学习目标
- 学习在金融分控领域常用的机器学习模型
- 学习机器学习模型的建模过程与调参流程
代码
import pandas as pd
import numpy as np
import warnings
import os
import seaborn as sns
import matplotlib.pyplot as plt
"""
sns 相关设置
@return:
"""
# 声明使用 Seaborn 样式
sns.set()
# 有五种seaborn的绘图风格，它们分别是：darkgrid, whitegrid, dark, white, ticks。默认的主题是darkgrid。
sns.set_style("whitegrid")
# 有四个预置的环境，按大小从小到大排列分别为：paper, notebook, talk, poster。其中，notebook是默认的。
sns.set_context('talk')
# 中文字体设置-黑体
plt.rcParams['font.sans-serif'] = ['SimHei']
# 解决保存图像是负号'-'显示为方块的问题
plt.rcParams['axes.unicode_minus'] = False
# 解决Seaborn中文显示问题并调整字体大小
sns.set(font='SimHei')data = pd.read_csv('./data/data_for_model.csv')from sklearn.model_selection import KFold
# 分离数据集，方便进行交叉验证
X_train = data.loc[data['sample']=='train', :].drop(['isDefault', 'sample', 'Unnamed: 0'], axis=1)
X_test = data.loc[data['sample']=='test', :].drop(['isDefault', 'sample', 'Unnamed: 0'], axis=1)
y_train = data.loc[data['sample']=='train', 'isDefault']# 5折交叉验证
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)"""对训练集数据进行划分，分成训练集和验证集，并进行相应的操作"""
from sklearn.model_selection import train_test_split
import lightgbm as lgb
# 数据集划分
X_train_split, X_val, y_train_split, y_val = train_test_split(X_train, y_train, test_size=0.2)
train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
valid_matrix = lgb.Dataset(X_val, label=y_val)params = {'boosting_type': 'gbdt','objective': 'binary','learning_rate': 0.1,'metric': 'auc','min_child_weight': 1e-3,'num_leaves': 31,'max_depth': -1,'reg_lambda': 0,'reg_alpha': 0,'feature_fraction': 1,'bagging_fraction': 1,'bagging_freq': 0,'seed': 2020,'nthread': 8,'silent': True,'verbose': -1,
}"""使用训练集数据进行模型训练"""
model = lgb.train(params, train_set=train_matrix, valid_sets=valid_matrix, num_boost_round=20000, verbose_eval=1000, early_stopping_rounds=200)这个时候就能出现结果啦
Training until validation scores don't improve for 200 rounds Early stopping, best iteration is: [297] valid_0's auc: 0.731087
然后获取没有调参前的lgb的AUC值
from sklearn import metrics
from sklearn.metrics import roc_auc_score"""预测并计算roc的相关指标"""
val_pre_lgb = model.predict(X_val, num_iteration=model.best_iteration)
fpr, tpr, threshold = metrics.roc_curve(y_val, val_pre_lgb)
roc_auc = metrics.auc(fpr, tpr)
print('未调参前lightgbm单模型在验证集上的AUC：{}'.format(roc_auc))
"""画出roc曲线图"""
plt.figure(figsize=(8, 8))
plt.title('Validation ROC')
plt.plot(fpr, tpr, 'b', label = 'Val AUC = %0.4f' % roc_auc)
plt.ylim(0,1)
plt.xlim(0,1)
plt.legend(loc='best')
plt.title('ROC')
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
# 画出对角线
plt.plot([0,1],[0,1],'r--')
plt.show()也可使用5折交叉验证进行模型性能评估
import lightgbm as lgb
"""使用lightgbm 5折交叉验证进行建模预测"""
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train)):print('************************************ {} ************************************'.format(str(i+1)))X_train_split, y_train_split, X_val, y_val = X_train.iloc[train_index], y_train[train_index], X_train.iloc[valid_index], y_train[valid_index]train_matrix = lgb.Dataset(X_train_split, label=y_train_split)valid_matrix = lgb.Dataset(X_val, label=y_val)params = {'boosting_type': 'gbdt','objective': 'binary','learning_rate': 0.1,'metric': 'auc','min_child_weight': 1e-3,'num_leaves': 31,'max_depth': -1,'reg_lambda': 0,'reg_alpha': 0,'feature_fraction': 1,'bagging_fraction': 1,'bagging_freq': 0,'seed': 2020,'nthread': 8,'silent': True,'verbose': -1,}model = lgb.train(params, train_set=train_matrix, num_boost_round=20000, valid_sets=valid_matrix, verbose_eval=1000, early_stopping_rounds=200)val_pred = model.predict(X_val, num_iteration=model.best_iteration)cv_scores.append(roc_auc_score(y_val, val_pred))print(cv_scores)print("lgb_scotrainre_list:{}".format(cv_scores))
print("lgb_score_mean:{}".format(np.mean(cv_scores)))
print("lgb_score_std:{}".format(np.std(cv_scores)))在得到基础的模型后就需要对模型进行调整，暂还需要学习。。。
在模型参数已经确定后，建立最终模型并对验证机进行验证
import lightgbm as lgb
"""使用lightgbm 5折交叉验证进行建模预测"""
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train)):print('************************************ {} ************************************'.format(str(i+1)))X_train_split, y_train_split, X_val, y_val = X_train.iloc[train_index], y_train[train_index], X_train.iloc[valid_index], y_train[valid_index]train_matrix = lgb.Dataset(X_train_split, label=y_train_split)valid_matrix = lgb.Dataset(X_val, label=y_val)params = {'boosting_type': 'gbdt','objective': 'binary','metric': 'auc','learning_rate': 0.01,'num_leaves': 14,'max_depth': 19,'min_data_in_leaf': 37,'min_child_weight':1.6,'bagging_fraction': 0.98,'feature_fraction': 0.69,'bagging_freq': 96,'reg_lambda': 9,'reg_alpha': 7,'min_split_gain': 0.4,'nthread': 8,'seed': 2020,'silent': True,}model = lgb.train(params, train_set=train_matrix, num_boost_round=14269, valid_sets=valid_matrix, verbose_eval=1000, early_stopping_rounds=200)val_pred = model.predict(X_val, num_iteration=model.best_iteration)cv_scores.append(roc_auc_score(y_val, val_pred))print(cv_scores)print("lgb_scotrainre_list:{}".format(cv_scores))
print("lgb_score_mean:{}".format(np.mean(cv_scores)))
print("lgb_score_std:{}".format(np.std(cv_scores)))通过验证可以确定最大迭代次数，在简历新模型时直接设置最大迭代次数，并使用验证集进行模型预测
""""""
base_params_lgb = {'boosting_type': 'gbdt','objective': 'binary','metric': 'auc','learning_rate': 0.01,'num_leaves': 14,'max_depth': 19,'min_data_in_leaf': 37,'min_child_weight':1.6,'bagging_fraction': 0.98,'feature_fraction': 0.69,'bagging_freq': 96,'reg_lambda': 9,'reg_alpha': 7,'min_split_gain': 0.4,'nthread': 8,'seed': 2020,'silent': True,
}"""使用训练集数据进行模型训练"""
final_model_lgb = lgb.train(base_params_lgb, train_set=train_matrix, valid_sets=valid_matrix, num_boost_round=13000, verbose_eval=1000, early_stopping_rounds=200)"""预测并计算roc的相关指标"""
val_pre_lgb = final_model_lgb.predict(X_val)
fpr, tpr, threshold = metrics.roc_curve(y_val, val_pre_lgb)
roc_auc = metrics.auc(fpr, tpr)
print('调参后lightgbm单模型在验证集上的AUC：{}'.format(roc_auc))
"""画出roc曲线图"""
plt.figure(figsize=(8, 8))
plt.title('Validation ROC')
plt.plot(fpr, tpr, 'b', label = 'Val AUC = %0.4f' % roc_auc)
plt.ylim(0,1)
plt.xlim(0,1)
plt.legend(loc='best')
plt.title('ROC')
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
# 画出对角线
plt.plot([0,1],[0,1],'r--')
plt.show()最后保存模型到本地
"""保存模型到本地"""
# 保存模型
import pickle
pickle.dump(final_model_lgb, open('dataset/model_lgb_best.pkl', 'wb'))