Merge pull request #188 from The-Strategy-Unit/hhd_intervention_logging

fix to the HHD intervention in the event log

Author: morganle-48

renal_capacity_model/config.py

@@ -3,19 +3,19 @@
 It can be adapted to take inputs from users
 """
 
-from renal_capacity_model.helpers import (
-    get_yearly_arrival_rate,
-    get_mean_iat_over_time_from_arrival_rate,
-)
 from renal_capacity_model.config_values import (
-    national_config_dict,
     load_time_to_event_curves,
+    national_config_dict,
     ttd_con_care_values,
-    tw_before_dialysis_values,
     ttd_krt_values,
+    tw_before_dialysis_values,
     tw_cadTx,
     tw_liveTx,
 )
+from renal_capacity_model.helpers import (
+    get_mean_iat_over_time_from_arrival_rate,
+    get_yearly_arrival_rate,
+)
 from renal_capacity_model.utils import get_logger
 
 logger = get_logger(__name__)
@@ -47,7 +47,7 @@ def __init__(
         self.sim_duration = config_dict.get(
             "sim_duration", int(13 * 365)
         )  # in days, but should be a multiple of 365 i.e. years.
-        self.random_seed = config_dict.get("random_seed", 0)
+        self.random_seed = config_dict.get("random_seed", 0)  ### our base random seed
         self.arrival_rate = config_dict["arrival_rate"]
         # how often to take a snapshot of the results_df
         self.snapshot_interval = config_dict.get("snapshot_interval", int(365))

renal_capacity_model/helpers.py

@@ -2,13 +2,15 @@
 Module with helper functions
 """
 
-from renal_capacity_model.utils import get_logger
-import pandas as pd
-import numpy as np
-from itertools import product
 import math
+from itertools import product
 from typing import TYPE_CHECKING
 
+import numpy as np
+import pandas as pd
+
+from renal_capacity_model.utils import get_logger
+
 if TYPE_CHECKING:
     from renal_capacity_model.config import Config
 
@@ -238,7 +240,7 @@ def adjust_next_modality(event_log: pd.DataFrame) -> pd.DataFrame:
 
 
 def process_event_log(event_log: pd.DataFrame) -> pd.DataFrame:
-    """Processes event log for easier validation and debugging
+    """Processes event log for easier validation and debugging. Also removes unnecessary rows that were outdated by the HHD intervention if applied.
 
     Args:
         event_log (pd.DataFrame): event log
@@ -247,6 +249,21 @@ def process_event_log(event_log: pd.DataFrame) -> pd.DataFrame:
         pd.DataFrame with additional columns ("year_start", "end_time", "year_end")
         and clearer information on which modality was next
     """
+    ## loop through the patient ids and remove any rows where time_starting_activity_from is equal to time_starting_activity from in the row below.
+    for patient_id in event_log["patient_id"].unique():
+        if (
+            event_log.loc[
+                event_log["patient_id"] == patient_id, "time_starting_activity_from"
+            ]
+            .duplicated()
+            .any()
+        ):
+            df = event_log.loc[
+                event_log["patient_id"] == patient_id, "time_starting_activity_from"
+            ]
+            duplicates_mask = df.duplicated(keep=False)
+            duplicate_index = df.index[duplicates_mask].tolist()[0]
+            event_log = event_log.drop(duplicate_index)
     event_log["year_start"] = event_log["time_starting_activity_from"].apply(
         calculate_lookup_year
     )