make dataset factory private

MannLabs · Sep 20, 2024 · c5cce03 · c5cce03
1 parent ac311c1
commit c5cce03
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 12 deletions.
diff --git a/alphastats/DataSet.py b/alphastats/DataSet.py
@@ -84,7 +84,7 @@ def __init__(
 
         # self.evidence_df: pd.DataFrame = loader.evidence_df  # TODO unused
 
-        self.dataset_factory = DataSetFactory(
+        self._dataset_factory = DataSetFactory(
             rawinput=self.rawinput,
             index_column=self.index_column,
             intensity_column=self._intensity_column,
@@ -93,7 +93,7 @@ def __init__(
         )
 
         rawmat, mat, metadata, sample, preprocessing_info, preprocessed = (
-            self._init_dataset()
+            self._get_init_dataset()
         )
         self.rawmat: pd.DataFrame = rawmat
         self.mat: pd.DataFrame = mat
@@ -104,10 +104,13 @@ def __init__(
 
         print("DataSet has been created.")
 
-    def _init_dataset(self):
-        rawmat, mat = self.dataset_factory.create_matrix_from_rawinput()
+    def _get_init_dataset(
+        self,
+    ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, str, Dict, bool]:
+        """Get the initial data structure for the DataSet."""
+        rawmat, mat = self._dataset_factory.create_matrix_from_rawinput()
 
-        metadata, sample = self.dataset_factory.create_metadata(mat)
+        metadata, sample = self._dataset_factory.create_metadata(mat)
 
         preprocessing_info = Preprocess.init_preprocessing_info(
             num_samples=mat.shape[0],
@@ -189,7 +192,7 @@ def reset_preprocessing(self):
             self.sample,
             self.preprocessing_info,
             self._preprocessed,
-        ) = self._init_dataset()
+        ) = self._get_init_dataset()
 
     def batch_correction(self, batch: str) -> None:
         """A wrapper for Preprocess.batch_correction(), see documentation there."""

diff --git a/tests/test_DataSet.py b/tests/test_DataSet.py
@@ -78,15 +78,15 @@ def test_load_metadata(self):
         def test_load_metadata_missing_sample_column(self, mock):
             # is error raised when name of sample column is missing
             path = self.metadata_path
-            self.obj.dataset_factory.sample_column = "wrong_sample_column"
-            self.obj.dataset_factory._load_metadata(file_path=path)
+            self.obj._dataset_factory.sample_column = "wrong_sample_column"
+            self.obj._dataset_factory._load_metadata(file_path=path)
             mock.assert_called_once()
 
         @patch("logging.Logger.warning")
         def test_load_metadata_warning(self, mock):
             # is dataframe None and is warning produced
             file_path = "wrong/file.xxx"
-            self.obj.dataset_factory._load_metadata(file_path=file_path)
+            self.obj._dataset_factory._load_metadata(file_path=file_path)
             mock.assert_called_once()
 
         def test_create_matrix(self):
@@ -220,15 +220,15 @@ def test_dataset_without_metadata(self):
     def test_load_metadata_fileformats(self):
         # test if different fileformats get loaded correctly
         metadata_path = "testfiles/alphapept/metadata.txt"
-        self.obj.dataset_factory._load_metadata(file_path=metadata_path)
+        self.obj._dataset_factory._load_metadata(file_path=metadata_path)
         self.assertEqual(self.obj.metadata.shape, (2, 2))
 
         metadata_path = "testfiles/alphapept/metadata.tsv"
-        self.obj.dataset_factory._load_metadata(file_path=metadata_path)
+        self.obj._dataset_factory._load_metadata(file_path=metadata_path)
         self.assertEqual(self.obj.metadata.shape, (2, 2))
 
         metadata_path = "testfiles/alphapept/metadata.csv"
-        self.obj.dataset_factory._load_metadata(file_path=metadata_path)
+        self.obj._dataset_factory._load_metadata(file_path=metadata_path)
         self.assertEqual(self.obj.metadata.shape, (2, 2))
 
     @patch("logging.Logger.warning")