基于LightGBM的UCI信贷数据建模（完整Python代码）

import pandas as pd 
import numpy as np
pd.set_option('display.max_columns', 100)
from IPython.display import display_html


import plotly_express as px
import plotly.graph_objects as go

import matplotlib
import matplotlib.pyplot as plt
plt.rcParams["font.sans-serif"]=["SimHei"] # 设置字体
plt.rcParams["axes.unicode_minus"]=False # 解决“-”负号的乱码问题

import seaborn as sns
%matplotlib inline 

import missingno as ms 
import gc

from datetime import datetime 
from sklearn.model_selection import train_test_split,StratifiedKFold,GridSearchCV
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.decomposition import PCA
from imblearn.under_sampling import ClusterCentroids
from imblearn.over_sampling import KMeansSMOTE, SMOTE
from sklearn.model_selection import KFold

from sklearn.metrics import accuracy_score, recall_score, precision_score, f1_score, auc
from sklearn.metrics import roc_auc_score,precision_recall_curve, confusion_matrix,classification_report

# Classifiers
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn import tree
from pydotplus import graph_from_dot_data
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier
from catboost import CatBoostClassifier
import lightgbm as lgb
import xgboost as xgb

from scipy import stats

import warnings 
warnings.filterwarnings("ignore")

df = pd.read_csv("UCI.csv")

df.head()

df.shape

(30000, 25)

df.columns  # 全部的字段名

Index(['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0',
       'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2',
       'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1',
       'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6',
       'default.payment.next.month'],
      dtype='object')

df.dtypes

ID                              int64
LIMIT_BAL                     float64
SEX                             int64
EDUCATION                       int64
MARRIAGE                        int64
AGE                             int64
PAY_0                           int64
PAY_2                           int64
PAY_3                           int64
PAY_4                           int64
PAY_5                           int64
PAY_6                           int64
BILL_AMT1                     float64
BILL_AMT2                     float64
BILL_AMT3                     float64
BILL_AMT4                     float64
BILL_AMT5                     float64
BILL_AMT6                     float64
PAY_AMT1                      float64
PAY_AMT2                      float64
PAY_AMT3                      float64
PAY_AMT4                      float64
PAY_AMT5                      float64
PAY_AMT6                      float64
default.payment.next.month      int64
dtype: object

pd.value_counts(df.dtypes)  # 统计不同类型的个数

float64    13
int64      12
Name: count, dtype: int64

df.describe().T  # 字段较多，转置后显示更直观  

df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 30000 entries, 0 to 29999
Data columns (total 25 columns):
 #   Column                      Non-Null Count  Dtype  
---  ------                      --------------  -----  
 0   ID                          30000 non-null  int64  
 1   LIMIT_BAL                   30000 non-null  float64
 2   SEX                         30000 non-null  int64  
 3   EDUCATION                   30000 non-null  int64  
 4   MARRIAGE                    30000 non-null  int64  
 5   AGE                         30000 non-null  int64  
 6   PAY_0                       30000 non-null  int64  
 7   PAY_2                       30000 non-null  int64  
 8   PAY_3                       30000 non-null  int64  
 9   PAY_4                       30000 non-null  int64  
 10  PAY_5                       30000 non-null  int64  
 11  PAY_6                       30000 non-null  int64  
 12  BILL_AMT1                   30000 non-null  float64
 13  BILL_AMT2                   30000 non-null  float64
 14  BILL_AMT3                   30000 non-null  float64
 15  BILL_AMT4                   30000 non-null  float64
 16  BILL_AMT5                   30000 non-null  float64
 17  BILL_AMT6                   30000 non-null  float64
 18  PAY_AMT1                    30000 non-null  float64
 19  PAY_AMT2                    30000 non-null  float64
 20  PAY_AMT3                    30000 non-null  float64
 21  PAY_AMT4                    30000 non-null  float64
 22  PAY_AMT5                    30000 non-null  float64
 23  PAY_AMT6                    30000 non-null  float64
 24  default.payment.next.month  30000 non-null  int64  
dtypes: float64(13), int64(12)
memory usage: 5.7 MB

df.rename(columns={"default.payment.next.month":"Label"},inplace=True)

df.isnull().sum().sort_values(ascending=False)

ID           0
BILL_AMT2    0
PAY_AMT6     0
PAY_AMT5     0
PAY_AMT4     0
PAY_AMT3     0
PAY_AMT2     0
PAY_AMT1     0
BILL_AMT6    0
BILL_AMT5    0
BILL_AMT4    0
BILL_AMT3    0
BILL_AMT1    0
LIMIT_BAL    0
PAY_6        0
PAY_5        0
PAY_4        0
PAY_3        0
PAY_2        0
PAY_0        0
AGE          0
MARRIAGE     0
EDUCATION    0
SEX          0
Label        0
dtype: int64

# 缺失值个数
total = df.isnull().sum().sort_values(ascending=False)

# 缺失值比例
percent = (df.isnull().sum() / df.isnull().count() * 100).sort_values(ascending=False) 

percent

ID           0.0
BILL_AMT2    0.0
PAY_AMT6     0.0
PAY_AMT5     0.0
PAY_AMT4     0.0
PAY_AMT3     0.0
PAY_AMT2     0.0
PAY_AMT1     0.0
BILL_AMT6    0.0
BILL_AMT5    0.0
BILL_AMT4    0.0
BILL_AMT3    0.0
BILL_AMT1    0.0
LIMIT_BAL    0.0
PAY_6        0.0
PAY_5        0.0
PAY_4        0.0
PAY_3        0.0
PAY_2        0.0
PAY_0        0.0
AGE          0.0
MARRIAGE     0.0
EDUCATION    0.0
SEX          0.0
Label        0.0
dtype: float64

pd.concat([total, percent],axis=1,keys=["Total","Percent"]).T

ms.bar(df,color="blue")                                                     

plt.show()

# ms.matrix(df, labels=True,label_rotation=45)
# plt.show()

df.columns

Index(['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0',
       'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2',
       'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1',
       'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6', 'Label'],
      dtype='object')

df.drop("ID",inplace=True,axis=1) 

df[['LIMIT_BAL', 'EDUCATION', 'MARRIAGE', 'AGE']].describe()

df["EDUCATION"].value_counts().sort_values(ascending=False)

EDUCATION
2    14030
1    10585
3     4917
5      280
4      123
6       51
0       14
Name: count, dtype: int64

df["MARRIAGE"].value_counts().sort_values(ascending=False)        

MARRIAGE
2    15964
1    13659
3      323
0       54
Name: count, dtype: int64

df["LIMIT_BAL"].value_counts().sort_values(ascending=False)

LIMIT_BAL
50000.0      3365
20000.0      1976
30000.0      1610
80000.0      1567
200000.0     1528
             ... 
800000.0        2
1000000.0       1
327680.0        1
760000.0        1
690000.0        1
Name: count, Length: 81, dtype: int64

plt.figure(figsize = (14,6))
plt.title('Density Plot of LIMIT_BAL')

sns.set_color_codes("pastel")
sns.distplot(df['LIMIT_BAL'],kde=True,bins=200)

plt.show()  

df[["PAY_0","PAY_2","PAY_3","PAY_4","PAY_5","PAY_6"]].describe()

repay = df[['PAY_0', 'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'Label']]

repay = pd.melt(repay, 
                id_vars="Label",
                var_name="Payment Status",
                value_name="Delay(Month)"
               )
repay.head()

fig = px.box(repay, x="Payment Status", y="Delay(Month)",color="Label")

fig.show()

df[['BILL_AMT1', 'BILL_AMT2', 'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6']].describe()

df.columns

Index(['LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0', 'PAY_2',
       'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2',
       'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1',
       'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6', 'Label'],
      dtype='object')

BILL_AMTS = ['BILL_AMT1', 'BILL_AMT2', 'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6']

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

for i, col in enumerate(BILL_AMTS):
    plt.subplot(2,3,i+1)
    sns.kdeplot(df.loc[(df["Label"] == 0),col], label="NO DEFAULT", color="red",shade=True)
    sns.kdeplot(df.loc[(df["Label"] == 1),col], label="DEFAULT", color="blue",shade=True)
    
    plt.xlim(-40000, 200000)
    plt.ylabel("")
    plt.xlabel(col, fontsize=12)
    plt.legend()
    plt.tight_layout()
    
plt.show()

df[['PAY_AMT1', 'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6']].describe()

PAY_AMTS = ['PAY_AMT1', 'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6']

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

for i, col in enumerate(PAY_AMTS):
    plt.subplot(2,3,i+1)
    sns.kdeplot(df.loc[(df["Label"] == 0),col], label="NO DEFAULT", color="red", shade=True)
    sns.kdeplot(df.loc[(df["Label"] == 1),col], label="DEFAULT", color="blue", shade=True)
    
    plt.xlim(-10000, 70000)
    plt.ylabel("")
    plt.xlabel(col, fontsize=12)
    plt.legend()
    plt.tight_layout()
    
plt.show()

df["Label"].value_counts()

Label
0    23364
1     6636
Name: count, dtype: int64

label = df["Label"].value_counts()
df_label = pd.DataFrame(label).reset_index()  

df_label

# plt.figure(figsize = (6,6))
# plt.title('Default = 0 & Not Default = 1')         
# sns.set_color_codes("pastel")

# sns.barplot(x = 'Label', y="count", data=df_label) 
# locs, labels = plt.xticks() 
# plt.show()

plt.figure(figsize = (5,5))
graph = sns.countplot(x="Label", data=df, palette=["red","blue"])

i = 0     

for p in graph.patches:
    print(type(p))
    h = p.get_height()
    percentage = round( 100 * df["Label"].value_counts()[i] / len(df),2)
    str_percentage = f"{percentage} %"
    graph.text(p.get_x()+p.get_width()/2., h - 100, str_percentage, ha="center")  
    
    i += 1
    
plt.title("class distribution")
plt.xticks([0,1], ["Non-Default","Default"])
plt.xlabel("Default Payment Next Month",fontsize=12)
plt.ylabel("Number of Clients")

plt.show()

# value_counts = df['Label'].value_counts()

# # 计算每个值的百分比
# percentages = value_counts / len(df)
# # 使用matplotlib绘制柱状图
# plt.bar(value_counts.index, value_counts.values)    

# # 在柱状图上添加百分比标签 
# for i, v in enumerate(percentages.values):                     
#     plt.text(i, v + 1, f'{v*100:.2f}%', ha='center',va="bottom")  
    
# # 设置xy轴标签、标题
# plt.title("Class Distribution")
# plt.xticks([0,1], ["Non-Default","Default"])
# plt.xlabel("Default Payment Next Month",fontsize=12)
# plt.ylabel("Number of Clients")

# plt.show()

value_counts = df['Label'].value_counts()  

# 计算每个值的百分比
percentages = value_counts / len(df)
# 使用matplotlib绘制柱状图
plt.bar(value_counts.index, value_counts.values)    

# 在柱状图上添加百分比标签 
for i, v in enumerate(percentages.values):
    plt.text(i, v + 1, f'{v*100:.2f}%', ha='center',va="bottom")
    
# 设置xy轴标签、标题
plt.title("Class Distribution")
plt.xticks([0,1], ["Non-Default","Default"])
plt.xlabel("Default Payment Next Month",fontsize=12)
plt.ylabel("Number of Clients")

plt.show()

numeric = ['LIMIT_BAL','AGE','PAY_0','PAY_2',
           'PAY_3','PAY_4','PAY_5','PAY_6',
           'BILL_AMT1','BILL_AMT2','BILL_AMT3',
           'BILL_AMT4','BILL_AMT5','BILL_AMT6']  # 全部数值型字段
numeric

['LIMIT_BAL',
 'AGE',
 'PAY_0',
 'PAY_2',
 'PAY_3',
 'PAY_4',
 'PAY_5',
 'PAY_6',
 'BILL_AMT1',
 'BILL_AMT2',
 'BILL_AMT3',
 'BILL_AMT4',
 'BILL_AMT5',
 'BILL_AMT6']

corr = df[numeric].corr()
corr.head()

mask = np.triu(np.ones_like(corr, dtype=bool))

plt.figure(figsize=(12,10))
sns.heatmap(corr,
            mask=mask,
            vmin=-1,
            vmax=1,
            center=0,
            square=True,
            cbar_kws={'shrink': .5}, 
            annot=True, 
            annot_kws={'size': 10},
            cmap="Blues")

plt.show()

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

pair_plot = sns.pairplot(df[['BILL_AMT1','BILL_AMT2','BILL_AMT3','BILL_AMT4','BILL_AMT5','BILL_AMT6','Label']], 
                         hue='Label',
                         diag_kind='kde', 
                         corner=True)

pair_plot._legend.remove()

sns.set_color_codes('pastel')  # 设置样式
fig, axs = plt.subplots(5, 3, figsize=(18,18))  # 图像大小和子图设置

numeric = ['LIMIT_BAL','AGE','BILL_AMT1','BILL_AMT2','BILL_AMT3','BILL_AMT4','BILL_AMT5',
           'BILL_AMT6','PAY_AMT1','PAY_AMT2','PAY_AMT3','PAY_AMT4','PAY_AMT5','PAY_AMT6']

i, j = 0, 0
for f in numeric:
    if j == 3:
        j = 0
        i = i + 1
    stats.probplot(df[f],  # 绘图数据：某个字段的全部取值
                   dist='norm', # 标准化
                   sparams=(df[f].mean(), df[f].std()), 
                   plot=axs[i,j])  # 子图位置
    
    axs[i,j].get_lines()[0].set_marker('.') 
    
    axs[i,j].grid() 
    axs[i,j].get_lines()[1].set_linewidth(3.0)
    j = j+1

fig.tight_layout()
axs[4,2].set_visible(False)
plt.show()

df["EDUCATION"].value_counts()

EDUCATION
2    14030
1    10585
3     4917
5      280
4      123
6       51
0       14
Name: count, dtype: int64

df["GRAD_SCHOOL"] = (df["EDUCATION"] == 1).astype("category")
df["UNIVERSITY"] = (df["EDUCATION"] == 2).astype("category")
df["HIGH_SCHOOL"] = (df["EDUCATION"] == 1).astype("category")

df.drop("EDUCATION",axis=1,inplace=True)

df['MALE'] = (df['SEX'] == 1).astype('category')
df.drop('SEX', axis=1, inplace=True)

df['MARRIED'] = (df['MARRIAGE'] == 1).astype('category')
df.drop('MARRIAGE', axis=1, inplace=True)

# 划分数据

y = df['Label']
X = df.drop('Label', axis=1, inplace=False)

# 切分数据

X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, random_state=24, stratify=y)

mm = MinMaxScaler()

X_train_norm = X_train_raw.copy()
X_test_norm = X_test_raw.copy()

# LIMIT_BAL + AGE

X_train_norm['LIMIT_BAL'] = mm.fit_transform(X_train_raw['LIMIT_BAL'].values.reshape(-1, 1))
X_test_norm['LIMIT_BAL'] = mm.transform(X_test_raw['LIMIT_BAL'].values.reshape(-1, 1))
X_train_norm['AGE'] = mm.fit_transform(X_train_raw['AGE'].values.reshape(-1, 1))
X_test_norm['AGE'] = mm.transform(X_test_raw['AGE'].values.reshape(-1, 1))

pay_list = ["PAY_0","PAY_2","PAY_3","PAY_4","PAY_5","PAY_6"]

for pay in pay_list:
    X_train_norm[pay] = mm.fit_transform(X_train_raw[pay].values.reshape(-1, 1))
    X_test_norm[pay] = mm.transform(X_test_raw[pay].values.reshape(-1, 1))

for i in range(1,7):
    X_train_norm['BILL_AMT' + str(i)] = mm.fit_transform(X_train_raw['BILL_AMT' + str(i)].values.reshape(-1, 1))
    X_test_norm['BILL_AMT' + str(i)] = mm.transform(X_test_raw['BILL_AMT' + str(i)].values.reshape(-1, 1))
    X_train_norm['PAY_AMT' + str(i)] = mm.fit_transform(X_train_raw['PAY_AMT' + str(i)].values.reshape(-1, 1))
    X_test_norm['PAY_AMT' + str(i)] = mm.transform(X_test_raw['PAY_AMT' + str(i)].values.reshape(-1, 1))

ss = StandardScaler()
X_train_std = X_train_raw.copy()
X_test_std = X_test_raw.copy()

X_train_std['LIMIT_BAL'] = ss.fit_transform(X_train_raw['LIMIT_BAL'].values.reshape(-1, 1))
X_test_std['LIMIT_BAL'] = ss.transform(X_test_raw['LIMIT_BAL'].values.reshape(-1, 1))

X_train_std['AGE'] = ss.fit_transform(X_train_raw['AGE'].values.reshape(-1, 1))
X_test_std['AGE'] = ss.transform(X_test_raw['AGE'].values.reshape(-1, 1))

pay_list = ["PAY_0","PAY_2","PAY_3","PAY_4","PAY_5","PAY_6"]

for pay in pay_list:
    X_train_std[pay] = mm.fit_transform(X_train_raw[pay].values.reshape(-1, 1))
    X_test_std[pay] = mm.transform(X_test_raw[pay].values.reshape(-1, 1))

for i in range(1,7):
    X_train_std['BILL_AMT' + str(i)] = ss.fit_transform(X_train_raw['BILL_AMT' + str(i)].values.reshape(-1, 1))
    X_test_std['BILL_AMT' + str(i)] = ss.transform(X_test_raw['BILL_AMT' + str(i)].values.reshape(-1, 1))
    X_train_std['PAY_AMT' + str(i)] = ss.fit_transform(X_train_raw['PAY_AMT' + str(i)].values.reshape(-1, 1))
    X_test_std['PAY_AMT' + str(i)] = ss.transform(X_test_raw['PAY_AMT' + str(i)].values.reshape(-1, 1))

sns.set_color_codes('deep')
numeric = ['LIMIT_BAL','AGE','BILL_AMT1','BILL_AMT2','BILL_AMT3','BILL_AMT4','BILL_AMT5',
           'BILL_AMT6','PAY_AMT1','PAY_AMT2','PAY_AMT3','PAY_AMT4','PAY_AMT5','PAY_AMT6']

fig, axs = plt.subplots(1, 2, figsize=(24,6))

sns.boxplot(data=X_train_norm[numeric], ax=axs[0])  
axs[0].set_title('Boxplot of normalized numeric features')
axs[0].set_xticklabels(labels=numeric, rotation=25)
axs[0].set_xlabel(' ')

sns.boxplot(data=X_train_std[numeric], ax=axs[1])
axs[1].set_title('Boxplot of standardized numeric features')
axs[1].set_xticklabels(labels=numeric, rotation=25)
axs[1].set_xlabel(' ')

fig.tight_layout()
plt.show()

pc = len(X_train_norm.columns.values) # 25
pca = PCA(n_components=pc)  # 指定主成分个数
pca.fit(X_train_norm)

sns.reset_orig()
sns.set_color_codes('pastel') # 设置绘图颜色
plt.figure(figsize = (8,4)) # 图的大小
plt.grid()  # 网格设置
plt.title('Explained Variance of Principal Components') # 标题设置
plt.plot(pca.explained_variance_ratio_, marker='o')  # 绘制单个主成分的方差解释比例
plt.plot(np.cumsum(pca.explained_variance_ratio_), marker='o')  # 累计解释方差

plt.legend(["Individual Explained Variance", "Cumulative Explained Variance"])  # 图例设置
plt.xlabel('Principal Component Indexes')  # x-y轴标题
plt.ylabel('Explained Variance Ratio')  
plt.tight_layout()  # 调整布局，更紧凑
plt.axvline(12, 0, ls='--')  # 设置虚线x=12
plt.show()  # 显示图像

cumsum = np.cumsum(pca.explained_variance_ratio_)  # 计算累计解释性方差
cumsum

array([0.44924877, 0.6321187 , 0.8046163 , 0.87590932, 0.92253799,
       0.95438576, 0.96762706, 0.97773098, 0.9842774 , 0.98824928,
       0.99088299, 0.99280785, 0.99444757, 0.99576128, 0.99690533,
       0.99781622, 0.99844676, 0.99890236, 0.99924315, 0.99955744,
       0.9997182 , 0.99983861, 0.99992993, 1.        , 1.        ])

indexes = ['PC' + str(i) for i in range(1, pc+1)]

cumsum_df = pd.DataFrame(data=cumsum, index=indexes, columns=['var1'])

cumsum_df.head()

# 保留4位小数
cumsum_df['var2'] = pd.Series([round(val, 4) for val in cumsum_df['var1']], 
                              index = cumsum_df.index)
# 转成百分比
cumsum_df['Cumulative Explained Variance'] = pd.Series(["{0:.2f}%".format(val * 100) for val in cumsum_df['var2']], 
                                                       index = cumsum_df.index)

cumsum_df.head()

cumsum_df = cumsum_df.drop(['var1','var2'], axis=1, inplace=False)
cumsum_df.T.iloc[:,:15]

pc = 12
pca = PCA(n_components=pc)
pca.fit(X_train_norm)

X_train = pd.DataFrame(pca.transform(X_train_norm))
X_test = pd.DataFrame(pca.transform(X_test_norm))

# 列名设置
X_train.columns = ['PC' + str(i) for i in range(1, pc+1)]
X_test.columns = ['PC' + str(i) for i in range(1, pc+1)]

X_train.head()

count = pd.value_counts(y_train)                               
count

Label
0    17523
1     4977
Name: count, dtype: int64

percentage = pd.value_counts(y_train, normalize=True) 
percentage

Label
0    0.7788
1    0.2212
Name: proportion, dtype: float64

class_count_df = pd.DataFrame(data=count.values,
                              index=['Non-defaulters', 'Defaulters'], 
                              columns=['Number'] 
                             )
class_count_df

class_count_df["Percentage"] = percentage.values 
class_count_df

class_count_df["Percentage"] = class_count_df["Percentage"].apply(lambda x: "{:.2%}".format(x))
class_count_df

def to_percent(x):  
    return "{:.2%}".format(x)

df[col] = df[col].apply(to_percent)

oversample = ClusterCentroids(random_state=24)  # 设置对象

# 针对X_train和y_train 的欠采样
X_train_cc, y_train_cc = oversample.fit_resample(X_train, y_train)  

count_cc = pd.value_counts(y_train_cc)  # 换成采样后的数据y_train_cc                              
percentage_cc = pd.value_counts(y_train_cc, normalize=True) 
class_count_df_cc = pd.DataFrame(data=count_cc.values,
                              index=['Non-defaulters', 'Defaulters'], 
                              columns=['Number']
                             )

class_count_df_cc["Percentage"] = percentage_cc.values
class_count_df_cc["Percentage"] = class_count_df_cc["Percentage"].apply(lambda x: "{:.2%}".format(x))
class_count_df_cc

oversample = SMOTE(random_state=24)

X_train_smote, y_train_smote = oversample.fit_resample(X_train, y_train)

count_smote = pd.value_counts(y_train_smote)  # y_train_smote                              
percentage_smote = pd.value_counts(y_train_smote, normalize=True) 
class_count_df_smote = pd.DataFrame(data=count_smote.values,
                              index=['Non-defaulters', 'Defaulters'], 
                              columns=['Number']
                             )
class_count_df_smote["Percentage"] = percentage_smote.values
class_count_df_smote["Percentage"] = class_count_df_smote["Percentage"].apply(lambda x: "{:.2%}".format(x))
class_count_df_smote

oversample = KMeansSMOTE(cluster_balance_threshold=0.00001, random_state=24)

X_train_ksmote, y_train_ksmote = oversample.fit_resample(X_train, y_train)

count_ksmote = pd.value_counts(y_train_ksmote)  # y_train_ksmote                              
percentage_ksmote = pd.value_counts(y_train_ksmote, normalize=True) 
class_count_df_ksmote = pd.DataFrame(data=count_ksmote.values,
                              index=['Non-defaulters', 'Defaulters'], 
                              columns=['Number']
                             )
class_count_df_ksmote["Percentage"] = percentage_ksmote.values
class_count_df_ksmote["Percentage"] = class_count_df_ksmote["Percentage"].apply(lambda x: "{:.2%}".format(x))
class_count_df_ksmote

display(class_count_df)
display(class_count_df_cc)
display(class_count_df_smote)
display(class_count_df_ksmote)

# pca降维后的数据y_train,
# 基于聚类中心的欠采样y_train_cc
# 基于SMOTE的过采样y_train_smote
# 基于聚类+SMOTE的采样y_train_smote
# y_train,y_train_cc,y_train_smote,y_train_ksmote

X_train  # 降维与归一化后的特征数据      

y_train              

24832    0
969      0
20833    1
21670    0
25380    0
        ..
20828    1
897      1
16452    0
3888     0
5743     0
Name: Label, Length: 22500, dtype: int64

# 模型训练

lgb_clf = lgb.LGBMClassifier()
lgb_clf.fit(X_train, y_train)
[LightGBM] [Info] Number of positive: 4977, number of negative: 17523
[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000607 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 3060
[LightGBM] [Info] Number of data points in the train set: 22500, number of used features: 12
[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.221200 -> initscore=-1.258687
[LightGBM] [Info] Start training from score -1.258687

# 模型预测

y_pred = lgb_clf.predict(X_test)
y_pred

array([1, 0, 0, ..., 0, 0, 0], dtype=int64)

acc = accuracy_score(y_test, y_pred)

print(acc)
0.8130666666666667

# 定义LightGBM分类器
lgb_clf_new = lgb.LGBMClassifier()

# 设置超参数网格搜索范围

param_grid = {
    'num_leaves': [31, 63, 127], 
    'learning_rate': [0.01, 0.02, 0.03, 0.04, 0.05],
    'n_estimators': [100, 200, 300],
    'max_depth': [4,5,6,7]
}

# 使用k折交叉验证和网格搜索进行超参数调优

# 5折交叉验证实例对象
# cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)  

cv = 5

# 网格搜索
grid_search = GridSearchCV(lgb_clf_new, #  lgb模型
                           param_grid,  # 参数
                           scoring='accuracy',  # 评估指标 
                           cv=cv,  # 5折交叉验证
                           n_jobs=-1  
                          ) 

# 网格搜索对象的训练

grid_search.fit(X_train, y_train)

grid_search.best_params_   

{'learning_rate': 0.02, 'max_depth': 5, 'n_estimators': 300, 'num_leaves': 63}

new_model = lgb.LGBMClassifier(learning_rate=0.02, 
                                max_depth=5, 
                                n_estimators=300, 
                                num_leaves=63)

new_model.fit(X_train,y_train)

y_pred_new = new_model.predict(X_test) 
y_pred_new

array([1, 0, 0, ..., 0, 0, 0], dtype=int64)

acc_new = accuracy_score(y_test, y_pred_new)

print(acc_new)
0.8330666666666667