z230

IWRS/create_accountability_report.py

@@ -5,14 +5,25 @@ from openpyxl import load_workbook
 from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
 from openpyxl.utils import get_column_letter
 
-# STUDY = "42847922MDD3003"
-STUDY = "77242113UCO3001"
+STUDY = "42847922MDD3003"
+#STUDY = "77242113UCO3001"
 
 INVENTORY_DIR   = Path(f"xls_reports_{STUDY}")
 DESTRUCTION_DIR = Path(f"xls_ip_destruction_{STUDY}")
+SHIPMENTS_FILE  = Path(f"xls_shipments_{STUDY}/shipments_report_{STUDY}.xlsx")
+DETAILS_DIR     = Path(f"xls_shipment_details_{STUDY}")
 OUTPUT_DIR      = Path("output")
 OUTPUT_FILE     = OUTPUT_DIR / f"{date.today().strftime('%Y-%m-%d')} {STUDY} CZ IWRS overview.xlsx"
 
+SHIPMENT_DROP_COLS = {
+    "Location", "Shipped Date", "Delivered Date [UTC]",
+    "Delivery Recipient", "Delivery Details", "Cancelled Date",
+    "Tracking #", "Total Medication IDs",
+    "Shipping Category", "Study", "Destination Location", "Destination Site",
+    "Medication type", "Container ID", "Quantity of Medication IDs",
+    "Packaged Lot description",
+}
+
 # ── Shared constants ──────────────────────────────────────────────────────────
 
 COLUMN_RENAMES = {
@@ -144,6 +155,85 @@ def format_sheet(ws, header_color, highlight_col=None, highlight_color=None):
     ws.freeze_panes    = "A2"
 
 
+# ── Shipment helpers ─────────────────────────────────────────────────────────
+
+def build_shipments():
+    sh = pd.read_excel(SHIPMENTS_FILE, sheet_name=0, header=5)
+    sh.columns = sh.columns.str.strip()
+    sh = sh.dropna(how="all")
+    sh["Shipment ID"] = sh["Shipment ID"].astype(str).str.strip()
+    sh = sh.drop(columns=[c for c in SHIPMENT_DROP_COLS if c in sh.columns])
+    shipment_cols = list(sh.columns)
+
+    all_rows = []
+    for _, s_row in sh.iterrows():
+        sid = s_row["Shipment ID"]
+        path = DETAILS_DIR / f"shipment_details_{sid}.xlsx"
+        if not path.exists():
+            continue
+        det = pd.read_excel(path, sheet_name=0, header=5)
+        det.columns = det.columns.str.strip()
+        det = det.dropna(how="all")
+        det["Shipment"] = det["Shipment"].astype(str).str.strip()
+        extra_cols = [c for c in det.columns if c not in shipment_cols and c != "Shipment" and c not in SHIPMENT_DROP_COLS]
+        for _, d_row in det.iterrows():
+            all_rows.append({**s_row.to_dict(), **{c: d_row[c] for c in extra_cols}})
+
+    result = pd.DataFrame(all_rows)
+    all_cols = shipment_cols + [c for c in extra_cols if c in result.columns]
+    result = result[all_cols]
+
+    for col in ["Request Date", "Received Date", "Expiration Date"]:
+        if col in result.columns:
+            result[col] = pd.to_datetime(result[col], errors="coerce")
+
+    print(f"  Shipments: {result['Shipment ID'].nunique()} shipments, {len(result)} kitu")
+    return result
+
+
+def build_site_summary(result):
+    STATUS_COLS = ["Available", "Assigned", "Dispensed", "Returned by Subject"]
+    pivot = result.groupby("Ship To:")["Status"].value_counts().unstack(fill_value=0)
+    for s in STATUS_COLS:
+        if s not in pivot.columns:
+            pivot[s] = 0
+    pivot = pivot[STATUS_COLS].reset_index().rename(columns={
+        "Ship To:": "Site", "Returned by Subject": "Returned"
+    })
+    pivot = pivot.sort_values("Site").reset_index(drop=True)
+    pivot["Total"] = pivot[["Available", "Assigned", "Dispensed", "Returned"]].sum(axis=1)
+    print(f"  Site Summary: {len(pivot)} center")
+    return pivot
+
+
+def format_shipment_sheet(ws, header_color_ship, header_color_detail, n_ship_cols):
+    thin   = Side(style="thin", color="000000")
+    border = Border(left=thin, right=thin, top=thin, bottom=thin)
+    hfont  = Font(bold=True, color="FFFFFF", name="Arial", size=10)
+    dfont  = Font(name="Arial", size=10)
+    fill_ship   = PatternFill("solid", start_color=header_color_ship)
+    fill_detail = PatternFill("solid", start_color=header_color_detail)
+
+    for cell in ws[1]:
+        cell.fill      = fill_ship if cell.column <= n_ship_cols else fill_detail
+        cell.font      = hfont
+        cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=True)
+        cell.border    = border
+        ws.column_dimensions[get_column_letter(cell.column)].width = min(len(str(cell.value or "")) + 4, 35)
+    ws.row_dimensions[1].height = 30
+
+    for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
+        for cell in row:
+            cell.font      = dfont
+            cell.border    = border
+            cell.alignment = Alignment(horizontal="center", vertical="center")
+            if cell.value.__class__.__name__ in ("datetime", "date", "Timestamp"):
+                cell.number_format = "DD-MMM-YYYY"
+
+    ws.auto_filter.ref = ws.dimensions
+    ws.freeze_panes    = "A2"
+
+
 # ── Build DataFrames ──────────────────────────────────────────────────────────
 
 def build_main(lookup):
@@ -234,13 +324,19 @@ def main():
     not_returned_df           = build_not_returned(df)
     destruction_df            = build_kits_for_destruction(df)
 
+    shipments_df   = build_shipments()
+    site_summary_df = build_site_summary(shipments_df)
+    n_ship_cols    = shipments_df.columns.tolist().index("Investigator")  # first detail col index (0-based)
+
     # Write all sheets
     with pd.ExcelWriter(OUTPUT_FILE, engine="openpyxl") as writer:
-        df.to_excel(             writer, index=False, sheet_name="CountryMedicationOverview")
-        expired_df.to_excel(     writer, index=False, sheet_name=expired_sheet)
-        assigned_df.to_excel(    writer, index=False, sheet_name="Assigned not dispensed")
-        not_returned_df.to_excel(writer, index=False, sheet_name="Not returned")
-        destruction_df.to_excel( writer, index=False, sheet_name="Kits for destruction")
+        df.to_excel(              writer, index=False, sheet_name="CountryMedicationOverview")
+        expired_df.to_excel(      writer, index=False, sheet_name=expired_sheet)
+        assigned_df.to_excel(     writer, index=False, sheet_name="Assigned not dispensed")
+        not_returned_df.to_excel( writer, index=False, sheet_name="Not returned")
+        destruction_df.to_excel(  writer, index=False, sheet_name="Kits for destruction")
+        shipments_df.to_excel(    writer, index=False, sheet_name="Shipments")
+        site_summary_df.to_excel( writer, index=False, sheet_name="Site Summary")
 
     # Format all sheets
     wb = load_workbook(OUTPUT_FILE)
@@ -261,9 +357,12 @@ def main():
     format_sheet(wb["Assigned not dispensed"],   header_color="833C00", highlight_col="Subject ID",     highlight_color="FFF2CC")
     format_sheet(wb["Not returned"],             header_color="375623", highlight_col="Max Visit Date",  highlight_color="E2EFDA")
     format_sheet(wb["Kits for destruction"],     header_color="595959")
+    format_shipment_sheet(wb["Shipments"],    "1F4E79", "375623", n_ship_cols)
+    format_sheet(wb["Site Summary"],          header_color="1F4E79")
 
     wb.save(OUTPUT_FILE)
     print(f"\nSaved: {OUTPUT_FILE}  ({len(df)} rows on main sheet, {wb.sheetnames})")
 
 
-main()
+if __name__ == "__main__":
+    main()