1 #!/usr/bin/env python2
2 # -*- coding: utf-8 -*-
3 """
4 Created on Sat Mar 31 21:19:09 2018
5
6 @author: hello4720
7 """
8 import numpy as np
9 import pandas as pd
10 import lightgbm as lgb
11 from sklearn import metrics
12 from sklearn.model_selection import train_test_split
13
14 ### 读取数据
15 print("载入数据")
16 dataset1 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data1.csv')
17 dataset2 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data2.csv')
18 dataset3 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data3.csv')
19 dataset4 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data4.csv')
20 dataset5 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data5.csv')
21
22 dataset1.drop_duplicates(inplace=True)
23 dataset2.drop_duplicates(inplace=True)
24 dataset3.drop_duplicates(inplace=True)
25 dataset4.drop_duplicates(inplace=True)
26 dataset5.drop_duplicates(inplace=True)
27
28 ### 数据合并
29 print("数据合并")
30 trains = pd.concat([dataset1,dataset2],axis=0)
31 trains = pd.concat([trains,dataset3],axis=0)
32 trains = pd.concat([trains,dataset4],axis=0)
33
34 online_test = dataset5
35
36 ### 数据拆分
37 print("数据拆分")
38 train_xy,offline_test = train_test_split(trains, test_size = 0.2,random_state=21)
39 train,val = train_test_split(train_xy, test_size = 0.2,random_state=21)
40
41 print("训练集")
42 y = train.is_trade # 训练集标签
43 X = train.drop(['instance_id','is_trade'],axis=1) # 训练集特征矩阵
44
45 print("验证集")
46 val_y = val.is_trade # 验证集标签
47 val_X = val.drop(['instance_id','is_trade'],axis=1) # 验证集特征矩阵
48
49 print("测试集")
50 offline_test_X=offline_test.drop(['instance_id','is_trade'],axis=1) # 线下测试特征矩阵
51 online_test_X=online_test.drop(['instance_id'],axis=1) # 线上测试特征矩阵
52
53 ### 数据转换
54 lgb_train = lgb.Dataset(X, y, free_raw_data=False)
55 lgb_eval = lgb.Dataset(val_X, val_y, reference=lgb_train,free_raw_data=False)
56
57 ### 开始训练
58 print('设置参数')
59 params = {
60 'boosting_type': 'gbdt',
61 'boosting': 'dart',
62 'objective': 'binary',
63 'metric': 'binary_logloss',
64
65 'learning_rate': 0.01,
66 'num_leaves':25,
67 'max_depth':3,
68
69 'max_bin':10,
70 'min_data_in_leaf':8,
71
72 'feature_fraction': 0.6,
73 'bagging_fraction': 1,
74 'bagging_freq':0,
75
76 'lambda_l1': 0,
77 'lambda_l2': 0,
78 'min_split_gain': 0
79 }
80
81 print("开始训练")
82 gbm = lgb.train(params, # 参数字典
83 lgb_train, # 训练集
84 num_boost_round=2000, # 迭代次数
85 valid_sets=lgb_eval, # 验证集
86 early_stopping_rounds=30) # 早停系数
87 ### 线下预测
88 print ("线下预测")
89 preds_offline = gbm.predict(offline_test_X, num_iteration=gbm.best_iteration) # 输出概率
90 offline=offline_test[['instance_id','is_trade']]
91 offline['preds']=preds_offline
92 offline.is_trade = offline['is_trade'].astype(np.float64)
93 print('log_loss', metrics.log_loss(offline.is_trade, offline.preds))
94
95 ### 线上预测
96 print("线上预测")
97 preds_online = gbm.predict(online_test_X, num_iteration=gbm.best_iteration) # 输出概率
98 online=online_test[['instance_id']]
99 online['preds']=preds_online
100 online.rename(columns={'preds':'predicted_score'},inplace=True)
101 online.to_csv("./data/20180405.txt",index=None,sep=' ')
102
103 ### 保存模型
104 from sklearn.externals import joblib
105 joblib.dump(gbm,'gbm.pkl')
106
107 ### 特征选择
108 df = pd.DataFrame(X.columns.tolist(), columns=['feature'])
109 df['importance']=list(gbm.feature_importance())
110 df = df.sort_values(by='importance',ascending=False)
111 df.to_csv("./data/feature_score_20180405.csv",index=None,encoding='gbk')
