模型融合

Datawhale 零基礎入門數據挖掘-Task5 ，賽題：零基礎入門數據挖掘 - 二手車交易價格預測，地址：https://tianchi.aliyun.com/competition/entrance/231784/introduction?spm=5176.12281957.1004.1.38b02448ausjSX

目的

數據調參之後進行的數據模型融合，進而得出實驗數據結果

模型融合的方式方法

1. 簡單加權融合:

   • 迴歸（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，並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

模型融合對測試集和訓練集進行模型篩選，交叉，得到最佳結果的模型策略。達到最好模型預測的結果

迴歸、分類概率融合一般採取：1.簡單加權平均，結果直接融合；2.Stacking融合(迴歸)；

分類模型融合方法：1.Voting投票機制；2.分類的Stacking\Blending融合；3分類的Stacking融合(利用mlxtend)

另外，其他將特徵放進模型中預測，並將預測結果變換並作爲新的特徵加入原有特徵中再經過模型預測結果 （Stacking變化）

代碼部分

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
## 數據讀取
Train_data = pd.read_csv('data/231784/used_car_train_20200313.csv', sep=' ')
TestA_data = pd.read_csv('data/231784/used_car_testA_20200313.csv', sep=' ')

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

Train_data.head()

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

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

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

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

X_test  = TestA_data[feature_cols_test]

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

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)

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

## 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))


## 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)


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)


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

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]

## 測試驗證集準確度
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)

## 預測數據部分
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['SaleID']
sub['price'] = subA
sub.to_csv('./sub_Weighted.csv',index=False)


## 與簡單的LR（線性迴歸）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)

## Starking

## 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)

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

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

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


## level2-method 
model_lr_Stacking = build_model_lr(Strak_X_train,y_train)
## 訓練集
train_pre_Stacking = model_lr_Stacking.predict(Strak_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(Strak_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(Strak_X_test)
MAE of Stacking-LR: 628.399441036
MAE of Stacking-LR: 707.673951794
Predict Stacking-LR...
subA_Stacking[subA_Stacking<10]=10  ## 去除過小的預測值

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

總結

學習了兩個星期，雖然感覺很累，但是總是覺得沒學到什麼，不過慶幸的是，終於把比賽結果提交了，也算是對這一階段的總結吧。後面要更加學習了。模型融合這部分總結，借用大佬的話就是，模型融合分爲對結果，特徵，模型方面融合。