administrator/janssen
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

z230

Browse Source
This commit is contained in:
vladimir.buzalka
2026-04-08 16:29:35 +02:00
parent 855cef678f
commit 1b00c10f42
8 changed files with 547 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
accountability_combined.xlsx
BIN
View File
Binary file not shown.
accountability_formatted.xlsx
BIN
View File
Binary file not shown.
create_accountability_report.py
+133 -48
View File
@@ -1,4 +1,5 @@
import pandas as pd
from datetime import date
from pathlib import Path
from openpyxl import load_workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
@@ -6,8 +7,10 @@ from openpyxl.utils import get_column_letter
INVENTORY_DIR = Path("xls_reports")
DESTRUCTION_DIR = Path("xls_ip_destruction")
OUTPUT_FILE = "accountability_combined.xlsx"
SHEET_NAME = "CountryMedicationOverview"
OUTPUT_DIR = Path("output")
OUTPUT_FILE = OUTPUT_DIR / f"{date.today().strftime('%Y-%m-%d')} 42847922MDD3003 CZ IWRS overview.xlsx"
# ── Shared constants ──────────────────────────────────────────────────────────
COLUMN_RENAMES = {
"Site": "Site",
@@ -35,7 +38,7 @@ COLUMN_RENAMES = {
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed", "Max Visit Date",
}
COLUMN_WIDTHS = {
@@ -60,8 +63,10 @@ COLUMN_WIDTHS = {
"Ret User": 18,
"Destroyed": 14,
"Basket No.": 12,
"Max Visit Date": 16,
}
# ── Helpers ───────────────────────────────────────────────────────────────────
def read_inventory(path):
df = pd.read_excel(path, header=None)
@@ -94,52 +99,15 @@ def read_destruction_lookup():
return lookup
def main():
lookup = read_destruction_lookup()
print(f"Loaded {len(lookup)} kits from destruction reports")
all_rows = []
for path in sorted(INVENTORY_DIR.glob("onsite_inventory_detail_*.xlsx")):
df, meta = read_inventory(path)
df["DestroyedOn"] = df["Medication ID"].apply(
lambda x: lookup.get(int(x), (None, None))[1] if pd.notna(x) else None
)
df["Basket number"] = df["Medication ID"].apply(
lambda x: lookup.get(int(x), (None, None))[0] if pd.notna(x) else None
)
df.insert(0, "Site", meta.get("site", path.stem))
all_rows.append(df)
print(f" {path.name}: {len(df)} kits")
combined = pd.concat(all_rows, ignore_index=True)
# Rename columns
combined.rename(columns=COLUMN_RENAMES, inplace=True)
# Convert date columns
for col in DATE_COLUMNS:
if col in combined.columns:
combined[col] = pd.to_datetime(combined[col], dayfirst=True, errors="coerce")
# Sort
combined.sort_values(["Site", "Rcv Date", "Med ID"], inplace=True, ignore_index=True)
combined.to_excel(OUTPUT_FILE, index=False, sheet_name=SHEET_NAME)
# ── Formatting ────────────────────────────────────────────────────────────
wb = load_workbook(OUTPUT_FILE)
ws = wb[SHEET_NAME]
header_fill = PatternFill("solid", start_color="1F4E79")
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
new_col_fill = PatternFill("solid", start_color="E2EFDA")
row_font = Font(name="Arial", size=10)
def format_sheet(ws, header_color, highlight_col=None, highlight_color=None):
thin = Side(style="thin", color="000000")
border = Border(left=thin, right=thin, top=thin, bottom=thin)
header_fill = PatternFill("solid", start_color=header_color)
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
row_font = Font(name="Arial", size=10)
hi_fill = PatternFill("solid", start_color=highlight_color) if highlight_color else None
headers = [cell.value for cell in ws[1]]
new_cols = {"Destroyed", "Basket No."}
for cell in ws[1]:
cell.fill = header_fill
@@ -155,8 +123,8 @@ def main():
cell.alignment = Alignment(horizontal="center")
if col_name in DATE_COLUMNS:
cell.number_format = "DD-MMM-YYYY"
if col_name in new_cols:
cell.fill = new_col_fill
if hi_fill and col_name == highlight_col:
cell.fill = hi_fill
for cell in ws[1]:
width = COLUMN_WIDTHS.get(cell.value, 14)
@@ -165,8 +133,125 @@ def main():
ws.auto_filter.ref = ws.dimensions
ws.freeze_panes = "A2"
# ── Build DataFrames ──────────────────────────────────────────────────────────
def build_main(lookup):
all_rows = []
for path in sorted(INVENTORY_DIR.glob("onsite_inventory_detail_*.xlsx")):
df, meta = read_inventory(path)
df["DestroyedOn"] = df["Medication ID"].apply(
lambda x: lookup.get(int(x), (None, None))[1] if pd.notna(x) else None)
df["Basket number"] = df["Medication ID"].apply(
lambda x: lookup.get(int(x), (None, None))[0] if pd.notna(x) else None)
df.insert(0, "Site", meta.get("site", path.stem))
all_rows.append(df)
print(f" {path.name}: {len(df)} kits")
combined = pd.concat(all_rows, ignore_index=True)
combined.rename(columns=COLUMN_RENAMES, inplace=True)
for col in DATE_COLUMNS:
if col in combined.columns:
combined[col] = pd.to_datetime(combined[col], dayfirst=True, errors="coerce")
combined.sort_values(["Site", "Rcv Date", "Med ID"], inplace=True, ignore_index=True)
return combined
def build_expired(df):
today = date.today()
mask = (
df["Basket No."].isna() &
df["Subject ID"].isna() &
(df["Exp Date"] < pd.Timestamp(today))
)
filtered = df[mask].copy().reset_index(drop=True)
sheet_name = f"Expired as of {today.strftime('%d-%b-%Y')}"
print(f" Expired: {len(filtered)}")
return filtered, sheet_name
def build_assigned_not_dispensed(df):
mask = df["Subject ID"].notna() & df["Disp Date"].isna()
filtered = df[mask].copy().reset_index(drop=True)
print(f" Assigned not dispensed: {len(filtered)}")
return filtered
def build_not_returned(df):
no_ret = df[
df["Date Ret"].isna() &
df["Subject ID"].notna() &
(df["Disp Status"].str.upper() != "NOT DISPENSED")
].copy()
max_asgn = df.groupby("Subject ID")["Date Asgn"].max().rename("Max Visit Date")
no_ret = no_ret.join(max_asgn, on="Subject ID")
filtered = no_ret[no_ret["Date Asgn"] < no_ret["Max Visit Date"]].copy()
filtered = filtered.drop(columns=["Qty Ret", "Date Ret", "Ret User", "Destroyed", "Basket No."])
filtered = filtered.reset_index(drop=True)
print(f" Not returned: {len(filtered)}")
return filtered
def build_kits_for_destruction(df):
mask = (
df["Basket No."].isna() &
(df["Date Ret"].notna() | (df["Disp Status"].str.upper() == "NOT DISPENSED"))
)
filtered = df[mask].copy().sort_values(["Site", "Date Ret"], ascending=[True, True])
filtered = filtered.drop(columns=["Destroyed", "Basket No."]).reset_index(drop=True)
print(f" Kits for destruction: {len(filtered)}")
return filtered
# ── Main ──────────────────────────────────────────────────────────────────────
def main():
# Prepare output dir, remove any previous overview file
OUTPUT_DIR.mkdir(exist_ok=True)
for old in OUTPUT_DIR.glob("*42847922MDD3003 CZ IWRS overview.xlsx"):
old.unlink()
print(f"Removed old file: {old.name}")
lookup = read_destruction_lookup()
print(f"Loaded {len(lookup)} kits from destruction reports")
df = build_main(lookup)
expired_df, expired_sheet = build_expired(df)
assigned_df = build_assigned_not_dispensed(df)
not_returned_df = build_not_returned(df)
destruction_df = build_kits_for_destruction(df)
# 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")
# Format all sheets
wb = load_workbook(OUTPUT_FILE)
# Main sheet — dark blue, green highlight for Destroyed/Basket No.
ws_main = wb["CountryMedicationOverview"]
format_sheet(ws_main, header_color="1F4E79")
# Extra: green fill for Destroyed and Basket No. columns
new_col_fill = PatternFill("solid", start_color="E2EFDA")
headers_main = [c.value for c in ws_main[1]]
for row in ws_main.iter_rows(min_row=2, max_row=ws_main.max_row):
for cell in row:
col_name = headers_main[cell.column - 1] if cell.column <= len(headers_main) else None
if col_name in ("Destroyed", "Basket No."):
cell.fill = new_col_fill
format_sheet(wb[expired_sheet], header_color="C00000", highlight_col="Exp Date", highlight_color="FFE0E0")
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")
wb.save(OUTPUT_FILE)
print(f"\nSaved: {OUTPUT_FILE} ({len(combined)} rows, sheet '{SHEET_NAME}')")
print(f"\nSaved: {OUTPUT_FILE} ({len(df)} rows on main sheet, {wb.sheetnames})")
main()
output/2026-04-08 42847922MDD3003 CZ IWRS overview.xlsx
BIN
View File
Binary file not shown.
sheet_assigned_not_dispensed.py
+92
View File
@@ -0,0 +1,92 @@
import pandas as pd
from openpyxl import load_workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter
SOURCE_FILE = "accountability_combined.xlsx"
OUTPUT_FILE = "sheet_assigned_not_dispensed.xlsx"
SHEET_NAME = "Assigned not dispensed"
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed",
}
COLUMN_WIDTHS = {
"Site": 14,
"Med ID": 10,
"Lot No.": 12,
"Orig Exp Date": 16,
"Exp Date": 14,
"Rcv Date": 14,
"Rcpt User": 22,
"Subject ID": 14,
"Qty Asgn": 9,
"IRT Tx": 8,
"Date Asgn": 14,
"Asgn User": 20,
"Disp Status": 16,
"Disp Date": 14,
"Qty Disp": 9,
"Disp User": 20,
"Qty Ret": 10,
"Date Ret": 14,
"Ret User": 18,
"Destroyed": 14,
"Basket No.": 12,
}
df = pd.read_excel(SOURCE_FILE)
for col in DATE_COLUMNS:
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
# Filter: Subject ID present AND Disp Date missing
mask = df["Subject ID"].notna() & df["Disp Date"].isna()
filtered = df[mask].copy().reset_index(drop=True)
print(f"Assigned not dispensed: {len(filtered)}")
filtered.to_excel(OUTPUT_FILE, index=False, sheet_name=SHEET_NAME)
# Formatting
wb = load_workbook(OUTPUT_FILE)
ws = wb[SHEET_NAME]
header_fill = PatternFill("solid", start_color="833C00") # dark orange
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
row_font = Font(name="Arial", size=10)
subj_fill = PatternFill("solid", start_color="FFF2CC") # light yellow highlight for Subject ID
thin = Side(style="thin", color="000000")
border = Border(left=thin, right=thin, top=thin, bottom=thin)
headers = [cell.value for cell in ws[1]]
for cell in ws[1]:
cell.fill = header_fill
cell.font = header_font
cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=False)
cell.border = border
for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
for cell in row:
col_name = headers[cell.column - 1] if cell.column <= len(headers) else None
cell.font = row_font
cell.border = border
cell.alignment = Alignment(horizontal="center")
if col_name in DATE_COLUMNS:
cell.number_format = "DD-MMM-YYYY"
if col_name == "Subject ID":
cell.fill = subj_fill
for cell in ws[1]:
width = COLUMN_WIDTHS.get(cell.value, 14)
ws.column_dimensions[get_column_letter(cell.column)].width = width
ws.auto_filter.ref = ws.dimensions
ws.freeze_panes = "A2"
wb.save(OUTPUT_FILE)
print(f"Saved: {OUTPUT_FILE} (sheet: '{SHEET_NAME}')")
sheet_expired.py
+97
View File
@@ -0,0 +1,97 @@
import pandas as pd
from datetime import date
from openpyxl import load_workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter
SOURCE_FILE = "accountability_combined.xlsx"
OUTPUT_FILE = "sheet_expired.xlsx"
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed",
}
COLUMN_WIDTHS = {
"Site": 14,
"Med ID": 10,
"Lot No.": 12,
"Orig Exp Date": 16,
"Exp Date": 14,
"Rcv Date": 14,
"Rcpt User": 22,
"Subject ID": 14,
"Qty Asgn": 9,
"IRT Tx": 8,
"Date Asgn": 14,
"Asgn User": 20,
"Disp Status": 16,
"Disp Date": 14,
"Qty Disp": 9,
"Disp User": 20,
"Qty Ret": 10,
"Date Ret": 14,
"Ret User": 18,
"Destroyed": 14,
"Basket No.": 12,
}
today = date.today()
sheet_name = f"Expired as of {today.strftime('%d-%b-%Y')}"
# Load source
df = pd.read_excel(SOURCE_FILE)
# Convert date columns
for col in DATE_COLUMNS:
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
# Filter: not in basket AND not assigned to patient AND Exp Date < today
mask = df["Basket No."].isna() & df["Subject ID"].isna() & (df["Exp Date"] < pd.Timestamp(today))
filtered = df[mask].copy().reset_index(drop=True)
print(f"Expired kits not in basket: {len(filtered)}")
filtered.to_excel(OUTPUT_FILE, index=False, sheet_name=sheet_name)
# Formatting
wb = load_workbook(OUTPUT_FILE)
ws = wb[sheet_name]
header_fill = PatternFill("solid", start_color="C00000") # dark red
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
row_font = Font(name="Arial", size=10)
exp_fill = PatternFill("solid", start_color="FFE0E0") # light red highlight for Exp Date
thin = Side(style="thin", color="000000")
border = Border(left=thin, right=thin, top=thin, bottom=thin)
headers = [cell.value for cell in ws[1]]
for cell in ws[1]:
cell.fill = header_fill
cell.font = header_font
cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=False)
cell.border = border
for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
for cell in row:
col_name = headers[cell.column - 1] if cell.column <= len(headers) else None
cell.font = row_font
cell.border = border
cell.alignment = Alignment(horizontal="center")
if col_name in DATE_COLUMNS:
cell.number_format = "DD-MMM-YYYY"
if col_name == "Exp Date":
cell.fill = exp_fill
for cell in ws[1]:
width = COLUMN_WIDTHS.get(cell.value, 14)
ws.column_dimensions[get_column_letter(cell.column)].width = width
ws.auto_filter.ref = ws.dimensions
ws.freeze_panes = "A2"
wb.save(OUTPUT_FILE)
print(f"Saved: {OUTPUT_FILE} (sheet: '{sheet_name}')")
sheet_kits_for_destruction.py
+99
View File
@@ -0,0 +1,99 @@
import pandas as pd
from openpyxl import load_workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter
SOURCE_FILE = "accountability_combined.xlsx"
OUTPUT_FILE = "sheet_kits_for_destruction.xlsx"
SHEET_NAME = "Kits for destruction"
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed",
}
COLUMN_WIDTHS = {
"Site": 14,
"Med ID": 10,
"Lot No.": 12,
"Orig Exp Date": 16,
"Exp Date": 14,
"Rcv Date": 14,
"Rcpt User": 22,
"Subject ID": 14,
"Qty Asgn": 9,
"IRT Tx": 8,
"Date Asgn": 14,
"Asgn User": 20,
"Disp Status": 16,
"Disp Date": 14,
"Qty Disp": 9,
"Disp User": 20,
"Qty Ret": 10,
"Date Ret": 14,
"Ret User": 18,
"Destroyed": 14,
"Basket No.": 12,
}
df = pd.read_excel(SOURCE_FILE)
for col in DATE_COLUMNS:
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
# Filter: no basket AND (Date Ret filled OR Disp Status == NOT DISPENSED)
mask = (
df["Basket No."].isna() &
(
df["Date Ret"].notna() |
(df["Disp Status"].str.upper() == "NOT DISPENSED")
)
)
filtered = df[mask].copy().sort_values(["Site", "Date Ret"], ascending=[True, True])
filtered = filtered.drop(columns=["Destroyed", "Basket No."]).reset_index(drop=True)
print(f"Kits for destruction: {len(filtered)}")
filtered.to_excel(OUTPUT_FILE, index=False, sheet_name=SHEET_NAME)
# Formatting
wb = load_workbook(OUTPUT_FILE)
ws = wb[SHEET_NAME]
header_fill = PatternFill("solid", start_color="595959") # dark grey
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
row_font = Font(name="Arial", size=10)
basket_fill = PatternFill("solid", start_color="FFE0E0") # light red for empty Basket No.
thin = Side(style="thin", color="000000")
border = Border(left=thin, right=thin, top=thin, bottom=thin)
headers = [cell.value for cell in ws[1]]
for cell in ws[1]:
cell.fill = header_fill
cell.font = header_font
cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=False)
cell.border = border
for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
for cell in row:
col_name = headers[cell.column - 1] if cell.column <= len(headers) else None
cell.font = row_font
cell.border = border
cell.alignment = Alignment(horizontal="center")
if col_name in DATE_COLUMNS:
cell.number_format = "DD-MMM-YYYY"
if col_name == "Basket No.":
cell.fill = basket_fill
for cell in ws[1]:
width = COLUMN_WIDTHS.get(cell.value, 14)
ws.column_dimensions[get_column_letter(cell.column)].width = width
ws.auto_filter.ref = ws.dimensions
ws.freeze_panes = "A2"
wb.save(OUTPUT_FILE)
print(f"Saved: {OUTPUT_FILE} (sheet: '{SHEET_NAME}')")
sheet_not_returned.py
+102
View File
@@ -0,0 +1,102 @@
import pandas as pd
from openpyxl import load_workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter
SOURCE_FILE = "accountability_combined.xlsx"
OUTPUT_FILE = "sheet_not_returned.xlsx"
SHEET_NAME = "Not returned"
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Max Visit Date",
}
COLUMN_WIDTHS = {
"Site": 14,
"Med ID": 10,
"Lot No.": 12,
"Orig Exp Date": 16,
"Exp Date": 14,
"Rcv Date": 14,
"Rcpt User": 22,
"Subject ID": 14,
"Qty Asgn": 9,
"IRT Tx": 8,
"Date Asgn": 14,
"Asgn User": 20,
"Disp Status": 16,
"Disp Date": 14,
"Qty Disp": 9,
"Disp User": 20,
"Max Visit Date": 16,
}
df = pd.read_excel(SOURCE_FILE)
for col in DATE_COLUMNS:
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
# Kits with no return date, assigned to a patient, and not "NOT DISPENSED"
no_ret = df[
df["Date Ret"].isna() &
df["Subject ID"].notna() &
(df["Disp Status"].str.upper() != "NOT DISPENSED")
].copy()
# Max Date Asgn per patient (from full dataset)
max_asgn = df.groupby("Subject ID")["Date Asgn"].max().rename("Max Visit Date")
no_ret = no_ret.join(max_asgn, on="Subject ID")
# Keep only kits where Date Asgn is NOT the latest for that patient
filtered = no_ret[no_ret["Date Asgn"] < no_ret["Max Visit Date"]].copy()
# Drop columns Q-U and keep Max Visit Date
filtered = filtered.drop(columns=["Qty Ret", "Date Ret", "Ret User", "Destroyed", "Basket No."])
filtered = filtered.reset_index(drop=True)
print(f"Not returned kits: {len(filtered)}")
filtered.to_excel(OUTPUT_FILE, index=False, sheet_name=SHEET_NAME)
# Formatting
wb = load_workbook(OUTPUT_FILE)
ws = wb[SHEET_NAME]
header_fill = PatternFill("solid", start_color="375623") # dark green
header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
row_font = Font(name="Arial", size=10)
ret_fill = PatternFill("solid", start_color="E2EFDA") # light green highlight for Date Ret
thin = Side(style="thin", color="000000")
border = Border(left=thin, right=thin, top=thin, bottom=thin)
headers = [cell.value for cell in ws[1]]
for cell in ws[1]:
cell.fill = header_fill
cell.font = header_font
cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=False)
cell.border = border
for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
for cell in row:
col_name = headers[cell.column - 1] if cell.column <= len(headers) else None
cell.font = row_font
cell.border = border
cell.alignment = Alignment(horizontal="center")
if col_name in DATE_COLUMNS:
cell.number_format = "DD-MMM-YYYY"
if col_name == "Max Visit Date":
cell.fill = ret_fill
for cell in ws[1]:
width = COLUMN_WIDTHS.get(cell.value, 14)
ws.column_dimensions[get_column_letter(cell.column)].width = width
ws.auto_filter.ref = ws.dimensions
ws.freeze_panes = "A2"
wb.save(OUTPUT_FILE)
print(f"Saved: {OUTPUT_FILE} (sheet: '{SHEET_NAME}')")