ddi-fw 0.0.226__py3-none-any.whl → 0.0.228__py3-none-any.whl

ddi_fw/datasets/core.py

@@ -4,7 +4,7 @@ import glob
 import logging
 from typing import Any, Dict, List, Optional, Type
 import chromadb
-from chromadb.api.types import IncludeEnum
+# from chromadb.api.types import IncludeEnum
 import numpy as np
 import pandas as pd
 from pydantic import BaseModel, Field, computed_field
@@ -307,7 +307,8 @@ class TextDatasetMixin(BaseModel):
             vector_db = chromadb.PersistentClient(
                 path=vector_db_persist_directory)
             collection = vector_db.get_collection(vector_db_collection_name)
-            include = [IncludeEnum.embeddings, IncludeEnum.metadatas]
+            # include = [IncludeEnum.embeddings, IncludeEnum.metadatas]
+            include: chromadb.Include = ["embeddings","metadatas"]
             dictionary: chromadb.GetResult
             # Fetch the embeddings and metadata
             if column == None:

ddi_fw/pipeline/multi_pipeline.py

@@ -191,15 +191,15 @@ class MultiPipeline():
         elif type== "ner_search":
             pipeline = NerParameterSearch(
                 library=library,
+                tracking_library=tracking_library,
+                tracking_params=tracking_params,
                 experiment_name=experiment_name,
                 experiment_description=experiment_description,
-                experiment_tags=experiment_tags,
-                tracking_uri=tracking_uri,
                 dataset_type=dataset_type,
+                dataset_additional_config=additional_config,
                 umls_code_types = None,
                 text_types = None,
-                columns=['tui', 'cui', 'entities'],
-                ner_data_file=ner_data_file,
+                columns=columns,
                 multi_modal= multi_modal
             )
 

ddi_fw/pipeline/ner_pipeline.py

@@ -10,19 +10,21 @@ from ddi_fw.vectorization.idf_helper import IDF
 from ddi_fw.ner.ner import CTakesNER
 from ddi_fw.ml.ml_helper import MultiModalRunner
 from ddi_fw.utils.enums import DrugBankTextDataTypes, UMLSCodeTypes
+import logging
 
-
+              
 class NerParameterSearch(BaseModel):
     library: str
     default_model:  Optional[Any] = None
     multi_modal:  Optional[Any] = None
     experiment_name: str
     experiment_description: Optional[str] = None
-    experiment_tags: Optional[Dict[str, Any]] = None
-    tracking_uri: str
+    tracking_library: str
+    tracking_params: Optional[Dict[str, Any]] = None
+    dataset_type: Type[BaseDataset]
+    dataset_additional_config: Optional[Dict[str, Any]] = None
     dataset_type: Type[BaseDataset]
     dataset_splitter_type: Type[DatasetSplitter] = DatasetSplitter
-    ner_data_file: Optional[str] = None
     columns: List[str] = Field(default_factory=list)
     umls_code_types: Optional[List[UMLSCodeTypes]] = None
     text_types: Optional[List[DrugBankTextDataTypes]] = None
@@ -33,7 +35,7 @@ class NerParameterSearch(BaseModel):
     # Internal fields (not part of the input)
     datasets: Dict[str, Any] = Field(default_factory=dict, exclude=True)
     items: List[Any] = Field(default_factory=list, exclude=True)
-    ner_df: Optional[Any] = Field(default=None, exclude=True)
+    # ner_df: Optional[Any] = Field(default=None, exclude=True)
     train_idx_arr: Optional[List[np.ndarray]] = Field(default=None, exclude=True)
     val_idx_arr: Optional[List[np.ndarray]] = Field(default=None, exclude=True)
     y_test_label: Optional[np.ndarray] = Field(default=None, exclude=True)
@@ -64,16 +66,24 @@ class NerParameterSearch(BaseModel):
             raise TypeError("self.dataset_type must be a class, not an instance")
 
         # Load NER data
-        if self.ner_data_file:
-            self.ner_df = CTakesNER(df=None).load(filename=self.ner_data_file)
+        ner_data_file = (
+                self.dataset_additional_config.get("ner", {}).get("data_file")
+                if self.dataset_additional_config else None
+            )        
+        
+        if ner_data_file:
+            ner_df = CTakesNER(df=None).load(filename=ner_data_file)
 
         # Initialize thresholds if not provided
         if not self.min_threshold_dict or not self.max_threshold_dict:
-            idf = IDF(self.ner_df, self.columns)
+            idf = IDF(ner_df, self.columns)
             idf.calculate()
             df = idf.to_dataframe()
             self.min_threshold_dict = {key: np.floor(df.describe()[key]["min"]) for key in df.describe().keys()}
             self.max_threshold_dict = {key: np.ceil(df.describe()[key]["max"]) for key in df.describe().keys()}
+    
+        print("Minimum thresholds:", self.min_threshold_dict)
+        print("Maximum thresholds:", self.max_threshold_dict)
 
         # Generate datasets and items
         for column in self.columns:
@@ -85,6 +95,8 @@ class NerParameterSearch(BaseModel):
                 "cui_threshold": 0,
                 "entities_threshold": 0,
             }
+            if self.dataset_additional_config:
+                kwargs["additional_config"]= self.dataset_additional_config
 
             for threshold in np.arange(min_threshold, max_threshold, self.increase_step):
                 if column.startswith("tui"):
@@ -93,10 +105,11 @@ class NerParameterSearch(BaseModel):
                     kwargs["cui_threshold"] = threshold
                 if column.startswith("entities"):
                     kwargs["entities_threshold"] = threshold
-
+                
+                print(f"Loading dataset for column: {column} with threshold: {threshold}")
+                # Create a new dataset instance for each threshold
                 dataset = self.dataset_type(
                     columns=[column],
-                    ner_df=self.ner_df,
                     dataset_splitter_type=self.dataset_splitter_type,
                     **kwargs,
                 )
@@ -113,22 +126,38 @@ class NerParameterSearch(BaseModel):
         self.train_idx_arr = dataset.train_idx_arr
         self.val_idx_arr = dataset.val_idx_arr
 
-    def run(self):
-        """Run the parameter search."""
-        mlflow.set_tracking_uri(self.tracking_uri)
-
-        if mlflow.get_experiment_by_name(self.experiment_name) is None:
-            mlflow.create_experiment(self.experiment_name)
-        if self.experiment_tags:
-            mlflow.set_experiment_tags(self.experiment_tags)
-        mlflow.set_experiment(self.experiment_name)
-
-        multi_modal_runner = MultiModalRunner(
-            library=self.library,
-            multi_modal=self.multi_modal,
-            default_model=self.default_model,
-            use_mlflow=True,
-        )
-        multi_modal_runner.set_data(self.items, self.train_idx_arr, self.val_idx_arr, self.y_test_label)
-        result = multi_modal_runner.predict()
-        return result
+    # def run(self):
+    #     """Run the parameter search."""
+    #     mlflow.set_tracking_uri(self.tracking_uri)
+
+    #     if mlflow.get_experiment_by_name(self.experiment_name) is None:
+    #         mlflow.create_experiment(self.experiment_name)
+    #     if self.experiment_tags:
+    #         mlflow.set_experiment_tags(self.experiment_tags)
+    #     mlflow.set_experiment(self.experiment_name)
+
+    #     multi_modal_runner = MultiModalRunner(
+    #         library=self.library,
+    #         multi_modal=self.multi_modal,
+    #         default_model=self.default_model,
+    #         use_mlflow=True,
+    #     )
+    #     multi_modal_runner.set_data(self.items, self.train_idx_arr, self.val_idx_arr, self.y_test_label)
+    #     result = multi_modal_runner.predict()
+    #     return result
+    
+        def run(self):
+            if self._tracking_service is None:
+                logging.warning("Tracking service is not initialized.")
+            else:
+                self._tracking_service.setup()
+
+            y_test_label = self.items[0][4]
+            multi_modal_runner = MultiModalRunner(
+                library=self.library, multi_modal=self.multi_modal, default_model=self.default_model, tracking_service=self._tracking_service)
+
+            multi_modal_runner.set_data(
+                self.items, self.train_idx_arr, self.val_idx_arr, y_test_label)
+            combinations = self.combinations if self.combinations is not None else []
+            result = multi_modal_runner.predict(combinations)
+            return result

{ddi_fw-0.0.226.dist-info → ddi_fw-0.0.228.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.226
+Version: 0.0.228
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
@@ -33,7 +33,7 @@ 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>0.3.16; extra == "llm"
-Requires-Dist: chromadb<1.0.0,>=0.6.0; extra == "llm"
+Requires-Dist: chromadb<=1.0.4,>=0.7.0; extra == "llm"
 Requires-Dist: nltk>=3.8.1; extra == "llm"
 Provides-Extra: ml
 Requires-Dist: scikit-learn<=1.6.1,>=1.5.2; extra == "ml"

{ddi_fw-0.0.226.dist-info → ddi_fw-0.0.228.dist-info}/RECORD

@@ -1,5 +1,5 @@
 ddi_fw/datasets/__init__.py,sha256=_I3iDHARwzmg7_EL5XKtB_TgG1yAkLSOVTujLL9Wz9Q,280
-ddi_fw/datasets/core.py,sha256=PX6MX4hmeYxIWAKAx7NnJr1fpzR11xA8g8vAjYcQNN8,16936
+ddi_fw/datasets/core.py,sha256=p-e3wP5C_SCh0fMXioUHUXKvLVtyCrsQCFvKRnH4fjs,17008
 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
@@ -84,9 +84,9 @@ 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=npJUXYT31fxD6kpJKSeixjbH5jNfPUwIVG7lRdBszRg,9852
+ddi_fw/pipeline/multi_pipeline.py,sha256=EjJnA3Vzd-WeEvUBaA2LDOy_iQ5-2eW2VhtxvvxDPfQ,9857
 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/ner_pipeline.py,sha256=AVp18Og4AozZvXwXcm94QNpUczdkawCaGAwoJoUYBp4,7246
 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
@@ -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-0.0.226.dist-info/METADATA,sha256=yGP96z5uVKjSep-oOmbxV4FLhJb21yEam1gOVB_HGk0,2631
-ddi_fw-0.0.226.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.226.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.226.dist-info/RECORD,,
+ddi_fw-0.0.228.dist-info/METADATA,sha256=f0FUmtvqF6hIEG0HfiB2Epcy9prPHxa0i-OxIw5RNb8,2632
+ddi_fw-0.0.228.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
+ddi_fw-0.0.228.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.228.dist-info/RECORD,,

{ddi_fw-0.0.226.dist-info → ddi_fw-0.0.228.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (78.1.1)
 Root-Is-Purelib: true
 Tag: py3-none-any