Update test.py

test.py

@@ -9,6 +9,38 @@ import re
 import boto3
 import botocore
 
+def filter_rows(group):
+    condition1 = (
+                    ((group["biomarker_name"]=="er") & (group["test_result"].str.lower().isin(['positive', 'pos', '+' ]))) |
+                    ((group["biomarker_name"]=="her2") & (group["test_result"].str.lower().isin(['negative', 'neg', '-' ])))
+    )
+    
+    condition2 = (
+                    ((group["biomarker_name"]=="pr") & (group["test_result"].str.lower().isin(['positive', 'pos', '+' ]))) |
+                    ((group["biomarker_name"]=="her2") & (group["test_result"].str.lower().isin(['negative', 'neg', '-' ])))
+    )
+    return group[condition1 | condition2]
+
+filtered_df_final = pd.concat([filter_rows(group) for _, group in finaldf.groupby("chai_patient_id")], ignore_index=True)
+stage_filter = ['1', '2', '3', 'i', 'ii', 'iii', 'iia', 'iiia', 'iib', 'iiib']
+x = filtered_df_final[filtered_df_final["stage_status"].isin(stage_filter)]
+y = x[["chai_patient_id", "clq_id"]].drop_duplicates()
+
+def filter_rows(group):
+    condition1 = (
+                    ((group["biomarker_name"]=="er") & (group["test_result"].str.lower().isin(['positive', 'pos', '+' ]))) |
+                    ((group["biomarker_name"]=="her2") & (group["test_result"].str.lower().isin(['negative', 'neg', '-' ])))
+    )
+    
+    condition2 = (
+                    ((group["biomarker_name"]=="pr") & (group["test_result"].str.lower().isin(['positive', 'pos', '+' ]))) |
+                    ((group["biomarker_name"]=="her2") & (group["test_result"].str.lower().isin(['negative', 'neg', '-' ])))
+    )
+    return group[condition1 | condition2]
+
+
+filtered_df = pd.concat([filter_rows(group) for _, group in df.groupby("chai_patient_id")], ignore_index=True)
+
 def list_files_in_bucket(bucket_name, prefix=''):
     """
     List all files in a given S3 bucket.