二手车交易价格预测task2

## 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
import csv
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

def read_file(path,count=None):
    '''
    定义读取文件的函数
        path: 文件路径
        count: 读取行数
    '''
    # 1
#     list = []
#     with open(path,"r",encoding='UTF-8') as f: #以只读的方式打开文件
#         read_scv=csv.reader(f) #调用csv的reader方法读取文件并赋值给read_scv变量
#         for i,line in enumerate(read_scv):
#             if i == count:
#                 break
#             list.append(line) #将读取到的数据追加到list列表里面
#     list = pd.DataFrame(list)
#     list.columns=['id','heartbeat_signals','label']
#     return list[1:] #返回列表数据
    # 2
    return pd.read_csv(path,sep=' ',nrows = count)

Train_data = read_file('used_car_train_20200313.csv')
TestA_data = read_file('used_car_testA_20200313.csv')

数据字段

• SaleID 交易ID，唯一编码
• name 汽车交易名称，已脱敏
• regDate 汽车注册日期，例如20160101，2016年01月01日
• model 车型编码，已脱敏
• brand 汽车品牌，已脱敏
• bodyType 车身类型：豪华轿车：0，微型车：1，厢型车：2，大巴车：3，敞篷车：4，双门汽车：5，商务车：6，搅拌车：7
• fuelType 燃油类型：汽油：0，柴油：1，液化石油气：2，天然气：3，混合动力：4，其他：5，电动：6
• gearbox 变速箱：手动：0，自动：1
• power 发动机功率：范围 [ 0, 600 ]
• kilometer 汽车已行驶公里，单位万km
• notRepairedDamage 汽车有尚未修复的损坏：是：0，否：1
• regionCode 地区编码，已脱敏
• seller 销售方：个体：0，非个体：1
• offerType 报价类型：提供：0，请求：1
• creatDate 汽车上线时间，即开始售卖时间
• price 二手车交易价格（预测目标）
• 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’（根据汽车的评论、标签等大量信息得到的embedding向量）匿名特征，包含v0-14在内15个匿名特征

数据观察

# 数据纵览
Train_data.head().append(Train_data.tail())
# TestA_data.head().append(TestA_data.tail())

	SaleID	name	regDate	model	brand	bodyType	fuelType	gearbox	power	kilometer	...	v_5	v_6	v_7	v_8	v_9	v_10	v_11	v_12	v_13	v_14
0	0	736	20040402	30.0	6	1.0	0.0	0.0	60	12.5	...	0.235676	0.101988	0.129549	0.022816	0.097462	-2.881803	2.804097	-2.420821	0.795292	0.914762
1	1	2262	20030301	40.0	1	2.0	0.0	0.0	0	15.0	...	0.264777	0.121004	0.135731	0.026597	0.020582	-4.900482	2.096338	-1.030483	-1.722674	0.245522
2	2	14874	20040403	115.0	15	1.0	0.0	0.0	163	12.5	...	0.251410	0.114912	0.165147	0.062173	0.027075	-4.846749	1.803559	1.565330	-0.832687	-0.229963
3	3	71865	19960908	109.0	10	0.0	0.0	1.0	193	15.0	...	0.274293	0.110300	0.121964	0.033395	0.000000	-4.509599	1.285940	-0.501868	-2.438353	-0.478699
4	4	111080	20120103	110.0	5	1.0	0.0	0.0	68	5.0	...	0.228036	0.073205	0.091880	0.078819	0.121534	-1.896240	0.910783	0.931110	2.834518	1.923482
149995	149995	163978	20000607	121.0	10	4.0	0.0	1.0	163	15.0	...	0.280264	0.000310	0.048441	0.071158	0.019174	1.988114	-2.983973	0.589167	-1.304370	-0.302592
149996	149996	184535	20091102	116.0	11	0.0	0.0	0.0	125	10.0	...	0.253217	0.000777	0.084079	0.099681	0.079371	1.839166	-2.774615	2.553994	0.924196	-0.272160
149997	149997	147587	20101003	60.0	11	1.0	1.0	0.0	90	6.0	...	0.233353	0.000705	0.118872	0.100118	0.097914	2.439812	-1.630677	2.290197	1.891922	0.414931
149998	149998	45907	20060312	34.0	10	3.0	1.0	0.0	156	15.0	...	0.256369	0.000252	0.081479	0.083558	0.081498	2.075380	-2.633719	1.414937	0.431981	-1.659014
149999	149999	177672	19990204	19.0	28	6.0	0.0	1.0	193	12.5	...	0.284475	0.000000	0.040072	0.062543	0.025819	1.978453	-3.179913	0.031724	-1.483350	-0.342674

10 rows × 31 columns

#数据行列信息
print('Train data shape:',Train_data.shape)
print('Test data shape:',TestA_data.shape)

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

# 数据信息查看
# 通过info来了解数据每列的type
# Train_data.info()
TestA_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 50000 entries, 0 to 49999
Data columns (total 30 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   SaleID             50000 non-null  int64  
 1   name               50000 non-null  int64  
 2   regDate            50000 non-null  int64  
 3   model              50000 non-null  float64
 4   brand              50000 non-null  int64  
 5   bodyType           48587 non-null  float64
 6   fuelType           47107 non-null  float64
 7   gearbox            48090 non-null  float64
 8   power              50000 non-null  int64  
 9   kilometer          50000 non-null  float64
 10  notRepairedDamage  50000 non-null  object 
 11  regionCode         50000 non-null  int64  
 12  seller             50000 non-null  int64  
 13  offerType          50000 non-null  int64  
 14  creatDate          50000 non-null  int64  
 15  v_0                50000 non-null  float64
 16  v_1                50000 non-null  float64
 17  v_2                50000 non-null  float64
 18  v_3                50000 non-null  float64
 19  v_4                50000 non-null  float64
 20  v_5                50000 non-null  float64
 21  v_6                50000 non-null  float64
 22  v_7                50000 non-null  float64
 23  v_8                50000 non-null  float64
 24  v_9                50000 non-null  float64
 25  v_10               50000 non-null  float64
 26  v_11               50000 non-null  float64
 27  v_12               50000 non-nu