python 打卡DAY27

##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

#聚类

from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering

from sklearn.preprocessing import StandardScaler

from sklearn.decomposition import PCA

from sklearn.manifold import TSNE

from sklearn.metrics import silhouette_score, calinski_harabasz_score, davies_bouldin_score

#3D可视化

from mpl_toolkits.mplot3d import Axes3D

import plotly.express as px

import plotly.graph_objects as go

# 导入 Pipeline 和相关预处理工具

from imblearn.over_sampling import SMOTE

from sklearn.pipeline import Pipeline # 用于创建机器学习工作流

from sklearn.compose import ColumnTransformer # 用于将不同的预处理应用于不同的列

from sklearn.preprocessing import OrdinalEncoder, OneHotEncoder, StandardScaler # 用于数据预处理（有序编码、独热编码、标准化）

from sklearn.impute import SimpleImputer # 用于处理缺失值

##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

#读取数据

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

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

y=data['Credit Default']

#定义pipeline相关定义&处理步骤

object_cols=x.select_dtypes(include=['object']).columns.tolist()

numeric_cols=x.select_dtypes(exclude=['object']).columns.tolist()

ordinal_features=['Years in current job']

ordinal_catagories=[['< 1 year', '1 year', '2 years', '3 years', '4 years', '5 years', '6 years', '7 years', '8 years', '9 years', '10+ years']] # Years in current job 的顺序 (对应1-11)

ordinal_transforms=Pipeline(steps=[

('imputer',SimpleImputer(strategy='most_frequent')),

('encoder',OrdinalEncoder(categories=ordinal_catagories,handle_unknown='use_encoded_value',unknown_value=-1))

])

print("有序特征处理 Pipeline 定义完成。")

nominal_features=['Home Ownership', 'Purpose', 'Term']

nominal_transformer=Pipeline(steps=[

('imputer',SimpleImputer(strategy='most_frequent')),

('onehot',OneHotEncoder(handle_unknown='ignore'))

])

print("标称特征处理 Pipeline 定义完成。")

continuous_cols=x.columns.difference(ordinal_features+nominal_features).tolist()

continuous_transformer=Pipeline(steps=[

('imputer',SimpleImputer(strategy='mean'))

])

print("连续特征处理 Pipeline 定义完成。")

# --- 构建 ColumnTransformer ---

preprocessor=ColumnTransformer(

transformers=[

('ordinal',ordinal_transforms,ordinal_features),

('nominal',nominal_transformer,nominal_features),

('continuous',continuous_transformer,continuous_cols)

],remainder='passthrough',verbose_feature_names_out=False

)

print("\nColumnTransformer (预处理器) 定义完成。")

pipeline=Pipeline(steps=[

('preprocessor',preprocessor)

])

print("\n完整的 Pipeline 定义完成。")

print("\n开始对原始数据进行预处理...")

start_time=time.time()

x_processed=pipeline.fit_transform(x)

end_time=time.time()

print(f"预处理完成，耗时: {end_time - start_time:.4f} 秒")

feature_names=preprocessor.get_feature_names_out()

x_processed_df=pd.DataFrame(x_processed,columns=feature_names)

print(x_processed_df.info())

#划分数据集

from sklearn.model_selection import train_test_split

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

#SMOTE(为了训练模型)

from imblearn.over_sampling import SMOTE

smote=SMOTE(random_state=42)

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

#标准化数据(为了聚类)

scaler=StandardScaler()

x_scaled=scaler.fit_transform(x_processed_df)

#kmeans++

k_range=(2,5)

inertia_value=[]

silhouette_scores=[]

ch_scores=[]

db_scores=[]

start_time=time.time()

for k in k_range:

kmeans=KMeans(n_clusters=k,random_state=42)

kmeans_label=kmeans.fit_predict(x_scaled)

inertia_value.append(kmeans.inertia_)

silhouette=silhouette_score(x_scaled,kmeans_label)

silhouette_scores.append(silhouette)

ch=calinski_harabasz_score(x_scaled,kmeans_label)

ch_scores.append(ch)

db=davies_bouldin_score(x_scaled,kmeans_label)

db_scores.append(db)

print(f'聚类分析耗时：{end_time-start_time:.4f}')

# #绘制评估指标图

# plt.figure(figsize=(12,6))

# ##肘部法则图

# plt.subplot(2,2,1)

# plt.plot(k_range,inertia_value,marker='o')

# plt.title('肘部法则确定最优聚类数 k(惯性，越小越好)')

# plt.xlabel('聚类数 (k)')

# plt.ylabel('惯性')

# plt.grid(True)

# ##轮廓系数图

# plt.subplot(2,2,2)

# plt.plot(k_range,silhouette_scores,marker='o',color='orange')

# plt.title('轮廓系数确定最优聚类数 k(越大越好)')

# plt.xlabel('聚类数 (k)')

# plt.ylabel('轮廓系数')

# plt.grid(True)

# #CH系数图

# plt.subplot(2,2,3)

# plt.plot(k_range,ch_scores,marker='o',color='yellow')

# plt.title('Calinski-Harabasz 指数确定最优聚类数 k(越大越好)')

# plt.xlabel('聚类数 (k)')

# plt.ylabel('CH 指数')

# plt.grid(True)

# ##DB系数图

# plt.subplot(2,2,4)

# plt.plot(k_range,db_scores,marker='o',color='red')

# plt.title('DB 指数确定最优聚类数 k(越小越好)')

# plt.xlabel('聚类数 (k)')

# plt.ylabel('DB 指数')

# plt.grid(True)

# plt.tight_layout()

# plt.show()

#选择K值进行聚类

selected_k=3

kmeans=KMeans(n_clusters=selected_k,random_state=42)

kmeans_label=kmeans.fit_predict(x_scaled)

x['KMeans_cluster']=kmeans_label

# ##PCA降维

# print(f"\n--- PCA 降维 ---")

# pca=PCA(n_components=3)

# x_pca=pca.fit_transform(x_scaled)

# ##聚类可视化

# plt.figure(figsize=(6,5))

# df_pca_2d=pd.DataFrame({

# 'x':x_pca[:,0],

# 'y':x_pca[:,1],

# 'cluster':kmeans_label})

# sample_size_2d=min(1000,len(df_pca_2d))

# df_sample_2d=df_pca_2d.sample(sample_size_2d,random_state=42)

# sns.scatterplot(

# x='x',y='y',

# hue='cluster',

# data=df_sample_2d,

# palette='viridis'

# )

# plt.title(f'KMean Clustering with k={selected_k} (PCA Visualization)')

# plt.xlabel('PCA Component 1')

# plt.ylabel('PCA Component 2')

# plt.show()

# ##3D可视化

# df_pca=pd.DataFrame(x_pca)

# df_pca['cluster']=x['KMeans_cluster']

# sample_size_3d=min(1000,len(df_pca))

# df_sample_3d=df_pca.sample(sample_size_3d,random_state=42)

# fig=px.scatter_3d(

# df_sample_3d,x=0,y=1,z=2,

# color='cluster',

# color_discrete_sequence=px.colors.qualitative.Bold,

# title='3D可视化'

# )

# fig.update_layout(

# scene=dict(

# xaxis_title='pca_0',

# yaxis_title='pca_1',

# zaxis_title='pca_2'

# ),

# width=1200,

# height=1000

# )

# fig.show()

# print(f"\n---t-SNE 降维 ---")

# n_component_tsne=3

# tsne=TSNE(

# n_components=n_component_tsne,

# perplexity=1000,

# n_iter=250,

# learning_rate='auto',

# random_state=42,

# n_jobs=-1

# )

# print("正在对训练集进行 t-SNE fit_transform...")

# start_time=time.time()

# x_tsne=tsne.fit_transform(x_scaled)

# end_time=time.time()

# print(f"训练集 t-SNE耗时: {end_time - start_time:.2f} 秒")

# # ##3D可视化

# # ##准备数据

# df_tsne=pd.DataFrame(x_tsne)

# df_tsne['cluster']=x['KMeans_cluster']

# fig=px.scatter_3d(

# df_tsne,x=0,y=1,z=2,

# color='cluster',

# color_discrete_sequence=px.colors.qualitative.Bold,

# title='T-SNE特征选择的3D可视化'

# )

# fig.update_layout(

# scene=dict(

# xaxis_title='tsne_0',

# yaxis_title='tsne_1',

# zaxis_title='tsne_2'

# ),

# width=1200,

# height=1000

# )

# fig.show()

##打印KMeans聚类前几行

print(f'KMeans Cluster labels(k={selected_k}added to x):')

print(x[['KMeans_cluster']].value_counts())

# # #SHAP分析

# start_time=time.time()

# rf1_model=RandomForestClassifier(random_state=42,class_weight='balanced')

# rf1_model.fit(x_train_smote,y_train_smote)

# explainer=shap.TreeExplainer(rf1_model)

# shap_value=explainer.shap_values(x_processed_df)

# print(shap_value.shape)

# end_time=time.time()

# print(f'SHAP分析耗时:{end_time-start_time:.4f}')

# # --- 1. SHAP 特征重要性蜂巢图 (Summary Plot - violin) ---

# print("--- 1. SHAP 特征重要性蜂巢图 ---")

# shap.summary_plot(shap_value[:,:,0],x_processed_df,plot_type='violin',show=False)

# plt.title('shap feature importance (bar plot)')

# plt.tight_layout()

# plt.show()

selected_features=['Credit Score','Current Loan Amount','Annual Income','Term_Long Term']

# fig,axes=plt.subplots(2,2,figsize=(10,8))

# axes=axes.flatten()

# for i,feature in enumerate(selected_features):

# unique_count=x_processed_df[feature].nunique()

# if unique_count<10:

# sns.countplot(x=x_processed_df[feature],ax=axes[i])

# axes[i].set_title(f'countplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('count')

# else:

# sns.histplot(x=x_processed_df[feature],ax=axes[i])

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('frequency')

# plt.tight_layout()

# plt.show()

print(x[['KMeans_cluster']].value_counts())

x_cluster0=x_processed_df[x['KMeans_cluster']==0]

x_cluster1=x_processed_df[x['KMeans_cluster']==1]

x_cluster2=x_processed_df[x['KMeans_cluster']==2]

# ##簇0

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

# axes=axes.flatten()

# for i,feature in enumerate(selected_features):

# unique_count=x_cluster0[feature].nunique()

# if unique_count<10:

# sns.countplot(x=x_cluster0[feature],ax=axes[i])

# axes[i].set_title(f'countplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('count')

# else:

# sns.histplot(x=x_cluster0[feature],ax=axes[i])

# axes[i].set_title(f'histplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('frequence')

# plt.tight_layout()

# plt.show()

# #簇1

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

# axes=axes.flatten()

# for i,feature in enumerate(selected_features):

# unique_count=x_cluster1[feature].nunique()

# if unique_count<10:

# sns.countplot(x=x_cluster1[feature],ax=axes[i])

# axes[i].set_title(f'countplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('count')

# else:

# sns.histplot(x=x_cluster1[feature],ax=axes[i])

# axes[i].set_title(f'histplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('frequence')

# plt.tight_layout()

# plt.show()

# #簇2

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

# axes=axes.flatten()

# for i,feature in enumerate(selected_features):

# unique_count=x_cluster0[feature].nunique()

# if unique_count<10:

# sns.countplot(x=x_cluster2[feature],ax=axes[i])

# axes[i].set_title(f'countplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('count')

# else:

# sns.histplot(x=x_cluster2[feature],ax=axes[i])

# axes[i].set_title(f'histplot of {feature}')

# axes[i].set_xlabel(feature)

# axes[i].set_ylabel('count')

# plt.tight_layout()

# plt.show()

print("--- 递归特征消除 (RFE) ---")

from sklearn.feature_selection import RFE

start_time=time.time()

base_model=xgb.XGBClassifier(random_state=42,class_weight='balanced')

rfe=RFE(base_model,n_features_to_select=3)

rfe.fit(x_train_smote,y_train_smote)

x_train_rfe=rfe.transform(x_train_smote)

x_test_rfe=rfe.transform(x_test)

selected_features_rfe=x_train.columns[rfe.support_]

print(f"RFE筛选后保留的特征数量: {len(selected_features_rfe)}")

print(f"保留的特征: {selected_features_rfe}")

end_time=time.time()

print(f'RFE分析耗时:{end_time-start_time:.4f}')

##3D可视化

x_selected=x_processed_df[selected_features_rfe]

df_viz=pd.DataFrame(x_selected)

df_viz['cluster']=x['KMeans_cluster']

fig=px.scatter_3d(

df_viz,

x=selected_features_rfe[0],

y=selected_features_rfe[1],

z=selected_features_rfe[2],

color='cluster',

color_discrete_sequence=px.colors.qualitative.Bold,

title='RFE特征选择的3D可视化'

)

fig.update_layout(

scene=dict(

xaxis_title=selected_features_rfe[0],

yaxis_title=selected_features_rfe[1],

zaxis_title=selected_features_rfe[2]

),

width=1200,

height=1000

)

fig.show()

##训练XGBOOST模型

xgb_model_rfe=xgb.XGBClassifier(random_state=42,class_weight='balanced')

xgb_model_rfe.fit(x_train_rfe,y_train_smote)

xgb_pred_rfe=xgb_model_rfe.predict(x_test_rfe)

print("\nRFE筛选后XGBOOST在测试集上的分类报告:")

print(classification_report(y_test, xgb_pred_rfe))

print("RFE筛选后XGBOOST在测试集上的混淆矩阵:")

print(confusion_matrix(y_test, xgb_pred_rfe))

# def outer():

# def inner():

# print('aaaa')

# return inner

# f=outer()

# print(f())

# def chocolate(func):

# print("🍫 [1] 巧克力包装机准备好了！") # 装饰器定义时立即执行这句

# def wrapper():

# print("🍫 [2] 开始包装蛋糕（外壳）")

# func() # 原始蛋糕制作

# print("🎁 [3] 包装完成，可以出售了")

# return wrapper # 返回 wrapper 替代原函数

# @chocolate # 在定义阶段就会触发 chocolate(make_cake)

# def make_cake():

# print("🎂 [ 中间 ] 蛋糕正在烘焙...")

# print("\n🟢 [4] 现在开始执行 make_cake()：\n")

# print(make_cake())

# import time

# def display_time(func):

# def wrapper():

# start_time=time.time()

# func()

# end_time=time.time()

# print(f"执行时间: {end_time - start_time} 秒")

# return wrapper

# def is_prime(num):

# if num<2:

# return False

# elif num==2:

# return True

# else:

# for i in range(2,num):

# if num%i==0:

# return False

# return True

# @display_time

# def prime_nums():

# for i in range(2,99999):

# if is_prime(i):

# # print(i)

# continue

# print(prime_nums())

# def logger(func):

# def wrapper(*args,**kwargs):

# print(f'开始执行函数{func.__name__},参数:{args},{kwargs}')

# result=func(*args,**kwargs)

# print(f'函数{func.__name__}执行完毕,返回值:{result}')

# return result

# return wrapper

# @logger

# def multiply(a,b):

# return a*b

# print(multiply(2,3))

# def class_logger(cls):

# original_init=cls.__init__

# def new_init(self,*args,**kwargs):

# print(f'[LOG]实例化对象:{cls.__name__}')

# original_init(self,*args,**kwargs)

# cls.__init__=new_init

# def log_message(self,message):

# print(f'[LOG]{message}')

# cls.log=log_message

# return cls

# @class_logger

# class SimplePrinter:

# def __init__(self,name):

# self.name=name

# def print_text(self,text):

# print(f'{self.name}:{text}')

# printer=SimplePrinter('Alice')

# printer.print_text('hello wrold')

# printer.log('这是装饰器添加的日志方法')

import pandas as pd

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestClassifier

iris=load_iris()

df=pd.DataFrame(iris.data,columns=iris.feature_names)

df['target']=iris.target

features=iris.feature_names

target='target'

x_train,x_test,y_train,y_test=train_test_split(df[features],df[target],test_size=0.2,random_state=42)

model=RandomForestClassifier(n_estimators=100,random_state=42)

model.fit(x_train,y_train)

import pdpbox

from pdpbox.info_plots import TargetPlot

print(pdpbox.__version__)

feature='petal length (cm)'

feature_name=feature

target_plot=TargetPlot(

df=df,

feature=feature,

feature_name=feature_name,

target='target',

grid_type='percentile',

num_grid_points=10

)

# print(target_plot.plot())

# print(type(target_plot.plot()))

# print(target_plot.plot()[0])

fig,axes,summary_df=target_plot.plot(

which_classes=None,

show_percentile=True,

engine='plotly',

template='plotly_white'

)

fig.update_layout(

width=800,

height=500,

title=dict(text=f'Target Plot:{feature_name}',x=0.5)

)

fig.show()