wast: add interventions

.gitattributes

@@ -9,3 +9,4 @@
 *.xlsx filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 resources/** filter=lfs diff=lfs merge=lfs -text
+resources/**/*.md !filter !diff !merge !text

docs/writeups.rst

@@ -46,7 +46,7 @@ Conditions of Early Childhood
 
 * **Diarrhoea**: Childhood diarrhoea caused by virus or bacteria resulting in dehydration, and the treatments associated. :download:`.docx <./write-ups/Diarrhoea.docx>`
 
-* **Childhood Undernutrition**: Acute and chronic undernutrition and its effects of Wasting and Stunting. :download:`.docx <./write-ups/ChildhoodUndernutrition.docx>`
+* **Childhood Undernutrition**: Acute and chronic undernutrition and its effects of Wasting :download:`.docx <./write-ups/Wasting.doc>` and Stunting :download:`.docx <./write-ups/Stunting.docx>`.
 
 
 Communicable Diseases

src/scripts/data_file_processing/healthsystem/consumables/consumable_resource_analyses_with_lmis/consumables_availability_estimation.py

@@ -1,13 +1,19 @@
 """
 This script generates estimates of availability of consumables used by disease modules:
 
-* ResourceFile_Consumables_availability_small.csv (estimate of consumable available - file for use in the
- simulation).
+* ResourceFile_Consumables_availability_small.csv (estimate of consumable availability for items with availability data
+   - smaller file).
+ * ResourceFile_Consumables_availability_all.csv (use estimates of consumable availability for items with availability
+     data from the RF..._small, and approximate availability for items without availability data, approximation by
+     average availability at the Facility_ID and month - smaller file).
 * ResourceFile_Consumables_Inflow_Outflow_Ratio.csv (a file that gives the ratio of inflow of consumables to outflow to
 * capture the extent of wastage as a proportion of use for each consumable by month, district and level.
 
 
-N.B. The file uses `ResourceFile_Consumables_matched.csv` as an input.
+N.B.
+The script uses `ResourceFile_LMIS_2018.csv`, `ResourceFile_Consumables_matched.csv`,
+`ResourceFile_hhfa_consumables.xlsx`, `ResourceFile_Master_Facilities_List.csv`,
+`ResourceFile_Population_2010.csv`, and 'ResourceFile_Consumables_Items_and_Packages.csv' as inputs.
 
 It creates one row for each consumable for availability at a specific facility and month when the data is extracted from
 the OpenLMIS dataset and one row for each consumable for availability aggregated across all facilities when the data is
@@ -705,7 +711,7 @@ def get_inflow_to_outflow_ratio_by_item_and_facilitylevel(_df):
 print(stkout_df.loc[(~(stkout_df.available_prop >= 0.0)) | (~(stkout_df.available_prop <= 1.0))].available_prop)
 assert not stkout_df.duplicated(['fac_type_tlo', 'fac_name', 'district', 'month', 'item_code']).any(), "No duplicates"
 
-# --- 6.7 Generate file for use in model run --- #
+# --- 6.7 Generate file including only item_codes with availability data --- #
 # 1) Smaller file size
 # 2) Indexed by the 'Facility_ID' used in the model (which is an amalgmation of district and facility_level, defined in
 #  the Master Facilities List.
@@ -888,6 +894,61 @@ def interpolate_missing_with_mean(_ser):
     index=False
 )
 
+# --- 6.8 Generate file including both item_codes with and without availability data --- #
+# - for use in model run
+# 1) Smaller file size
+# 2) Indexed by the 'Facility_ID' used in the model (which is an amalgmation of district and facility_level, defined in
+#  the Master Facilities List.
+# 3) if item_code in ResourceFile_Consumables_availability_small.csv, use those availability estimates,
+#  if item_code in ResourceFile_Consumables_Items_and_Packages.csv, but not in
+#  ResourceFile_Consumables_availability_small.csv, approximate the availability by average availability at the
+#  'Facility_ID' and 'month'
+
+# Load the CSV files
+items_and_packages = pd.read_csv(path_for_new_resourcefiles /'ResourceFile_Consumables_Items_and_Packages.csv')
+availability_small = pd.read_csv(path_for_new_resourcefiles /'ResourceFile_Consumables_availability_small.csv')
+
+# Extract all item codes from the RF Items_and_Packages
+all_item_codes = set(items_and_packages['Item_Code'])
+
+# Extract item codes with availability data from RF availability_small
+available_item_codes = set(availability_small['item_code'])
+
+# Find missing item codes
+missing_item_codes = all_item_codes - available_item_codes
+
+# Calculate average availability for each combination of 'Facility_ID' and 'month'
+avg_availability = (
+    availability_small.groupby(['Facility_ID', 'month'])['available_prop']
+    .mean()
+    .reset_index()
+    .rename(columns={'available_prop': 'avg_available_prop'})
+)
+
+# Create rows for missing item codes
+missing_rows = []
+for item_code in missing_item_codes:
+    for _, row in avg_availability.iterrows():
+        missing_rows.append({
+            'Facility_ID': row['Facility_ID'],
+            'month': row['month'],
+            'item_code': item_code,
+            'available_prop': row['avg_available_prop']
+        })
+
+# Convert missing rows to a DataFrame
+missing_df = pd.DataFrame(missing_rows)
+
+# Combine the original availability data with the missing rows
+availability_all = pd.concat([availability_small, missing_df], ignore_index=True)
+
+# Ensure Facility_ID and month columns are integers before saving
+availability_all['Facility_ID'] = availability_all['Facility_ID'].astype(int)
+availability_all['month'] = availability_all['month'].astype(int)
+
+# Save the new file
+availability_all.to_csv(path_for_new_resourcefiles / 'ResourceFile_Consumables_availability_all.csv', index=False)
+
 # %%
 # 7. COMPARISON WITH HHFA DATA, 2018/19 ##
 #########################################################################################

src/scripts/undernutrition_analyses/stunting/stunting_analysis_scenario.py → src/scripts/stunting_analyses/stunting/stunting_analysis_scenario.py

@@ -3,10 +3,10 @@
 HealthSystem availability - including the effects of Diarrhoea and Alri and all the Labour modules.
 
 Run on the batch system using:
-```tlo batch-submit src/scripts/undernutrition_analyses/stunting/stunting_analysis_scenario.py```
+```tlo batch-submit src/scripts/stunting_analyses/stunting/stunting_analysis_scenario.py```
 
 Or locally using:
-```tlo scenario-run src/scripts/undernutrition_analyses/stunting/stunting_analysis_scenario.py```
+```tlo scenario-run src/scripts/stunting_analyses/stunting/stunting_analysis_scenario.py```
 """
 
 from pathlib import Path

src/scripts/wasting_analyses/add_pars_page_ToAllPDFs.py

@@ -0,0 +1,94 @@
+import itertools
+import re
+import sys
+from io import BytesIO
+from pathlib import Path
+
+from PyPDF2 import PdfReader, PdfWriter
+from reportlab.pdfgen import canvas
+
+# Define the parameter values in a dictionary
+parameters = {
+    "base_death_rate_untreated_sam": [0.01, 0.03, 0.05, 0.08, 0.1],
+    "mod_wast_incidence__coef": [0.1, 0.3, 0.5, 0.7, 0.9],
+    "progression_to_sev_wast__coef": [1, 5, 10, 15, 20],
+    "prob_death_after_SAMcare__as_prop_of_death_rate_untreated_sam": [0.85, 0.7, 0.55, 0.4]
+}
+
+# Create the parameter combinations
+param_names = list(parameters.keys())
+param_values = list(parameters.values())
+pars_combinations = list(itertools.product(*param_values))
+
+# Function to create a PDF with parameter values
+def create_parameter_page(params):
+    buffer = BytesIO()
+    c = canvas.Canvas(buffer, pagesize=(200, 45))  # Smaller page size
+    c.setFont("Helvetica", 5)  # Set font and size
+    y_position = 35
+    for name, value in zip(param_names, params):
+        c.drawString(10, y_position, f"{name} = {value}")
+        y_position -= 10  # Move down for the next parameter
+    c.showPage()
+    c.save()
+    buffer.seek(0)
+    return buffer
+
+# Base directory path
+BASE_PATH = Path("/home/eva/PycharmProjects/TLOmodel/outputs/sejjej5@ucl.ac.uk/wasting/")
+
+# Function to extract the indices from the file name
+def extract_indices(file_name):
+    match = re.search(r'_(\d+)_(\d+)\.pdf$', file_name)
+    return (int(match.group(1)), int(match.group(2))) if match else (-1, -1)
+
+# Process each PDF
+def process_pdfs(in_folder_name):
+    pdf_dir = BASE_PATH / in_folder_name / "_outcome_figures"
+    output_dir = BASE_PATH / in_folder_name / "_outputs_with_pars"
+    output_dir.mkdir(exist_ok=True)
+    print(f"Processing PDFs in directory: {pdf_dir}")
+
+    pdf_files = list(pdf_dir.glob("*.pdf"))
+    if not pdf_files:
+        print("No PDF files found in the directory.")
+        return
+
+    # Sort the PDF files by the extracted indices
+    pdf_files.sort(key=lambda x: extract_indices(x.name))
+
+    # Extract the draw indices from the file names
+    existing_draws = {extract_indices(pdf_file.name)[0] for pdf_file in pdf_files}
+
+    # Filter out the parameter combinations for the missing draws
+    filtered_pars_combinations = [params for i, params in enumerate(pars_combinations) if i in existing_draws]
+
+    for pdf_file, params in zip(pdf_files, filtered_pars_combinations):
+        print(f"Processing file: {pdf_file}")
+        reader = PdfReader(str(pdf_file))
+        writer = PdfWriter()
+
+        # Create the parameter page
+        parameter_page = create_parameter_page(params)
+        parameter_reader = PdfReader(parameter_page)
+        writer.add_page(parameter_reader.pages[0])
+
+        # Add the original pages
+        for page in reader.pages:
+            writer.add_page(page)
+
+        # Save the new PDF with _pars added to the original name
+        output_pdf = output_dir / f"{pdf_file.stem}_pars.pdf"
+        with open(output_pdf, "wb") as f:
+            writer.write(f)
+        print(f"Saved updated PDF: {output_pdf}")
+
+    print("PDFs have been updated with parameter pages.")
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python add_pars_page_ToAllPDFs.py <folder_name>")
+    else:
+        folder_name = sys.argv[1]
+        process_pdfs(folder_name)
+