Update tmp.py

tmp.py

@@ -1,14 +1,94 @@
-import pandas as pd
+def date_dict(df_list, pif_key):
+    encounter_dates = []
+    for df in df_list:
+        df['encounter_date'].fillna('', inplace=True)
+        df_date = df.loc[df['pif_key'].astype(str) == str(pif_key), 'encounter_date'].values
+        if len(df_date) > 0:
+            encounter_dates.extend(df_date)
+    if encounter_dates:
+        ingested_date = max(encounter_dates)
+    else:
+        ingested_date = ''
+    date_insert_dict = {
+        'attribute_name': 'report_date',
+        'attribute_method': 'cv',
+        'attribute_normalized_prediction': '',
+        'attribute_prediction': str(ingested_date),
+        'attribute_version': 'v2_090523',
+        'attribute_vocab': '',
+        'attribute_code': '',
+        'date_of_service': ''
+    }    
+    return date_insert_dict, encounter_dates, ingested_date
 
-# Sample DataFrame
-data = {'Date': [202205270000.0, '', 202206010000.0]}
 
-df = pd.DataFrame(data)
+def report_date_insertion(dict_list, df_list, logging_df):
+    col_names = {col['attribute_name'] for col in dict_list}
+    if 'report_date' not in col_names:
+        pif_key = next((col['attribute_prediction'] for col in dict_list if col['attribute_name'] == 'pif_key'), None)
+        if pif_key is not None:
+            date_insert_dict, encounter_dates, ingested_date = date_dict(df_list, pif_key)
+            dict_list.insert(1, date_insert_dict)
+            if ingested_date:
+                if len(encounter_dates)>1:
+                    logging_df = logging_df.append({'pif_key': pif_key,
+                                                    'json_report_date_exists': False,
+                                                    'encounter_dates': encounter_dates,
+                                                    'ingested_date': ingested_date,
+                                                    'multiple_date': True, 'old_date': 'missing'}, ignore_index=True)
+                else:
+                    logging_df = logging_df.append({'pif_key': pif_key,
+                                                    'json_report_date_exists': False,
+                                                    'encounter_dates': encounter_dates,
+                                                    'ingested_date': ingested_date,
+                                                    'multiple_date': False, 'old_date': 'missing'}, ignore_index=True)
+            else:
+                logging_df = logging_df.append({'pif_key': pif_key,
+                                                'json_report_date_exists': False,
+                                                'encounter_dates': None,
+                                                'ingested_date': '',
+                                                'multiple_date': False, 'old_date': 'missing'}, ignore_index=True)
 
-# Define a lambda function to convert numeric date to string date
-convert_to_date = lambda x: pd.to_datetime(str(int(x)), format='%Y%m%d', errors='coerce').strftime('%Y-%m-%d') if x != '' else ''
+    elif 'report_date' in col_names:
+        pif_key = next((col['attribute_prediction'] for col in dict_list if col['attribute_name'] == 'pif_key'), None)
+        if pif_key is not None:
+            date_insert_dict, encounter_dates, ingested_date = date_dict(df_list, pif_key)
+            if ingested_date:
+                for report_date_idx, tm in enumerate(dict_list):
+                    if tm['attribute_name']=='report_date':
+                        old_date = tm['attribute_prediction']
+                        break
+                dict_list.pop(report_date_idx)
+                dict_list.insert(1, date_insert_dict)
+                if len(encounter_dates)>1:
+                    logging_df = logging_df.append({'pif_key': pif_key,
+                                                    'json_report_date_exists': True,
+                                                    'encounter_dates': encounter_dates,
+                                                    'ingested_date': ingested_date,
+                                                    'multiple_date': True, 'old_date': old_date}, ignore_index=True)
+                else:
+                    logging_df = logging_df.append({'pif_key': pif_key,
+                                                    'json_report_date_exists': True,
+                                                    'encounter_dates': encounter_dates,
+                                                    'ingested_date': ingested_date,
+                                                    'multiple_date': False, 'old_date': old_date}, ignore_index=True)
+            else:
+                for report_date_idx, tm in enumerate(dict_list):
+                    if tm['attribute_name']=='report_date':
+                        old_date = tm['attribute_prediction']
+                        break
+                logging_df = logging_df.append({'pif_key': pif_key,
+                                                'json_report_date_exists': True,
+                                                'encounter_dates': None,
+                                                'ingested_date': '',
+                                                'multiple_date': False, 'old_date': old_date}, ignore_index=True)
+    return dict_list, logging_df
 
-# Apply the lambda function to the DataFrame column
-df['Date'] = df['Date'].apply(convert_to_date)
-
-print(df)
+def json_report_date_insertion(json_data, df_list, logging_df):
+    for biomarker_detail in json_data['patient_level']['biomarkers']['details']:
+        for attribute in biomarker_detail['attribute']:
+            attribute_details = attribute['attribute_details']
+            dict_list, logging_df = report_date_insertion(attribute_details, df_list, logging_df)
+            attribute['attribute_details'] = dict_list
+    
+    return json_data, logging_df