【Machine Learning】Part IV. K-M curves plotting

Original coding for K-M curves plotting. Sharing as supplemental materials of my article.

# 数据包导入 import pandas as pd import numpy as np import os import sklearn import scipy from lifelines.datasets import load_waltons from lifelines import KaplanMeierFitter from lifelines.utils import median_survival_times from sklearn.model_selection import learning_curve from sklearn.model_selection import ShuffleSplit from sklearn.metrics import accuracy_score from sklearn.metrics import mean_squared_error import matplotlib.pyplot as plt

kmf = KaplanMeierFitter()

#根据病例预后导入数据文件，显示本信息 FilePath = 'D:/Radiomics/ICH and pneumonia/AI5/' data = pd.read_excel(os.path.join(FilePath,'RISA-SAP-survival.xlsx')) print(数据特征 print(data.info()) data

import  matplotlib.pyplot as plt groups = data['SAP'] ix = (groups == 1)  plt.figure(figsize=(6,4), dpi=200) ax = plt.subplot(1,1,1)  kmf.fit(data['survival_time'][ix], data['death'][ix], label='With SAP') ax = kmf.plot() treatment_median_confidence_interval_ = median_survival_times(kmf.confidence_interval_) print("SAP患者存活50%对应的存活时间95%的信心范围：\n'", treatment_median_confidence_interval_, '\n')  kmf.fit(data['survival_time'][~ix], data['death'][~ix], label='Without SAP') #共享一张画布 ax = kmf.plot(ax=ax)  ax.set_xlim([-3,65]) ax.set_ylim([0.25,1.05]) ax.set_xlabel("Post-stroke Timeline (m)",fontsize = 14) ax.set_ylabel("Survival Rate",fontsize = 14) ax.set_title("K-M Curves on SAP/Individual Survival",fontsize = 16) ax.grid() control_median_confidence_interval_ = median_survival_times(kmf.confidence_interval_)  plt.show()  plt.savefig(os.path.join(FilePath,'output','K-M curve.png'))