模型融合

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('D:/迅雷下载/二手车数据/used_car_train_20200313.csv', sep=' ')
TestA_data = pd.read_csv('D:/迅雷下载/二手车数据/used_car_test_20200313.csv', sep=' ')

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

(150000, 31)
(50000, 30)

Train_data.head()

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 5923.32733333
_ptp 99988
_std 7501.97346988
_var 56279605.9427

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: 558.212360169
Val mae 693.120168439
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’: 0.1, ‘n_estimators’: 80}

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)

Sta inf of lgb:
_min -126.864734992
_max: 90152.4775557
_mean 5917.96632163
_ptp 90279.3422907
_std 7358.88582391
_var 54153200.5693
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: 730.877443666
Sta inf:
_min -2816.93914153
_max: 88576.7842223
_mean 5920.38233546
_ptp 91393.7233639
_std 7325.20946801
_var 53658693.7502

## 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: 2597.45638384

## Starking

## 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)

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()

Method_1	Method_2	Method_3

0 39682.037093 41029.078125 40552.596813
1 239.498371 266.032654 393.909761
2 6915.162439 7345.680664 7623.552178
3 11861.783785 11721.493164 11463.293245
4 583.773267 513.307983 520.665295

## level2-method 
model_lr_Stacking = build_model_lr(Strak_X_train,y_train)
## 训练集
train_pre_Stacking = model_lr_Stacking.predict(Strak_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(Strak_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(Strak_X_test)

MAE of Stacking-LR: 628.399441036
MAE of Stacking-LR: 707.673951794
Predict Stacking-LR…

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

sub = pd.DataFrame()
sub['SaleID'] = TestA_data.SaleID
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: 90849.3729816
_mean 5917.39429976
_ptp 90839.3729816
_std 7396.09766172
_var 54702260.6217