Task5 模型融合

参考链接：https://github.com/datawhalechina/team-learning-data-mining/blob/master/SecondHandCarPriceForecast/Task5%20%E6%A8%A1%E5%9E%8B%E8%9E%8D%E5%90%88.md

1. 模型融合目标

对于多种调参完成的模型进行模型融合。

2. Stacking相关理论介绍

stacking 是用初始训练数据学习出若干个基学习器后，将这几个学习器的预测结果作为新的训练集，来学习一个新的学习器。
结合策略可以将基学习器结合在一起。分类问题用投票法来选择输出最多的类。回归问题将分类器输出的结果求平均值。
投票法和平均法都是很有效的结合策略，Stacking是另一种结合策略，使用另外一个机器学习算法来将个体机器学习器的结果结合在一起。
在stacking方法中，分为初级学习器（个体学习器）和次级学习器或元学习器（用于结合的学习器）。

3. 代码实现

导包

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

读取数据

Train_data = pd.read_csv('used_car_train_20200313.csv', sep=' ')
TestB_data = pd.read_csv('used_car_testB_20200421.csv', sep=' ')

print(Train_data.shape)
print(TestB_data.shape)

Train_data.head()

查看数据并预处理

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']]

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

X_test  = TestB_data[feature_cols]

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))