notebook

Covance_UCO3001/create_report.py

@@ -8,11 +8,11 @@ from openpyxl.utils import get_column_letter
 from datetime import date, datetime
 
 # Paths
-src_dir = "U:/PythonProject/Janssen/Covance_UCO3001/"
+src_dir = "U:/janssen/Covance_UCO3001/"
 out_dir = "U:/Dropbox/!!!Days/Downloads Z230/"
 
 # Find source files
-src_files = glob.glob(src_dir + "3001Specimeninventoryreport*.xlsx")
+src_files = glob.glob(src_dir + "Protocol 77242113UCO3001 - All Samples*.xlsx")
 assert src_files, "Source file not found!"
 src_file = src_files[0]
 print(f"Source xlsx: {src_file}")
@@ -35,10 +35,10 @@ for old in glob.glob(out_dir + "*77242113UCO3001 Speciment Inventory report*.xls
 shutil.copy2(src_file, out_path)
 
 # Load data with pandas for analysis
-df = pd.read_excel(src_file, sheet_name=0, header=2)
+df = pd.read_excel(src_file, sheet_name=0, header=0)
 
 # All unique patients
-all_patients = sorted(df['Patient Number'].dropna().unique())
+all_patients = sorted(df['Patient No.'].dropna().unique())
 
 # BXSCR and DNA rows
 bxscr = df[df['Protocol Visit Code'] == 'BXSCR']
@@ -53,29 +53,40 @@ def fmt_date(val):
     return pd.to_datetime(val).to_pydatetime()
 
 # Get Container Receipt Date + Excel row for patient+specimen from given visit dataframe
-# Excel row = pandas df index + 4 (rows 1-2 title, row 3 header, data from row 4)
+OK_STATUSES = {'Received', 'In Inventory', 'Shipped'}
+
+# Excel row = pandas df index + 2 (row 1 header, data from row 2)
 def get_specimen_info(visit_df, patient, specimen_type=None):
-    rows = visit_df[visit_df['Patient Number'] == patient]
+    rows = visit_df[visit_df['Patient No.'] == patient]
     if specimen_type:
         rows = rows[rows['Specimen Type'] == specimen_type]
+    rows = rows[rows['Sample Status'].isin(OK_STATUSES)]
     if rows.empty:
         return '', None
     row = rows.iloc[0]
-    return fmt_date(row['Container Receipt Date']), rows.index[0] + 4
+    return fmt_date(row['Container Receipt Date']), rows.index[0] + 2
 
 # Get Container Receipt Date + Excel row by Container Label Line 1 code and visit code
 def get_label_info(patient, label_code, visit_code):
-    rows = df[(df['Patient Number'] == patient) &
+    rows = df[(df['Patient No.'] == patient) &
               (df['Protocol Visit Code'] == visit_code) &
               (df['Container Label Line 1'] == label_code)]
+    rows = rows[rows['Sample Status'].isin(OK_STATUSES)]
     if rows.empty:
         return '', None
     row = rows.iloc[0]
-    return fmt_date(row['Container Receipt Date']), rows.index[0] + 4
+    return fmt_date(row['Container Receipt Date']), rows.index[0] + 2
 
 # Open copied workbook and add analysis sheet
 out_wb = load_workbook(out_path)
 
+# Rename and autofit first sheet
+src_ws = out_wb.active
+src_ws.title = "Zdroj"
+for col in src_ws.columns:
+    max_len = max((len(str(cell.value)) if cell.value is not None else 0) for cell in col)
+    src_ws.column_dimensions[get_column_letter(col[0].column)].width = min(max_len + 2, 50)
+
 # Create analysis sheet
 analysis_ws = out_wb.create_sheet("Přehled vzorků")
 
@@ -172,10 +183,10 @@ for i, row in _pat_pre.iterrows():
         patient_row_map[pat] = i + 2  # +1 for 1-based, +1 for header row
 
 # Only patients with any BXSCR record
-bxscr_patients = sorted(bxscr['Patient Number'].dropna().unique())
+bxscr_patients = sorted(bxscr['Patient No.'].dropna().unique())
 
 for row_idx, patient in enumerate(bxscr_patients, 3):
-    investigator = bxscr[bxscr['Patient Number'] == patient].iloc[0]['Investigator Name']
+    investigator = bxscr[bxscr['Patient No.'] == patient].iloc[0]['Investigator Name']
     sm11, sm11_row    = get_specimen_info(bxscr, patient, 'Tissue , Paraffin Block')
     rna,  rna_row     = get_specimen_info(bxscr, patient, 'Biopsy RNA Later')
     cryo, cryo_row    = get_specimen_info(bxscr, patient, 'Biopsy, Frozen Tissue')