CCF个贷违约预测0.891的baseline代码分享
作者：互联网
比赛涨分无非是：模型、特征、数据，这题的特征做起来收益太少（也可能我没找到），模型lgb已经很不错了，数据方面，剩下的就是尽量减少噪音的基础上好好利用测试集+两张表的数据了。
有部分人说无法复现到0.89，所以我把代码放出来，“YB统计人工智能”分享的884的代码，之所以涨分，我发现还有一个重要原因就是增加了噪音较少的训练样本，所以这题把测试集做成伪标签也加入训练，当然也要限定阈值0.5，小于0.5的以0标签放入，其余的不放入。同理把“YB统计人工智能”分享的884的代码的阈值也改成0.5，也就是增加了internet+测试集的少噪音数据
第一步：下载比赛数据，train_public.csv、submit_example.csv、test_public.csv、train_internet.csv，
新建文件夹raw_data，并把上面的csv文件放到这个文件夹里，运行下面的代码（这个代码完全是复制“YB统计人工智能”分享的884的代码）
import matplotlib.pyplot as plt
import seaborn as sns
import gc
import re
import pandas as pd
import lightgbm as lgb
import numpy as np
from sklearn.metrics import roc_auc_score, precision_recall_curve, roc_curve, average_precision_score
from sklearn.model_selection import KFold
from lightgbm import LGBMClassifier
import matplotlib.pyplot as plt
import seaborn as sns
import gc
from sklearn.model_selection import StratifiedKFold
from dateutil.relativedelta import relativedelta
train_data = pd.read_csv('raw_data/train_public.csv')
submit_example = pd.read_csv('raw_data/submit_example.csv')
test_public = pd.read_csv('raw_data/test_public.csv')
train_inte = pd.read_csv('raw_data/train_internet.csv')
pd.set_option('max_columns', None)
pd.set_option('max_rows', 200)
pd.set_option('float_format', lambda x: '%.3f' % x)
def train_model(data_, test_, y_, folds_):
oof_preds = np.zeros(data_.shape[0])
sub_preds = np.zeros(test_.shape[0])
feature_importance_df = pd.DataFrame()
feats = [f for f in data_.columns if f not in ['loan_id', 'user_id', 'isDefault'] ]
for n_fold, (trn_idx, val_idx) in enumerate(folds_.split(data_)):
trn_x, trn_y = data_[feats].iloc[trn_idx], y_.iloc[trn_idx]
val_x, val_y = data_[feats].iloc[val_idx], y_.iloc[val_idx]
clf = LGBMClassifier(
n_estimators=4000,
learning_rate=0.08,
num_leaves=2**5,
colsample_bytree=.65,
subsample=.9,
max_depth=5,
# max_bin=250,
reg_alpha=.3,
reg_lambda=.3,
min_split_gain=.01,
min_child_weight=2,
silent=-1,
verbose=-1,
)
clf.fit(trn_x, trn_y,
eval_set= [(trn_x, trn_y), (val_x, val_y)],
eval_metric='auc', verbose=100, early_stopping_rounds=40 #30
)
oof_preds[val_idx] = clf.predict_proba(val_x, num_iteration=clf.best_iteration_)[:, 1]
sub_preds += clf.predict_proba(test_[feats], num_iteration=clf.best_iteration_)[:, 1] / folds_.n_splits
fold_importance_df = pd.DataFrame()
fold_importance_df["feature"] = feats
fold_importance_df["importance"] = clf.feature_importances_
fold_importance_df["fold"] = n_fold + 1
feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)
print('Fold %2d AUC : %.6f' % (n_fold + 1, roc_auc_score(val_y, oof_preds[val_idx])))
del clf, trn_x, trn_y, val_x, val_y
gc.collect()
print('Full AUC score %.6f' % roc_auc_score(y, oof_preds))
test_['isDefault'] = sub_preds
return oof_preds, test_[['loan_id', 'isDefault']], feature_importance_df
def display_importances(feature_importance_df_):
# Plot feature importances
cols = feature_importance_df_[["feature", "importance"]].groupby("feature").mean().sort_values(
by="importance", ascending=False)[:50].index
best_features = feature_importance_df_.loc[feature_importance_df_.feature.isin(cols)]
plt.figure(figsize=(8,10))
sns.barplot(x="importance", y="feature",
data=best_features.sort_values(by="importance", ascending=False))
plt.title('LightGBM Features (avg over folds)')
plt.tight_layout()
plt.savefig('lgbm_importances.png')
def workYearDIc(x):
if str(x)=='nan':
return -1
x = x.replace('< 1','0')
return int(re.search('(\d+)', x).group())
def findDig(val):
fd = re.search('(\d+-)', val)
if fd is None:
return '1-'+val
return val + '-01'
class_dict = {
'A': 1,
'B': 2,
'C': 3,
'D': 4,
'E': 5,
'F': 6,
'G': 7,
}
timeMax = pd.to_datetime('1-Dec-21')
train_data['work_year'] = train_data['work_year'].map(workYearDIc)
test_public['work_year'] = test_public['work_year'].map(workYearDIc)
train_data['class'] = train_data['class'].map(class_dict)
test_public['class'] = test_public['class'].map(class_dict)
train_data['earlies_credit_mon'] = pd.to_datetime(train_data['earlies_credit_mon'].map(findDig))
test_public['earlies_credit_mon'] = pd.to_datetime(test_public['earlies_credit_mon'].map(findDig))
train_data.loc[ train_data['earlies_credit_mon']>timeMax,'earlies_credit_mon' ] = train_data.loc[ train_data['earlies_credit_mon']>timeMax,'earlies_credit_mon' ]+ pd.offsets.DateOffset(years=-100)
test_public.loc[ test_public['earlies_credit_mon']>timeMax,'earlies_credit_mon' ] = test_public.loc[ test_public['earlies_credit_mon']>timeMax,'earlies_credit_mon' ]+ pd.offsets.DateOffset(years=-100)
train_data['issue_date'] = pd.to_datetime(train_data['issue_date'])
test_public['issue_date'] = pd.to_datetime(test_public['issue_date'])
#Internet数据处理
train_inte['work_year'] = train_inte['work_year'].map(workYearDIc)
train_inte['class'] = train_inte['class'].map(class_dict)
train_inte['earlies_credit_mon'] = pd.to_datetime(train_inte['earlies_credit_mon'])
train_inte['issue_date'] = pd.to_datetime(train_inte['issue_date'])
train_data['issue_date_month'] = train_data['issue_date'].dt.month
test_public['issue_date_month'] = test_public['issue_date'].dt.month
train_data['issue_date_dayofweek'] = train_data['issue_date'].dt.dayofweek
test_public['issue_date_dayofweek'] = test_public['issue_date'].dt.dayofweek
train_data['earliesCreditMon'] = train_data['earlies_credit_mon'].dt.month
test_public['earliesCreditMon'] = test_public['earlies_credit_mon'].dt.month
train_data['earliesCreditYear'] = train_data['earlies_credit_mon'].dt.year
test_public['earliesCreditYear'] = test_public['earlies_credit_mon'].dt.year
###internet数据
train_inte['issue_date_month'] = train_inte['issue_date'].dt.month
train_inte['issue_date_dayofweek'] = train_inte['issue_date'].dt.dayofweek
train_inte['earliesCreditMon'] = train_inte['earlies_credit_mon'].dt.month
train_inte['earliesCreditYear'] = train_inte['earlies_credit_mon'].dt.year
cat_cols = ['employer_type', 'industry']
from sklearn.preprocessing import LabelEncoder
for col in cat_cols:
lbl = LabelEncoder().fit(train_data[col])
train_data[col] = lbl.transform(train_data[col])
test_public[col] = lbl.transform(test_public[col])
#Internet处理
train_inte[col] = lbl.transform(train_inte[col])
# 'f1','policy_code','app_type' 这三个去掉是881
# ,'f1','policy_code','app_type'
col_to_drop = ['issue_date', 'earlies_credit_mon']
train_data = train_data.drop(col_to_drop, axis=1)
test_public = test_public.drop(col_to_drop, axis=1 )
##internet处理
train_inte = train_inte.drop(col_to_drop, axis=1 )
# 暂时不变
# train_inte = train_inte.rename(columns={'is_default':'isDefault'})
# data = pd.concat( [train_data,test_public] )
tr_cols = set(train_data.columns)
same_col = list(tr_cols.intersection(set(train_inte.columns)))
train_inteSame = train_inte[same_col].copy()
Inte_add_cos = list(tr_cols.difference(set(same_col)))
for col in Inte_add_cos:
train_inteSame[col] = np.nan
#81后加
# for col in cat_cols:
# dum = pd.get_dummies(data[col], prefix='OneHot_'+col +'_')
# data = pd.concat([data, dum], axis=1)
# # del data[col]
# del dum
y = train_data['isDefault']
folds = KFold(n_splits=5, shuffle=True, random_state=546789)
oof_preds, IntePre, importances = train_model(train_data, train_inteSame, y, folds)
IntePre['isDef'] = train_inte['is_default']
from sklearn.metrics import roc_auc_score
roc_auc_score(IntePre['isDef'],IntePre.isDefault)
## 选择阈值0.05，从internet表中提取预测小于该概率的样本，并对不同来源的样本赋予来源值
InteId = IntePre.loc[IntePre.isDefault<0.05, 'loan_id'].tolist()
train_data['dataSourse'] = 1
test_public['dataSourse'] = 1
train_inteSame['dataSourse'] = 0
train_inteSame['isDefault'] = train_inte['is_default']
use_te = train_inteSame[train_inteSame.loan_id.isin( InteId )].copy()
data = pd.concat([ train_data,test_public,use_te]).reset_index(drop=True)
# InteId = IntePre.loc[IntePre.isDefault<0.05, 'loan_id'].tolist()
# train_inte = train_inte.rename(columns={'is_default':'isDefault'})
# train_data['dataSourse'] = 1
# test_public['dataSourse'] = 1
# train_inte['dataSourse'] = 0
# use_te = train_inte[train_inte.loan_id.isin( InteId )].copy()
# data = pd.concat([ train_data,test_public,use_te]).reset_index(drop=True)
# IntePre.isDefault
plt.figure(figsize=(16,6))
plt.title("Distribution of Default values IntePre")
sns.distplot(IntePre['isDefault'],color="black", kde=True,bins=120, label='train_data')
# sns.distplot(train_inte[col],color="red", kde=True,bins=120, label='train_inte')
plt.legend();plt.show()
train = data[data['isDefault'].notna()]
test = data[data['isDefault'].isna()]
# for col in ['sub_class', 'work_type']:
# del train[col]
# del test[col]
del data
del train_data,test_public
y = train['isDefault']
folds = KFold(n_splits=5, shuffle=True, random_state=546789)
oof_preds, test_preds, importances = train_model(train, test, y, folds)
test_preds.rename({'loan_id': 'id'}, axis=1)[['id', 'isDefault']].to_csv('nn2.csv', index=False)
第二步，运行下面的代码，这是我自己写的
import pandas as pd
train_data = pd.read_csv('raw_data/train_public.csv')
test_data = pd.read_csv('raw_data/test_public.csv')
sub=pd.read_csv("nn2.csv")
sub=sub.rename(columns={'id': 'loan_id'})
sub.loc[sub['isDefault']<0.5,'isDefault'] = 0
nw_sub=sub[(sub['isDefault']==0)]
nw_test_data=test_data.merge(nw_sub,on='loan_id',how='inner')
nw_train_data = pd.concat([train_data,nw_test_data]).reset_index(drop=True)
nw_train_data.to_csv("raw_data/nw_train_public.csv",index=0)
第三步，修改了一下“YB统计人工智能”884的代码
import matplotlib.pyplot as plt
import seaborn as sns
import gc
import re
import pandas as pd
import lightgbm as lgb
import numpy as np
from sklearn.metrics import roc_auc_score, precision_recall_curve, roc_curve, average_precision_score
from sklearn.model_selection import KFold
from lightgbm import LGBMClassifier
import matplotlib.pyplot as plt
import seaborn as sns
import gc
from sklearn.model_selection import StratifiedKFold
from dateutil.relativedelta import relativedelta
train_data = pd.read_csv('raw_data/nw_train_public.csv')
submit_example = pd.read_csv('raw_data/submit_example.csv')
test_public = pd.read_csv('raw_data/test_public.csv')
train_inte = pd.read_csv('raw_data/train_internet.csv')
pd.set_option('max_columns', None)
pd.set_option('max_rows', 200)
pd.set_option('float_format', lambda x: '%.3f' % x)
def train_model(data_, test_, y_, folds_):
oof_preds = np.zeros(data_.shape[0])
sub_preds = np.zeros(test_.shape[0])
feature_importance_df = pd.DataFrame()
feats = [f for f in data_.columns if f not in ['loan_id', 'user_id', 'isDefault'] ]
for n_fold, (trn_idx, val_idx) in enumerate(folds_.split(data_)):
trn_x, trn_y = data_[feats].iloc[trn_idx], y_.iloc[trn_idx]
val_x, val_y = data_[feats].iloc[val_idx], y_.iloc[val_idx]
clf = LGBMClassifier(
n_estimators=4000,
learning_rate=0.08,
num_leaves=2**5,
colsample_bytree=.65,
subsample=.9,
max_depth=5,
# max_bin=250,
reg_alpha=.3,
reg_lambda=.3,
min_split_gain=.01,
min_child_weight=2,
silent=-1,
verbose=-1,
)
clf.fit(trn_x, trn_y,
eval_set= [(trn_x, trn_y), (val_x, val_y)],
eval_metric='auc', verbose=100, early_stopping_rounds=40 #30
)
oof_preds[val_idx] = clf.predict_proba(val_x, num_iteration=clf.best_iteration_)[:, 1]
sub_preds += clf.predict_proba(test_[feats], num_iteration=clf.best_iteration_)[:, 1] / folds_.n_splits
fold_importance_df = pd.DataFrame()
fold_importance_df["feature"] = feats
fold_importance_df["importance"] = clf.feature_importances_
fold_importance_df["fold"] = n_fold + 1
feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)
print('Fold %2d AUC : %.6f' % (n_fold + 1, roc_auc_score(val_y, oof_preds[val_idx])))
del clf, trn_x, trn_y, val_x, val_y
gc.collect()
print('Full AUC score %.6f' % roc_auc_score(y, oof_preds))
test_['isDefault'] = sub_preds
return oof_preds, test_[['loan_id', 'isDefault']], feature_importance_df
def display_importances(feature_importance_df_):
# Plot feature importances
cols = feature_importance_df_[["feature", "importance"]].groupby("feature").mean().sort_values(
by="importance", ascending=False)[:50].index
best_features = feature_importance_df_.loc[feature_importance_df_.feature.isin(cols)]
plt.figure(figsize=(8,10))
sns.barplot(x="importance", y="feature",
data=best_features.sort_values(by="importance", ascending=False))
plt.title('LightGBM Features (avg over folds)')
plt.tight_layout()
plt.savefig('lgbm_importances.png')
def workYearDIc(x):
if str(x)=='nan':
return -1
x = x.replace('< 1','0')
return int(re.search('(\d+)', x).group())
def findDig(val):
fd = re.search('(\d+-)', val)
if fd is None:
return '1-'+val
return val + '-01'
class_dict = {
'A': 1,
'B': 2,
'C': 3,
'D': 4,
'E': 5,
'F': 6,
'G': 7,
}
timeMax = pd.to_datetime('1-Dec-21')
train_data['work_year'] = train_data['work_year'].map(workYearDIc)
test_public['work_year'] = test_public['work_year'].map(workYearDIc)
train_data['class'] = train_data['class'].map(class_dict)
test_public['class'] = test_public['class'].map(class_dict)
train_data['earlies_credit_mon'] = pd.to_datetime(train_data['earlies_credit_mon'].map(findDig))
test_public['earlies_credit_mon'] = pd.to_datetime(test_public['earlies_credit_mon'].map(findDig))
train_data.loc[ train_data['earlies_credit_mon']>timeMax,'earlies_credit_mon' ] = train_data.loc[ train_data['earlies_credit_mon']>timeMax,'earlies_credit_mon' ]+ pd.offsets.DateOffset(years=-100)
test_public.loc[ test_public['earlies_credit_mon']>timeMax,'earlies_credit_mon' ] = test_public.loc[ test_public['earlies_credit_mon']>timeMax,'earlies_credit_mon' ]+ pd.offsets.DateOffset(years=-100)
train_data['issue_date'] = pd.to_datetime(train_data['issue_date'])
test_public['issue_date'] = pd.to_datetime(test_public['issue_date'])
#Internet数据处理
train_inte['work_year'] = train_inte['work_year'].map(workYearDIc)
train_inte['class'] = train_inte['class'].map(class_dict)
train_inte['earlies_credit_mon'] = pd.to_datetime(train_inte['earlies_credit_mon'])
train_inte['issue_date'] = pd.to_datetime(train_inte['issue_date'])
train_data['issue_date_month'] = train_data['issue_date'].dt.month
test_public['issue_date_month'] = test_public['issue_date'].dt.month
train_data['issue_date_dayofweek'] = train_data['issue_date'].dt.dayofweek
test_public['issue_date_dayofweek'] = test_public['issue_date'].dt.dayofweek
train_data['earliesCreditMon'] = train_data['earlies_credit_mon'].dt.month
test_public['earliesCreditMon'] = test_public['earlies_credit_mon'].dt.month
train_data['earliesCreditYear'] = train_data['earlies_credit_mon'].dt.year
test_public['earliesCreditYear'] = test_public['earlies_credit_mon'].dt.year
###internet数据
train_inte['issue_date_month'] = train_inte['issue_date'].dt.month
train_inte['issue_date_dayofweek'] = train_inte['issue_date'].dt.dayofweek
train_inte['earliesCreditMon'] = train_inte['earlies_credit_mon'].dt.month
train_inte['earliesCreditYear'] = train_inte['earlies_credit_mon'].dt.year
cat_cols = ['employer_type', 'industry']
from sklearn.preprocessing import LabelEncoder
for col in cat_cols:
lbl = LabelEncoder().fit(train_data[col])
train_data[col] = lbl.transform(train_data[col])
test_public[col] = lbl.transform(test_public[col])
#Internet处理
train_inte[col] = lbl.transform(train_inte[col])
# 'f1','policy_code','app_type' 这三个去掉是881
# ,'f1','policy_code','app_type'
col_to_drop = ['issue_date', 'earlies_credit_mon']
train_data = train_data.drop(col_to_drop, axis=1)
test_public = test_public.drop(col_to_drop, axis=1 )
##internet处理
train_inte = train_inte.drop(col_to_drop, axis=1 )
# 暂时不变
# train_inte = train_inte.rename(columns={'is_default':'isDefault'})
# data = pd.concat( [train_data,test_public] )
tr_cols = set(train_data.columns)
same_col = list(tr_cols.intersection(set(train_inte.columns)))
train_inteSame = train_inte[same_col].copy()
Inte_add_cos = list(tr_cols.difference(set(same_col)))
for col in Inte_add_cos:
train_inteSame[col] = np.nan
#81后加
# for col in cat_cols:
# dum = pd.get_dummies(data[col], prefix='OneHot_'+col +'_')
# data = pd.concat([data, dum], axis=1)
# # del data[col]
# del dum
y = train_data['isDefault']
folds = KFold(n_splits=5, shuffle=True, random_state=546789)
oof_preds, IntePre, importances = train_model(train_data, train_inteSame, y, folds)
IntePre['isDef'] = train_inte['is_default']
from sklearn.metrics import roc_auc_score
roc_auc_score(IntePre['isDef'],IntePre.isDefault)
## 选择阈值0.05，从internet表中提取预测小于该概率的样本，并对不同来源的样本赋予来源值
InteId = IntePre.loc[IntePre.isDefault<0.5, 'loan_id'].tolist()
train_data['dataSourse'] = 1
test_public['dataSourse'] = 1
train_inteSame['dataSourse'] = 0
train_inteSame['isDefault'] = train_inte['is_default']
use_te = train_inteSame[train_inteSame.loan_id.isin( InteId )].copy()
data = pd.concat([ train_data,test_public,use_te]).reset_index(drop=True)
# InteId = IntePre.loc[IntePre.isDefault<0.05, 'loan_id'].tolist()
# train_inte = train_inte.rename(columns={'is_default':'isDefault'})
# train_data['dataSourse'] = 1
# test_public['dataSourse'] = 1
# train_inte['dataSourse'] = 0
# use_te = train_inte[train_inte.loan_id.isin( InteId )].copy()
# data = pd.concat([ train_data,test_public,use_te]).reset_index(drop=True)
# IntePre.isDefault
plt.figure(figsize=(16,6))
plt.title("Distribution of Default values IntePre")
sns.distplot(IntePre['isDefault'],color="black", kde=True,bins=120, label='train_data')
# sns.distplot(train_inte[col],color="red", kde=True,bins=120, label='train_inte')
plt.legend();plt.show()
train = data[data['isDefault'].notna()]
test = data[data['isDefault'].isna()]
# for col in ['sub_class', 'work_type']:
# del train[col]
# del test[col]
del data
del train_data,test_public
y = train['isDefault']
folds = KFold(n_splits=5, shuffle=True, random_state=546789)
oof_preds, test_preds, importances = train_model(train, test, y, folds)
test_preds.rename({'loan_id': 'id'}, axis=1)[['id', 'isDefault']].to_csv('baseline891.csv', index=False)
标签：inte,baseline,0.891,train,pd,test,CCF,data,public 来源： https://blog.csdn.net/sinat_23971513/article/details/120693694