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
2026-05-05 14:51:32 +02:00
parent cf872477af
commit b7248e4a2b
17 changed files with 161 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Covance/create_report.py
+161 -13
View File
@@ -39,7 +39,9 @@ EVEN_FILL = PatternFill("solid", fgColor="EBF3FB")
ODD_FILL = PatternFill("solid", fgColor="FFFFFF")
NOTRCV_FILL = PatternFill("solid", fgColor="FCE4D6")
CANCELLED_FILL = PatternFill("solid", fgColor="F2F2F2")
OPEN_FILL = PatternFill("solid", fgColor="FFC7CE")
OPEN_FILL = PatternFill("solid", fgColor="FFC7CE")
OPEN_QUERY_FILL = PatternFill("solid", fgColor="FFD966")
HYPERLINK_FONT = Font(name="Arial", size=10, color="0563C1", underline="single")
CENTER = Alignment(horizontal="center", vertical="center")
LEFT = Alignment(horizontal="left", vertical="center")
@@ -84,6 +86,33 @@ def load_data():
return pd.DataFrame(rows, columns=cols)
def load_equery_data():
conn = 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,
)
sql = """
SELECT site_code, investigator_name, subject, visit,
accession, visit_collection_date, equery_id,
create_date, response_datetime, issue_type, status,
time_before_response, user_name, study_role
FROM covance_equeries
WHERE import_id = (
SELECT MAX(import_id) FROM iwrs_import
WHERE study = %s AND report_type = 'covance_equeries'
)
ORDER BY site_code ASC, create_date DESC
"""
cursor = conn.cursor()
cursor.execute(sql, (STUDY,))
cols = [d[0] for d in cursor.description]
rows = cursor.fetchall()
cursor.close()
conn.close()
return pd.DataFrame(rows, columns=cols)
def load_kit_data():
conn = mysql.connector.connect(
host=db_config.DB_HOST, port=db_config.DB_PORT,
@@ -137,7 +166,9 @@ def write_title(ws, text, ncols):
# ── sheet 1: Přehled ─────────────────────────────────────────────────────────
def write_prehled(wb, df):
def write_prehled(wb, df, accession_eq_row=None):
if accession_eq_row is None:
accession_eq_row = {}
ws = wb.create_sheet("Přehled")
ws.sheet_view.showGridLines = False
@@ -163,16 +194,24 @@ def write_prehled(wb, df):
)
for r_idx, row in agg.iterrows():
excel_row = r_idx + 3
excel_row = r_idx + 3
has_missing = row["not_received"] > 0
fill = NOTRCV_FILL if has_missing else (EVEN_FILL if r_idx % 2 == 0 else ODD_FILL)
accession = row["accession"]
eq_row = accession_eq_row.get(accession) # None pokud nemá Open query
if eq_row:
fill = OPEN_QUERY_FILL
elif has_missing:
fill = NOTRCV_FILL
else:
fill = EVEN_FILL if r_idx % 2 == 0 else ODD_FILL
col_date = row["collection_date"]
date_str = col_date.strftime("%d-%b-%Y") if hasattr(col_date, "strftime") else str(col_date)
values = [
row["investigator_no"], row["investigator_name"], row["patient_no"],
row["protocol_visit_code"], row["accession"], date_str,
row["protocol_visit_code"], accession, date_str,
int(row["celkem"]), int(row["received"]), int(row["not_received"]),
]
for c_idx, val in enumerate(values, 1):
@@ -180,7 +219,11 @@ def write_prehled(wb, df):
cell.fill = fill
cell.border = BORDER
cell.alignment = CENTER if c_idx in (1, 4, 5, 6, 7, 8, 9) else LEFT
if c_idx == 9 and has_missing:
if c_idx == 5 and eq_row:
cell.hyperlink = f"#'eQueries'!A{eq_row}"
cell.font = HYPERLINK_FONT
elif c_idx == 9 and has_missing:
cell.font = RED_FONT
else:
cell.font = NORMAL_FONT
@@ -359,9 +402,66 @@ def write_kity(wb, df_kits):
ws.freeze_panes = "A3"
# ── sheet 4: ZDROJ (samples) ─────────────────────────────────────────────────
# ── sheet 4: eQueries ────────────────────────────────────────────────────────
# ── sheet 5: ZDROJ Kity ──────────────────────────────────────────────────────
def write_equeries(wb, df_eq):
ws = wb.create_sheet("eQueries")
ws.sheet_view.showGridLines = False
today = datetime.date.today().strftime("%d-%b-%Y")
write_title(ws, f"eQueries — {STUDY} ({today})", 14)
headers = ["Site", "Investigátor", "Pacient", "Visit", "Accession",
"Visit Datum", "eQuery ID", "Vytvořeno", "Odpovězeno",
"Issue Type", "Status", "Čas odpovědi", "Uživatel", "Role"]
widths = [9, 22, 14, 26, 13, 13, 10, 16, 16, 20, 9, 13, 22, 13]
write_headers(ws, headers, widths)
def fmt_dt(val, fmt="%d-%b-%Y %H:%M"):
if val is None or (isinstance(val, float) and val != val):
return None
try:
if pd.isna(val):
return None
except (TypeError, ValueError):
pass
if hasattr(val, "strftime"):
return val.strftime(fmt)
return str(val)
for r_idx, row in df_eq.iterrows():
excel_row = r_idx + 3
is_open = str(row.get("status", "")).strip().lower() == "open"
fill = OPEN_FILL if is_open else (EVEN_FILL if r_idx % 2 == 0 else ODD_FILL)
font = Font(name="Arial", bold=True, size=10, color="9C0006") if is_open else NORMAL_FONT
values = [
row["site_code"], row["investigator_name"], row["subject"],
row["visit"], row["accession"],
fmt_dt(row["visit_collection_date"], "%d-%b-%Y"),
row["equery_id"],
fmt_dt(row["create_date"]),
fmt_dt(row["response_datetime"]),
row["issue_type"], row["status"],
row["time_before_response"], row["user_name"], row["study_role"],
]
for c_idx, val in enumerate(values, 1):
if isinstance(val, float) and val != val:
val = None
cell = ws.cell(row=excel_row, column=c_idx, value=val)
cell.fill = fill
cell.border = BORDER
cell.font = font
cell.alignment = CENTER if c_idx in (1, 6, 7, 8, 9, 11, 12) else LEFT
ws.row_dimensions[excel_row].height = 16
ws.freeze_panes = "A3"
ws.auto_filter.ref = f"A2:N{len(df_eq) + 2}"
# ── sheet 5: ZDROJ Vzorky ────────────────────────────────────────────────────
# ── sheet 6: ZDROJ Kity ──────────────────────────────────────────────────────
def write_zdroj_kity(wb, df_kits):
ws = wb.create_sheet("ZDROJ Kity")
@@ -427,6 +527,41 @@ def write_zdroj(wb, df):
ws.auto_filter.ref = f"A1:{get_column_letter(len(headers))}1"
def write_zdroj_equeries(wb, df_eq):
ws = wb.create_sheet("ZDROJ eQuery")
ws.sheet_view.showGridLines = True
headers = list(df_eq.columns)
for c, h in enumerate(headers, 1):
cell = ws.cell(row=1, column=c, value=h)
cell.font = Font(name="Arial", bold=True, size=9, color="FFFFFF")
cell.fill = PatternFill("solid", fgColor="404040")
cell.alignment = LEFT
cell.border = BORDER
ws.column_dimensions[get_column_letter(c)].width = 20
for r_idx, (_, row) in enumerate(df_eq.iterrows(), 2):
fill = EVEN_FILL if r_idx % 2 == 0 else ODD_FILL
for c_idx, col in enumerate(headers, 1):
val = row[col]
try:
is_na = pd.isna(val)
except (TypeError, ValueError):
is_na = False
if is_na or val is None:
val = ""
elif hasattr(val, "strftime"):
val = val.strftime("%Y-%m-%d %H:%M")
cell = ws.cell(row=r_idx, column=c_idx, value=val)
cell.font = Font(name="Arial", size=9)
cell.fill = fill
cell.border = BORDER
cell.alignment = LEFT
ws.freeze_panes = "A2"
ws.auto_filter.ref = f"A1:{get_column_letter(len(headers))}1"
# ── main ─────────────────────────────────────────────────────────────────────
def main():
@@ -435,20 +570,33 @@ def main():
print("Načítám data z MySQL...")
df = load_data()
df_kits = load_kit_data()
print(f" Vzorky: {len(df)} řádků, {df['patient_no'].nunique()} pacientů")
print(f" Kity: {len(df_kits)} kitů, {df_kits['site_code'].nunique()} center")
df_eq = load_equery_data()
print(f" Vzorky: {len(df)} řádků, {df['patient_no'].nunique()} pacientů")
print(f" Kity: {len(df_kits)} kitů, {df_kits['site_code'].nunique()} center")
print(f" eQueries: {len(df_eq)} záznamů ({(df_eq['status']=='Open').sum()} Open)")
# mapping accession → řádek v listu eQueries (jen Open queries, první výskyt)
open_accs = set(df_eq[df_eq["status"] == "Open"]["accession"].dropna())
accession_eq_row = {}
for r_idx, row in df_eq.iterrows():
acc = row.get("accession")
if acc and acc in open_accs and acc not in accession_eq_row:
accession_eq_row[acc] = r_idx + 3 # řádek 1=title, 2=header, data od 3
wb = Workbook()
wb.remove(wb.active)
write_prehled(wb, df)
write_prehled(wb, df, accession_eq_row)
write_chybejici(wb, df)
write_kity(wb, df_kits)
write_equeries(wb, df_eq)
write_zdroj(wb, df)
write_zdroj_kity(wb, df_kits)
write_zdroj_equeries(wb, df_eq)
today = datetime.date.today().strftime("%Y-%m-%d")
out_path = unique_path(f"{today} {STUDY} Covance Samples")
now = datetime.datetime.now()
stamp = now.strftime("%Y-%m-%d %H%M%S")
out_path = unique_path(f"{stamp} {STUDY} Covance")
wb.save(out_path)
print(f"Uloženo: {out_path}")