为我提供TPR、FPR、K1、ROC、AUC、KS、GAIN、LIFT、GINI、KSI的函数代码

这些指标函数的代码可以在不同的编程语言中实现，下面是Python中的代码示例：

1. TPR (True Positive Rate) 和 FPR (False Positive Rate)：

from sklearn.metrics import confusion_matrix

def tpr_fpr(y_true, y_pred):
    tn, fp, fn, tp = confusion_matrix(y_true, y_pred).ravel()
    tpr = tp / (tp + fn)
    fpr = fp / (fp + tn)
    return tpr, fpr

2. K1 (Kappa)：

from sklearn.metrics import cohen_kappa_score

def kappa(y_true, y_pred):
    return cohen_kappa_score(y_true, y_pred)

3. ROC (Receiver Operating Characteristic) 和 AUC (Area Under the Curve)：

from sklearn.metrics import roc_curve, auc

def roc_auc(y_true, y_pred_prob):
    fpr, tpr, thresholds = roc_curve(y_true, y_pred_prob)
    roc_auc = auc(fpr, tpr)
    return roc_auc

4. KS (Kolmogorov-Smirnov)：

from scipy.stats import ks_2samp

def ks(y_true, y_pred_prob):
    tpr_fpr_df = pd.DataFrame({'y_true': y_true, 'y_pred_prob': y_pred_prob})
    p0 = tpr_fpr_df[tpr_fpr_df.y_true == 0].y_pred_prob
    p1 = tpr_fpr_df[tpr_fpr_df.y_true == 1].y_pred_prob
    ks_statistic, p_value = ks_2samp(p0, p1)
    return ks_statistic

5. GAIN：

import numpy as np

def gain(y_true, y_pred_prob, n_bins=10):
    df = pd.DataFrame({'y_true': y_true, 'y_pred_prob': y_pred_prob})
    df['y_true'] = df['y_true'].astype(int)
    df['n'] = 1
    df['decile'] = pd.qcut(df['y_pred_prob'], n_bins)
    grouped = df.groupby('decile', as_index=False)
    agg_df = grouped.agg({'y_true': np.sum, 'n': np.sum})
    agg_df['pct_total'] = agg_df['n'] / agg_df['n'].sum()
    agg_df['pct_pos'] = agg_df['y_true'] / agg_df['y_true'].sum()
    agg_df['cum_pct_total'] = agg_df['pct_total'].cumsum()
    agg_df['cum_pct_pos'] = agg_df['pct_pos'].cumsum()
    agg_df['cum_pct_neg'] = agg_df['cum_pct_total'] - agg_df['cum_pct_pos']
    agg_df['lift'] = agg_df['cum_pct_pos'] / agg_df['pct_total'].mean()
    agg_df['gain'] = agg_df['cum_pct_pos'] / agg_df['cum_pct_pos'].max()
    return agg_df[['decile', 'pct_total', 'pct_pos', 'cum_pct_pos', 'cum_pct_neg', 'lift', 'gain']]

6. LIFT：

import numpy as np

def lift(y_true, y_pred_prob, n_bins=10):
    df = pd.DataFrame({'y_true': y_true, 'y_pred_prob': y_pred_prob})
    df['y_true'] = df['y_true'].astype(int)
    df['n'] = 1
    df['decile'] = pd.qcut(df['y_pred_prob'], n_bins)
    grouped = df.groupby('decile', as_index=False)
    agg_df = grouped.agg({'y_true': np.sum, 'n': np.sum})
    agg_df['pct_total'] = agg_df['n'] / agg_df['n'].sum()
    agg_df['pct_pos'] = agg_df['y_true'] / agg_df['y_true'].sum()
    agg_df['cum_pct_total'] = agg_df['pct_total'].cumsum()
    agg_df['cum_pct_pos'] = agg_df['pct_pos'].cumsum()
    base_pos_rate = agg_df.y_true.sum() / len(df)
    lift_series = agg_df.cum_pct_pos / (agg_df.cum_pct_total * base_pos_rate)
    return lift_series

7. GINI：

from sklearn.metrics import roc_curve

def gini(y_true, y_pred_prob):
    fpr, tpr, thresholds = roc_curve(y_true, y_pred_prob)
    auc_score = auc(fpr, tpr)
    gini_coefficient = 2 * auc_score - 1
    return gini_coefficient

8. KSI：

from scipy.stats import norm

def ksi(y_true_train, y_pred_prob_train, y_true_test, y_pred_prob_test):
    mu_train, std_train = norm.fit(y_pred_prob_train)
    mu_test, std_test = norm.fit(y_pred_prob_test)

    cdf_train_train = norm.cdf(y_pred_prob_train, loc=mu_train, scale=std_train)
    cdf_train_test = norm.cdf(y_pred_prob_test, loc=mu_train, scale=std_train)
    
    cdf_test_test = norm.cdf(y_pred_prob_test, loc=mu_test, scale=std_test)
    
    ksi_train = np.abs((cdf_train_train - cdf_train_test).mean())
    ksi_test = np.abs((cdf_test_test - cdf_train_test).mean())
    
    return ksi_train, ksi_test