天池龙珠数据挖掘训练营 Task6 学习笔记（二手车交易价格预测）

天池龙珠数据挖掘训练营学习笔记

• 天池龙珠数据挖掘训练营 Task1 学习笔记（赛题理解）
• 天池龙珠数据挖掘训练营 Task2 学习笔记（数据分析）
• 天池龙珠数据挖掘训练营 Task3 学习笔记（特征工程）
• 天池龙珠数据挖掘训练营 Task4 学习笔记（建模调参）
• 天池龙珠数据挖掘训练营 Task5 学习笔记（模型融合）
• 天池龙珠数据挖掘训练营 Task6 学习笔记（二手车交易价格预测）

---

---

前言

本节就是将前面一些处理的方法进行综合建模。最后提交到真实的比赛，得到相应的分数。

---

代码

加载数据

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('datalab/231784/used_car_train_20200313.csv', sep=' ')
#TestA_data = pd.read_csv('datalab/231784/used_car_testA_20200313.csv', sep=' ')

path = './data/'
## 1) 载入训练集和测试集；
Train_data = pd.read_csv(path+'train.csv', sep=' ')
TestA_data = pd.read_csv(path+'testB.csv', sep=' ')

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

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

获取特征与标签

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)

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
'''

处理缺失值

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: 605.8937109470886
Val mae 694.2272962269537

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}
GradientBoostingRegressor(alpha=0.9, criterion=‘friedman_mse’, init=None,
learning_rate=0.2, loss=‘ls’, max_depth=5, max_features=None,
max_leaf_nodes=None, min_impurity_decrease=0.0,
min_impurity_split=None, min_samples_leaf=1,
min_samples_split=2, min_weight_fraction_leaf=0.0,
n_estimators=100, presort=‘auto’, random_state=None,
subsample=0.85, verbose=0, warm_start=False)

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)

print('Sta inf of lgb:')
Sta_inf(subA_lgb)
'''
Sta inf of lgb:
_min -462.18157107391255
_max: 91502.77205939365
_mean 5917.571343443128
_ptp 91964.95363046757
_std 7366.829386894228
_var 54270175.215608396
'''

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: 730.6870930823274
Sta inf:
_min -113.68750101924977
_max: 88380.91067520258
_mean 5915.43900009489
_ptp 88494.59817622183
_std 7334.234664443518
_var 53790998.11312493
'''

## 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)

Starking融合

## 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

## 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: 628.3662731003963
MAE of Stacking-LR: 717.1252151815779
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) #成绩为 712.8339

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

总结

1. 将以上代码运行结果提交到竞赛平台，得到相应的成绩如下。
   
2. 模型有很多地方可以优化。比如上面的特征只选了26个特征，在缺失值时只用 -1 进行填充。
3. 许多特征数据不平衡很严重，可以对数处理，归一化处理等。
4. 标签数据也同样存在不平衡性，可以做进一步处理。
5. 除了上述的提到的特征工程外，调参也是一项重要的方向。
   总之通过不断的优化，我相信会有更好的结果。

如果你是从第一个任务看到这里，我很开心，也很感激。谢谢你。
这系列的文章中大量的代码，是从jupyter note 复制过来的，并不能保证完全正确。如果错误和遗漏欢迎你指出。