code review fixes, sort to stabilize order output in tests

Author: AmandaBirmingham

notebooks/pacbio_sample_sheet_builder.ipynb

@@ -196,7 +196,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# determine which columns are required and\n",
+    "# determine which columns are required\n",
     "cols_to_get = [sample_name_col_key, plate_col_key, well_col_key,\n",
     "               barcode_col_key, twist_adaptor_id_col_key, project_name_col_key,\n",
     "               qiita_id_key, sample_type_key]\n",
@@ -224,7 +224,7 @@
     "# eventually may make a sample sheet for each different run id in the\n",
     "# processing doc, but for now just error if more than one\n",
     "curr_run_ids = set(list(info_df[run_id_key].values))\n",
-    "if len(curr_run_ids) >1:\n",
+    "if len(curr_run_ids) > 1:\n",
     "    raise ValueError(f\"Multiple run ids found: {curr_run_ids}\")\n",
     "\n",
     "curr_run_id = list(curr_run_ids)[0]\n",
@@ -241,7 +241,7 @@
     "# drop any row that doesn't have a qiita id\n",
     "info_df = info_df.dropna(subset=[qiita_id_key])\n",
     "\n",
-    "# get all the unique qiita ids in the curr_run_df\n",
+    "# get all the unique qiita ids in the dataframe\n",
     "qiita_ids = set(list(info_df[qiita_id_key].values))\n",
     "qiita_ids"
    ]
@@ -445,7 +445,7 @@
    "outputs": [],
    "source": [
     "# loop over each qiita id and add to the metadata dictionary for it\n",
-    "for curr_qiita_id in qiita_ids:\n",
+    "for curr_qiita_id in sorted(qiita_ids):\n",
     "    # get the subset of plate_df for this qiita id\n",
     "    curr_qiita_id_mask = plate_df[qiita_id_key] == curr_qiita_id\n",
     "    curr_qiita_id_df = plate_df.loc[curr_qiita_id_mask].copy()\n",

notebooks/tests/notebook_test_helpers.py

@@ -15,7 +15,7 @@ class TestNotebook(unittest.TestCase):
     _ZERO_DATES_FUNC_KEY = "zero_dates_func"  # func to replace for dates
 
     # TODO: turn off before committing
-    _SAVE_UNMATCHED_OUTPUTS = True  # whether to save unmatched outputs
+    _SAVE_UNMATCHED_OUTPUTS = False  # whether to save unmatched outputs
 
     def setUp(self):
         self.notebooks_dir = os.path.dirname(os.path.dirname(__file__))
@@ -26,7 +26,7 @@ def _help_test_files_exact_text_match(self, file_1, file_2, filename=None,
                                           zero_dates_func=None):
         """Helper function to compare two text files for exact match."""
 
-        filename = filename if not filename else f"{filename} "
+        filename = f"{filename} " if filename else ""
         msg = f"{filename}files do not match exactly."
         self.maxDiff = None
         with open(file_1, 'r', encoding='utf-8') as f1, \

notebooks/tests/test_pacbio_sample_sheet_builder.py

@@ -83,7 +83,7 @@ def test_pacbio_v11_pooled_absquant(self):
                     ('{path}/SampleSheets/'
                      'pacbio_v11_absquant_pooled_sample_sheet.csv'),
                 self._FILE_PATH_KEY: True
-            },
+            }
         }
 
         self._run_notebook_test(run_params, output_params)