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
2026-06-05 11:56:43 +02:00
parent eb05691149
commit 58ba9ca218
130 changed files with 78 additions and 23758 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Clario/create_report_v1.5.py
-477
View File
@@ -1,477 +0,0 @@
"""
create_report.py
Verze: 1.5
Datum: 2026-06-01
Generuje Excel report (.xlsm) pro studii 77242113UCO3001 z MongoDB databáze Clario.
Výstup: U:/Dropbox/!!!Days/Downloads Z230/YYYY-MM-DD 77242113UCO3001 Clario Reports.xlsm
Zdroj dat:
MongoDB 192.168.1.76, databáze Clario
Kolekce Clario.MayoScore — skóre Mayo per pacient × visit
Kolekce Clario.MayoDiary — denní záznamy deníku pacienta
Listy:
MayoScore — jeden řádek = pacient × visit
sloupec „KLIKNI SEM" naviguje na filtrovaný EligibleDays
řádky I-0 s Modified Mayo < 5 červeně tučně
MayoDiary — jeden řádek = denní záznam deníku pacienta
EligibleDays — jeden řádek = jeden eligible day z MayoScore obohacený o data z MayoDiary;
included/excluded flag, excluded dny šedě na žlutém pozadí
VBA makro (Worksheet_SelectionChange na listu MayoScore):
Klik na sloupec „KLIKNI SEM" → přepne na EligibleDays a vyfiltruje záznamy
pro daného pacienta a visit. Vyžaduje povolení maker při otevření souboru.
"""
VERSION = "1.5"
from datetime import datetime
from pathlib import Path
import time
from pymongo import MongoClient
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter
import xlwings as xw
# ---------------------------------------------------------------------------
# Konfigurace
# ---------------------------------------------------------------------------
MONGO_URI = "mongodb://192.168.1.76:27017"
DB_NAME = "Clario"
OUTPUT_DIR = Path(r"U:\Dropbox\!!!Days\Downloads Z230")
VISIT_ORDER = ["I-0", "I-2", "I-4", "I-8", "I-12"]
COLUMNS_SCORE = [
("KLIKNI SEM", lambda d: "▶ klikni sem"),
("Site", lambda d: d.get("site", {}).get("name", "")),
("Subject ID", lambda d: d.get("subject", {}).get("id", "")),
("Visit", lambda d: d["fields"].get("Visit", "")),
("Visit Date", lambda d: d["fields"].get("Visit Date", "")),
("Baseline Stool Frequency", lambda d: _num(d["fields"].get("Baseline Stool Frequency", ""))),
("Central Endoscopy Score", lambda d: _num(d["fields"].get("Central Endoscopy Score", ""))),
("PGA Score", lambda d: _num(d["fields"].get("PGA Score", ""))),
("Stool Frequency Sub-score", lambda d: _num(d["fields"].get("Stool Frequency Sub-score", ""))),
("Rectal Bleeding Sub-score", lambda d: _num(d["fields"].get("Rectal Bleeding Sub-score", ""))),
("Partial Mayo Score", lambda d: _num(d["fields"].get("Partial Mayo Score", ""))),
("Modified Mayo Score", lambda d: _num(d["fields"].get("Modified Mayo Score", ""))),
("Full Mayo Score", lambda d: _num(d["fields"].get("Full Mayo Score", ""))),
("Site Action", lambda d: d.get("Site Action") or ""),
("Last Mayo Score Submission", lambda d: d.get("Last Mayo Score Submission") or ""),
("Wk I-12 Responder", lambda d: d.get("Week I-12 Clinical Responder") or ""),
("Wk I-12 Remission", lambda d: d.get("Week I-12 Clinical Remission") or ""),
("Clinical Flare", lambda d: d.get("Clinical Flare") or ""),
("Loss of Response", lambda d: d.get("Loss of Response") or ""),
("Partial Mayo Post LoR", lambda d: d.get("Partial Mayo Response Post Loss of Response") or ""),
("Partial Mayo Non-Resp", lambda d: d.get("Partial Mayo Response for Clinical Non-Responders") or ""),
]
COLUMNS_DIARY = [
("Subject ID", lambda d: d.get("subject", {}).get("id", "")),
("Report Date", lambda d: d["fields"].get("Report Date", "")),
("Baseline Stool Count", lambda d: _num(d["fields"].get("Baseline Stool Count", ""))),
("Stool Frequency", lambda d: _num(d["fields"].get("Stool Frequency", ""))),
("MAYO050", lambda d: d["fields"].get("MAYO050", "")),
("Not Applicable", lambda d: d["fields"].get("Not Applicable", "")),
("Constipation", lambda d: d["fields"].get("Constipation", "")),
("Diarrhea", lambda d: d["fields"].get("Diarrhea", "")),
("Irregularity", lambda d: d["fields"].get("Irregularity", "")),
]
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _num(value):
"""Převede číselný string na int, jinak vrátí původní hodnotu nebo None."""
if value == "" or value is None:
return None
try:
return int(value)
except (ValueError, TypeError):
try:
return float(value)
except (ValueError, TypeError):
return value
def _visit_sort_key(doc):
visit = doc["fields"].get("Visit", "")
try:
idx = VISIT_ORDER.index(visit)
except ValueError:
idx = len(VISIT_ORDER)
return (doc.get("site", {}).get("name", ""), doc.get("subject", {}).get("id", ""), idx, visit)
def _iso_to_date(value):
"""ISO string → Python date pro Excel."""
if not isinstance(value, str):
return value
try:
return datetime.fromisoformat(value).date()
except ValueError:
return value
# ---------------------------------------------------------------------------
# Styly
# ---------------------------------------------------------------------------
HEADER_FILL = PatternFill("solid", fgColor="1F497D")
HEADER_FONT = Font(bold=True, color="FFFFFF", size=10)
CELL_FONT = Font(size=10)
ALIGN_CTR = Alignment(horizontal="center", vertical="center", wrap_text=False)
ALIGN_LEFT = Alignment(horizontal="left", vertical="center")
THIN = Side(style="thin", color="BFBFBF")
BORDER = Border(left=THIN, right=THIN, top=THIN, bottom=THIN)
# zebra
FILL_ODD = PatternFill("solid", fgColor="FFFFFF")
FILL_EVEN = PatternFill("solid", fgColor="EBF1DE")
SCORE_COLS = {"Partial Mayo Score", "Modified Mayo Score", "Full Mayo Score"}
SCORE_FILL = PatternFill("solid", fgColor="FFC7CE") # červená pro skóre ≥ 5 (placeholder — nepoužíváme podmíněné formátování)
# ---------------------------------------------------------------------------
# Sestavení sheetu
# ---------------------------------------------------------------------------
def _build_sheet(ws, docs, columns, date_cols, center_cols, col_widths, row_font_fn=None):
headers = [c[0] for c in columns]
for col_idx, header in enumerate(headers, 1):
cell = ws.cell(row=1, column=col_idx, value=header)
cell.font = HEADER_FONT
cell.fill = HEADER_FILL
cell.alignment = ALIGN_CTR
cell.border = BORDER
ws.row_dimensions[1].height = 28
for row_idx, doc in enumerate(docs, 2):
fill = FILL_EVEN if row_idx % 2 == 0 else FILL_ODD
font = row_font_fn(doc) if row_font_fn else CELL_FONT
for col_idx, (col_name, getter) in enumerate(columns, 1):
value = getter(doc)
if col_name in date_cols and isinstance(value, str):
value = _iso_to_date(value)
cell = ws.cell(row=row_idx, column=col_idx, value=value)
cell.font = font
cell.fill = fill
cell.border = BORDER
cell.alignment = ALIGN_CTR if col_name in center_cols else ALIGN_LEFT
for col_idx, (col_name, _) in enumerate(columns, 1):
ws.column_dimensions[get_column_letter(col_idx)].width = col_widths.get(col_name, 14)
for col_name in date_cols:
if col_name in headers:
letter = get_column_letter(headers.index(col_name) + 1)
for row_idx in range(2, len(docs) + 2):
ws[f"{letter}{row_idx}"].number_format = "DD-MMM-YYYY"
ws.freeze_panes = "A2"
ws.auto_filter.ref = f"A1:{get_column_letter(len(headers))}1"
def _score_row_font(doc):
visit = doc["fields"].get("Visit", "")
try:
mod_mayo = int(doc["fields"].get("Modified Mayo Score", ""))
except (ValueError, TypeError):
mod_mayo = None
if visit == "I-0" and mod_mayo is not None and mod_mayo < 5:
return Font(size=10, bold=True, color="FF0000")
return CELL_FONT
def build_mayo_score_sheet(ws, docs):
_build_sheet(
ws, docs, COLUMNS_SCORE,
date_cols={"Visit Date", "Last Mayo Score Submission"},
center_cols={"KLIKNI SEM", "Visit", "Central Endoscopy Score", "PGA Score",
"Stool Frequency Sub-score", "Rectal Bleeding Sub-score",
"Partial Mayo Score", "Modified Mayo Score", "Full Mayo Score",
"Baseline Stool Frequency",
"Wk I-12 Responder", "Wk I-12 Remission", "Clinical Flare",
"Loss of Response", "Partial Mayo Post LoR", "Partial Mayo Non-Resp",
"Last Mayo Score Submission"},
col_widths={
"KLIKNI SEM": 14,
"Site": 18, "Subject ID": 16, "Visit": 12, "Visit Date": 14,
"Baseline Stool Frequency": 14, "Central Endoscopy Score": 14,
"PGA Score": 10, "Stool Frequency Sub-score": 14,
"Rectal Bleeding Sub-score": 14, "Partial Mayo Score": 14,
"Modified Mayo Score": 14, "Full Mayo Score": 13,
"Site Action": 22, "Last Mayo Score Submission": 16,
"Wk I-12 Responder": 14, "Wk I-12 Remission": 14,
"Clinical Flare": 14, "Loss of Response": 14,
"Partial Mayo Post LoR": 20, "Partial Mayo Non-Resp": 20,
},
row_font_fn=_score_row_font,
)
# Speciální styl pro sloupec KLIKNI SEM — vypadá jako tlačítko/odkaz
link_font = Font(size=10, bold=True, color="FFFFFF")
link_fill = PatternFill("solid", fgColor="2E75B6")
for row in range(2, len(docs) + 2):
cell = ws.cell(row=row, column=1)
cell.font = link_font
cell.fill = link_fill
cell.alignment = ALIGN_CTR
def build_mayo_diary_sheet(ws, docs):
_build_sheet(
ws, docs, COLUMNS_DIARY,
date_cols={"Report Date"},
center_cols={"Baseline Stool Count", "Stool Frequency", "Not Applicable",
"Constipation", "Diarrhea", "Irregularity"},
col_widths={
"Subject ID": 16, "Report Date": 14, "Baseline Stool Count": 14,
"Stool Frequency": 14, "MAYO050": 48, "Not Applicable": 14,
"Constipation": 14, "Diarrhea": 12, "Irregularity": 14,
},
)
def build_eligible_days_sheet(ws, score_docs, diary_docs):
# Lookup diary records by (subject_id, date_part YYYY-MM-DD)
diary_lookup: dict[tuple, dict] = {}
for d in diary_docs:
subj = d.get("subject", {}).get("id", "")
date_iso = d["fields"].get("Report Date", "")
date_part = date_iso[:10] if date_iso else ""
if subj and date_part:
diary_lookup[(subj, date_part)] = d
headers = [
"Included", "Subject ID", "Visit", "Visit Date", "Day",
"Report Date", "Baseline Stool Count", "Stool Frequency",
"MAYO050", "Not Applicable", "Constipation", "Diarrhea", "Irregularity",
]
col_widths = {
"Included": 10, "Subject ID": 16, "Visit": 10, "Visit Date": 14, "Day": 8,
"Report Date": 14, "Baseline Stool Count": 14, "Stool Frequency": 14,
"MAYO050": 48, "Not Applicable": 14, "Constipation": 14,
"Diarrhea": 12, "Irregularity": 14,
}
center_cols = {"Included", "Visit", "Day", "Baseline Stool Count", "Stool Frequency",
"Not Applicable", "Constipation", "Diarrhea", "Irregularity"}
date_cols = {"Visit Date", "Report Date"}
no_fill = PatternFill("solid", fgColor="FFF2CC") # žlutá pro excluded dny
for col_idx, header in enumerate(headers, 1):
cell = ws.cell(row=1, column=col_idx, value=header)
cell.font = HEADER_FONT
cell.fill = HEADER_FILL
cell.alignment = ALIGN_CTR
cell.border = BORDER
ws.row_dimensions[1].height = 28
row_idx = 2
for score_doc in score_docs:
subj = score_doc.get("subject", {}).get("id", "")
visit = score_doc["fields"].get("Visit", "")
visit_date = score_doc["fields"].get("Visit Date", "")
for n in range(1, 11):
day_date_iso = score_doc["fields"].get(f"Eligible Day (-{n})")
if not day_date_iso or day_date_iso == "-":
continue
date_part = day_date_iso[:10]
excl_reason = score_doc["fields"].get(f"Day (-{n}) Excluded Reason(s)", "")
included = "No" if excl_reason and excl_reason != "-" else "Yes"
diary = diary_lookup.get((subj, date_part), {})
df = diary.get("fields", {})
fill = no_fill if included == "No" else (FILL_EVEN if row_idx % 2 == 0 else FILL_ODD)
font = Font(size=10, color="808080") if included == "No" else CELL_FONT
values = [
included,
subj,
visit,
_iso_to_date(visit_date) if isinstance(visit_date, str) else visit_date,
f"-{n}",
_iso_to_date(day_date_iso),
_num(df.get("Baseline Stool Count", "")),
_num(df.get("Stool Frequency", "")),
df.get("MAYO050", ""),
df.get("Not Applicable", ""),
df.get("Constipation", ""),
df.get("Diarrhea", ""),
df.get("Irregularity", ""),
]
for col_idx, (header, value) in enumerate(zip(headers, values), 1):
cell = ws.cell(row=row_idx, column=col_idx, value=value)
cell.font = font
cell.fill = fill
cell.border = BORDER
if header in date_cols:
cell.number_format = "DD-MMM-YYYY"
cell.alignment = ALIGN_CTR if header in center_cols else ALIGN_LEFT
row_idx += 1
for col_idx, header in enumerate(headers, 1):
ws.column_dimensions[get_column_letter(col_idx)].width = col_widths.get(header, 14)
ws.freeze_panes = "A2"
ws.auto_filter.ref = f"A1:{get_column_letter(len(headers))}1"
# ---------------------------------------------------------------------------
# Helpers: výstupní cesta
# ---------------------------------------------------------------------------
def _unique_path(directory: Path, stem: str, suffix: str) -> Path:
candidate = directory / f"{stem}{suffix}"
if not candidate.exists():
return candidate
n = 2
while True:
candidate = directory / f"{stem} ({n}){suffix}"
if not candidate.exists():
return candidate
n += 1
# ---------------------------------------------------------------------------
# Timing helper
# ---------------------------------------------------------------------------
def _tick(label: str, t0: float) -> float:
"""Vypíše dobu od t0 a vrátí aktuální čas jako nový t0."""
elapsed = time.perf_counter() - t0
print(f" {label:<30} {elapsed:6.2f} s")
return time.perf_counter()
# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------
def main():
t_total = time.perf_counter()
print("Spouštím generování reportu...")
print()
# -- 1. MongoDB: připojení + načtení + seřazení --------------------------
t = time.perf_counter()
client = MongoClient(MONGO_URI, serverSelectionTimeoutMS=5000)
client.admin.command("ping")
db = client[DB_NAME]
score_docs = list(db["Clario.MayoScore"].find({}))
diary_docs = list(db["Clario.MayoDiary"].find({}))
client.close()
score_docs.sort(key=_visit_sort_key)
diary_docs.sort(key=lambda d: (
d.get("subject", {}).get("id", ""),
d["fields"].get("Report Date", ""),
))
t = _tick(f"MongoDB (ping, fetch, sort → {len(score_docs)} + {len(diary_docs)} záznamů)", t)
# -- 2–4. Tvorba listů ---------------------------------------------------
wb = Workbook()
ws_score = wb.active
ws_score.title = "MayoScore"
build_mayo_score_sheet(ws_score, score_docs)
t = _tick("List MayoScore (KLIKNI SEM, zebra, červené I-0, autofilter)", t)
ws_diary = wb.create_sheet("MayoDiary")
build_mayo_diary_sheet(ws_diary, diary_docs)
t = _tick("List MayoDiary (zebra, formátování dat, autofilter)", t)
ws_days = wb.create_sheet("EligibleDays")
build_eligible_days_sheet(ws_days, score_docs, diary_docs)
t = _tick("List EligibleDays (diary lookup, included/excluded flag, autofilter)", t)
# -- 5. Uložení XLSX -----------------------------------------------------
OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
today = datetime.now().strftime("%Y-%m-%d")
base_stem = f"{today} 77242113UCO3001 Clario Reports"
xlsm_path = _unique_path(OUTPUT_DIR, base_stem, ".xlsm")
xlsx_path = xlsm_path.with_suffix(".xlsx")
wb.save(str(xlsx_path))
t = _tick("Uložení XLSX (openpyxl, dočasný soubor)", t)
# -- 6. Injektování VBA --------------------------------------------------
inject_vba(xlsx_path, xlsm_path)
xlsx_path.unlink(missing_ok=True)
_tick("Injektování VBA (xlwings: open → AddFromString → SaveAs .xlsm)", t)
# -- Souhrn --------------------------------------------------------------
total = time.perf_counter() - t_total
print()
print(f" {'Celkem':<30} {total:6.2f} s")
print()
print(f"Uloženo: {xlsm_path}")
def inject_vba(xlsx_path: Path, xlsm_path: Path) -> None:
vba_code = '''\
Private Sub Worksheet_SelectionChange(ByVal Target As Range)
If Target.Row < 2 Then Exit Sub
If Target.Rows.Count > 1 Then Exit Sub
If Target.Column <> 1 Then Exit Sub
Dim subjectId As String
Dim visit As String
subjectId = CStr(Me.Cells(Target.Row, 3).Value)
visit = CStr(Me.Cells(Target.Row, 4).Value)
If subjectId = "" Or visit = "" Then Exit Sub
Dim ws As Worksheet
On Error Resume Next
Set ws = ThisWorkbook.Sheets("EligibleDays")
On Error GoTo 0
If ws Is Nothing Then Exit Sub
Application.ScreenUpdating = False
ws.AutoFilterMode = False
ws.Range("A1").AutoFilter
ws.Range("A1").AutoFilter Field:=2, Criteria1:=subjectId
ws.Range("A1").AutoFilter Field:=3, Criteria1:=visit
ws.Activate
ws.Range("A2").Select
Application.ScreenUpdating = True
End Sub
'''
app = xw.App(visible=False)
try:
wb = app.books.open(str(xlsx_path))
# Najdi VBComponent odpovídající listu "MayoScore" podle tab názvu
vb_comp = None
for comp in wb.api.VBProject.VBComponents:
if comp.Type == 100: # xlSheet
try:
if comp.Properties("Name").Value == "MayoScore":
vb_comp = comp
break
except Exception:
pass
if vb_comp is None:
# fallback: první sheet (Sheet1)
vb_comp = wb.api.VBProject.VBComponents("Sheet1")
vb_comp.CodeModule.AddFromString(vba_code)
wb.api.SaveAs(str(xlsm_path), FileFormat=52) # 52 = xlOpenXMLWorkbookMacroEnabled
wb.close()
finally:
app.quit()
if __name__ == "__main__":
main()