天池&DataWhale：Task05：模型融合

天池&DataWhale：Task05：模型融合

專案地址：https://github.com/datawhalechina/team-learning-data-mining/tree/master/FinancialRiskControl

比賽地址：https://tianchi.aliyun.com/competition/entrance/531830/introduction

模型融合目標

• 對于多種調參完成的模型進行模型融合，

• 完成對于多種模型的融合，提交融合結果并打卡，

內容介紹

模型融合是比賽后期一個重要的環節，大體來說有如下的型別方式，

1. 簡單加權融合:

   • 回歸（分類概率）：算術平均融合（Arithmetic mean），幾何平均融合（Geometric mean）；
   • 分類：投票（Voting)
   • 綜合：排序融合(Rank averaging)，log融合

2. stacking/blending:

   • 構建多層模型，并利用預測結果再擬合預測，

3. boosting/bagging（在xgboost，Adaboost,GBDT中已經用到）:

   • 多樹的提升方法

DEMO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



## 資料讀取
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()

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的五折交叉回歸驗證實作
## 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折交叉驗證方式
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

多種方法訓練

# 劃分資料集，并用多種方法訓練和預測
## 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}


# 一般比賽中效果最為顯著的兩種方法
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

加權融合

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]

## 測驗驗證集準確度
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)

## 預測資料部分
subA = Weighted_method(subA_lgb,subA_xgb,subA_gbdt,w)
print('Sta inf:')
Sta_inf(subA)
## 生成提交檔案
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


## 與簡單的LR（線性回歸）進行對比
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

Stacking融合

## Stacking

## 第一層
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()

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

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

## 預測集
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  ## 去除過小的預測值

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

經驗總結

• 1）結果層面的融合，這種是最常見的融合方法，其可行的融合方法也有很多，比如根據結果的得分進行加權融合，還可以做Log，exp處理等，在做結果融合的時候，有一個很重要的條件是模型結果的得分要比較近似，然后結果的差異要比較大，這樣的結果融合往往有比較好的效果提升，

• 2）特征層面的融合，這個層面其實感覺不叫融合，準確說可以叫分割，很多時候如果我們用同種模型訓練，可以把特征進行切分給不同的模型，然后在后面進行模型或者結果融合有時也能產生比較好的效果，

• 3）模型層面的融合，模型層面的融合可能就涉及模型的堆疊和設計，比如加Staking層，部分模型的結果作為特征輸入等，這些就需要多實驗和思考了，基于模型層面的融合最好不同模型型別要有一定的差異，用同種模型不同的引數的收益一般是比較小的，