ddi-fw 0.0.209__py3-none-any.whl → 0.0.211__py3-none-any.whl

ddi_fw/pipeline/multi_pipeline.py

@@ -1,4 +1,5 @@
 import json
+from typing import Optional
 from ddi_fw.pipeline.pipeline import Pipeline
 from ddi_fw.pipeline.ner_pipeline import NerParameterSearch
 import importlib
@@ -41,11 +42,68 @@ def get_import(full_path_of_import):
 
 
 class MultiPipeline():
-    def __init__(self, experiments_config_file):
-        self.experiments_config = load_config(experiments_config_file)
+    # def __init__(self, experiments_config_file, experiments_config):
+    #     if experiments_config_file is None and experiments_config is None:
+    #         raise ValueError("Either experiments_config_file or experiments_config must be provided.")
+    #     if experiments_config_file is not None and experiments_config is not None:  
+    #         raise ValueError("Only one of experiments_config_file or experiments_config should be provided.")
+    #     if experiments_config_file is not None:
+    #         self.experiments_config = load_config(experiments_config_file)
+    #     else:
+    #         self.experiments_config = experiments_config
+    #     self.items = []
+    #     self.pipeline_resuts = dict()
+    
+    def __init__(self, experiments_config_file: Optional[str] = None, experiments_config: Optional[dict] = None):
+        """
+        Initialize the MultiPipeline.
+
+        Args:
+            experiments_config_file (str, optional): Path to the experiments configuration file.
+            experiments_config (dict, optional): Dictionary containing the experiments configuration.
+
+        Raises:
+            ValueError: If neither or both of the parameters are provided.
+        """
+        self.experiments_config = self._validate_and_load_config(experiments_config_file, experiments_config)
         self.items = []
+        # self.pipeline_results = {}
         self.pipeline_resuts = dict()
 
+    def _validate_and_load_config(self, experiments_config_file: Optional[str], experiments_config: Optional[dict]) -> dict:
+        """
+        Validate and load the experiments configuration.
+
+        Args:
+            experiments_config_file (str, optional): Path to the experiments configuration file.
+            experiments_config (dict, optional): Dictionary containing the experiments configuration.
+
+        Returns:
+            dict: The loaded experiments configuration.
+
+        Raises:
+            ValueError: If neither or both of the parameters are provided.
+        """
+        if experiments_config_file is None and experiments_config is None:
+            raise ValueError("Either 'experiments_config_file' or 'experiments_config' must be provided.")
+        if experiments_config_file is not None and experiments_config is not None:
+            raise ValueError("Only one of 'experiments_config_file' or 'experiments_config' should be provided.")
+
+        if experiments_config_file is not None:
+            try:
+               config = load_config(experiments_config_file)
+            except FileNotFoundError:
+                raise FileNotFoundError(f"Configuration file '{experiments_config_file}' not found.")
+        else:
+            config = experiments_config
+        if config is None:
+            raise ValueError("Configuration cannot be None.")
+        if not isinstance(config, dict):
+            raise ValueError("Configuration must be a dictionary.")
+        # if "experiments" not in config: 
+        #     raise ValueError("Configuration must contain 'experiments' key.")
+        return config
+
     def __create_pipeline(self, config):
         type = config.get("type")
         library = config.get("library")
@@ -57,7 +115,7 @@ class MultiPipeline():
         tracking_uri = config.get("tracking_uri")
         artifact_location = config.get("artifact_location")
         #new
-        default_model = config.get("default_model"),
+        default_model = config.get("default_model")
         multi_modal = config.get("multi_modal")
         columns = config.get("columns")
         ner_data_file = config.get("ner_data_file")

ddi_fw/pipeline/pipeline.py

@@ -33,18 +33,18 @@ class Pipeline(BaseModel):
     embedding_pooling_strategy_type: Type[PoolingStrategy] | None = None
     ner_data_file: Optional[str] = None
     ner_threshold: Optional[dict] = None
-    combinations: Optional[List[str]] = None
+    combinations: Optional[List[tuple]] = None
     model: Optional[Any] = None
     default_model:  Optional[Any] = None
     multi_modal:  Optional[Any] = None
     use_mlflow: bool = False
-    _dataset: BaseDataset = []
+    _dataset: BaseDataset | None = None
     _items: List = []
     _train_idx_arr: List | None = []
     _val_idx_arr: List | None = []
 
     @property
-    def dataset(self) -> BaseDataset:
+    def dataset(self) -> BaseDataset | None:
         return self._dataset
     
     @property
@@ -126,14 +126,14 @@ class Pipeline(BaseModel):
                 kwargs[k] = v
         
 
-        # self.ner_df = CTakesNER(df=None).load(
-        #     filename=self.ner_data_file) if self.ner_data_file else None
+        self.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 issubclass(self.dataset_type, TextDatasetMixin):
-
+            kwargs["ner_df"] = self.ner_df
             dataset = self.dataset_type(
                 embedding_dict=self.embedding_dict, 
                 pooling_strategy=pooling_strategy,

{ddi_fw-0.0.209.dist-info → ddi_fw-0.0.211.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.209
+Version: 0.0.211
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.209.dist-info → ddi_fw-0.0.211.dist-info}/RECORD

@@ -83,9 +83,9 @@ 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=L0Apy2Z909GnR8KMX_q7-kluZmIG3CT0yfMuL22poaQ,5737
+ddi_fw/pipeline/multi_pipeline.py,sha256=SZFJ9QSPD_3mcG9NHZOtMqKyNvyWrodsdsLryMyDdUw,8686
 ddi_fw/pipeline/ner_pipeline.py,sha256=Bp6BA6nozfWFaMHH6jKlzesnCGO6qiMkzdGy_ed6nh0,5947
-ddi_fw/pipeline/pipeline.py,sha256=s6fYtgAyWcap4oC6bAKZATju8BnasRtLopnM2Blt2Fo,9125
+ddi_fw/pipeline/pipeline.py,sha256=_sRzMyxGSJo4GhM8ZJhxwvMvKsqFa1WSSECpx4SgdDw,9181
 ddi_fw/utils/__init__.py,sha256=HC32XkYQTYH_9vt0eX6tqQngEFG-R70hGrYkT-BcHCk,519
 ddi_fw/utils/categorical_data_encoding_checker.py,sha256=gzb_vUDBrCMUhBxY1fBYTe8hmK72p0_uw3DTga8cqP8,1580
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
@@ -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-0.0.209.dist-info/METADATA,sha256=l7kgYVXWsiIRjTlkKiSTiiX0v3STNUMckbwWRDls6ig,2631
-ddi_fw-0.0.209.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.209.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.209.dist-info/RECORD,,
+ddi_fw-0.0.211.dist-info/METADATA,sha256=HO-fzXxm5AGnMMB8S0hnkOtH18bvaanoIAJgLOCP8gk,2631
+ddi_fw-0.0.211.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.211.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.211.dist-info/RECORD,,