95 fix docstring for with columns

.github/workflows/mypy-flake-test.yml

@@ -25,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10.6"]
 
     # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
@@ -46,9 +46,8 @@ jobs:
           poetry install -E all
       - name: Run MyPy
         run: |
-          poetry run mypy --install-types --non-interactive .
-          poetry run mypy fhir_pyrate/
-          poetry run mypy tests/
+          poetry run mypy --install-types --non-interactive fhir_pyrate
+          poetry run mypy --install-types --non-interactive tests
       - name: Run Flake8
         run: |
           poetry run flake8 fhir_pyrate/

README.md

@@ -56,7 +56,7 @@ Table of Contents:
       * [sail_through_search_space](https://github.com/UMEssen/FHIR-PYrate/#sail_through_search_space)
       * [trade_rows_for_bundles](https://github.com/UMEssen/FHIR-PYrate/#trade_rows_for_bundles)
       * [bundles_to_dataframe](https://github.com/UMEssen/FHIR-PYrate/#bundles_to_dataframe)
-      * [***_dataframe](https://github.com/UMEssen/FHIR-PYrate/#***_dataframe)
+      * [***_dataframe](https://github.com/UMEssen/FHIR-PYrate/#_dataframe)
    * [Miner](https://github.com/UMEssen/FHIR-PYrate/#miner)
    * [DicomDownloader](https://github.com/UMEssen/FHIR-PYrate/#dicomdownloader)
 * [Contributing](https://github.com/UMEssen/FHIR-PYrate/#contributing)

fhir_pyrate/dicom_downloader.py

@@ -280,7 +280,7 @@ def download_data(
             base_dict[self.series_instance_uid_field] = series_uid
 
         # Init the readers/writers
-        series_reader = sitk.ImageSeriesReader()
+        series_reader = sitk.ImageSeriesReader()  # type: ignore
         with tempfile.TemporaryDirectory() as tmp_dir:
             # Create the download dir
             current_tmp_dir = pathlib.Path(tmp_dir)
@@ -308,11 +308,11 @@ def download_data(
             progress_bar.close()
 
             # Get Series ID names from folder
-            series_uids = sitk.ImageSeriesReader.GetGDCMSeriesIDs(str(current_tmp_dir))
+            series_uids = sitk.ImageSeriesReader.GetGDCMSeriesIDs(str(current_tmp_dir))  # type: ignore
             logger.info(f"Study ID has {len(series_uids)} series.")
             for series in series_uids:
                 # Get the DICOMs corresponding to the series
-                files = series_reader.GetGDCMSeriesFileNames(
+                files = series_reader.GetGDCMSeriesFileNames(  # type: ignore
                     str(current_tmp_dir), series
                 )
                 current_dict = base_dict.copy()
@@ -324,8 +324,8 @@ def download_data(
                     with simpleitk_warning_file.open("w") as f, stdout_redirected(
                         f, stdout=sys.stderr
                     ):
-                        series_reader.SetFileNames(files)
-                        image = series_reader.Execute()
+                        series_reader.SetFileNames(files)  # type: ignore
+                        image = series_reader.Execute()  # type: ignore
                     with simpleitk_warning_file.open("r") as f:
                         content = f.read()
                     if "warning" in content.lower():

fhir_pyrate/pirate.py

@@ -445,13 +445,14 @@ def trade_rows_for_dataframe(
         {"date": [("ge", "init_date_column"), ("le", "end_date_column")]}
         :param request_params: The parameters for the query, e.g. _count, _id
         :param num_pages: The number of pages of bundles that should be returned per request,
-        the default is -1 (all bundles),
-        with any other value exactly that value of bundles will be returned,
-        assuming that there are that many
+        the default is -1 (all bundles), with any other value exactly that value of bundles will
+        be returned, assuming that there are that many
         :param with_ref: Whether the input columns of `df_constraints` should be added to the
         output DataFrame
         :param with_columns: Whether additional columns from the source DataFrame should be
-        added to output DataFrame, as a list of column names from the source DataFrames
+        added to output DataFrame. The columns from the source DataFrame can be either specified
+        as a list of columns `[col1, col2, ...]` or as a list of tuples
+        `[(new_name_for_col1, col1), (new_name_for_col2, col2), ...]`
         :param merge_on: Whether to merge the results on a certain row after computing. This is
         useful when using includes, if you store the IDs on the same column you can use that column
         to merge all the rows into one, an example is given in `bundles_to_dataframe`