0.196}/src/ddi_fw/datasets/ddi_mdl/base.py

@@ -1,6 +1,6 @@
 import pathlib
 from typing import List, Optional, Tuple
-from ddi_fw.datasets.core import TextDatasetMixin, generate_sim_matrices_new, generate_vectors
+from ddi_fw.datasets.core import BaseDataset, TextDatasetMixin, generate_sim_matrices_new, generate_vectors
 from ddi_fw.datasets.db_utils import create_connection
 import numpy as np
 import pandas as pd
@@ -32,7 +32,7 @@ LIST_OF_NER_COLUMNS = ['tui', 'cui', 'entities']
 HERE = pathlib.Path(__file__).resolve().parent
 
 
-class DDIMDLDataset(TextDatasetMixin):
+class DDIMDLDataset(BaseDataset,TextDatasetMixin):
     dataset_name: str = "DDIMDLDataset"
     index_path: str = Field(default_factory=lambda: str(
         pathlib.Path(__file__).resolve().parent.joinpath('indexes')))
@@ -62,6 +62,26 @@ class DDIMDLDataset(TextDatasetMixin):
     def __init__(self, **kwargs):
 
         super().__init__(**kwargs)
+        
+        columns = kwargs['columns']
+        if columns:
+            chemical_property_columns = []
+            embedding_columns = []
+            ner_columns = []
+            for column in columns:
+                if column in LIST_OF_CHEMICAL_PROPERTY_COLUMNS:
+                    chemical_property_columns.append(column)
+                elif column in LIST_OF_EMBEDDING_COLUMNS:
+                    embedding_columns.append(column)
+                elif column in LIST_OF_NER_COLUMNS:
+                    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.class_column = 'event_category'
         _db_path = HERE.joinpath('data/event.db')
 

{ddi_fw-0.0.194 → ddi_fw-0.0.196}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.194
+Version: 0.0.196
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>