python打卡DAY5

于 2025-05-11 00:10:39 发布
阅读量304 收藏 5
点赞数 5
CC 4.0 BY-SA版权
文章标签： python 开发语言
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.youkuaiyun.com/Bugabooo/article/details/147861511

##注入所需库

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

import random

import numpy as np

import time

import shap

from sklearn.svm import SVC #支持向量机分类器

# from sklearn.neighbors import KNeighborsClassifier #K近邻分类器

# from sklearn.linear_model import LogisticRegression #逻辑回归分类器

import xgboost as xgb #XGBoost分类器

import lightgbm as lgb #LightGBM分类器

from sklearn.ensemble import RandomForestClassifier #随机森林分类器

# from catboost import CatBoostClassifier #CatBoost分类器

# from sklearn.tree import DecisionTreeClassifier #决策树分类器

# from sklearn.naive_bayes import GaussianNB #高斯朴素贝叶斯分类器

from skopt import BayesSearchCV

from skopt.space import Integer

from deap import base, creator, tools, algorithms

from sklearn.model_selection import StratifiedKFold, cross_validate # 引入分层 K 折和交叉验证工具

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score # 用于评估分类器性能的指标

from sklearn.metrics import classification_report, confusion_matrix #用于生成分类报告和混淆矩阵

from sklearn.metrics import make_scorer#定义函数

import warnings #用于忽略警告信息

warnings.filterwarnings("ignore") # 忽略所有警告信息

#设置中文字体&负号正确显示

plt.rcParams['font.sans-serif']=['STHeiti']

plt.rcParams['axes.unicode_minus']=True

plt.rcParams['figure.dpi']=100

#查看基本信息&读取数据

data=pd.read_csv(r'data.csv')

print(f'{data.info()}\n{data.isnull().sum()}\n{data.head()}\n{data.columns}')

#绘制图像

# plt.figure(figsize=(6,4))

# sns.boxplot(x=data['Annual Income'])

# plt.title('年收入箱线图')

# plt.xlabel('年收入')

# plt.tight_layout()

# plt.show()

# plt.figure(figsize=(6,4))

# sns.boxenplot(x='Credit Default',y='Annual Income',data=data)

# plt.title('年收入分类箱线图')

# plt.xlabel('是否欠款')

# plt.ylabel('金额')

# plt.xticks([0,1],['n','y'])

# plt.tight_layout()

# plt.show()

# plt.figure(figsize=(6,4))

# sns.histplot(

# x='Annual Income',

# hue='Credit Default',

# hue_order=(0,1),

# data=data,

# element='bars',

# kde=True

# )

# plt.title('年收入直方图')

# plt.xlabel('年收入')

# plt.ylabel('金额')

# plt.tight_layout()

# plt.show()

#数据填补

for i in data.columns:

if data[i].dtype!='object':

if data[i].isnull().sum()>0:

data[i].fillna(data[i].mean(),inplace=True)

else:

if data[i].isnull().sum()>0:

data[i].fillna(data[i].mode()[0],inplace=True)

print(f'{data.isnull().sum()}\n{data.info()}')

#数据编码

mapping={'10+ years':0,

'9 years':1,

'8 years':2,

'7 years':3,

'6 years':4,

'5 years':5,

'4 years':6,

'3 years':7,

'2 years':8,

'1 year':9,

'< 1 year':10}

data['Years in current job']=data['Years in current job'].map(mapping)

dummies_list=[]

data2=pd.read_csv(r'data.csv')

data=pd.get_dummies(data=data,drop_first=True)

for i in data.columns:

if i not in data2.columns:

dummies_list.append(i)

for i in dummies_list:

data[i]=data[i].astype(int)

print(f'{data.info()}\n{data.columns}')

#绘制相关热力图

# continuous_list=['Annual Income', 'Years in current job',

# 'Number of Open Accounts', 'Years of Credit History',

# 'Maximum Open Credit', 'Number of Credit Problems',

# 'Months since last delinquent', 'Current Loan Amount',

# 'Current Credit Balance', 'Monthly Debt', 'Credit Score']

# correlation_matrix=data[continuous_list].corr()

# plt.figure(figsize=(12,10))

# sns.heatmap(correlation_matrix,annot=True,cmap='coolwarm',vmin=-1,vmax=1)

# plt.title('相关热力图')

# plt.xticks(rotation=45,ha='right')

# plt.tight_layout()

# plt.show()

# #绘制箱线图子图

features=['Annual Income','Years in current job','Tax Liens','Number of Open Accounts']

# fig,axes=plt.subplots(2,2,figsize=(6,4))

# for i,feature in enumerate(features):

# row,col=i//2,i%2

# axes[row,col].boxplot(data[features])

# axes[row,col].set_title(f'box of {feature}')

# axes[row,col].set_ylabel(feature)

# plt.tight_layout()

# plt.show()

#分类箱线图

# fig,axes=plt.subplots(2,2,figsize=(6,4))

# for i,feature in enumerate(features):

# row,col=i//2,i%2

# sns.boxplot(

# x='Credit Default',

# y=feature,

# data=data,

# ax=axes[row,col]

# )

# axes[row,col].set_title(f'box of {feature}')

# axes[row,col].set_xticks([0,1],['n','y'])

# axes[row,col].set_xlabel(feature)

# axes[row,col].set_ylabel('count')

# plt.tight_layout()

# plt.tight_layout()

# plt.show()

# #分类直方图子图

# fig,axes=plt.subplots(2,2,figsize=(6,4))

# for i,feature in enumerate(features):

# row,col=i//2,i%2

# sns.histplot(

# x=feature,

# hue='Credit Default',

# hue_order=[0,1],

# kde=True,

# element='bars',

# data=data,

# ax=axes[row,col]

# )

# axes[row,col].set_title('分类直方图')

# axes[row,col].set_xlabel(feature)

# axes[row,col].set_ylabel('count')

# plt.tight_layout()

# plt.show()

from sklearn.model_selection import train_test_split

x=data.drop('Credit Default',axis=1)

y=data['Credit Default']

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=42)

print(f'train:{x_train.shape}\ntest:{x_test.shape}')

# #SVM

# print("--- 1. 默认参数SVM (训练集 -> 测试集) ---")

# start_time=time.time()

# svm_model=SVC(random_state=42,class_weight='balanced')

# svm_model.fit(x_train,y_train)

# svm_pred=svm_model.predict(x_test)

# end_time=time.time()

# print(f'训练与预测耗时:{end_time-start_time:.4f}')

# print('\nSVM分类报告')

# print(classification_report(y_test,svm_pred))

# print('\nSVM混淆矩阵')

# print(confusion_matrix(y_test,svm_pred))

# #randomforrest

# print("--- 1. 默认参数随机森林 (训练集 -> 测试集) ---")

# start_time=time.time()

# rf_model=RandomForestClassifier(random_state=42,class_weight='balanced')

# rf_model.fit(x_train,y_train)

# rf_pred=rf_model.predict(x_test)

# end_time=time.time()

# print(f'训练与预测耗时:{end_time - start_time:.4f}')

# print('\n随机森林分类报告')

# print(classification_report(y_test,rf_pred))

# print('\n随机森林混淆矩阵')

# print(confusion_matrix(y_test,rf_pred))

#定义约登指数

def youden_score(y_true,y_pred):

tn,fp,fn,tp=confusion_matrix(y_true,y_pred).ravel()

sensitivity=tp/(tp+fn)

specificity=tn/(tn+fp)

return sensitivity+specificity-1

youden_scorer=make_scorer(youden_score)

# # # #SMOTE过采样后带权重网格搜索优化的随机森林

# #SMOTE

# from imblearn.over_sampling import SMOTE

# smote=SMOTE(random_state=42)

# x_train_smote,y_train_smote=smote.fit_resample(x_train,y_train)

# #网格搜索&交叉验证

# from sklearn.model_selection import GridSearchCV

# cv_strategy=StratifiedKFold(n_splits=5,shuffle=True,random_state=42)

# param_grid={

# 'n_estimators':[5,10,15],

# 'max_depth':[None,5,10],

# 'min_samples_split':[2,3,4],

# 'min_samples_leaf':[2,3,4]

# }

# grid_search=GridSearchCV(

# estimator=RandomForestClassifier(random_state=42,class_weight='balanced'),

# param_grid=param_grid,

# cv=cv_strategy,

# n_jobs=-1,

# scoring=youden_score

# )

# start_time=time.time()

# grid_search.fit(x_train_smote,y_train_smote)

# end_time=time.time()

# best_model=grid_search.best_estimator_

# best_pred=best_model.predict(x_test)

# print(f'网格搜索耗时:{end_time-start_time:.4f}秒')

# print('最佳参数:',grid_search.best_params_)

# print('\n带权重网格搜索优化后的随机森林在测试集上的分类报告')

# print(classification_report(y_test,best_pred))

# print('网格搜索优化后的随机森林在测试集上的混淆矩阵')

# print(confusion_matrix(y_test,best_pred))

#SMOTE过采样后带权重的贝叶斯优化的随机森林

#SMOTE过采样

from imblearn.over_sampling import SMOTE

smote=SMOTE(random_state=42)

x_train_smote,y_train_smote=smote.fit_resample(x_train,y_train)

#贝叶斯优化&交叉验证

from sklearn.model_selection import GridSearchCV

cv_strategy=StratifiedKFold(n_splits=5,shuffle=True,random_state=42)

search_space={

'n_estimators':Integer(1,5),

'max_depth':Integer(1,5),

'min_samples_split':Integer(2,6),

'min_samples_leaf':Integer(1,5)

}

bayes_search=BayesSearchCV(

estimator=RandomForestClassifier(random_state=42,class_weight='balanced'),

search_spaces=search_space,

n_iter=5,

cv=cv_strategy,

n_jobs=-1,

scoring=youden_scorer

)

start_time=time.time()

bayes_search.fit(x_train_smote,y_train_smote)

end_time=time.time()

best_model=bayes_search.best_estimator_

best_pred=best_model.predict(x_test)

print(f'贝叶斯优化耗时:{end_time-start_time:.4f}秒')

print('最佳参数',bayes_search.best_params_)

print('\n贝叶斯优化后的随机森林在测试集上的分类报告')

print(classification_report(y_test,best_pred))

print('\n贝叶斯优化后的随机森林在测试集上的混淆矩阵')

print(confusion_matrix(y_test,best_pred))

#shap分析

start_time=time.time()

explainer=shap.TreeExplainer(best_model)

shap_values=explainer.shap_values(x_test)

end_time=time.time()

print(f"shap分析耗时: {end_time - start_time:.4f} 秒")

print('shap_value shape:',shap_values.shape)

print('shap_values[0]shape:',shap_values[0].shape)

print('shape_values[:,:,0]shape',shap_values[:,:,0].shape)

print('x_test shape:',x_test.shape)

# # SHAP 特征重要性条形图 (Summary Plot - bar)

# print("--- 2. SHAP 特征重要性条形图 ---")

# shap.summary_plot(shap_values[:,:,0],x_test,plot_type='bar',show=False)

# plt.title('SHAP特征重要性条形图')

# plt.tight_layout()

# plt.show()

#SHAP特征重要性蜂巢图

print("--- 2. SHAP 特征重要性蜂巢图 ---")

shap.summary_plot(shap_values[:,:,0],x_test,plot_type='violin',show=False)

plt.title('SHAP特征重要性蜂窝图')

plt.tight_layout()

plt.show()

Bugabooo
关注
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值