零基础入门数据挖掘 - 二手车交易价格预测

项目介绍

赛题以预测二手车的交易价格为任务，数据集报名后可见并可下载，该数据来自某交易平台的二手车交易记录，总数据量超过40w，包含31列变量信息，其中15列为匿名变量。为了保证比赛的公平性，将会从中抽取15万条作为训练集，5万条作为测试集A，5万条作为测试集B，同时会对name、model、brand和regionCode等信息进行脱敏。

零基础入门数据挖掘 - 二手车交易价格预测_学习赛_天池大赛-阿里云天池的成绩 (aliyun.com)

导入了若干常用的Python库，这些库主要用于数据处理、模型构建、可视化及评估。

## 基础工具
import numpy as np
import pandas as pd
import warnings
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
from scipy.special import jn
from IPython.display import display, clear_output
import time

warnings.filterwarnings('ignore')
%matplotlib inline

## 模型预测的
from sklearn import linear_model
from sklearn import preprocessing
from sklearn.svm import SVR
from sklearn.ensemble import RandomForestRegressor,GradientBoostingRegressor

## 数据降维处理的
from sklearn.decomposition import PCA,FastICA,FactorAnalysis,SparsePCA

import lightgbm as lgb
import xgboost as xgb

## 参数搜索和评价的
from sklearn.model_selection import GridSearchCV,cross_val_score,StratifiedKFold,train_test_split
from sklearn.metrics import mean_squared_error, mean_absolute_error

数据分析

通过Pandas对于数据进行读取 (pandas是一个很友好的数据读取函数库)

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

## 输出数据的大小信息
print('Train data shape:',Train_data.shape)
print('TestA data shape:',TestA_data.shape)
     
   

Train data shape: (150000, 31)
TestA data shape: (50000, 30)

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')

categorical_cols = Train_data.select_dtypes(include = 'object').columns
print(categorical_cols)

Index(['notRepairedDamage'], dtype='object')

特征工程

• 时间类特征：获取年、月等特征；

• 类别特征：先进行分桶，再进行特征交叉，得到其统计量数据以及峰值与偏度，构造更多特征；

• 匿名特征：由EDA可知，14个匿名特征分布均匀，可以保留，进行特征组合，构造更多的特征，尤其是与预测值强相关的匿名特征。

## 选择特征列
feature_cols = [col for col in numerical_cols if col not in ['SaleID','name','regDate','creatDate','price','model','brand','regionCode','seller']]
feature_cols = [col for col in feature_cols if 'Type' not in col]

## 提前特征列，标签列构造训练样本和测试样本
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, 18)
X test shape: (50000, 18)

## 定义了一个统计函数，方便后续信息统计
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))

X_data = X_data.fillna(-1)
X_test = X_test.fillna(-1)

建模调参

## xgb-Model
xgr = xgb.XGBRegressor(n_estimators=120, learning_rate=0.1, gamma=0, 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_trainmean_absolute_error=(train_y,pred_train_xgb)
    scores_train.append(score)
    score = mean_absolute_error(val_y,pred_xgb)
    scores.append(score)

print('Train mae:',np.mean(score_train))
print('Val mae',np.mean(scores))

---------------------------------------------------------------------------

NameError                                 Traceback (most recent call last)

Cell In[24], line 21
     19 pred_xgb=xgr.predict(val_x)
     20 score_trainmean_absolute_error=(train_y,pred_train_xgb)
---> 21 scores_train.append(score)
     22 score = mean_absolute_error(val_y,pred_xgb)
     23 scores.append(score)


NameError: name 'score' is not defined

def build_model_xgb(x_train,y_train):
    model = xgb.XGBRegressor(n_estimators=150, learning_rate=0.1, gamma=0, subsample=0.8,\
        colsample_bytree=0.9, max_depth=7) #, objective ='reg:squarederror'
    model.fit(x_train, y_train)
    return model

def build_model_lgb(x_train,y_train):
    estimator = lgb.LGBMRegressor(num_leaves=127,n_estimators = 150)
    param_grid = {
        'learning_rate': [0.01, 0.05, 0.1, 0.2],
    }
    gbm = GridSearchCV(estimator, param_grid)
    gbm.fit(x_train, y_train)
    return gbm

## Split data with val
x_train,x_val,y_train,y_val = train_test_split(X_data,Y_data,test_size=0.3)

print('Train lgb...')
model_lgb = build_model_lgb(x_train,y_train)
val_lgb = model_lgb.predict(x_val)
MAE_lgb = mean_absolute_error(y_val,val_lgb)
print('MAE of val with lgb:',MAE_lgb)

print('Predict lgb...')
model_lgb_pre = build_model_lgb(X_data,Y_data)
subA_lgb = model_lgb_pre.predict(X_test)
print('Sta of Predict lgb:')
Sta_inf(subA_lgb)

Sta of Predict lgb:
_min -589.8793550785414
_max: 90760.26063584947
_mean 5906.935218383807
_ptp 91350.13999092802
_std 7344.644970956768
_var 53943809.749400534

print('Train xgb...')
model_xgb = build_model_xgb(x_train,y_train)
val_xgb = model_xgb.predict(x_val)
MAE_xgb = mean_absolute_error(y_val,val_xgb)
print('MAE of val with xgb:',MAE_xgb)

print('Predict xgb...')
model_xgb_pre = build_model_xgb(X_data,Y_data)
subA_xgb = model_xgb_pre.predict(X_test)
print('Sta of Predict xgb:')
Sta_inf(subA_xgb)

Train xgb...
MAE of val with xgb: 701.8386043459124
Predict xgb...
Sta of Predict xgb:
_min -542.2186
_max: 91425.125
_mean 5909.7793
_ptp 91967.34
_std 7352.523
_var 54059590.0

## 这里我们采取了简单的加权融合的方式
val_Weighted = (1-MAE_lgb/(MAE_xgb+MAE_lgb))*val_lgb+(1-MAE_xgb/(MAE_xgb+MAE_lgb))*val_xgb
val_Weighted[val_Weighted<0]=10 # 由于我们发现预测的最小值有负数，而真实情况下，price为负是不存在的，由此我们进行对应的后修正
print('MAE of val with Weighted ensemble:',mean_absolute_error(y_val,val_Weighted))

MAE of val with Weighted ensemble: 682.6768016902015

sub_Weighted = (1-MAE_lgb/(MAE_xgb+MAE_lgb))*subA_lgb+(1-MAE_xgb/(MAE_xgb+MAE_lgb))*subA_xgb

## 查看预测值的统计进行
plt.hist(Y_data)
plt.show()
plt.close()

sub = pd.DataFrame()
sub['SaleID'] = TestA_data.SaleID
sub['price'] = sub_Weighted
sub.to_csv('./sub_Weighted-1.csv',index=False)

sub.head()

	SaleID	price
0	200000	1177.684794
1	200001	1868.829303
2	200002	8525.297256
3	200003	1329.352287
4	200004	2052.231852