Merge pull request #336 from MannLabs/rename_metadat_param

rename metadata_path -> metadata_path_or_df

alphastats/DataSet.py

@@ -47,14 +47,14 @@ class DataSet:
     def __init__(
         self,
         loader: BaseLoader,
-        metadata_path: Optional[Union[str, pd.DataFrame]] = None,
+        metadata_path_or_df: Optional[Union[str, pd.DataFrame]] = None,
         sample_column: Optional[str] = None,
     ):
         """Create DataSet
 
         Args:
             loader (_type_): loader of class AlphaPeptLoader, MaxQuantLoader, DIANNLoader, FragPipeLoader, SpectronautLoader
-            metadata_path (str or pd.DataFrame, optional): path to metadata file or an actual df. Defaults to None.
+            metadata_path_or_df (str or pd.DataFrame, optional): path to metadata file or an actual df. Defaults to None.
             sample_column (str, optional): column in metadata file indicating the sample IDs. Defaults to None.
 
         Attributes of a DataSet instance:
@@ -86,7 +86,7 @@ def __init__(
             rawinput=self.rawinput,
             index_column=self.index_column,
             intensity_column=self._intensity_column,
-            metadata_path=metadata_path,
+            metadata_path_or_df=metadata_path_or_df,
             sample_column=sample_column,
         )
 

alphastats/dataset_factory.py

@@ -15,14 +15,14 @@ def __init__(
         rawinput: pd.DataFrame,
         index_column: str,
         intensity_column: Union[List[str], str],
-        metadata_path: Union[str, pd.DataFrame],
+        metadata_path_or_df: Union[str, pd.DataFrame],
         sample_column: str,
     ):
         self.rawinput: pd.DataFrame = rawinput
         self.sample_column: str = sample_column
         self.index_column: str = index_column
         self.intensity_column: Union[List[str], str] = intensity_column
-        self.metadata_path: Union[str, pd.DataFrame] = metadata_path
+        self.metadata_path_or_df: Union[str, pd.DataFrame] = metadata_path_or_df
 
     def create_matrix_from_rawinput(self) -> Tuple[pd.DataFrame, pd.DataFrame]:
         """Creates a matrix: features (Proteins) as columns, samples as rows."""
@@ -61,9 +61,9 @@ def _check_matrix_values(mat: pd.DataFrame) -> None:
     def create_metadata(self, mat: pd.DataFrame) -> Tuple[pd.DataFrame, str]:
         """Create metadata DataFrame from metadata file or DataFrame."""
 
-        if self.metadata_path is not None:
+        if self.metadata_path_or_df is not None:
             sample = self.sample_column
-            metadata = self._load_metadata(file_path=self.metadata_path)
+            metadata = self._load_metadata(file_path=self.metadata_path_or_df)
             metadata = self._remove_missing_samples_from_metadata(mat, metadata, sample)
         else:
             sample = "sample"

alphastats/gui/pages/02_Import Data.py

@@ -159,7 +159,7 @@ def _finalize_data_loading(
 
     dataset = DataSet(
         loader=loader,
-        metadata_path=metadatafile_df,
+        metadata_path_or_df=metadatafile_df,
         sample_column=sample_column,
     )
     metadata_columns = metadatafile_df.columns.to_list()

alphastats/gui/utils/import_helper.py

@@ -109,15 +109,19 @@ def load_example_data():
 
     loader = MaxQuantLoader(file=filepath)
     # TODO why is this done twice?
-    dataset = DataSet(loader=loader, metadata_path=metadatapath, sample_column="sample")
+    dataset = DataSet(
+        loader=loader, metadata_path_or_df=metadatapath, sample_column="sample"
+    )
     metadatapath = (
         os.path.join(_parent_directory, "sample_data", "metadata.xlsx")
         .replace("pages/", "")
         .replace("pages\\", "")
     )
 
     loader = MaxQuantLoader(file=filepath)
-    dataset = DataSet(loader=loader, metadata_path=metadatapath, sample_column="sample")
+    dataset = DataSet(
+        loader=loader, metadata_path_or_df=metadatapath, sample_column="sample"
+    )
 
     dataset.metadata = dataset.metadata[
         [

docs/import_data.md

@@ -14,7 +14,7 @@ maxquant_data = alphastats.MaxQuantLoader(
 
 dataset = alphastats.DataSet(
     loader = maxquant_data,
-    metadata_path="../testfiles/maxquant/metadata.xlsx",
+    metadata_path_or_df="../testfiles/maxquant/metadata.xlsx",
     sample_column="sample"
 )
 ```
@@ -126,7 +126,7 @@ maxquant_data = alphastats.MaxQuantLoader(
 
 dataset = alphastats.DataSet(
     loader = maxquant_data,
-    metadata_path="../testfiles/maxquant/metadata.xlsx",
+    metadata_path_or_df="../testfiles/maxquant/metadata.xlsx",
     sample_column="sample"
 )
 ```

docs/workflow_mq.html

@@ -781,7 +781,7 @@ <h2>2. Create a DataSet<a class="headerlink" href="#2.-Create-a-DataSet" title="
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">ds</span> <span class="o">=</span> <span class="n">alphastats</span><span class="o">.</span><span class="n">DataSet</span><span class="p">(</span>
     <span class="n">loader</span> <span class="o">=</span> <span class="n">maxquant_data</span><span class="p">,</span>
-    <span class="n">metadata_path</span> <span class="o">=</span> <span class="s2">&quot;../testfiles/maxquant/metadata.xlsx&quot;</span><span class="p">,</span>
+    <span class="n">metadata_path_or_df</span> <span class="o">=</span> <span class="s2">&quot;../testfiles/maxquant/metadata.xlsx&quot;</span><span class="p">,</span>
     <span class="n">sample_column</span> <span class="o">=</span> <span class="s2">&quot;sample&quot;</span> <span class="c1"># specify the column that corresponds to the sample names in proteinGroups</span>
 <span class="p">)</span>
 </pre></div>

nbs/getting_started.ipynb

@@ -723,7 +723,7 @@
    "source": [
     "ds = DataSet(\n",
     "    loader=maxquant_data,\n",
-    "    metadata_path=\"../testfiles/maxquant/metadata.xlsx\",\n",
+    "    metadata_path_or_df=\"../testfiles/maxquant/metadata.xlsx\",\n",
     "    sample_column=\"sample\",  # specify the column that corresponds to the sample names in proteinGroups\n",
     ")"
    ]

nbs/liu_2019.ipynb

@@ -92,7 +92,7 @@
     ")\n",
     "dataset = DataSet(\n",
     "    loader=loader,\n",
-    "    metadata_path=\"../testfiles/maxquant/metadata.xlsx\",\n",
+    "    metadata_path_or_df=\"../testfiles/maxquant/metadata.xlsx\",\n",
     "    sample_column=\"sample\",\n",
     ")"
    ]

tests/gui/conftest.py

@@ -30,7 +30,7 @@ def create_dataset_alphapept():
     metadata_path = TEST_INPUT_FILES_PATH / "alphapept/metadata.csv"
     return DataSet(
         loader=loader,
-        metadata_path=str(metadata_path),
+        metadata_path_or_df=str(metadata_path),
         sample_column="sample",
     )
 

tests/test_DataSet.py

@@ -205,7 +205,7 @@ def setUp(self):
         self.metadata_path = "testfiles/alphapept/metadata.csv"
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="sample",
         )
         # expected dimensions of matrix
@@ -239,7 +239,7 @@ def test_remove_misc_samples_in_metadata(self, mock):
         )
         obj = DataSet(
             loader=self.loader,
-            metadata_path=df,
+            metadata_path_or_df=df,
             sample_column="sample",
         )
         #  is sample C removed
@@ -253,7 +253,7 @@ def test_load_metadata_df(self):
             df = pd.read_excel(self.metadata_path)
         obj = DataSet(
             loader=self.loader,
-            metadata_path=df,
+            metadata_path_or_df=df,
             sample_column="sample",
         )
         self.assertIsInstance(obj.metadata, pd.DataFrame)
@@ -403,7 +403,7 @@ def setUp(self):
         self.metadata_path = "testfiles/maxquant/metadata.xlsx"
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="sample",
         )
         # expected dimensions of matrix
@@ -419,7 +419,7 @@ def test_load_evidence_wrong_sample_names(self):
             )
             DataSet(
                 loader=loader,
-                metadata_path=self.metadata_path,
+                metadata_path_or_df=self.metadata_path,
                 sample_column="sample",
             )
 
@@ -468,7 +468,7 @@ def test_plot_volcano_with_grouplist_wrong_names(self):
     def test_plot_volcano_compare_preprocessing_modes_no_randomforest(self):
         obj_ut = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="sample",
         )
 
@@ -487,7 +487,7 @@ def test_plot_volcano_compare_preprocessing_modes_no_randomforest(self):
     def test_plot_volcano_compare_preprocessing_modes_randomforest(self):
         obj_ut = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="sample",
         )
 
@@ -801,7 +801,7 @@ def setUp(self):
         self.metadata_path = "testfiles/diann/metadata.xlsx"
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="analytical_sample external_id",
         )
         # expected dimensions of matrix
@@ -916,7 +916,7 @@ def setUp(self):
         self.metadata_path = "testfiles/fragpipe/metadata.xlsx"
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="analytical_sample external_id",
         )
         # expected dimensions of matrix
@@ -937,7 +937,7 @@ def setUpClass(cls):
         cls.cls_metadata_path = "testfiles/spectronaut/metadata.xlsx"
         cls.cls_obj = DataSet(
             loader=cls.cls_loader,
-            metadata_path=cls.cls_metadata_path,
+            metadata_path_or_df=cls.cls_metadata_path,
             sample_column="sample",
         )
 
@@ -983,7 +983,7 @@ def setUpClass(cls):
         cls.cls_metadata_path = "testfiles/fragpipe/metadata2.xlsx"
         cls.cls_obj = DataSet(
             loader=cls.cls_loader,
-            metadata_path=cls.cls_metadata_path,
+            metadata_path_or_df=cls.cls_metadata_path,
             sample_column="analytical_sample external_id",
         )
 

tests/test_DataSet_Pathway.py

@@ -111,7 +111,7 @@ def setUp(self):
 
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=metadata,
+            metadata_path_or_df=metadata,
             sample_column="sample",
         )
         self.fg_sample = "AC399"

tests/test_gpt.py

@@ -22,7 +22,7 @@ def setUp(self):
         self.metadata_path = "testfiles/maxquant/metadata.xlsx"
         self.obj = DataSet(
             loader=self.loader,
-            metadata_path=self.metadata_path,
+            metadata_path_or_df=self.metadata_path,
             sample_column="sample",
         )
         # expected dimensions of matrix