Merge pull request #157 from umccr/dev

umccr · Oct 30, 2023 · 3828edc · 3828edc
2 parents 0dbe35b + d79b80d
commit 3828edc
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 2 deletions.
diff --git a/Changelog.md b/Changelog.md
@@ -15,6 +15,8 @@ For changes in deployment, please see the [deployment changelog](deploy/cttso-ic
 
 * Update sample type trimming of _sample suffix (https://github.com/umccr/cttso-ica-to-pieriandx/pull/150)
   * Resolves https://github.com/umccr/cttso-ica-to-pieriandx/issues/149
+* Update patient_care naming to patientcare (https://github.com/umccr/cttso-ica-to-pieriandx/pull/156)
+  * Resolves https://github.com/umccr/cttso-ica-to-pieriandx/issues/155
 
 ## 2023-10-18
 

diff --git a/deploy/cttso-ica-to-pieriandx-cdk/Changelog.md b/deploy/cttso-ica-to-pieriandx-cdk/Changelog.md
@@ -13,6 +13,8 @@ are nested under deploy/cttso-ica-to-pieriandx-cdk.
 
 * Dont resubmit deleted samples - also remove deleted samples from the lims sheet (https://github.com/umccr/cttso-ica-to-pieriandx/pull/151)
   * Resolves https://github.com/umccr/cttso-ica-to-pieriandx/issues/146 
+* Use loc over iloc for pandas selection (https://github.com/umccr/cttso-ica-to-pieriandx/pull/154)
+  * Resolves https://github.com/umccr/cttso-ica-to-pieriandx/issues/153
 
 ## 2023-10-18
 

diff --git a/...ieriandx-cdk/lambdas/launch_available_payloads_and_update_cttso_lims_sheet/lambda_code.py b/...ieriandx-cdk/lambdas/launch_available_payloads_and_update_cttso_lims_sheet/lambda_code.py
@@ -263,7 +263,7 @@ def get_libraries_for_processing(merged_df) -> pd.DataFrame:
             logger.warning(f"Already run and deleted this combination {process_row['subject_id']} / {process_row['library_id']} / {process_row['portal_wfr_id']}, not reprocessing")
 
     # Delete via index
-    to_process_df = to_process_df.iloc[list(
+    to_process_df = to_process_df.loc[list(
         set(to_process_df.index.tolist()) - set(already_deleted_list_index)
     )]
 

diff --git a/utils/accession.py b/utils/accession.py
@@ -450,7 +450,11 @@ def sanitise_data_frame(input_df: pd.DataFrame) -> pd.DataFrame:
     # Coerce patient care sample to patientcare
     input_df["sample_type"] = input_df["sample_type"].apply(lambda x:
                                                             SampleType(
-                                                                re.sub(r"_?sample$", "", x.lower().replace(" ", ""))
+                                                                re.sub(
+                                                                    r"_?sample$",
+                                                                    "",
+                                                                    x.lower().replace(" ", "").replace("patient_care", "patientcare")
+                                                                )
                                                             ))
     input_df["ethnicity"] = input_df["ethnicity"].apply(lambda x: Ethnicity(x.lower()))
     input_df["race"] = input_df["race"].apply(lambda x: Race(x.lower()))