python3 << 'EOF' import openpyxl import pandas as pd import numpy as np from scipy import stats wb = openpyxl.load_workbook('/home/daytona/workspace/attachments/451a809a-a430-4e9e-a771-af6016fd2494/dr smita today.xlsx') ws = wb.active rows = [] for row in ws.iter_rows(min_row=6, max_row=55, values_only=True): rows.append(row) data = [] for r in rows: urea = r[4]; creat = r[5]; chol = r[6]; tg = r[7]; hdl = r[8] cysc = r[14]; gfr_creat = r[19]; gfr_cysc = r[20] try: ldl = float(chol) - float(hdl) - float(tg)/5 except: ldl = None try: vldl = float(tg)/5 except: vldl = None try: tc_hdl = float(chol)/float(hdl) except: tc_hdl = None try: ldl_hdl = float(ldl)/float(hdl) if ldl is not None else None except: ldl_hdl = None data.append({'UREA': urea, 'CREATININE': creat, 'CHOL': chol, 'TG': tg, 'HDL': hdl, 'LDL': ldl, 'VLDL': vldl, 'TC_HDL': tc_hdl, 'LDL_HDL': ldl_hdl, 'CYS_C': cysc, 'GFR_CREAT': gfr_creat, 'GFR_CYSC': gfr_cysc}) df = pd.DataFrame(data) for col in df.columns: df[col] = pd.to_numeric(df[col], errors='coerce') lipid_vars = ['CHOL', 'TG', 'HDL', 'LDL', 'VLDL', 'TC_HDL', 'LDL_HDL'] renal_vars = ['CYS_C', 'GFR_CYSC', 'GFR_CREAT', 'CREATININE', 'UREA'] print("=" * 90) print("PEARSON CORRELATION: Lipid Markers vs Renal/GFR Markers") print("=" * 90) print(f"{'Variable Pair':<35} {'r':>8} {'p-value':>12} {'Significance':>14}") print("-" * 90) pearson_results = [] for renal in renal_vars: for lipid in lipid_vars: x = df[lipid].dropna() y = df[renal].dropna() common = df[[lipid, renal]].dropna() r, p = stats.pearsonr(common[lipid], common[renal]) sig = '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else 'NS')) pearson_results.append((renal, lipid, r, p, sig)) pair = f"{lipid} vs {renal}" print(f" {pair:<33} {r:>8.4f} {p:>12.4f} {sig:>14}") print() print("\n" + "=" * 90) print("SPEARMAN CORRELATION: Lipid Markers vs Renal/GFR Markers") print("=" * 90) print(f"{'Variable Pair':<35} {'rho':>8} {'p-value':>12} {'Significance':>14}") print("-" * 90) spearman_results = [] for renal in renal_vars: for lipid in lipid_vars: common = df[[lipid, renal]].dropna() rho, p = stats.spearmanr(common[lipid], common[renal]) sig = '***' if p < 0.001 else ('**' if p < 0.01 else ('*' if p < 0.05 else 'NS')) spearman_results.append((renal, lipid, rho, p, sig)) pair = f"{lipid} vs {renal}" print(f" {pair:<33} {rho:>8.4f} {p:>12.4f} {sig:>14}") print() print("Significance: *** p<0.001 | ** p<0.01 | * p<0.05 | NS = not significant") EOF