python ks曲线_python之KS曲线

# 自定义绘制ks曲线的函数

def plot_ks(y_test, y_score, positive_flag):

# 对y_test,y_score重新设置索引

y_test.index = np.arange(len(y_test))

#y_score.index = np.arange(len(y_score))

# 构建目标数据集

target_data = pd.DataFrame({‘y_test’:y_test, ‘y_score’:y_score})

# 按y_score降序排列

target_data.sort_values(by = ‘y_score’, ascending = False, inplace = True)

# 自定义分位点

cuts = np.arange(0.1,1,0.1)

# 计算各分位点对应的Score值

index = len(target_data.y_score)*cuts

scores = target_data.y_score.iloc[index.astype(‘int’)]

# 根据不同的Score值，计算Sensitivity和Specificity

Sensitivity = []

Specificity = []

for score in scores:

# 正例覆盖样本数量与实际正例样本量

positive_recall = target_data.loc[(target_data.y_test == positive_flag) & (target_data.y_score>score),:].shape[0]

positive = sum(target_data.y_test == positive_flag)

# 负例覆盖样本数量与实际负例样本量

negative_recall = target_data.loc[(target_data.y_test != positive_flag) & (target_data.y_score<=score),:].shape[0]

negative = sum(target_data.y_test != positive_flag)

Sensitivity.append(positive_recall/positive)

Specificity.append(negative_recall/negative)

# 构建绘图数据

plot_data = pd.DataFrame({‘cuts’:cuts,’y1′:1-np.array(Specificity),’y2′:np.array(Sensitivity),

‘ks’:np.array(Sensitivity)-(1-np.array(Specificity))})

# 寻找Sensitivity和1-Specificity之差的最大值索引

max_ks_index = np.argmax(plot_data.ks)

plt.plot([0]+cuts.tolist()+[1], [0]+plot_data.y1.tolist()+[1], label = ‘1-Specificity’)

plt.plot([0]+cuts.tolist()+[1], [0]+plot_data.y2.tolist()+[1], label = ‘Sensitivity’)

# 添加参考线

plt.vlines(plot_data.cuts[max_ks_index], ymin = plot_data.y1[max_ks_index],

ymax = plot_data.y2[max_ks_index], linestyles = ‘–‘)

# 添加文本信息

plt.text(x = plot_data.cuts[max_ks_index]+0.01,

y = plot_data.y1[max_ks_index]+plot_data.ks[max_ks_index]/2,

s = ‘KS= %.2f’ %plot_data.ks[max_ks_index])

# 显示图例

plt.legend()

# 显示图形

plt.show()

# 调用自定义函数，绘制K-S曲线

plot_ks(y_test = y_test, y_score = y_score, positive_flag = 1)