Files
janssen/IWRS/Drugs/Working/create_studie_report.py
T
2026-05-05 12:19:51 +02:00

394 lines
14 KiB
Python

import sys
import os
import mysql.connector
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
from openpyxl.utils import get_column_letter
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."))
import db_config
STUDIES = [
("77242113UCO3001", "UCO"),
("42847922MDD3003", "MDD"),
]
BASE_DIR = Path(os.path.dirname(os.path.abspath(__file__)))
OUTPUT_DIR = BASE_DIR / "output"
DATE_COLUMNS = {
"Orig Exp Date", "Exp Date", "Rcv Date",
"Date Asgn", "Disp Date", "Date Ret", "Destroyed", "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,
"Qty Ret": 10,
"Date Ret": 14,
"Ret User": 18,
"Destroyed": 14,
"Basket No.": 12,
"Max Visit Date": 16,
}
N_SHIP_COLS = 9 # počet shipment sloupců (modrý header v Shipments sheetu)
# ── DB ────────────────────────────────────────────────────────────────────────
def get_conn():
return mysql.connector.connect(
host=db_config.DB_HOST, port=db_config.DB_PORT,
user=db_config.DB_USER, password=db_config.DB_PASSWORD,
database=db_config.DB_NAME,
)
def get_latest_import_id(cursor, study):
cursor.execute(
"SELECT MAX(import_id) AS mid FROM iwrs_import WHERE study=%s AND report_type='drugs'",
(study,),
)
row = cursor.fetchone()
mid = row["mid"]
if mid is None:
raise RuntimeError(f"Žádná data v MySQL pro studii {study}")
return mid
# ── Načítání dat ──────────────────────────────────────────────────────────────
def load_inventory(cursor, study, import_id):
sql = """
SELECT
i.site AS Site,
i.medication_id AS `Med ID`,
i.packaged_lot_no AS `Lot No.`,
i.original_expiration_date AS `Orig Exp Date`,
i.expiration_date AS `Exp Date`,
i.received_date AS `Rcv Date`,
i.receipt_user AS `Rcpt User`,
i.subject_identifier AS `Subject ID`,
i.quantity_assigned AS `Qty Asgn`,
i.irt_transaction AS `IRT Tx`,
i.date_assigned AS `Date Asgn`,
i.assignment_user AS `Asgn User`,
i.dispensation_status AS `Disp Status`,
i.dispensing_date AS `Disp Date`,
i.quantity_dispensed AS `Qty Disp`,
i.dispensing_user AS `Disp User`,
i.quantity_returned AS `Qty Ret`,
i.date_returned AS `Date Ret`,
i.return_user AS `Ret User`,
d.destruction_date AS Destroyed,
d.basket_id AS `Basket No.`
FROM iwrs_inventory i
LEFT JOIN (
SELECT medication_id,
ANY_VALUE(basket_id) AS basket_id,
ANY_VALUE(destruction_date) AS destruction_date
FROM iwrs_destruction
WHERE study = %s
GROUP BY medication_id
) d ON d.medication_id = i.medication_id
WHERE i.import_id = %s
AND i.study = %s
ORDER BY i.site, i.received_date, i.medication_id
"""
cursor.execute(sql, (study, import_id, study))
rows = cursor.fetchall()
df = pd.DataFrame(rows)
for col in DATE_COLUMNS:
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
print(f" Inventory: {len(df)} kitu")
return df
def load_shipments(cursor, study, import_id):
sql = """
SELECT
s.shipment_id AS `Shipment ID`,
s.status AS `IRT Shipment Status`,
s.type AS Type,
s.ship_from AS `Shipment From`,
s.ship_to_site AS `Ship To:`,
s.request_date AS `Request Date`,
s.received_date AS `Received Date`,
s.received_by AS `Received by`,
s.expected_arrival AS `Expected Arrival`,
i.investigator AS Investigator,
i.medication_description AS `Medication Description`,
i.medication_id AS `Medication ID`,
i.packaged_lot_no AS `Packaged Lot number`,
i.expiration_date AS `Expiration Date`,
i.item_status AS Status
FROM iwrs_shipments s
JOIN iwrs_shipment_items i
ON i.study = s.study
AND i.shipment_id = s.shipment_id
AND i.import_id = %s
WHERE s.import_id = %s
AND s.study = %s
ORDER BY s.ship_to_site, s.shipment_id, i.medication_id
"""
cursor.execute(sql, (import_id, import_id, study))
rows = cursor.fetchall()
df = pd.DataFrame(rows)
for col in ("Request Date", "Received Date", "Expiration Date", "Expected Arrival"):
if col in df.columns:
df[col] = pd.to_datetime(df[col], errors="coerce")
n_ship = df["Shipment ID"].nunique() if len(df) else 0
print(f" Shipments: {n_ship} zásilek, {len(df)} kitu")
return df
# ── Odvozené sheety ───────────────────────────────────────────────────────────
def build_site_summary(shipments_df):
STATUS_COLS = ["Available", "Assigned", "Dispensed", "Returned by Subject"]
pivot = shipments_df.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"})
.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 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)
print(f" Expired: {len(filtered)}")
return filtered
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"].fillna("").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"].fillna("").str.upper() == "NOT DISPENSED"))
)
filtered = (
df[mask]
.copy()
.sort_values(["Site", "Date Ret"], ascending=[True, True])
.drop(columns=["Destroyed", "Basket No."])
.reset_index(drop=True)
)
print(f" Kits for destruction: {len(filtered)}")
return filtered
# ── Formátování ───────────────────────────────────────────────────────────────
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]]
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 hi_fill and col_name == highlight_col:
cell.fill = hi_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"
def format_overview_sheet(ws):
format_sheet(ws, header_color="1F4E79")
new_col_fill = PatternFill("solid", start_color="E2EFDA")
headers = [c.value for c in ws[1]]
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
if col_name in ("Destroyed", "Basket No."):
cell.fill = new_col_fill
def format_shipment_sheet(ws):
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="1F4E79")
fill_detail = PatternFill("solid", start_color="375623")
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"
# ── Main ──────────────────────────────────────────────────────────────────────
SHEETS_DEF = [
("CountryMedicationOverview", "overview"),
("Expired", "expired"),
("Assigned not dispensed", "assigned"),
("Not returned", "not_returned"),
("Kits for destruction", "destruction"),
("Shipments", "shipments"),
("Site Summary", "site_summary"),
]
FORMAT_MAP = {
"overview": lambda ws: format_overview_sheet(ws),
"expired": lambda ws: format_sheet(ws, "C00000", "Exp Date", "FFE0E0"),
"assigned": lambda ws: format_sheet(ws, "833C00", "Subject ID", "FFF2CC"),
"not_returned": lambda ws: format_sheet(ws, "375623", "Max Visit Date", "E2EFDA"),
"destruction": lambda ws: format_sheet(ws, "595959"),
"shipments": lambda ws: format_shipment_sheet(ws),
"site_summary": lambda ws: format_sheet(ws, "1F4E79"),
}
def process_study(cursor, study):
today = date.today().strftime("%d-%b-%Y")
import_id = get_latest_import_id(cursor, study)
print(f" import_id = {import_id}")
df = load_inventory(cursor, study, import_id)
shipments_df = load_shipments(cursor, study, import_id)
expired_df = build_expired(df)
assigned_df = build_assigned_not_dispensed(df)
not_returned_df = build_not_returned(df)
destruction_df = build_kits_for_destruction(df)
site_summ_df = build_site_summary(shipments_df)
return [
df, expired_df, assigned_df, not_returned_df,
destruction_df, shipments_df, site_summ_df,
]
def save_study_report(study, data_frames):
output_file = OUTPUT_DIR / f"{date.today().strftime('%Y-%m-%d')} {study} report.xlsx"
with pd.ExcelWriter(output_file, engine="openpyxl") as writer:
for (sheet_name, _), df_sheet in zip(SHEETS_DEF, data_frames):
df_sheet.to_excel(writer, index=False, sheet_name=sheet_name)
wb = load_workbook(output_file)
for (sheet_name, fmt_key) in SHEETS_DEF:
FORMAT_MAP[fmt_key](wb[sheet_name])
wb.save(output_file)
print(f" Uloženo: {output_file}")
def main():
OUTPUT_DIR.mkdir(exist_ok=True)
conn = get_conn()
cursor = conn.cursor(dictionary=True)
for study, _ in STUDIES:
print(f"\n{'='*55}")
print(f"[{study}]")
print(f"{'='*55}")
try:
data_frames = process_study(cursor, study)
save_study_report(study, data_frames)
except Exception as e:
import traceback
print(f" CHYBA: {e}")
traceback.print_exc()
cursor.close()
conn.close()
print(f"\nHotovo.")
if __name__ == "__main__":
main()