DFF Integration into TLO

src/tlo/methods/enhanced_lifestyle.py

@@ -692,7 +692,9 @@ def predict_rural_urban_status(self, df, rng=None, **externals) -> pd.Series:
             # check all districts have been corectly mapped to their rural urban proportions
             assert not rural_urban_props.isnull().any(), 'some districts are not mapped to their rural urban values'
             # check urban rural proportion is greater or equal to 0 but less or equal to 1
-            assert rural_urban_props.apply(lambda x: 0.0 <= x <= 1.0).any(), 'proportion less than 0 or greater than 1'
+            rural_urban_props = df['district_of_residence'].map(p['init_p_urban']['prop_urban']).astype(float)
+            assert rural_urban_props.between(0.0, 1.0).all(), 'proportion less than 0 or greater than 1'
+            # assert rural_urban_props.apply(lambda x: 0.0 <= x <= 1.0).any(), 'proportion less than 0 or greater than 1'
 
             # get individual's rural urban status
             rural_urban = rural_urban_props > rnd_draw

src/tlo/methods/hiv.py

@@ -113,11 +113,13 @@ def __init__(self, name=None, run_with_checks=False):
         ),
         "hv_on_cotrimoxazole": Property(
             Types.BOOL,
-            "Whether the person is currently taking and receiving a malaria-protective effect from cotrimoxazole",
+            "Whether the person is currently taking and receiving a malaria-protective "
+            "effect from cotrimoxazole",
         ),
         "hv_is_on_prep": Property(
             Types.BOOL,
-            "Whether the person is currently taking and receiving a protective effect from Pre-Exposure Prophylaxis",
+            "Whether the person is currently taking and receiving a protective effect "
+            "from Pre-Exposure Prophylaxis",
         ),
         "hv_behaviour_change": Property(
             Types.BOOL,
@@ -140,6 +142,7 @@ def __init__(self, name=None, run_with_checks=False):
             Types.DATA_FRAME, "prob of time since infection for baseline adult pop"
         ),
         "art_coverage": Parameter(Types.DATA_FRAME, "coverage of ART at baseline"),
+        "art_coverage_pregnant_women": Parameter(Types.REAL, "coverage of pregnant women on ART at baseline"),
         "treatment_cascade": Parameter(Types.DATA_FRAME, "spectrum estimates of treatment cascade"),
         # Natural history - transmission - overall rates
         "beta": Parameter(Types.REAL, "Transmission rate"),
@@ -431,9 +434,20 @@ def read_parameters(self, resourcefilepath: Optional[Path] = None):
         # Shortcut to parameters dict
         p = self.parameters
 
-        workbook = read_csv_files(resourcefilepath/'ResourceFile_HIV', files=None)
+        workbook = read_csv_files(resourcefilepath / 'ResourceFile_HIV', files=None)
         self.load_parameters_from_dataframe(workbook["parameters"])
 
+        # preg_art_path = resourcefilepath / 'ResourceFile_HIV' / 'art_coverage_pregnant_women.csv'
+        # preg_art_df = pd.read_csv(preg_art_path)
+        #
+        # # Extract the value for 'art_coverage_pregnant_women'
+        # art_cov_value = preg_art_df.loc[
+        #     preg_art_df['parameter_name'] == 'art_coverage_pregnant_women', 'value'
+        # ].values[0]
+        #
+        # # Assign it to the parameters dictionary
+        # p['art_coverage_pregnant_women'] = float(art_cov_value)
+
         # Load data on HIV prevalence
         p["hiv_prev"] = workbook["hiv_prevalence"]
 
@@ -743,6 +757,20 @@ def initialise_baseline_art(self, population):
             worksheet.year == 2010, ["year", "single_age", "sex", "prop_coverage"]
         ]
 
+        # hiv_positive_pregnant_women = df[
+        #     df.is_alive &
+        #     (df.sex == "F") &
+        #     df.hv_inf &
+        #     (df["is_pregnant"]) &
+        #     (df.hv_art == "not")].index
+        # # Randomly assign ART based on coverage parameter
+        # n = len(hiv_positive_pregnant_women)
+        # n_to_assign = int(n * params["art_coverage_pregnant_women"])
+        # assigned_art_preg = self.rng.choice(hiv_positive_pregnant_women, size=n_to_assign, replace=False)
+        #
+        # df.loc[assigned_art_preg, "hv_art"] = "on_VL_suppressed"
+
+
         # merge all susceptible individuals with their coverage probability based on sex and age
         prob_art = df.loc[df.is_alive, ["age_years", "sex"]].merge(
             art_data,
@@ -777,6 +805,10 @@ def initialise_baseline_art(self, population):
         p["overall_prob_of_art"] = p["scaled_rel_prob_by_time_infected"] * p["prob_art"]
         random_draw = self.rng.random_sample(size=len(df))
 
+        # art_idx = df.index[
+        #     (random_draw < p["overall_prob_of_art"]) & df.is_alive & df.hv_inf
+        #     ].union(assigned_art_preg)
+
         art_idx = df.index[
             (random_draw < p["overall_prob_of_art"]) & df.is_alive & df.hv_inf
             ]
@@ -1678,6 +1710,7 @@ def do_at_generic_first_appt(
             )
             schedule_hsi_event(event, priority=0, topen=self.sim.date)
 
+
 # ---------------------------------------------------------------------------
 #   Main Polling Event
 # ---------------------------------------------------------------------------
@@ -2474,7 +2507,6 @@ def apply(self, person_id, squeeze_factor):
             # set cap for number of repeat tests
             self.counter_for_test_not_available += 1  # The current appointment is included in the count.
 
-
             if (
                 self.counter_for_test_not_available
                 <= self.module.parameters["hiv_healthseekingbehaviour_cap"]
@@ -2532,7 +2564,7 @@ def apply(self, person_id, squeeze_factor):
 
                 # Add used equipment
                 self.add_equipment({'Drip stand', 'Stool, adjustable height', 'Autoclave',
-                                       'Bipolar Diathermy Machine', 'Bed, adult', 'Trolley, patient'})
+                                    'Bipolar Diathermy Machine', 'Bed, adult', 'Trolley, patient'})
 
                 # Schedule follow-up appts
                 # schedule first follow-up appt, 3 days from procedure;
@@ -2744,7 +2776,7 @@ def apply(self, person_id, squeeze_factor):
         # check whether person had Rx at least 3 months ago and is now due repeat prescription
         # alternate routes into testing/tx may mean person already has recent ARV dispensation
         if person['hv_date_last_ART'] > (
-                self.sim.date - pd.DateOffset(months=self.module.parameters['dispensation_period_months'])):
+            self.sim.date - pd.DateOffset(months=self.module.parameters['dispensation_period_months'])):
             return self.sim.modules["HealthSystem"].get_blank_appt_footprint()
 
         if art_status_at_beginning_of_hsi == "not":
@@ -2945,13 +2977,13 @@ def get_drugs(self, age_of_person):
                     self.module.item_codes_for_consumables_required[
                         "First line ART regimen: young child"
                     ]: dispensation_days
-                    * 2
+                       * 2
                 },
                 optional_item_codes={
                     self.module.item_codes_for_consumables_required[
                         "First line ART regimen: young child: cotrimoxazole"
                     ]: dispensation_days
-                    * 240
+                       * 240
                 },
                 return_individual_results=True,
             )
@@ -2962,7 +2994,7 @@ def get_drugs(self, age_of_person):
                 item_codes={self.module.item_codes_for_consumables_required[
                                 'First line ART regimen: older child']: dispensation_days * 3},
                 optional_item_codes={self.module.item_codes_for_consumables_required[
-                    'First line ART regimen: older child: cotrimoxazole']: dispensation_days * 480},
+                                'First line ART regimen: older child: cotrimoxazole']: dispensation_days * 480},
                 return_individual_results=True)
 
         else:
@@ -2971,7 +3003,7 @@ def get_drugs(self, age_of_person):
                 item_codes={self.module.item_codes_for_consumables_required[
                                 'First-line ART regimen: adult']: dispensation_days},
                 optional_item_codes={self.module.item_codes_for_consumables_required[
-                    'First-line ART regimen: adult: cotrimoxazole']: dispensation_days * 960},
+                                         'First-line ART regimen: adult: cotrimoxazole']: dispensation_days * 960},
                 return_individual_results=True)
 
         # add drug names to dict

src/tlo/methods/labour_lm.py

@@ -501,7 +501,7 @@ def predict_postnatal_check(self, df, rng=None, **externals):
 
     result[(df.la_parity > 4)] *= params['or_pnc_parity_>4']
 
-    result[(df.ac_total_anc_visits_current_pregnancy > 3)] *= params['or_pnc_anc4+']
+    result[(df.ac_total_anc_visits_current_pregnancy > 3)] *= params['or_pnc_anc4+'] #changing for DFF
 
     result[externals['mode_of_delivery'] == 'caesarean_section'] *= params['or_pnc_caesarean_delivery']
     result[(externals['delivery_setting'] == 'health_centre') | (externals['delivery_setting'] == 'hospital')] \

src/tlo/methods/malaria.py

@@ -186,7 +186,9 @@ def __init__(self, name=None):
         "scaleup_parameters": Parameter(
             Types.DATA_FRAME,
             "the parameters and values changed in scenario analysis"
-        )
+        ),
+        'iptp_coverage': Parameter(Types.REAL, 'Proportion of eligible pregnant women to receive IPTp this month')
+
     }
 
     PROPERTIES = {
@@ -296,6 +298,9 @@ def read_parameters(self, resourcefilepath: Optional[Path] = None):
         all_inc = all_inc.reset_index()
 
         all_inc['district_num'] = all_inc['admin'].map(mapper_district_name_to_num)
+
+        # Filter to only include Rumphi district (district_num = 3)
+        all_inc = all_inc[all_inc['district_num'] == 3].copy()
         assert not all_inc['district_num'].isna().any()
 
         self.all_inc = all_inc.drop(columns=['admin']).set_index(['month', 'district_num', 'llin', 'irs'])
@@ -930,7 +935,10 @@ def apply(self, population):
 
         p1 = df.index[p1_condition]
 
-        for person_index in p1:
+        selected_for_iptp = self.module.rng.random_sample(len(p1)) < self.module.parameters['iptp_coverage']
+        p1_selected = p1[selected_for_iptp]
+
+        for person_index in p1_selected:
             logger.debug(key='message',
                          data=f'MalariaIPTp: scheduling HSI_Malaria_IPTp for person {person_index}')
 

tests/test_demography.py

@@ -177,7 +177,45 @@ def test_calc_of_scaling_factor(tmpdir, seed):
     # Check that the scaling factor is calculated in the log correctly:
     output = parse_log_file(sim.log_filepath)
     sf = output['tlo.methods.demography']['scaling_factor'].at[0, 'scaling_factor']
-    assert sf == approx(14.5e6 / popsize, rel=0.10)
+
+    # Get the actual total census population (sum of all active districts)
+    demog = sim.modules['Demography']
+
+    # Primary (prefered) approach: pop_2010['Count'] (matches your parameter dump)
+    total_pop = None
+    if 'pop_2010' in demog.parameters:
+        pop_df = demog.parameters['pop_2010']
+        if isinstance(pop_df, pd.DataFrame) and 'Count' in pop_df.columns:
+            total_pop = float(pop_df['Count'].sum())
+
+    # Fallback: search parameters for anything with "pop" in the key and sum numeric content
+    if (total_pop is None) or (total_pop == 0):
+        total_pop = 0.0
+        for k, v in demog.parameters.items():
+            if 'pop' not in k.lower():
+                continue
+            # DataFrame case
+            if isinstance(v, pd.DataFrame):
+                if 'Count' in v.columns:
+                    total_pop += float(v['Count'].sum())
+                else:
+                    # sum all numeric columns
+                    total_pop += float(v.select_dtypes(include=[np.number]).to_numpy().sum())
+            # Series case
+            elif isinstance(v, pd.Series):
+                # numeric_only for newer pandas
+                total_pop += float(v.sum(numeric_only=True))
+            # numeric scalar
+            else:
+                try:
+                    total_pop += float(v)
+                except Exception:
+                    # ignore non-numeric params
+                    pass
+
+    assert total_pop > 0, f"Could not determine total population from parameters: {list(demog.parameters.keys())}"
+
+    assert sf == approx(total_pop / popsize, rel=0.10)
 
     # Check that the scaling factor is also logged in `tlo.methods.population`
     assert output['tlo.methods.demography']['scaling_factor'].at[0, 'scaling_factor'] == \