ddi-fw 0.0.154__py3-none-any.whl → 0.0.157__py3-none-any.whl

ddi_fw/datasets/ddi_mdl/base.py

@@ -15,6 +15,9 @@ from abc import ABC, abstractmethod
 from sklearn.preprocessing import LabelBinarizer
 
 from sklearn.model_selection import KFold, StratifiedKFold, train_test_split
+import logging
+
+logger = logging.getLogger(__name__)
 
 # Constants for embedding, chemical properties, and NER columns
 LIST_OF_EMBEDDING_COLUMNS = [
@@ -57,6 +60,7 @@ class DDIMDLDataset(TextDatasetMixin):
         return values
 
     def __init__(self, **kwargs):
+
         super().__init__(**kwargs)
         self.class_column = 'event_category'
         _db_path = HERE.joinpath('data/event.db')
@@ -67,6 +71,7 @@ class DDIMDLDataset(TextDatasetMixin):
         # TODO with resource
         self._conn = create_connection(_db_path.absolute().as_posix())
         self.load_drugs_and_events()
+        logger.info(f'{self.dataset_name} is initialized')
 
     def load_drugs_and_events(self):
         self.drugs_df = self.__select_all_drugs_as_dataframe__()

ddi_fw/datasets/feature_vector_generation.py

@@ -35,7 +35,7 @@ class SimilarityMatrixGenerator:
         return jaccard_sim_matrix
 
     # https://github.com/YifanDengWHU/DDIMDL/blob/master/DDIMDL.py , def Jaccard(matrix):
-    def create_jaccard_similarity_matrices(self, matrix):
+    def create_jaccard_similarity_matrices(self, matrix)->np.ndarray:
         matrix = np.mat(matrix)
         numerator = matrix * matrix.T
         denominator = np.ones(np.shape(matrix)) * matrix.T + \

ddi_fw/pipeline/multi_pipeline.py

@@ -68,6 +68,7 @@ class MultiPipeline():
         # Dynamically import the model and dataset classes
         # model_type = get_import(config.get("model_type"))
         dataset_type = get_import(config.get("dataset_type"))
+        dataset_splitter_type = get_import(config.get("dataset_splitter_type"))
 
         combination_type = None
         kwargs_combination_params=None
@@ -89,6 +90,7 @@ class MultiPipeline():
                 artifact_location=artifact_location,
                 tracking_uri=tracking_uri,
                 dataset_type=dataset_type,
+                dataset_splitter_type=dataset_splitter_type,
                 columns=columns,
                 column_embedding_configs=column_embedding_configs,
                 vector_db_persist_directory=vector_db_persist_directory,

ddi_fw-0.0.157.dist-info/METADATA

@@ -0,0 +1,76 @@
+Metadata-Version: 2.4
+Name: ddi_fw
+Version: 0.0.157
+Summary: Do not use :)
+Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
+Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
+Keywords: Machine Learning
+Classifier: Development Status :: 1 - Planning
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Framework :: Pytest
+Classifier: Framework :: tox
+Classifier: Framework :: Sphinx
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: tqdm>=4.66.6
+Requires-Dist: pandas>=2.2.0
+Provides-Extra: llm
+Requires-Dist: sentence-transformers<=3.3.1,>=3.0.1; extra == "llm"
+Requires-Dist: transformers>=4.42.4; extra == "llm"
+Requires-Dist: stanza==1.9.2; extra == "llm"
+Requires-Dist: tokenizers>=0.19.1; extra == "llm"
+Requires-Dist: openai>=1.52.2; extra == "llm"
+Requires-Dist: langchain>=0.3.4; extra == "llm"
+Requires-Dist: langchain_community==0.3.3; extra == "llm"
+Provides-Extra: ml
+Requires-Dist: scikit-learn==1.5.2; extra == "ml"
+Requires-Dist: tensorflow<2.18.0,>=2.17.0; extra == "ml"
+Requires-Dist: tf-keras==2.17.0; extra == "ml"
+Requires-Dist: mlflow==2.16.1; extra == "ml"
+Requires-Dist: accelerate>=0.33.0; extra == "ml"
+Requires-Dist: numpy>=1.26.4; extra == "ml"
+Requires-Dist: scipy==1.13.1; extra == "ml"
+Requires-Dist: pandas>=2.2.0; extra == "ml"
+Requires-Dist: plotly==5.24.1; extra == "ml"
+Requires-Dist: matplotlib==3.8.0; extra == "ml"
+Requires-Dist: rdkit==2023.3.3; extra == "ml"
+Requires-Dist: datasets==3.0.2; extra == "ml"
+Requires-Dist: tqdm>=4.66.6; extra == "ml"
+Provides-Extra: datasets
+Requires-Dist: datasets==3.0.2; extra == "datasets"
+Requires-Dist: unstructured==0.16.3; extra == "datasets"
+Requires-Dist: py7zr==0.22.0; extra == "datasets"
+Requires-Dist: xmlschema==3.4.2; extra == "datasets"
+Provides-Extra: drugbank
+Requires-Dist: rdkit==2023.3.3; extra == "drugbank"
+Requires-Dist: openai>=1.52.2; extra == "drugbank"
+Provides-Extra: pipeline-and-ner
+Requires-Dist: nltk>=3.8.1; extra == "pipeline-and-ner"
+Requires-Dist: stanza==1.9.2; extra == "pipeline-and-ner"
+Requires-Dist: transformers>=4.42.4; extra == "pipeline-and-ner"
+Requires-Dist: sentence-transformers<=3.3.1,>=3.0.1; extra == "pipeline-and-ner"
+Requires-Dist: mlflow==2.16.1; extra == "pipeline-and-ner"
+Provides-Extra: utils
+Requires-Dist: pydantic==2.10.6; extra == "utils"
+Requires-Dist: python-stopwatch==1.1.11; extra == "utils"
+Requires-Dist: importlib-resources==6.4.5; extra == "utils"
+Requires-Dist: lxml==5.3.0; extra == "utils"
+Requires-Dist: pyarrow==17.0.0; extra == "utils"
+Requires-Dist: pycryptodomex==3.22.0; extra == "utils"
+Requires-Dist: pydantic-settings-2.8.1; extra == "utils"
+Requires-Dist: python-dotenv-1.1.0; extra == "utils"
+Requires-Dist: python-iso639-2025.2.18; extra == "utils"
+Requires-Dist: python-magic-0.4.27; extra == "utils"
+Requires-Dist: pyzstd==0.16.2; extra == "utils"
+Requires-Dist: databricks-sdk-0.47.0; extra == "utils"
+Requires-Dist: python-tml-1.0.2; extra == "utils"

{ddi_fw-0.0.154.dist-info → ddi_fw-0.0.157.dist-info}/RECORD

@@ -3,10 +3,10 @@ ddi_fw/datasets/core.py,sha256=vRMpUsIHIbOKi-6TuUPNu1Ve3ny3cS9hdsydQxFCNvE,8078
 ddi_fw/datasets/dataset_splitter.py,sha256=8H8uZTAf8N9LUZeSeHOMawtJFJhnDgUUqFcnl7dquBQ,1672
 ddi_fw/datasets/db_utils.py,sha256=OTsa3d-Iic7z3HmzSQK9UigedRbHDxYChJk0s4GfLnw,6191
 ddi_fw/datasets/embedding_generator.py,sha256=jiDKwLaPMaQkloxQkuCrhl-A-2OdvocmkSzjWtUnk4g,2255
-ddi_fw/datasets/feature_vector_generation.py,sha256=gvjpEzkgVV8dp4V8NMMv59u0v-1tNAJ7v83R-keWGoA,4748
+ddi_fw/datasets/feature_vector_generation.py,sha256=Z1A_DOBqDFPqLN4YB-3oYlOQWJK-X6Oes6UFjpzR47Q,4760
 ddi_fw/datasets/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
 ddi_fw/datasets/setup_._py,sha256=khYVJuW5PlOY_i_A16F3UbSZ6s6o_ljw33Byw3C-A8E,1047
-ddi_fw/datasets/ddi_mdl/base.py,sha256=sj4WfwNmcTFznVxlND6FYoyqnL7VUrjn0TG24LDYk3w,9353
+ddi_fw/datasets/ddi_mdl/base.py,sha256=yLxNzDYjLekq1qE6mKh6WkzUU5Xvn3JBEET9Ed-7b_E,9471
 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
@@ -86,7 +86,7 @@ ddi_fw/ner/mmlrestclient.py,sha256=NZta7m2Qm6I_qtVguMZhqtAUjVBmmXn0-TMnsNp0jpg,6
 ddi_fw/ner/ner.py,sha256=FHyyX53Xwpdw8Hec261dyN88yD7Z9LmJua2mIrQLguI,17967
 ddi_fw/pipeline/__init__.py,sha256=tKDM_rW4vPjlYTeOkNgi9PujDzb4e9O3LK1w5wqnebw,212
 ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=JSyuP71b1I1yuk0s2ecCJZTtCED85jBtkpwTUxibJvI,1706
-ddi_fw/pipeline/multi_pipeline.py,sha256=D_BZ3ciHbVGuuB7m7cEmVQHESruh1gqhA-vxCMfNKj0,5407
+ddi_fw/pipeline/multi_pipeline.py,sha256=NfcH4Ze5U-JRiH3lrxEDWj-VPxYQYtp7tq6bLCImBzs,5550
 ddi_fw/pipeline/ner_pipeline.py,sha256=q1aKjb54Ra1HzZ7dARvBw6lB37je9R-POEf2h6QT_nU,6018
 ddi_fw/pipeline/pipeline.py,sha256=70lYsluAnTWDLTlf6rbecffw3Bl34L1_6ALfLUoSvtY,11324
 ddi_fw/utils/__init__.py,sha256=77563ikqAtdzjjgRlLp5OAsJBbpLA1Cao8iecGaVUXQ,354
@@ -97,7 +97,7 @@ ddi_fw/utils/package_helper.py,sha256=erl8_onmhK-41zQoaED2qyDUV9GQxmT9sdoyRp9_q5
 ddi_fw/utils/py7zr_helper.py,sha256=gOqaFIyJvTjUM-btO2x9AQ69jZOS8PoKN0wetYIckJw,4747
 ddi_fw/utils/utils.py,sha256=szwnxMTDRrZoeNRyDuf3aCbtzriwtaRk4mHSH3asLdA,4301
 ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,5567
-ddi_fw-0.0.154.dist-info/METADATA,sha256=u9w1h_7YiMy64J3Ul7uEkz_YQAePYycw9AL12gU7FNI,2082
-ddi_fw-0.0.154.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
-ddi_fw-0.0.154.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.154.dist-info/RECORD,,
+ddi_fw-0.0.157.dist-info/METADATA,sha256=BDNkvrnqN1gxAqUjpmyUqE-YGz86JZpVF0NM_q-oEJk,3612
+ddi_fw-0.0.157.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.157.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.157.dist-info/RECORD,,

{ddi_fw-0.0.154.dist-info → ddi_fw-0.0.157.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.0.2)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ddi_fw-0.0.154.dist-info/METADATA

@@ -1,54 +0,0 @@
-Metadata-Version: 2.4
-Name: ddi_fw
-Version: 0.0.154
-Summary: Do not use :)
-Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
-Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
-Keywords: Machine Learning
-Classifier: Development Status :: 1 - Planning
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Framework :: Pytest
-Classifier: Framework :: tox
-Classifier: Framework :: Sphinx
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-Requires-Dist: pydantic==2.10.6
-Requires-Dist: importlib-resources==6.4.5
-Requires-Dist: python-stopwatch==1.1.11
-Requires-Dist: lxml==5.3.0
-Requires-Dist: matplotlib==3.8.0
-Requires-Dist: mlflow==2.16.1
-Requires-Dist: nltk>=3.8.1
-Requires-Dist: numpy>=1.26.4
-Requires-Dist: pandas>=2.2.0
-Requires-Dist: plotly==5.24.1
-Requires-Dist: rdkit==2023.3.3
-Requires-Dist: scikit-learn==1.5.2
-Requires-Dist: scipy==1.13.1
-Requires-Dist: accelerate>=0.33.0
-Requires-Dist: sentence-transformers<=3.3.1,>=3.0.1
-Requires-Dist: transformers>=4.42.4
-Requires-Dist: stanza==1.9.2
-Requires-Dist: tokenizers>=0.19.1
-Requires-Dist: tqdm>=4.66.6
-Requires-Dist: xmlschema==3.4.2
-Requires-Dist: zipp>=3.20.2
-Requires-Dist: py7zr==0.22.0
-Requires-Dist: openai>=1.52.2
-Requires-Dist: langchain>=0.3.4
-Requires-Dist: chromadb>=0.5.15
-Requires-Dist: langchain_community==0.3.3
-Requires-Dist: datasets==3.0.2
-Requires-Dist: unstructured==0.16.3
-Requires-Dist: tensorflow<2.18.0,>=2.17.0
-Requires-Dist: tf-keras==2.17.0