1.官方代码
代码简介：三种树模型lgb、xgb、cat（CatBoostRegressor）
链接：https://github.com/datawhalechina/team-learning-data-mining/blob/master/FinancialRiskControl/baseline.md
代码：
#! /usr/bin/env python
# -*- coding:utf-8 -*-
#====#====#====#====
'''
'''
#====#====#====#====
#---导入包
import pandas as pd
import os
import gc
import lightgbm as lgb
import xgboost as xgb
from catboost import CatBoostRegressor
from sklearn.linear_model import SGDRegressor, LinearRegression, Ridge
from sklearn.preprocessing import MinMaxScaler
import math
import numpy as np
from tqdm import tqdm
from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score, log_loss
import matplotlib.pyplot as plt
import time
import warnings
warnings.filterwarnings('ignore')
#---读取数据
train = pd.read_csv('finance2/train.csv')
testA = pd.read_csv('finance2/testA.csv')
#查看数据
print(train.head())
data = pd.concat([train, testA], axis=0, ignore_index=True)
#---数据预处理
#可以看到很多变量不能直接训练，比如grade、subGrade、employmentLength、issueDate、earliesCreditLine，需要进行预处理
print(sorted(data['grade'].unique()))
print(sorted(data['subGrade'].unique()))
data['employmentLength'].value_counts(dropna=False).sort_index()
##--首先对employmentLength进行转换到数值
data['employmentLength'].replace(to_replace='10+ years', value='10 years', inplace=True)
data['employmentLength'].replace('< 1 year', '0 years', inplace=True)
def employmentLength_to_int(s):
if pd.isnull(s):
return s
else:
return np.int8(s.split()[0])
data['employmentLength'] = data['employmentLength'].apply(employmentLength_to_int)
data['employmentLength'].value_counts(dropna=False).sort_index()
##--对earliesCreditLine进行预处理
data['earliesCreditLine'].sample(5)
data['earliesCreditLine'] = data['earliesCreditLine'].apply(lambda s: int(s[-4:]))
data['earliesCreditLine'].describe()
print(data.head())
##--类别特征处理
# 部分类别特征
cate_features = ['grade', 'subGrade', 'employmentTitle', 'homeOwnership', 'verificationStatus', 'purpose', 'postCode', 'regionCode', \
'applicationType', 'initialListStatus', 'title', 'policyCode']
for f in cate_features:
print(f, '类型数：', data[f].nunique())
# 类型数在2之上，又不是高维稀疏的
data = pd.get_dummies(data, columns=['grade', 'subGrade', 'homeOwnership', 'verificationStatus', 'purpose', 'regionCode'], drop_first=True)
# 高维类别特征需要进行转换
for f in ['employmentTitle', 'postCode', 'title']:
data[f+'_cnts'] = data.groupby([f])['id'].transform('count')
data[f+'_rank'] = data.groupby([f])['id'].rank(ascending=False).astype(int)
del data[f]
#---训练数据/测试数据准备
features = [f for f in data.columns if f not in ['id','issueDate','isDefault']]
train = data[data.isDefault.notnull()].reset_index(drop=True)
test = data[data.isDefault.isnull()].reset_index(drop=True)
x_train = train[features]
x_test = test[features]
y_train = train['isDefault']
#---模型训练
#直接构建了一个函数，可以调用三种树模型，方便快捷
def cv_model(clf, train_x, train_y, test_x, clf_name):
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
train = np.zeros(train_x.shape[0])
test = np.zeros(test_x.shape[0])
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(train_x, train_y)):
print('************************************ {} ************************************'.format(str(i + 1)))
trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], \
train_y[valid_index]
if clf_name == "lgb":
train_matrix = clf.Dataset(trn_x, label=trn_y)
valid_matrix = clf.Dataset(val_x, label=val_y)
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': 'auc',
'min_child_weight': 5,
'num_leaves': 2 ** 5,
'lambda_l2': 10,
'feature_fraction': 0.8,
'bagging_fraction': 0.8,
'bagging_freq': 4,
'learning_rate': 0.1,
'seed': 2020,
'nthread': 28,
'n_jobs': 24,
'silent': True,
'verbose': -1,
}
model = clf.train(params, train_matrix, 50000, valid_sets=[train_matrix, valid_matrix], verbose_eval=200,
early_stopping_rounds=200)
val_pred = model.predict(val_x, num_iteration=model.best_iteration)
test_pred = model.predict(test_x, num_iteration=model.best_iteration)
# print(list(sorted(zip(features, model.feature_importance("gain")), key=lambda x: x[1], reverse=True))[:20])
if clf_name == "xgb":
train_matrix = clf.DMatrix(trn_x, label=trn_y)
valid_matrix = clf.DMatrix(val_x, label=val_y)
test_matrix = clf.DMatrix(test_x)
params = {'booster': 'gbtree',
'objective': 'binary:logistic',
'eval_metric': 'auc',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.04,
'tree_method': 'exact',
'seed': 2020,
'nthread': 36,
"silent": True,
}
watchlist = [(train_matrix, 'train'), (valid_matrix, 'eval')]
model = clf.train(params, train_matrix, num_boost_round=50000, evals=watchlist, verbose_eval=200,
early_stopping_rounds=200)
val_pred = model.predict(valid_matrix, ntree_limit=model.best_ntree_limit)
test_pred = model.predict(test_matrix, ntree_limit=model.best_ntree_limit)
if clf_name == "cat":
params = {'learning_rate': 0.05, 'depth': 5, 'l2_leaf_reg': 10, 'bootstrap_type': 'Bernoulli',
'od_type': 'Iter', 'od_wait': 50, 'random_seed': 11, 'allow_writing_files': False}
model = clf(iterations=20000, **params)
model.fit(trn_x, trn_y, eval_set=(val_x, val_y),
cat_features=[], use_best_model=True, verbose=500)
val_pred = model.predict(val_x)
test_pred = model.predict(test_x)
train[valid_index] = val_pred
test = test_pred / kf.n_splits
cv_scores.append(roc_auc_score(val_y, val_pred))
print(cv_scores)
print("%s_scotrainre_list:" % clf_name, cv_scores)
print("%s_score_mean:" % clf_name, np.mean(cv_scores))
print("%s_score_std:" % clf_name, np.std(cv_scores))
return train, test
def lgb_model(x_train, y_train, x_test):
lgb_train, lgb_test = cv_model(lgb, x_train, y_train, x_test, "lgb")
return lgb_train, lgb_test
def xgb_model(x_train, y_train, x_test):
xgb_train, xgb_test = cv_model(xgb, x_train, y_train, x_test, "xgb")
return xgb_train, xgb_test
def cat_model(x_train, y_train, x_test):
cat_train, cat_test = cv_model(CatBoostRegressor, x_train, y_train, x_test, "cat")
return cat_train, cat_test
lgb_train, lgb_test = lgb_model(x_train, y_train, x_test)
xgb_train, xgb_test = xgb_model(x_train, y_train, x_test)
cat_train, cat_test = cat_model(x_train, y_train, x_test)
rh_test = lgb_test*0.5 + xgb_test*0.5
testA['isDefault'] = rh_test
testA[['id','isDefault']].to_csv('test_sub.csv', index=False)
【最后的运行结果】
代码简介：Baseline-LGBM
- 手动删除若干疑似重复列n2；
- 没有引入业务知识；
- 对所有非数值字段直接Target encode；
- 采用LGBMRegressor，随手设置了一些参数；
- 本地十折AUC均值0.7317，线上0.7291
链接：https://tianchi.aliyun.com/forum/postDetail?spm=5176.12586969.1002.21.3b306856mDlndD&postId=128654
代码：
import pandas as pd
import numpy as np
from category_encoders.target_encoder import TargetEncoder
from sklearn.model_selection import KFold
from sklearn.metrics import auc, roc_curve
from lightgbm import LGBMRegressor
# 导入数据
train = pd.read_csv('finance2/train.csv', index_col='id')
test = pd.read_csv('finance2/testA.csv', index_col='id')
target = train.pop('isDefault')
test = test[train.columns]
# 非数值列
s = train.apply(lambda x:x.dtype)
tecols = s[s=='object'].index.tolist()
# 模型
def makelgb():
lgbr = LGBMRegressor(num_leaves=30
,max_depth=5
,learning_rate=.02
,n_estimators=1000
,subsample_for_bin=5000
,min_child_samples=200
,colsample_bytree=.2
,reg_alpha=.1
,reg_lambda=.1
)
return lgbr
# 本地验证
kf = KFold(n_splits=10, shuffle=True, random_state=100)
devscore = []
for tidx, didx in kf.split(train.index):
tf = train.iloc[tidx]
df = train.iloc[didx]
tt = target.iloc[tidx]
dt = target.iloc[didx]
te = TargetEncoder(cols=tecols)
tf = te.fit_transform(tf, tt)
df = te.transform(df)
lgbr = makelgb()
lgbr.fit(tf, tt)
pre = lgbr.predict(df)
fpr, tpr, thresholds = roc_curve(dt, pre)
score = auc(fpr, tpr)
devscore.append(score)
print(np.mean(devscore))
# 在整个train集上重新训练，预测test，输出结果
lgbr = makelgb()
te = TargetEncoder(cols=tecols)
tf = te.fit_transform(train, target)
df = te.transform(test)
lgbr.fit(tf, target)
pre = lgbr.predict(df)
pd.Series(pre, name='isDefault', index=test.index).reset_index().to_csv('submit.csv', index=False)【遇到问题：安装category-encoders包】
【代码结果】
