ddi-fw 0.0.195__py3-none-any.whl → 0.0.197__py3-none-any.whl

ddi_fw/datasets/core.py

@@ -135,7 +135,7 @@ class BaseDataset(BaseModel):
         skip deriving them. Otherwise, derive them from the dataframe and indices.
         """
         self.prep()
-        
+
         if isinstance(self, TextDatasetMixin):
             self.process_text()
 
@@ -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")
@@ -267,6 +267,9 @@ class TextDatasetMixin(BaseDataset):
     vector_db_persist_directory: Optional[str] = None
     vector_db_collection_name: Optional[str] = None
 
+    class Config:
+        arbitrary_types_allowed = True
+
     def __create_or_update_embeddings__(self, embedding_dict, vector_db_persist_directory, vector_db_collection_name, column=None):
         """
         Fetch embeddings and metadata from a persistent Chroma vector database and update the provided embedding_dict.
@@ -314,14 +317,13 @@ class TextDatasetMixin(BaseDataset):
         else:
             raise ValueError(
                 "Persistent directory for the vector DB is not specified.")
-    
+
     def process_text(self):
         # 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   
-           
-           
+        #     ) if self.embedding_pooling_strategy_type else None
+
         # 'enzyme','target','pathway','smile','all_text','indication', 'description','mechanism_of_action','pharmacodynamics', 'tui', 'cui', 'entities'
         # kwargs = {"columns": self.columns}
         # if self.ner_threshold:
@@ -346,9 +348,10 @@ 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/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')))

{ddi_fw-0.0.195.dist-info → ddi_fw-0.0.197.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.195
+Version: 0.0.197
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.195.dist-info → ddi_fw-0.0.197.dist-info}/RECORD

@@ -1,9 +1,9 @@
 ddi_fw/datasets/__init__.py,sha256=_I3iDHARwzmg7_EL5XKtB_TgG1yAkLSOVTujLL9Wz9Q,280
-ddi_fw/datasets/core.py,sha256=HXU09CTbe3zpdBiUcE2w2Yxx_3yHfY_rqa31oS959jw,15531
+ddi_fw/datasets/core.py,sha256=eLS4TtQN1_1kI0huMt7eTOCz5hY3da9PHhEeiLjWtQg,15605
 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
-ddi_fw/datasets/ddi_mdl/base.py,sha256=Nltf1P6ZMVT9oVsXMtrtpnlSz5hk_sa8FV2TpFYhSgc,10193
+ddi_fw/datasets/ddi_mdl/base.py,sha256=rS8lSGE-SLeoE3GuElJ-TNaRHIGhaZBeOM2UH3JUS4M,10218
 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
@@ -99,7 +99,7 @@ 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-0.0.195.dist-info/METADATA,sha256=hUXOkRgECPRDv1EyePv2mcCJRedgmnj6afwpFfwFVhk,2542
-ddi_fw-0.0.195.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.195.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.195.dist-info/RECORD,,
+ddi_fw-0.0.197.dist-info/METADATA,sha256=pVnij5JFvkPUgjVqvHmFLdI2OKSFRYxt7-vLVXhpldU,2542
+ddi_fw-0.0.197.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.197.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.197.dist-info/RECORD,,