ddi-fw 0.0.153__tar.gz → 0.0.154__tar.gz

{ddi_fw-0.0.153 → ddi_fw-0.0.154}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.153
+Version: 0.0.154
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.153 → ddi_fw-0.0.154}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.153"
+version = "0.0.154"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.153 → ddi_fw-0.0.154}/src/ddi_fw/datasets/dataset_splitter.py

@@ -14,11 +14,11 @@ class DatasetSplitter(BaseModel):
     class Config:
         arbitrary_types_allowed = True
 
-    def split(self, X: pd.DataFrame, y: pd.Series)-> Tuple[
-    pd.DataFrame, pd.DataFrame, pd.Series, pd.Series, pd.Index, pd.Index, List[np.ndarray], List[np.ndarray]]:
+    def split(self, X: pd.DataFrame, y: pd.Series) -> Tuple[
+            pd.DataFrame, pd.DataFrame, pd.Series, pd.Series, pd.Index, pd.Index, List[np.ndarray], List[np.ndarray]]:
         print(
             f"Splitting dataset into {self.fold_size} folds with shuffle={self.shuffle}...")
-        #TODO check it
+        # TODO check it
         if len(y.shape) == 1:
             y = pd.Series(np.expand_dims(y.to_numpy(), axis=1).flatten())
         stacked = np.vstack(tuple(y.to_numpy()))

{ddi_fw-0.0.153 → ddi_fw-0.0.154}/src/ddi_fw/pipeline/pipeline.py

@@ -1,4 +1,5 @@
 from typing import Any, Dict, List, Optional, Type, Union
+from ddi_fw.datasets.dataset_splitter import DatasetSplitter
 import numpy as np
 import pandas as pd
 import chromadb
@@ -23,6 +24,7 @@ class Pipeline(BaseModel):
     artifact_location: Optional[str] = None
     tracking_uri: Optional[str] = None
     dataset_type: Type[BaseDataset]
+    dataset_splitter_type: Type[DatasetSplitter] = DatasetSplitter
     columns: Optional[List[str]] = None
     embedding_dict: Optional[Dict[str, Any]] = None
     column_embedding_configs: Optional[Dict] = None
@@ -181,6 +183,8 @@ class Pipeline(BaseModel):
         # 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()
+        
         if issubclass(self.dataset_type, TextDatasetMixin):
             key, value = next(iter(embedding_dict.items()))
             embedding_size = value[next(iter(value))][0].shape[0]
@@ -190,6 +194,7 @@ class Pipeline(BaseModel):
                 embedding_dict=embedding_dict,
                 embedding_size=embedding_size,
                 embeddings_pooling_strategy=pooling_strategy,
+                dataset_splitter = dataset_splitter,
                 **kwargs)
         else:
             dataset = self.dataset_type(**kwargs)

{ddi_fw-0.0.153 → ddi_fw-0.0.154}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.153
+Version: 0.0.154
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>