Task5:模型融合

最新推荐文章于 2023-06-05 23:46:10 发布

orangecatcat

最新推荐文章于 2023-06-05 23:46:10 发布

阅读量511

点赞数

文章标签：机器学习 python 数据分析

本文链接：https://blog.csdn.net/orangecatcat/article/details/105316673

版权

Task5:模型融合

5.1 模型融合目标

学习内容来自：https://github.com/datawhalechina/team-learning/blob/master/%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98%E5%AE%9E%E8%B7%B5%EF%BC%88%E4%BA%8C%E6%89%8B%E8%BD%A6%E4%BB%B7%E6%A0%BC%E9%A2%84%E6%B5%8B%EF%BC%89/Task5%20%E6%A8%A1%E5%9E%8B%E8%9E%8D%E5%90%88.md

对于多种调参完成的模型进行模型融合。
完成对于多种模型的融合，提交融合结果并打卡。

5.2 内容介绍

模型融合是比赛后期一个重要的环节，大体来说有如下的类型方式。

简单加权融合:
- 回归（分类概率）：算术平均融合（Arithmetic mean），几何平均融合（Geometric mean）；
- 分类：投票（Voting)
- 综合：排序融合(Rank averaging)，log融合
stacking/blending:
- 构建多层模型，并利用预测结果再拟合预测。
boosting/bagging（在xgboost，Adaboost,GBDT中已经用到）:
- 多树的提升方法

5.3 赛题例子

import pandas as pd
import numpy as np
import warnings
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns

warnings.filterwarnings('ignore')
%matplotlib inline

import itertools
import matplotlib.gridspec as gridspec
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier
# from mlxtend.classifier import StackingClassifier
from sklearn.model_selection import cross_val_score, train_test_split
# from mlxtend.plotting import plot_learning_curves
# from mlxtend.plotting import plot_decision_regions

from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split

from sklearn import linear_model
from sklearn import preprocessing
from sklearn.svm import SVR
from sklearn.decomposition import PCA,FastICA,FactorAnalysis,SparsePCA

import lightgbm as lgb
import xgboost as xgb
from sklearn.model_selection import GridSearchCV,cross_val_score
from sklearn.ensemble import RandomForestRegressor,GradientBoostingRegressor

from sklearn.metrics import mean_squared_error, mean_absolute_error

## 数据读取
Train_data = pd.read_csv('data/used_car_train_20200313.csv', sep=' ')
TestA_data = pd.read_csv('data/used_car_testA_20200313.csv', sep=' ')

print(Train_data.shape)
print(TestA_data.shape)

(150000, 31)
(50000, 30)

Train_data.head()

	SaleID	name	regDate	model	brand	bodyType	gearbox	power	kilometer	...	v_5	v_6	v_7	v_8	v_9	v_10	v_11	v_12	v_13	v_14
0	0	736	20040402	30.0	6	1.0	0.0	60	12.5	...	0.235676	0.101988	0.129549	0.022816	0.097462	-2.881803	2.804097	-2.420821	0.795292	0.914762
1	1	2262	20030301	40.0	1	2.0	0.0	0	15.0	...	0.264777	0.121004	0.135731	0.026597	0.020582	-4.900482	2.096338	-1.030483	-1.722674	0.245522
2	2	14874	20040403	115.0	15	1.0	0.0	163	12.5	...	0.251410	0.114912	0.165147	0.062173	0.027075	-4.846749	1.803559	1.565330	-0.832687	-0.229963
3	3	71865	19960908	109.0	10	0.0	1.0	193	15.0	...	0.274293	0.110300	0.121964	0.033395	0.000000	-4.509599	1.285940	-0.501868	-2.438353	-0.478699
4	4	111080	20120103	110.0	5	1.0	0.0	68	5.0	...	0.228036	0.073205	0.091880	0.078819	0.121534	-1.896240	0.910783	0.931110	2.834518	1.923482

5 rows × 31 columns

numerical_cols = Train_data.select_dtypes(exclude = 'object').columns
print(numerical_cols)

Index(['SaleID', 'name', 'regDate', 'model', 'brand', 'bodyType', 'fuelType',
       'gearbox', 'power', 'kilometer', 'regionCode', 'seller', 'offerType',
       'creatDate', 'price', 'v_0', 'v_1', 'v_2', 'v_3', 'v_4', 'v_5', 'v_6',
       'v_7', 'v_8', 'v_9', 'v_10', 'v_11', 'v_12', 'v_13', 'v_14'],
      dtype='object')

feature_cols = [col for col in numerical_cols if col not in ['SaleID','name','regDate','price']]

X_data = Train_data[feature_cols]
Y_data = Train_data['price']

X_test  = TestA_data[feature_cols]

print('X train shape:',X_data.shape)
print('X test shape:',X_test.shape)

X train shape: (150000, 26)
X test shape: (50000, 26)

def Sta_inf(data):
    print('_min',np.min(data))
    print('_max:',np.max(data))
    print('_mean',np.mean(data))
    print('_ptp',np.ptp(data))
    print('_std',np.std(data))
    print('_var',np.var(data))

print('Sta of label:')
Sta_inf(Y_data)

Sta of label:
_min 11
_max: 99999
_mean 5923.327333333334
_ptp 99988
_std 7501.973469876635
_var 56279605.942732885

X_data = X_data.fillna(-1)
X_test = X_test.fillna(-1)

def build_model_lr(x_train,y_train):
    reg_model = linear_model.LinearRegression()
    reg_model.fit(x_train,y_train)
    return reg_model

def build_model_ridge(x_train,y_train):
    reg_model = linear_model.Ridge(alpha=0.8)#alphas=range(1,100,5)
    reg_model.fit(x_train,y_train)
    return reg_model

def build_model_lasso(x_train,y_train):
    reg_model = linear_model.LassoCV()
    reg_model.fit(x_train,y_train)
    return reg_model

def build_model_gbdt(x_train,y_train):
    estimator =GradientBoostingRegressor(loss='ls',subsample= 0.85,max_depth= 5,n_estimators = 100)
    param_grid = { 
            'learning_rate': [0.05,0.08,0.1,0.2],
            }
    gbdt = GridSearchCV(estimator, param_grid,cv=3)
    gbdt.fit(x_train,y_train)
    print(gbdt.best_params_)
    # print(gbdt.best_estimator_ )
    return gbdt

def build_model_xgb(x_train,y_train):
    model = xgb.XGBRegressor(n_estimators=120, learning_rate=0.08, gamma=0, subsample=0.8,\
        colsample_bytree=0.9, max_depth=5) #, objective ='reg:squarederror'
    model.fit(x_train, y_train)
    return model

def build_model_lgb(x_train,y_train):
    estimator = lgb.LGBMRegressor(num_leaves=63,n_estimators = 100)
    param_grid = {
        'learning_rate': [0.01, 0.05, 0.1],
    }
    gbm = GridSearchCV(estimator, param_grid)
    gbm.fit(x_train, y_train)
    return gbm

## XGBoost的五折交叉回归验证实现
## xgb
xgr = xgb.XGBRegressor(n_estimators=120, learning_rate=0.1, subsample=0.8,\
        colsample_bytree=0.9, max_depth=7) # ,objective ='reg:squarederror'

scores_train = []
scores = []

## 5折交叉验证方式
sk=StratifiedKFold(n_splits=5,shuffle=True,random_state=0)
for train_ind,val_ind in sk.split(X_data,Y_data):
    
    train_x=X_data.iloc[train_ind].values
    train_y=Y_data.iloc[train_ind]
    val_x=X_data.iloc[val_ind].values
    val_y=Y_data.iloc[val_ind]
    
    xgr.fit(train_x,train_y)
    pred_train_xgb=xgr.predict(train_x)
    pred_xgb=xgr.predict(val_x)
    
    score_train = mean_absolute_error(train_y,pred_train_xgb)
    scores_train.append(score_train)
    score = mean_absolute_error(val_y,pred_xgb)
    scores.append(score)

print('Train mae:',np.mean(score_train))
print('Val mae',np.mean(scores))

Train mae: 600.0127885014529
Val mae 691.9976473362078

5.3.1 多种方法训练

# 划分数据集，并用多种方法训练和预测
## Split data with val
x_train,x_val,y_train,y_val = train_test_split(X_data,Y_data,test_size=0.3)

## Train and Predict
print('Predict LR...')
model_lr = build_model_lr(x_train,y_train)
val_lr = model_lr.predict(x_val)
subA_lr = model_lr.predict(X_test)

print('Predict Ridge...')
model_ridge = build_model_ridge(x_train,y_train)
val_ridge = model_ridge.predict(x_val)
subA_ridge = model_ridge.predict(X_test)

print('Predict Lasso...')
model_lasso = build_model_lasso(x_train,y_train)
val_lasso = model_lasso.predict(x_val)
subA_lasso = model_lasso.predict(X_test)

print('Predict GBDT...')
model_gbdt = build_model_gbdt(x_train,y_train)
val_gbdt = model_gbdt.predict(x_val)
subA_gbdt = model_gbdt.predict(X_test)

Predict LR...
Predict Ridge...
Predict Lasso...
Predict GBDT...
{'learning_rate': 0.2}

# 一般比赛中效果最为显著的两种方法
print('predict XGB...')
model_xgb = build_model_xgb(x_train,y_train)
val_xgb = model_xgb.predict(x_val)
subA_xgb = model_xgb.predict(X_test)

print('predict lgb...')
model_lgb = build_model_lgb(x_train,y_train)
val_lgb = model_lgb.predict(x_val)
subA_lgb = model_lgb.predict(X_test)

predict XGB...
predict lgb...

print('Sta inf of lgb:')
Sta_inf(subA_lgb)

Sta inf of lgb:
_min -183.5346885743444
_max: 87514.11713966732
_mean 5926.692984246488
_ptp 87697.65182824167
_std 7371.052328311919
_var 54332412.426712565

5.3.2 加权融合

def Weighted_method(test_pre1,test_pre2,test_pre3,w=[1/3,1/3,1/3]):
    Weighted_result = w[0]*pd.Series(test_pre1)+w[1]*pd.Series(test_pre2)+w[2]*pd.Series(test_pre3)
    return Weighted_result

## Init the Weight
w = [0.3,0.4,0.3]

## 测试验证集准确度
val_pre = Weighted_method(val_lgb,val_xgb,val_gbdt,w)
MAE_Weighted = mean_absolute_error(y_val,val_pre)
print('MAE of Weighted of val:',MAE_Weighted)

## 预测数据部分
subA = Weighted_method(subA_lgb,subA_xgb,subA_gbdt,w)
print('Sta inf:')
Sta_inf(subA)
## 生成提交文件
sub = pd.DataFrame()
sub['SaleID'] = X_test.index
sub['price'] = subA
sub.to_csv('./sub_Weighted.csv',index=False)

MAE of Weighted of val: 722.4371711779407
Sta inf:
_min -748.3094464296096
_max: 86961.51700443946
_mean 5929.89705489961
_ptp 87709.82645086908
_std 7351.960778474033
_var 54051327.28822051

## 与简单的LR（线性回归）进行对比
val_lr_pred = model_lr.predict(x_val)
MAE_lr = mean_absolute_error(y_val,val_lr_pred)
print('MAE of lr:',MAE_lr)

MAE of lr: 2599.193170853424

5.3.3 Stacking融合

## Stacking

## 第一层
train_lgb_pred = model_lgb.predict(x_train)
train_xgb_pred = model_xgb.predict(x_train)
train_gbdt_pred = model_gbdt.predict(x_train)

Stack_X_train = pd.DataFrame()
Stack_X_train['Method_1'] = train_lgb_pred
Stack_X_train['Method_2'] = train_xgb_pred
Stack_X_train['Method_3'] = train_gbdt_pred

Stack_X_val = pd.DataFrame()
Stack_X_val['Method_1'] = val_lgb
Stack_X_val['Method_2'] = val_xgb
Stack_X_val['Method_3'] = val_gbdt

Stack_X_test = pd.DataFrame()
Stack_X_test['Method_1'] = subA_lgb
Stack_X_test['Method_2'] = subA_xgb
Stack_X_test['Method_3'] = subA_gbdt

Stack_X_test.head()

	Method_1	Method_2	Method_3
0	42063.070016	40670.992188	41630.731967
1	316.444941	297.938507	173.515799
2	7245.437440	7426.350098	7495.818904
3	11755.252587	11995.381836	11689.648844
4	539.252642	512.093628	549.944899

## level2-method 
model_lr_Stacking = build_model_lr(Stack_X_train,y_train)
## 训练集
train_pre_Stacking = model_lr_Stacking.predict(Stack_X_train)
print('MAE of Stacking-LR:',mean_absolute_error(y_train,train_pre_Stacking))

## 验证集
val_pre_Stacking = model_lr_Stacking.predict(Stack_X_val)
print('MAE of Stacking-LR:',mean_absolute_error(y_val,val_pre_Stacking))

## 预测集
print('Predict Stacking-LR...')
subA_Stacking = model_lr_Stacking.predict(Stack_X_test)

MAE of Stacking-LR: 628.0883315330257
MAE of Stacking-LR: 711.5275218526992
Predict Stacking-LR...

subA_Stacking[subA_Stacking<10]=10  ## 去除过小的预测值

sub = pd.DataFrame()
sub['SaleID'] = X_test.index
sub['price'] = subA_Stacking
sub.to_csv('./sub_Stacking.csv',index=False)

print('Sta inf:')
Sta_inf(subA_Stacking)

Sta inf:
_min 10.0
_max: 87428.84906583659
_mean 5929.537761262649
_ptp 87418.84906583659
_std 7414.192031815497
_var 54970243.4846364

5.4 经验总结

比赛的融合这个问题，个人的看法来说其实涉及多个层面，也是提分和提升模型鲁棒性的一种重要方法：

1）结果层面的融合，这种是最常见的融合方法，其可行的融合方法也有很多，比如根据结果的得分进行加权融合，还可以做Log，exp处理等。在做结果融合的时候，有一个很重要的条件是模型结果的得分要比较近似，然后结果的差异要比较大，这样的结果融合往往有比较好的效果提升。
2）特征层面的融合，这个层面其实感觉不叫融合，准确说可以叫分割，很多时候如果我们用同种模型训练，可以把特征进行切分给不同的模型，然后在后面进行模型或者结果融合有时也能产生比较好的效果。
3）模型层面的融合，模型层面的融合可能就涉及模型的堆叠和设计，比如加Staking层，部分模型的结果作为特征输入等，这些就需要多实验和思考了，基于模型层面的融合最好不同模型类型要有一定的差异，用同种模型不同的参数的收益一般是比较小的。