perf_metrics.py

def get_performance_metrics(y, pred, class_labels, tp=TP, tn=TN, fp=FP,fn=FN,
                            acc=accuracy, spec=specificity, sens=sensitivity, 
                            ppv=ppv, npv=npv, auc=auc_score, f1=fscore, 
                            prevalence=prevalence, thresholds=[]):
    if len(thresholds) != len(class_labels):
        thresholds = [.5] * len(class_labels)
		
    func_dict = locals()
    func_keys = list(func_dict.keys())
    columns = [""]
    for k in func_keys:
        columns.append(func_dict[k].__name__)
	
    df = pd.DataFrame(columns=columns)
	
    for i in range(len(class_labels)):
        df.loc[i] = [""] + [0] * (len(columns) - 1)
        df.loc[i][0] = class_labels[i]
        for j in range(1,len(columns)-1):
            if func_keys[j] == 'auc' or func_keys[j] == 'f1':
                df.loc[i][j] = round(func_dict[func_keys[j]](y[:, i], pred[:, i]), 3) if auc != None else "Not Defined"
	    if func_keys[j] == 'prevalence':
	        df.loc[i][j] = round(func_dict[func_keys[j]](y[:, i]), 3) if auc != None else "Not Defined"
				
            df.loc[i][j] = round(func_dict[func_keys[j]](y[:, i], pred[:, i], thresholds[i]), 3) if auc != None else "Not Defined"
        
	df.loc[i][len(columns)-1] = round(thresholds[i], 3)

    df = df.set_index("")
    return df