#!/usr/bin/env python3

# -*- coding: utf-8 -*-

"""

Created on Sun Feb 26 15:36:18 2023

@author: ming

"""

#import packages

from sklearn.metrics import precision_score

import xgboost as xgb

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from matplotlib.colors import ListedColormap

from sklearn.preprocessing import LabelEncoder

from sklearn.metrics import classification_report

from sklearn.model_selection import GridSearchCV #网格搜索

import matplotlib.pyplot as plt#可视化

import seaborn as sns#绘图包

from sklearn.model_selection import train_test_split

# import data

X=pd.read_csv(r"/Users/ming/Downloads/Xset3.csv")

Y=pd.read_csv(r"/Users/ming/Downloads/Y.csv")

from imblearn.over_sampling import RandomOverSampler

ros = RandomOverSampler(random_state=0)

X_resampled, y_resampled = ros.fit_resample(X, Y)

X_resampled.info()

# split data

trainX, testX, trainY, testY = train_test_split(X_resampled, y_resampled, random_state=3, test_size=0.2)

model=xgb.XGBClassifier()

# 训练模型

model.fit(trainX,trainY)

# 预测值

y_pred = model.predict(testX)

#评估指标

# 求出预测和真实一样的数目

true = np.sum(y_pred == testY.values.tolist())

print('the right number of prediction：', true)

print('预测错的的结果数目为：', testY.shape[0]-true)

# 评估指标

from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,cohen_kappa_score

print('预测数据的准确率为： {:.4}%'.format(accuracy_score(testY,y_pred)*100))

print('预测数据的精确率为：{:.4}%'.format(

      precision_score(testY,y_pred)*100))

print('预测数据的召回率为：{:.4}%'.format(

      recall_score(testY,y_pred)*100))

# print("训练数据的F1值为：", f1score_train)

print('预测数据的F1值为：',

      f1_score(testY,y_pred))

print('预测数据的Cohen’s Kappa系数为：',

      cohen_kappa_score(testY,y_pred))

# 打印分类报告

print('the evaluation report：',

      classification_report(testY,y_pred))

from xgboost import plot_importance

# plt.figure(figsize=(15,15))

plt.rcParams["figure.figsize"] = (14, 8)

plot_importance(model)

# ROC曲线、AUC

from sklearn.metrics import precision_recall_curve

from sklearn import metrics

# 预测正例的概率

y_pred_prob=model.predict_proba(testX)[:,1]

# y_pred_prob ,返回两列，第一列代表类别0,第二列代表类别1的概率

fpr, tpr, thresholds = metrics.roc_curve(testY,y_pred_prob, pos_label=1)

#pos_label，代表真阳性标签，就是说是分类里面的好的标签，这个要看你的特征目标标签是0,1，还是1,2

roc_auc = metrics.auc(fpr, tpr)  #auc为Roc曲线下的面积

# print(roc_auc)

plt.figure(figsize=(8,6))

plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')

plt.plot(fpr, tpr, 'r',label='AUC = %0.2f'% roc_auc)

plt.legend(loc='lower right')

# plt.plot([0, 1], [0, 1], 'r--')

plt.xlim([0, 1.1])

plt.ylim([0, 1.1])

plt.xlabel('False Positive Rate') #横坐标是fpr

plt.ylabel('True Positive Rate')  #纵坐标是tpr

plt.title('Receiver operating characteristic example')

plt.show()

y_pred_prob1=model.predict_proba(X)[:,1]

y_pred1=model.predict(X)

#5-fold cross validation

from sklearn.model_selection import cross_val_score

scores = cross_val_score(model, X_resampled, y_resampled, cv=10)

print("%0.2f accuracy with a standard deviation of %0.2f" % (scores.mean(), scores.std()))