ddi-fw 0.0.217__py3-none-any.whl → 0.0.219__py3-none-any.whl

ddi_fw/pipeline/multi_pipeline.py

@@ -107,30 +107,57 @@ class MultiPipeline():
     def __create_pipeline(self, config):
         type = config.get("type")
         library = config.get("library")
-
-        use_mlflow = config.get("use_mlflow")
         experiment_name = config.get("experiment_name")
         experiment_description = config.get("experiment_description")
-        experiment_tags = config.get("experiment_tags")
-        tracking_uri = config.get("tracking_uri")
-        artifact_location = config.get("artifact_location")
-        #new
-        default_model = config.get("default_model")
+          
+        # Tracking configuration
+        tracking_config = config.get("tracking_config", {})
+        tracking_library = tracking_config.get("library")
+        use_tracking = tracking_config.get("use_tracking", False)
+        tracking_params = tracking_config.get("params", {}).get(tracking_library, {})
+        
+        # tracking_uri = config.get("tracking_uri")
+        # artifact_location = config.get("artifact_location")
+      
+         # Dataset configuration
+        dataset_config = config.get("dataset", {})
+        dataset_type = get_import(dataset_config.get("dataset_type"))
+        dataset_splitter_type = get_import(dataset_config.get("dataset_splitter_type"))
+        columns = dataset_config.get("columns", [])
+        additional_config = dataset_config.get("additional_config", {})
+        
+         # Vector database configuration
+        vector_database = config.get("vector_databases", {})
+        vector_db_persist_directory = None
+        vector_db_collection_name = None
+        embedding_pooling_strategy = None
+        column_embedding_configs = None
+        if vector_database:
+            vector_db_persist_directory = vector_database.get("vector_db_persist_directory")
+            vector_db_collection_name = vector_database.get("vector_db_collection_name")
+            embedding_pooling_strategy = get_import(vector_database.get("embedding_pooling_strategy"))
+            column_embedding_configs = vector_database.get("column_embedding_configs")
+            
+        # Combination strategy
+        combination_strategy_config = config.get("combination_strategy", {})
+        combination_type = get_import(combination_strategy_config.get("type")) if combination_strategy_config else None
+        kwargs_combination_params = combination_strategy_config.get("params", {})
+        combinations = combination_type(**kwargs_combination_params).generate() if combination_type else []
+
+        # Default model configuration
+        default_model = config.get("default_model", {})
+        default_model_type = get_import(default_model.get("model_type"))
+        default_model_params = default_model.get("params", {})
+        
         multi_modal = config.get("multi_modal")
-        columns = config.get("columns")
-        ner_data_file = config.get("ner_data_file")
-        ner_threshold = config.get("ner_threshold")
-        ner_min_threshold_dict = config.get("ner_min_threshold_dict")
-        ner_max_threshold_dict = config.get("ner_max_threshold_dict")
-        column_embedding_configs = config.get("column_embedding_configs")
-        vector_db_persist_directory = config.get("vector_db_persist_directory")
-        vector_db_collection_name = config.get("vector_db_collection_name")
-        embedding_pooling_strategy = get_import(
-            config.get("embedding_pooling_strategy_type")) if config.get("embedding_pooling_strategy_type") else None
-        # 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"))
+        
+
+
+        #ner move it to related dataset
+        
+        # ner_data_file = config.get("ner_data_file")
+        # ner_threshold = config.get("ner_threshold")
+      
 
         combination_type = None
         kwargs_combination_params=None
@@ -146,21 +173,18 @@ class MultiPipeline():
         if type == "general":
             pipeline = Pipeline(
                 library=library,
-                use_mlflow=use_mlflow,
+                tracking_library=tracking_library,
+                tracking_params=tracking_params,
                 experiment_name=experiment_name,
                 experiment_description=experiment_description,
-                experiment_tags=experiment_tags,
-                artifact_location=artifact_location,
-                tracking_uri=tracking_uri,
                 dataset_type=dataset_type,
+                dataset_additional_config=additional_config,
                 dataset_splitter_type=dataset_splitter_type,
                 columns=columns,
                 column_embedding_configs=column_embedding_configs,
                 vector_db_persist_directory=vector_db_persist_directory,
                 vector_db_collection_name=vector_db_collection_name,
                 embedding_pooling_strategy_type=embedding_pooling_strategy,
-                ner_data_file=ner_data_file,
-                ner_threshold=ner_threshold,
                 combinations=combinations,
                 default_model=default_model,
                 multi_modal= multi_modal)
@@ -172,14 +196,10 @@ class MultiPipeline():
                 experiment_tags=experiment_tags,
                 tracking_uri=tracking_uri,
                 dataset_type=dataset_type,
-                dataset_splitter_type=dataset_splitter_type,
                 umls_code_types = None,
                 text_types = None,
-                min_threshold_dict=ner_min_threshold_dict,
-                max_threshold_dict=ner_max_threshold_dict,
-                columns=columns,
+                columns=['tui', 'cui', 'entities'],
                 ner_data_file=ner_data_file,
-                default_model=default_model,
                 multi_modal= multi_modal
             )
 

ddi_fw/pipeline/{multi_pipeline_v2.py → multi_pipeline_org.py}

@@ -107,57 +107,30 @@ class MultiPipeline():
     def __create_pipeline(self, config):
         type = config.get("type")
         library = config.get("library")
+
+        use_mlflow = config.get("use_mlflow")
         experiment_name = config.get("experiment_name")
         experiment_description = config.get("experiment_description")
         experiment_tags = config.get("experiment_tags")
-        
-        # Tracking configuration
-        tracking_config = config.get("tracking_config", {})
-        tracking_library = tracking_config.get("library")
-        use_tracking = tracking_config.get("use_tracking", False)
-        tracking_params = tracking_config.get("params", {}).get(tracking_library, {})
-        
-        # tracking_uri = config.get("tracking_uri")
-        # artifact_location = config.get("artifact_location")
-      
-         # Dataset configuration
-        dataset_config = config.get("dataset", {})
-        dataset_type = get_import(dataset_config.get("dataset_type"))
-        dataset_splitter_type = get_import(dataset_config.get("dataset_splitter_type"))
-        columns = dataset_config.get("columns", [])
-        additional_config = dataset_config.get("additional_config", {})
-        
-         # Vector database configuration
-        vector_database = config.get("vector_databases", {})
-        vector_db_persist_directory = None
-        vector_db_collection_name = None
-        embedding_pooling_strategy = None
-        if vector_database:
-            vector_db_persist_directory = vector_database.get("vector_db_persist_directory")
-            vector_db_collection_name = vector_database.get("vector_db_collection_name")
-            embedding_pooling_strategy = get_import(vector_database.get("embedding_pooling_strategy"))
-            column_embedding_configs = vector_database.get("column_embedding_configs")
-            
-        # Combination strategy
-        combination_strategy_config = config.get("combination_strategy", {})
-        combination_type = get_import(combination_strategy_config.get("type")) if combination_strategy_config else None
-        kwargs_combination_params = combination_strategy_config.get("params", {})
-        combinations = combination_type(**kwargs_combination_params).generate() if combination_type else []
-
-        # Default model configuration
-        default_model_config = config.get("default_model", {})
-        default_model_type = get_import(default_model_config.get("model_type"))
-        default_model_params = default_model_config.get("params", {})
-        
+        tracking_uri = config.get("tracking_uri")
+        artifact_location = config.get("artifact_location")
+        #new
+        default_model = config.get("default_model")
         multi_modal = config.get("multi_modal")
-        
-
-
-        #ner move it to related dataset
-        
-        # ner_data_file = config.get("ner_data_file")
-        # ner_threshold = config.get("ner_threshold")
-      
+        columns = config.get("columns")
+        ner_data_file = config.get("ner_data_file")
+        ner_threshold = config.get("ner_threshold")
+        ner_min_threshold_dict = config.get("ner_min_threshold_dict")
+        ner_max_threshold_dict = config.get("ner_max_threshold_dict")
+        column_embedding_configs = config.get("column_embedding_configs")
+        vector_db_persist_directory = config.get("vector_db_persist_directory")
+        vector_db_collection_name = config.get("vector_db_collection_name")
+        embedding_pooling_strategy = get_import(
+            config.get("embedding_pooling_strategy_type")) if config.get("embedding_pooling_strategy_type") else None
+        # 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
@@ -199,10 +172,14 @@ class MultiPipeline():
                 experiment_tags=experiment_tags,
                 tracking_uri=tracking_uri,
                 dataset_type=dataset_type,
+                dataset_splitter_type=dataset_splitter_type,
                 umls_code_types = None,
                 text_types = None,
-                columns=['tui', 'cui', 'entities'],
+                min_threshold_dict=ner_min_threshold_dict,
+                max_threshold_dict=ner_max_threshold_dict,
+                columns=columns,
                 ner_data_file=ner_data_file,
+                default_model=default_model,
                 multi_modal= multi_modal
             )
 

ddi_fw/pipeline/pipeline.py

@@ -1,29 +1,24 @@
-from typing import Any, Dict, List, Optional, Type, Union
+from typing import Any, Dict, List, Optional, Type
 from ddi_fw.datasets.dataset_splitter import DatasetSplitter
-import numpy as np
-import pandas as pd
-import chromadb
-from collections import defaultdict
-from chromadb.api.types import IncludeEnum
 
 from pydantic import BaseModel
 from ddi_fw.datasets.core import TextDatasetMixin
-from ddi_fw.ner.ner import CTakesNER
+from ddi_fw.ml.tracking_service import TrackingService
 from ddi_fw.langchain.embeddings import PoolingStrategy
-from ddi_fw.datasets import BaseDataset, DDIMDLDataset
-from ddi_fw.langchain.embeddings import SumPoolingStrategy
-import mlflow
+from ddi_fw.datasets import BaseDataset
 from ddi_fw.ml import MultiModalRunner
+import logging
 
 
 class Pipeline(BaseModel):
+
     library: str = 'tensorflow'
     experiment_name: str
     experiment_description: str
-    experiment_tags: Optional[Dict[str, Any]] = None
-    artifact_location: Optional[str] = None
-    tracking_uri: Optional[str] = None
+    tracking_library: str
+    tracking_params: Optional[Dict[str, Any]] = None
     dataset_type: Type[BaseDataset]
+    dataset_additional_config: Optional[Dict[str, Any]] = None
     dataset_splitter_type: Type[DatasetSplitter] = DatasetSplitter
     columns: Optional[List[str]] = None
     embedding_dict: Optional[Dict[str, Any]] = None
@@ -31,22 +26,24 @@ class Pipeline(BaseModel):
     vector_db_persist_directory: Optional[str] = None
     vector_db_collection_name: Optional[str] = None
     embedding_pooling_strategy_type: Type[PoolingStrategy] | None = None
-    ner_data_file: Optional[str] = None
-    ner_threshold: Optional[dict] = None
     combinations: Optional[List[tuple]] = None
     model: Optional[Any] = None
     default_model:  Optional[Any] = None
     multi_modal:  Optional[Any] = None
-    use_mlflow: bool = False
+    _tracking_service: TrackingService | None = None
     _dataset: BaseDataset | None = None
     _items: List = []
     _train_idx_arr: List | None = []
     _val_idx_arr: List | None = []
 
+    @property
+    def tracking_service(self) -> TrackingService | None:
+        return self._tracking_service
+
     @property
     def dataset(self) -> BaseDataset | None:
         return self._dataset
-    
+
     @property
     def items(self) -> List:
         return self._items
@@ -62,56 +59,11 @@ class Pipeline(BaseModel):
     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.
-
-    #     Args:
-    #     - vector_db_persist_directory (str): The path to the directory where the Chroma vector database is stored.
-    #     - vector_db_collection_name (str): The name of the collection to query.
-    #     - embedding_dict (dict): The existing dictionary to update with embeddings.
-
-    #     """
-    #     if vector_db_persist_directory:
-    #         # Initialize the Chroma client and get the collection
-    #         vector_db = chromadb.PersistentClient(
-    #             path=vector_db_persist_directory)
-    #         collection = vector_db.get_collection(vector_db_collection_name)
-    #         include = [IncludeEnum.embeddings, IncludeEnum.metadatas]
-    #         dictionary: chromadb.GetResult
-    #         # Fetch the embeddings and metadata
-    #         if column == None:
-    #             dictionary = collection.get(
-    #                 include=include
-    #                 # include=['embeddings', 'metadatas']
-    #             )
-    #             print(
-    #                 f"Embeddings are calculated from {vector_db_collection_name}")
-    #         else:
-    #             dictionary = collection.get(
-    #                 include=include,
-    #                 # include=['embeddings', 'metadatas'],
-    #                 where={
-    #                     "type": {"$eq": f"{column}"}})
-    #             print(
-    #                 f"Embeddings of {column} are calculated from {vector_db_collection_name}")
-
-    #         # Populate the embedding dictionary with embeddings from the vector database
-    #         metadatas = dictionary["metadatas"]
-    #         embeddings = dictionary["embeddings"]
-    #         if metadatas is None or embeddings is None:
-    #             raise ValueError(
-    #                 "The collection does not contain embeddings or metadatas.")
-    #         for metadata, embedding in zip(metadatas, embeddings):
-    #             embedding_dict[metadata["type"]
-    #                            ][metadata["id"]].append(embedding)
-
-    #     else:
-    #         raise ValueError(
-    #             "Persistent directory for the vector DB is not specified.")
-
-    #TODO embedding'leri set etme kimin görevi
+    # TODO embedding'leri set etme kimin görevi
     def build(self):
+        self._tracking_service = TrackingService(self.experiment_name,
+                                                 backend=self.tracking_library, tracking_params=self.tracking_params)
+
         if self.embedding_pooling_strategy_type is not None and not isinstance(self.embedding_pooling_strategy_type, type):
             raise TypeError(
                 "self.embedding_pooling_strategy_type must be a class, not an instance")
@@ -120,29 +72,29 @@ class Pipeline(BaseModel):
                 "self.dataset_type must be a class, not an instance")
 
         # 'enzyme','target','pathway','smile','all_text','indication', 'description','mechanism_of_action','pharmacodynamics', 'tui', 'cui', 'entities'
-        kwargs = {"columns": self.columns}
-        if self.ner_threshold:
-            for k, v in self.ner_threshold.items():
-                kwargs[k] = v
-        
+        kwargs = {"columns": self.columns,
+                  "additional_config": self.dataset_additional_config}
+        # DDIMDL Dataset'e aktar
+        # if self.ner_threshold:
+        #     for k, v in self.ner_threshold.items():
+        #         kwargs[k] = v
 
-        ner_df = CTakesNER(df=None).load(
-            filename=self.ner_data_file) if self.ner_data_file else None
+        # ner_df = CTakesNER(df=None).load(
+        #     filename=self.ner_data_file) if self.ner_data_file else None
 
         dataset_splitter = self.dataset_splitter_type()
         pooling_strategy = self.embedding_pooling_strategy_type(
-            ) if self.embedding_pooling_strategy_type else None   
+        ) if self.embedding_pooling_strategy_type else None
         if issubclass(self.dataset_type, TextDatasetMixin):
-            kwargs["ner_df"] = ner_df
             dataset = self.dataset_type(
-                embedding_dict=self.embedding_dict, 
+                embedding_dict=self.embedding_dict,
                 pooling_strategy=pooling_strategy,
                 column_embedding_configs=self.column_embedding_configs,
                 vector_db_persist_directory=self.vector_db_persist_directory,
                 vector_db_collection_name=self.vector_db_collection_name,
                 dataset_splitter_type=self.dataset_splitter_type,
                 **kwargs)
-            
+
         elif self.dataset_type == BaseDataset:
             dataset = self.dataset_type(
                 dataset_splitter_type=self.dataset_splitter_type,
@@ -151,11 +103,11 @@ class Pipeline(BaseModel):
             dataset = self.dataset_type(**kwargs)
 
         # 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
-        
+
         dataframe = dataset.dataframe
 
         # Check if any of the arrays are None or empty
@@ -180,25 +132,15 @@ class Pipeline(BaseModel):
         return self
 
     def run(self):
-        if self.use_mlflow:
-            if self.tracking_uri is None:
-                raise ValueError("Tracking uri should be specified")
-            mlflow.set_tracking_uri(self.tracking_uri)
-
-            if mlflow.get_experiment_by_name(self.experiment_name) == None:
-                mlflow.create_experiment(
-                    self.experiment_name, self.artifact_location)
-                if self.experiment_tags is not None:
-                    mlflow.set_experiment_tags(self.experiment_tags)
-            mlflow.set_experiment(self.experiment_name)
+        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 , use_mlflow=self.use_mlflow)
-        # multi_modal_runner = MultiModalRunner(
-        #     library=self.library, model_func=model_func, batch_size=batch_size,  epochs=epochs)
-        # multi_modal = TFMultiModal(
-        #     model_func=model_func, batch_size=batch_size,  epochs=epochs)  # 100
+            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 []

ddi_fw/utils/utils.py

@@ -2,7 +2,7 @@ import gzip
 import json
 import os
 from datetime import datetime, timezone
-from matplotlib import pyplot as plt
+# from matplotlib import pyplot as plt
 import shutil
 
 def create_folder_if_not_exists(path):
@@ -65,53 +65,53 @@ def clear_directory(directory_path):
         print(f"The directory does not exist: {directory_path}")
 
 
-if __name__ == "__main__":
-    # json_file = f'C:\\Users\\kivanc\\Downloads\\metrics.json'
-    # file_data = open(json_file, "r", 1).read()
-    # a = json.loads(file_data)  # store in json structure
-    # # a = {'key1':1, 'key2':2}
-    # compressed = compress_data(a)
-    # with gzip.open('deneme.gzip', 'wb') as f:
-    #     f.write(compressed)
-
-    # with gzip.open('deneme.gzip', 'r') as fin:        # 4. gzip
-    #     json_bytes = fin.read()                      # 3. bytes (i.e. UTF-8)
-    # json_bytes = gzip.decompress(json_bytes)
-    # json_str = json_bytes.decode('UTF-8')            # 2. string (i.e. JSON)
-    # data = json.loads(json_str)
-    # print(data)
-
-    gzip_file = f'C:\\Users\\kivanc\\Downloads\\metrics (2).gzip'
-    stored_file =  f'C:\\Users\\kivanc\\Downloads\\save.png'
-    metrics = decompress(gzip_file)
-    # print(metrics)
-
-    # Plot Precision-Recall curves for each class and micro-average
-    fig = plt.figure()
-    plt.step(metrics['recall']['micro_event'], metrics['precision']['micro_event'],
-             color='b', alpha=0.2, where='post')
-    plt.fill_between(
-        metrics['recall']["micro_event"], metrics['precision']["micro_event"], step='post', alpha=0.2, color='b')
-
-    # for i in range(65):
-    #     plt.step( metrics['recall'][str(i)],  metrics['precision'][str(i)], where='post',
-    #              label='Class {0} (AUC={1:0.2f})'.format(i, metrics['roc_aupr'][str(i)]))
-
-    plt.xlabel('Recall')
-    plt.ylabel('Precision')
-    plt.ylim([0.0, 1.05])
-    plt.xlim([0.0, 1.0])
-    plt.title(
-        'Micro-average Precision-Recall curve: AUC={0:0.2f}'.format(metrics['roc_aupr']["micro"]))
-    plt.legend(loc='best')
-    plt.savefig(stored_file)
-    # plt.show()
-
-    import plotly.express as px
-    import pandas as pd
-    df = pd.DataFrame(dict(
-    r=[1, 5, 2, 2, 3],
-    theta=['processing cost','mechanical properties','chemical stability',
-            'thermal stability', 'device integration']))
-    fig = px.line_polar(df, r='r', theta='theta', line_close=True)
-    fig.show()
+# if __name__ == "__main__":
+#     # json_file = f'C:\\Users\\kivanc\\Downloads\\metrics.json'
+#     # file_data = open(json_file, "r", 1).read()
+#     # a = json.loads(file_data)  # store in json structure
+#     # # a = {'key1':1, 'key2':2}
+#     # compressed = compress_data(a)
+#     # with gzip.open('deneme.gzip', 'wb') as f:
+#     #     f.write(compressed)
+
+#     # with gzip.open('deneme.gzip', 'r') as fin:        # 4. gzip
+#     #     json_bytes = fin.read()                      # 3. bytes (i.e. UTF-8)
+#     # json_bytes = gzip.decompress(json_bytes)
+#     # json_str = json_bytes.decode('UTF-8')            # 2. string (i.e. JSON)
+#     # data = json.loads(json_str)
+#     # print(data)
+
+#     gzip_file = f'C:\\Users\\kivanc\\Downloads\\metrics (2).gzip'
+#     stored_file =  f'C:\\Users\\kivanc\\Downloads\\save.png'
+#     metrics = decompress(gzip_file)
+#     # print(metrics)
+
+#     # Plot Precision-Recall curves for each class and micro-average
+#     fig = plt.figure()
+#     plt.step(metrics['recall']['micro_event'], metrics['precision']['micro_event'],
+#              color='b', alpha=0.2, where='post')
+#     plt.fill_between(
+#         metrics['recall']["micro_event"], metrics['precision']["micro_event"], step='post', alpha=0.2, color='b')
+
+#     # for i in range(65):
+#     #     plt.step( metrics['recall'][str(i)],  metrics['precision'][str(i)], where='post',
+#     #              label='Class {0} (AUC={1:0.2f})'.format(i, metrics['roc_aupr'][str(i)]))
+
+#     plt.xlabel('Recall')
+#     plt.ylabel('Precision')
+#     plt.ylim([0.0, 1.05])
+#     plt.xlim([0.0, 1.0])
+#     plt.title(
+#         'Micro-average Precision-Recall curve: AUC={0:0.2f}'.format(metrics['roc_aupr']["micro"]))
+#     plt.legend(loc='best')
+#     plt.savefig(stored_file)
+#     # plt.show()
+
+#     import plotly.express as px
+#     import pandas as pd
+#     df = pd.DataFrame(dict(
+#     r=[1, 5, 2, 2, 3],
+#     theta=['processing cost','mechanical properties','chemical stability',
+#             'thermal stability', 'device integration']))
+#     fig = px.line_polar(df, r='r', theta='theta', line_close=True)
+#     fig.show()

{ddi_fw-0.0.217.dist-info → ddi_fw-0.0.219.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.217
+Version: 0.0.219
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.217.dist-info → ddi_fw-0.0.219.dist-info}/RECORD

@@ -1,9 +1,9 @@
 ddi_fw/datasets/__init__.py,sha256=_I3iDHARwzmg7_EL5XKtB_TgG1yAkLSOVTujLL9Wz9Q,280
-ddi_fw/datasets/core.py,sha256=WuNPDxLAEtw7k15X38mwbOoCslXQ1hHQWhiIIwzrpRA,16880
+ddi_fw/datasets/core.py,sha256=12S7gJnWlxBvUwhQ5HoBy1ILwTW1xm9r1v6P9pPgu_Y,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=Vvyzxd2BnFK9Bn2mn-3aS5ZczlPElQ0-TKMAqgkyJiI,10483
+ddi_fw/datasets/ddi_mdl/base.py,sha256=_45xa9oo5mBY5gooIy3hxlHBVJcx4NFRjzMCBIMllvA,11247
 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=ILdvu7pBMazt-FxRWzIaqO2PmbkyooEOT3U9vSoV3PY,6398
+ddi_fw/datasets/mdf_sa_ddi/base.py,sha256=CRhcbADi_CkRyXY2Eq7fYXH-ywmDhrTTB67JLKbk8F4,15907
 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
@@ -72,21 +72,22 @@ ddi_fw/langchain/__init__.py,sha256=zS0CQrakWEP19biSRewFJGcBT8WBZq4899HrEKiMqUY,
 ddi_fw/langchain/embeddings.py,sha256=eEWy4okcjdhUJHi4N48Wd8XauPXyeaQVLUdNWEvtEcY,6754
 ddi_fw/langchain/sentence_splitter.py,sha256=h_bYElx4Ud1mwDNJfL7mUwvgadwKX3GKlSzu5L2PXzg,280
 ddi_fw/langchain/storage.py,sha256=OizKyWm74Js7T6Q9kez-ulUoBGzIMFo4R46h4kjUyIM,11200
-ddi_fw/ml/__init__.py,sha256=tIxiW0g6q1VsmDYVXR_ovvHQR3SCir8g2bKxx_CrS7s,221
+ddi_fw/ml/__init__.py,sha256=FteYEawCkVQOaK-cTv2VrHZ2ZnfeFr31BD6VucO7_DQ,268
 ddi_fw/ml/evaluation_helper.py,sha256=2-7CLSgGTqLEk4HkgCVIOt-GxfLAn6SBozJghAtHb5M,11581
-ddi_fw/ml/ml_helper.py,sha256=6BO1ikCHmlYK9TPDN7Atov0BuTtoyLg06NoSGl3RYGA,7716
-ddi_fw/ml/model_wrapper.py,sha256=kabPXuo7S8tGkp9a00V04n4rXDmv7dD8wYGMjotISRc,1050
+ddi_fw/ml/ml_helper.py,sha256=RbFUz4kLkqv6WUXXscDFtYBMWcmv7uWOf8YIR5DBfqA,7701
+ddi_fw/ml/model_wrapper.py,sha256=38uBdHI4H_sjDKPWuhGXovUy_L1tpSNm5tEqCtwmlpY,973
 ddi_fw/ml/pytorch_wrapper.py,sha256=pe6UsjP2XeTgLxDnIUiodoyhJTGCxV27wD4Cjxysu2Q,8553
-ddi_fw/ml/tensorflow_wrapper.py,sha256=Vw6M2rHDHV90jzfCr0XWpUqYVl4vmZeKsS7FUb3VkH4,12980
+ddi_fw/ml/tensorflow_wrapper.py,sha256=Zdf1FmJ9488pFBG4xBLkC5GzyLv9tn5OrdFzHGHPmCM,16172
+ddi_fw/ml/tracking_service.py,sha256=eHWFI3lyQX_xM16CRekgITwldHj2RBMYl5XG8lD8Zks,7508
 ddi_fw/ner/__init__.py,sha256=JwhGXrepomxPSsGsg2b_xPRC72AjvxOIn2CW5Mvscn0,26
 ddi_fw/ner/mmlrestclient.py,sha256=NZta7m2Qm6I_qtVguMZhqtAUjVBmmXn0-TMnsNp0jpg,6859
 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=AbErwu05-3YIPnCcXRsj-jxPJG8HG2H7cMZlGjzaYa8,9037
-ddi_fw/pipeline/multi_pipeline_v2.py,sha256=7IGtaGFhgJqW29a6nDheUrVtn_7_xvWFdD6GC--sehM,10003
+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=YhUBVLC29ZD2tmVd0e8X1FVBLhSKECZL2OP57oEW6HE,9171
+ddi_fw/pipeline/pipeline.py,sha256=IxqvIy2thLQyO-0Qon1JAKT3k8mLk5OpTGE25ZTTsOQ,6133
 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
@@ -95,12 +96,12 @@ ddi_fw/utils/kaggle.py,sha256=wKRJ18KpQ6P-CubpZklEgsDtyFpR9RUL1_HyyF6ttEE,2425
 ddi_fw/utils/numpy_utils.py,sha256=gd1WNq5NpWD2MBEMTtFuS5I0h8B6FAUNcq6BVOlxdhY,797
 ddi_fw/utils/package_helper.py,sha256=erl8_onmhK-41zQoaED2qyDUV9GQxmT9sdoyRp9_q5I,1056
 ddi_fw/utils/py7zr_helper.py,sha256=gOqaFIyJvTjUM-btO2x9AQ69jZOS8PoKN0wetYIckJw,4747
-ddi_fw/utils/utils.py,sha256=szwnxMTDRrZoeNRyDuf3aCbtzriwtaRk4mHSH3asLdA,4301
+ddi_fw/utils/utils.py,sha256=PY-zDawREKoXQfzX7lVkxBLVFQPkfvr9385kHCjaNXo,4391
 ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,5567
 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-0.0.217.dist-info/METADATA,sha256=G1lQHwAd3_yxL53MryeC1s0Lq_daknO2yzt33ZGnICw,2631
-ddi_fw-0.0.217.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.217.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.217.dist-info/RECORD,,
+ddi_fw-0.0.219.dist-info/METADATA,sha256=kPgF9a4rw8e9GoqXTQ1_fwb3i8L1RLBWUClZEcfeQnM,2631
+ddi_fw-0.0.219.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.219.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.219.dist-info/RECORD,,