房价预测A

import pandas as pd     # 工具
import numpy as np
import joblib
import os

from sklearn.preprocessing import PowerTransformer, PolynomialFeatures, StandardScaler, LabelEncoder      # 预处理
from sklearn.ensemble import RandomForestRegressor      # 离群点和错误值筛选
from sklearn.ensemble import IsolationForest
from sklearn.feature_selection import variance_threshold    # 特征选择
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split, cross_val_score, KFold    # 切分数据集
from sklearn.linear_model import Lasso, Ridge, LinearRegression     # 算法
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
from mlxtend import regressor
from sklearn.metrics import mean_absolute_error, r2_score, mean_squared_error   # 评分
from hyperopt import Trials, tpe, pyll, fmin, hp    # 动态调参
import functools
import time
import matplotlib.pyplot as plt

E:\anaconda\envs\pd\lib\site-packages\sklearn\utils\deprecation.py:144: FutureWarning: The sklearn.feature_selection.variance_threshold module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)

'''
# 注：
# 1.以下数据处理均为非先验数据处理，即行业小白不主观合并特征，只有常规数据处理。
# 2.限于时间关系，这个程序没有进行模块化和严格调参，只是为了得到较高的R2以及验证思路的正确。

# 创新点1: 发现lasso回归更偏向于提取相关特征，而随机森林更偏向提取非相关特征，set(feature(随机森林)>阈值)-set(feature(Lasso）>阈值)可以提取非相关性特征。
# 由于特征处理一般会用相关系数提取特征的方法，加上这些非相关特征有奇效。
# 创新点2：数据小的话，可以遍历，去除对分数影响大的离群点；数量大的话时间会变慢，解决办法：一个是应用分布式来计算，
# 另一个可以将数据划分N份，观察每份均值。比如150个数据，分为 15组*10个(记为a1~15) 或者 10组*15个(记为：b1~10)，分别测定。
# 如果a1和b1偏离均值，说明a1前五个可能含有离群点，分别测定。
'''

pd.set_option("display.max_columns", 500)
pd.set_option("display.width", 1000)
pd.set_option("display.max_rows", 500)
# pd.set_option("display.height", 1000)  # 测试时不能进行行高设置

train = pd.read_csv("E:/python/house_predict/data/train.csv")
x_test = pd.read_csv("E:/python/house_predict/data/test.csv")
y_test = pd.read_csv('E:/python/house_predict/data/sample_submission.csv')

train.shape, x_test.shape, y_test.shape

((1460, 81), (1459, 80), (1459, 2))

test = pd.concat([x_test, y_test.iloc[:, [-1]]], axis=1)

test.shape

(1459, 81)

str_col_list = ["MSSubClass", "OverallCond", "YrSold", "MoSold", "OverallQual"]
for col in str_col_list:
    train.loc[:, col] = train.loc[:, col].astype(str)

train.head()

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	LotConfig	LandSlope	Neighborhood	Condition1	Condition2	BldgType	HouseStyle	OverallQual	OverallCond	YearBuilt	YearRemodAdd	RoofStyle	RoofMatl	Exterior1st	Exterior2nd	MasVnrType	MasVnrArea	ExterQual	ExterCond	Foundation	BsmtQual	BsmtCond	BsmtExposure	BsmtFinType1	BsmtFinSF1	BsmtFinType2	BsmtFinSF2	BsmtUnfSF	TotalBsmtSF	Heating	HeatingQC	CentralAir	Electrical	1stFlrSF	2ndFlrSF	LowQualFinSF	GrLivArea	BsmtFullBath	BsmtHalfBath	FullBath	HalfBath	BedroomAbvGr	KitchenAbvGr	KitchenQual	TotRmsAbvGrd	Functional	Fireplaces	FireplaceQu	GarageType	GarageYrBlt	GarageFinish	GarageCars	GarageArea	GarageQual	GarageCond	PavedDrive	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	PoolQC	Fence	MiscFeature	MiscVal	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	Inside	Gtl	CollgCr	Norm	Norm	1Fam	2Story	7	5	2003	2003	Gable	CompShg	VinylSd	VinylSd	BrkFace	196.0	Gd	TA	PConc	Gd	TA	No	GLQ	706	Unf	0	150	856	GasA	Ex	Y	SBrkr	856	854	0	1710	1	0	2	1	3	1	Gd	8	Typ	0	NaN	Attchd	2003.0	RFn	2	548	TA	TA	Y	0	61	0	0	0	0	NaN	NaN	NaN	0	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	FR2	Gtl	Veenker	Feedr	Norm	1Fam	1Story	6	8	1976	1976	Gable	CompShg	MetalSd	MetalSd	None	0.0	TA	TA	CBlock	Gd	TA	Gd	ALQ	978	Unf	0	284	1262	GasA	Ex	Y	SBrkr	1262	0	0	1262	0	1	2	0	3	1	TA	6	Typ	1	TA	Attchd	1976.0	RFn	2	460	TA	TA	Y	298	0	0	0	0	0	NaN	NaN	NaN	0	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	Inside	Gtl	CollgCr	Norm	Norm	1Fam	2Story	7	5	2001	2002	Gable	CompShg	VinylSd	VinylSd	BrkFace	162.0	Gd	TA	PConc	Gd	TA	Mn	GLQ	486	Unf	0	434	920	GasA	Ex	Y	SBrkr	920	866	0	1786	1	0	2	1	3	1	Gd	6	Typ	1	TA	Attchd	2001.0	RFn	2	608	TA	TA	Y	0	42	0	0	0	0	NaN	NaN	NaN	0	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	Corner	Gtl	Crawfor	Norm	Norm	1Fam	2Story	7	5	1915	1970	Gable	CompShg	Wd Sdng	Wd Shng	None	0.0	TA	TA	BrkTil	TA	Gd	No	ALQ	216	Unf	0	540	756	GasA	Gd	Y	SBrkr	961	756	0	1717	1	0	1	0	3	1	Gd	7	Typ	1	Gd	Detchd	1998.0	Unf	3	642	TA	TA	Y	0	35	272	0	0	0	NaN	NaN	NaN	0	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	FR2	Gtl	NoRidge	Norm	Norm	1Fam	2Story	8	5	2000	2000	Gable	CompShg	VinylSd	VinylSd	BrkFace	350.0	Gd	TA	PConc	Gd	TA	Av	GLQ	655	Unf	0	490	1145	GasA	Ex	Y	SBrkr	1145	1053	0	2198	1	0	2	1	4	1	Gd	9	Typ	1	TA	Attchd	2000.0	RFn	3	836	TA	TA	Y	192	84	0	0	0	0	NaN	NaN	NaN	0	12	2008	WD	Normal	250000

missinglist = train.isnull().sum()[train.isnull().sum() != 0]

pd.concat([missinglist, train.loc[:, missinglist.index].dtypes], axis=1)

	0	1
LotFrontage	259	float64
Alley	1369	object
MasVnrType	8	object
MasVnrArea	8	float64
BsmtQual	37	object
BsmtCond	37	object
BsmtExposure	38	object
BsmtFinType1	37	object
BsmtFinType2	38	object
Electrical	1	object
FireplaceQu	690	object
GarageType	81	object
GarageYrBlt	81	float64
GarageFinish	81	object
GarageQual	81	object
GarageCond	81	object
PoolQC	1453	object
Fence	1179	object
MiscFeature	1406	object

missing_df = pd.concat([missinglist, train.loc[:, missinglist.index].dtypes], axis=1)
missing_int_list = missing_df.loc[missing_df.iloc[:, 1] != 'object', :].index.tolist()
missing_str_list = missing_df.loc[missing_df.iloc[:, 1] == 'object', :].index.tolist()

missing_int_list, missing_str_list

(['LotFrontage', 'MasVnrArea', 'GarageYrBlt'],
 ['Alley',
  'MasVnrType',
  'BsmtQual',
  'BsmtCond',
  'BsmtExposure',
  'BsmtFinType1',
  'BsmtFinType2',
  'Electrical',
  'FireplaceQu',
  'GarageType',
  'GarageFinish',
  'GarageQual',
  'GarageCond',
  'PoolQC',
  'Fence',
  'MiscFeature'])

train.loc[:, missing_int_list] = train.loc[:, missing_int_list].fillna(0)

train.loc[:, missing_str_list] = train.loc[:, missing_str_list].fillna('AN')

train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 81 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1460 non-null   int64  
 1   MSSubClass     1460 non-null   object 
 2   MSZoning       1460 non-null   object 
 3   LotFrontage    1460 non-null   float64
 4   LotArea        1460 non-null   int64  
 5   Street         1460 non-null   object 
 6   Alley          1460 non-null   object 
 7   LotShape       1460 non-null   object 
 8   LandContour    1460 non-null   object 
 9   Utilities      1460 non-null   object 
 10  LotConfig      1460 non-null   object 
 11  LandSlope      1460 non-null   object 
 12  Neighborhood   1460 non-null   object 
 13  Condition1     1460 non-null   object 
 14  Condition2     1460 non-null   object 
 15  BldgType       1460 non-null   object 
 16  HouseStyle     1460 non-null   object 
 17  OverallQual    1460 non-null   object 
 18  OverallCond    1460 non-null   object 
 19  YearBuilt      1460 non-null   int64  
 20  YearRemodAdd   1460 non-null   int64  
 21  RoofStyle      1460 non-null   object 
 22  RoofMatl       1460 non-null   object 
 23  Exterior1st    1460 non-null   object 
 24  Exterior2nd    1460 non-null   object 
 25  MasVnrType     1460 non-null   object 
 26  MasVnrArea     1460 non-null   float64
 27  ExterQual      1460 non-null   object 
 28  ExterCond      1460 non-null   object 
 29  Foundation     1460 non-null   object 
 30  BsmtQual       1460 non-null   object 
 31  BsmtCond       1460 non-null   object 
 32  BsmtExposure   1460 non-null   object 
 33  BsmtFinType1   1460 non-null   object 
 34  BsmtFinSF1     1460 non-null   int64  
 35  BsmtFinType2   1460 non-null   object 
 36  BsmtFinSF2     1460 non-null   int64  
 37  BsmtUnfSF      1460 non-null   int64  
 38  TotalBsmtSF    1460 non-null   int64  
 39  Heating        1460 non-null   object 
 40  HeatingQC      1460 non-null   object 
 41  CentralAir     1460 non-null   object 
 42  Electrical     1460 non-null   object 
 43  1stFlrSF       1460 non-null   int64  
 44  2ndFlrSF       1460 non-null   int64  
 45  LowQualFinSF   1460 non-null   int64  
 46  GrLivArea      1460 non-null   int64  
 47  BsmtFullBath   1460 non-null   int64  
 48  BsmtHalfBath   1460 non-null   int64  
 49  FullBath       1460 non-null   int64  
 50  HalfBath       1460 non-null   int64  
 51  BedroomAbvGr   1460 non-null   int64  
 52  KitchenAbvGr   1460 non-null   int64  
 53  KitchenQual    1460 non-null   object 
 54  TotRmsAbvGrd   1460 non-null   int64  
 55  Functional     1460 non-null   object 
 56  Fireplaces     1460 non-null   int64  
 57  FireplaceQu    1460 non-null   object 
 58  GarageType     1460 non-null   object 
 59  GarageYrBlt    1460 non-null   float64
 60  GarageFinish   1460 non-null   object 
 61  GarageCars     1460 non-null   int64  
 62  GarageArea     1460 non-null   int64  
 63  GarageQual     1460 non-null   object 
 64  GarageCond     1460 non-null   object 
 65  PavedDrive     1460 non-null   object 
 66  WoodDeckSF     1460 non-null   int64  
 67  OpenPorchSF    1460 non-null   int64  
 68  EnclosedPorch  1460 non-null   int64  
 69  3SsnPorch      1460 non-null   int64  
 70  ScreenPorch    1460 non-null   int64  
 71  PoolArea       1460 non-null   int64  
 72  PoolQC         1460 non-null   object 
 73  Fence          1460 non-null   object 
 74  MiscFeature    1460 non-null   object 
 75  MiscVal        1460 non-null   int64  
 76  MoSold         1460 non-null   object 
 77  YrSold         1460 non-null   object 
 78  SaleType       1460 non-null   object 
 79  SaleCondition  1460 non-null   object 
 80  SalePrice      1460 non-null   int64  
dtypes: float64(3), int64(30), object(48)
memory usage: 924.0+ KB

rfr = RandomForestRegressor(500, n_jobs=-1, random_state=42)

train.drop(['Id'], axis=1, inplace=True)

train.shape

(1460, 80)

rfr.fit(train.iloc[:, 0:-1], train.iloc[:, [-1]])

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

ValueError                                Traceback (most recent call last)

<ipython-input-20-21f43b35ac6b> in <module>
----> 1 rfr.fit(train.iloc[:, 0:-1], train.iloc[:, [-1]])


E:\anaconda\envs\pd\lib\site-packages\sklearn\ensemble\_forest.py in fit(self, X, y, sample_weight)
    293         """
    294         # Validate or convert input data
--> 295         X = check_array(X, accept_sparse="csc", dtype=DTYPE)
    296         y = check_array(y, accept_sparse='csc', ensure_2d=False, dtype=None)
    297         if sample_weight is not None:


E:\anaconda\envs\pd\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    529                     array = array.astype(dtype, casting="unsafe", copy=False)
    530                 else:
--> 531                     array = np.asarray(array, order=order, dtype=dtype)
    532             except ComplexWarning:
    533                 raise ValueError("Complex data not supported\n"


E:\anaconda\envs\pd\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 


ValueError: could not convert string to float: 'RL'

train.corr()

	LotFrontage	LotArea	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	BsmtFinSF2	BsmtUnfSF	TotalBsmtSF	1stFlrSF	2ndFlrSF	LowQualFinSF	GrLivArea	BsmtFullBath	BsmtHalfBath	FullBath	HalfBath	BedroomAbvGr	KitchenAbvGr	TotRmsAbvGrd	Fireplaces	GarageYrBlt	GarageCars	GarageArea	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	SalePrice
LotFrontage	1.000000	0.100739	0.036853	0.078686	0.105010	0.076670	-0.009312	0.160829	0.238274	0.245181	0.042549	0.049981	0.220347	0.010514	-0.027856	0.120548	-0.012952	0.144494	0.034425	0.221396	0.044018	0.019317	0.165229	0.201473	-0.016780	0.069605	0.027366	0.023499	0.022969	0.114106	-0.059606	0.209624
LotArea	0.100739	1.000000	0.014228	0.013788	0.103321	0.214103	0.111170	-0.002618	0.260833	0.299475	0.050986	0.004779	0.263116	0.158155	0.048046	0.126031	0.014259	0.119690	-0.017784	0.190015	0.271364	0.072599	0.154871	0.180403	0.171698	0.084774	-0.018340	0.020423	0.043160	0.077672	0.038068	0.263843
YearBuilt	0.036853	0.014228	1.000000	0.592855	0.311600	0.249503	-0.049107	0.149040	0.391452	0.281986	0.010308	-0.183784	0.199010	0.187599	-0.038162	0.468271	0.242656	-0.070651	-0.174800	0.095589	0.147716	0.272029	0.537850	0.478954	0.224880	0.188686	-0.387268	0.031355	-0.050364	0.004950	-0.034383	0.522897
YearRemodAdd	0.078686	0.013788	0.592855	1.000000	0.176529	0.128451	-0.067759	0.181133	0.291066	0.240379	0.140024	-0.062419	0.287389	0.119470	-0.012337	0.439046	0.183331	-0.040581	-0.149598	0.191740	0.112581	0.146357	0.420622	0.371600	0.205726	0.226298	-0.193919	0.045286	-0.038740	0.005829	-0.010286	0.507101
MasVnrArea	0.105010	0.103321	0.311600	0.176529	1.000000	0.261256	-0.071330	0.113862	0.360067	0.339850	0.173800	-0.068628	0.388052	0.083010	0.027403	0.272999	0.199108	0.102775	-0.038450	0.279568	0.247015	0.132696	0.361945	0.370884	0.159991	0.122528	-0.109907	0.019144	0.062248	0.011928	-0.029512	0.472614
BsmtFinSF1	0.076670	0.214103	0.249503	0.128451	0.261256	1.000000	-0.050117	-0.495251	0.522396	0.445863	-0.137079	-0.064503	0.208171	0.649212	0.067418	0.058543	0.004262	-0.107355	-0.081007	0.044316	0.260011	0.115843	0.224054	0.296970	0.204306	0.111761	-0.102303	0.026451	0.062021	0.140491	0.003571	0.386420
BsmtFinSF2	-0.009312	0.111170	-0.049107	-0.067759	-0.071330	-0.050117	1.000000	-0.209294	0.104810	0.097117	-0.099260	0.014807	-0.009640	0.158678	0.070948	-0.076444	-0.032148	-0.015728	-0.040751	-0.035227	0.046921	0.035070	-0.038264	-0.018227	0.067898	0.003093	0.036543	-0.029993	0.088871	0.041709	0.004940	-0.011378
BsmtUnfSF	0.160829	-0.002618	0.149040	0.181133	0.113862	-0.495251	-0.209294	1.000000	0.415360	0.317987	0.004469	0.028167	0.240257	-0.422900	-0.095804	0.288886	-0.041118	0.166643	0.030086	0.250647	0.051575	0.042720	0.214175	0.183303	-0.005316	0.129005	-0.002538	0.020764	-0.012579	-0.035092	-0.023837	0.214479
TotalBsmtSF	0.238274	0.260833	0.391452	0.291066	0.360067	0.522396	0.104810	0.415360	1.000000	0.819530	-0.174512	-0.033245	0.454868	0.307351	-0.000315	0.323722	-0.048804	0.050450	-0.068901	0.285573	0.339519	0.176359	0.434585	0.486665	0.232019	0.247264	-0.095478	0.037384	0.084489	0.126053	-0.018479	0.613581
1stFlrSF	0.245181	0.299475	0.281986	0.240379	0.339850	0.445863	0.097117	0.317987	0.819530	1.000000	-0.202646	-0.014241	0.566024	0.244671	0.001956	0.380637	-0.119916	0.127401	0.068101	0.409516	0.410531	0.166642	0.439317	0.489782	0.235459	0.211671	-0.065292	0.056104	0.088758	0.131525	-0.021096	0.605852
2ndFlrSF	0.042549	0.050986	0.010308	0.140024	0.173800	-0.137079	-0.099260	0.004469	-0.174512	-0.202646	1.000000	0.063353	0.687501	-0.169494	-0.023855	0.421378	0.609707	0.502901	0.059306	0.616423	0.194561	0.064402	0.183926	0.138347	0.092165	0.208026	0.061989	-0.024358	0.040606	0.081487	0.016197	0.319334
LowQualFinSF	0.049981	0.004779	-0.183784	-0.062419	-0.068628	-0.064503	0.014807	0.028167	-0.033245	-0.014241	0.063353	1.000000	0.134683	-0.047143	-0.005842	-0.000710	-0.027080	0.105607	0.007522	0.131185	-0.021272	-0.146467	-0.094480	-0.067601	-0.025444	0.018251	0.061081	-0.004296	0.026799	0.062157	-0.003793	-0.025606
GrLivArea	0.220347	0.263116	0.199010	0.287389	0.388052	0.208171	-0.009640	0.240257	0.454868	0.566024	0.687501	0.134683	1.000000	0.034836	-0.018918	0.630012	0.415772	0.521270	0.100063	0.825489	0.461679	0.162543	0.467247	0.468997	0.247433	0.330224	0.009113	0.020643	0.101510	0.170205	-0.002416	0.708624
BsmtFullBath	0.010514	0.158155	0.187599	0.119470	0.083010	0.649212	0.158678	-0.422900	0.307351	0.244671	-0.169494	-0.047143	0.034836	1.000000	-0.147871	-0.064512	-0.030905	-0.150673	-0.041503	-0.053275	0.137928	0.049270	0.131881	0.179189	0.175315	0.067341	-0.049911	-0.000106	0.023148	0.067616	-0.023047	0.227122
BsmtHalfBath	-0.027856	0.048046	-0.038162	-0.012337	0.027403	0.067418	0.070948	-0.095804	-0.000315	0.001956	-0.023855	-0.005842	-0.018918	-0.147871	1.000000	-0.054536	-0.012340	0.046519	-0.037944	-0.023836	0.028976	0.016811	-0.020891	-0.024536	0.040161	-0.025324	-0.008555	0.035114	0.032121	0.020025	-0.007367	-0.016844
FullBath	0.120548	0.126031	0.468271	0.439046	0.272999	0.058543	-0.076444	0.288886	0.323722	0.380637	0.421378	-0.000710	0.630012	-0.064512	-0.054536	1.000000	0.136381	0.363252	0.133115	0.554784	0.243671	0.137464	0.469672	0.405656	0.187703	0.259977	-0.115093	0.035353	-0.008106	0.049604	-0.014290	0.560664
HalfBath	-0.012952	0.014259	0.242656	0.183331	0.199108	0.004262	-0.032148	-0.041118	-0.048804	-0.119916	0.609707	-0.027080	0.415772	-0.030905	-0.012340	0.136381	1.000000	0.226651	-0.068263	0.343415	0.203649	0.117166	0.219178	0.163549	0.108080	0.199740	-0.095317	-0.004972	0.072426	0.022381	0.001290	0.284108
BedroomAbvGr	0.144494	0.119690	-0.070651	-0.040581	0.102775	-0.107355	-0.015728	0.166643	0.050450	0.127401	0.502901	0.105607	0.521270	-0.150673	0.046519	0.363252	0.226651	1.000000	0.198597	0.676620	0.107570	-0.009850	0.086106	0.065253	0.046854	0.093810	0.041570	-0.024478	0.044300	0.070703	0.007767	0.168213
KitchenAbvGr	0.034425	-0.017784	-0.174800	-0.149598	-0.038450	-0.081007	-0.040751	0.030086	-0.068901	0.068101	0.059306	0.007522	0.100063	-0.041503	-0.037944	0.133115	-0.068263	0.198597	1.000000	0.256045	-0.123936	-0.157991	-0.050634	-0.064433	-0.090130	-0.070091	0.037312	-0.024600	-0.051613	-0.014525	0.062341	-0.135907
TotRmsAbvGrd	0.221396	0.190015	0.095589	0.191740	0.279568	0.044316	-0.035227	0.250647	0.285573	0.409516	0.616423	0.131185	0.825489	-0.053275	-0.023836	0.554784	0.343415	0.676620	0.256045	1.000000	0.326114	0.095607	0.362289	0.337822	0.165984	0.234192	0.004151	-0.006683	0.059383	0.083757	0.024763	0.533723
Fireplaces	0.044018	0.271364	0.147716	0.112581	0.247015	0.260011	0.046921	0.051575	0.339519	0.410531	0.194561	-0.021272	0.461679	0.137928	0.028976	0.243671	0.203649	0.107570	-0.123936	0.326114	1.000000	0.186264	0.300789	0.269141	0.200019	0.169405	-0.024822	0.011257	0.184530	0.095074	0.001409	0.466929
GarageYrBlt	0.019317	0.072599	0.272029	0.146357	0.132696	0.115843	0.035070	0.042720	0.176359	0.166642	0.064402	-0.146467	0.162543	0.049270	0.016811	0.137464	0.117166	-0.009850	-0.157991	0.095607	0.186264	1.000000	0.598005	0.560783	0.117305	0.049877	-0.076822	0.029401	0.061416	0.015858	-0.006669	0.261366
GarageCars	0.165229	0.154871	0.537850	0.420622	0.361945	0.224054	-0.038264	0.214175	0.434585	0.439317	0.183926	-0.094480	0.467247	0.131881	-0.020891	0.469672	0.219178	0.086106	-0.050634	0.362289	0.300789	0.598005	1.000000	0.882475	0.226342	0.213569	-0.151434	0.035765	0.050494	0.020934	-0.043080	0.640409
GarageArea	0.201473	0.180403	0.478954	0.371600	0.370884	0.296970	-0.018227	0.183303	0.486665	0.489782	0.138347	-0.067601	0.468997	0.179189	-0.024536	0.405656	0.163549	0.065253	-0.064433	0.337822	0.269141	0.560783	0.882475	1.000000	0.224666	0.241435	-0.121777	0.035087	0.051412	0.061047	-0.027400	0.623431
WoodDeckSF	-0.016780	0.171698	0.224880	0.205726	0.159991	0.204306	0.067898	-0.005316	0.232019	0.235459	0.092165	-0.025444	0.247433	0.175315	0.040161	0.187703	0.108080	0.046854	-0.090130	0.165984	0.200019	0.117305	0.226342	0.224666	1.000000	0.058661	-0.125989	-0.032771	-0.074181	0.073378	-0.009551	0.324413
OpenPorchSF	0.069605	0.084774	0.188686	0.226298	0.122528	0.111761	0.003093	0.129005	0.247264	0.211671	0.208026	0.018251	0.330224	0.067341	-0.025324	0.259977	0.199740	0.093810	-0.070091	0.234192	0.169405	0.049877	0.213569	0.241435	0.058661	1.000000	-0.093079	-0.005842	0.074304	0.060762	-0.018584	0.315856
EnclosedPorch	0.027366	-0.018340	-0.387268	-0.193919	-0.109907	-0.102303	0.036543	-0.002538	-0.095478	-0.065292	0.061989	0.061081	0.009113	-0.049911	-0.008555	-0.115093	-0.095317	0.041570	0.037312	0.004151	-0.024822	-0.076822	-0.151434	-0.121777	-0.125989	-0.093079	1.000000	-0.037305	-0.082864	0.054203	0.018361	-0.128578
3SsnPorch	0.023499	0.020423	0.031355	0.045286	0.019144	0.026451	-0.029993	0.020764	0.037384	0.056104	-0.024358	-0.004296	0.020643	-0.000106	0.035114	0.035353	-0.004972	-0.024478	-0.024600	-0.006683	0.011257	0.029401	0.035765	0.035087	-0.032771	-0.005842	-0.037305	1.000000	-0.031436	-0.007992	0.000354	0.044584
ScreenPorch	0.022969	0.043160	-0.050364	-0.038740	0.062248	0.062021	0.088871	-0.012579	0.084489	0.088758	0.040606	0.026799	0.101510	0.023148	0.032121	-0.008106	0.072426	0.044300	-0.051613	0.059383	0.184530	0.061416	0.050494	0.051412	-0.074181	0.074304	-0.082864	-0.031436	1.000000	0.051307	0.031946	0.111447
PoolArea	0.114106	0.077672	0.004950	0.005829	0.011928	0.140491	0.041709	-0.035092	0.126053	0.131525	0.081487	0.062157	0.170205	0.067616	0.020025	0.049604	0.022381	0.070703	-0.014525	0.083757	0.095074	0.015858	0.020934	0.061047	0.073378	0.060762	0.054203	-0.007992	0.051307	1.000000	0.029669	0.092404
MiscVal	-0.059606	0.038068	-0.034383	-0.010286	-0.029512	0.003571	0.004940	-0.023837	-0.018479	-0.021096	0.016197	-0.003793	-0.002416	-0.023047	-0.007367	-0.014290	0.001290	0.007767	0.062341	0.024763	0.001409	-0.006669	-0.043080	-0.027400	-0.009551	-0.018584	0.018361	0.000354	0.031946	0.029669	1.000000	-0.021190
SalePrice	0.209624	0.263843	0.522897	0.507101	0.472614	0.386420	-0.011378	0.214479	0.613581	0.605852	0.319334	-0.025606	0.708624	0.227122	-0.016844	0.560664	0.284108	0.168213	-0.135907	0.533723	0.466929	0.261366	0.640409	0.623431	0.324413	0.315856	-0.128578	0.044584	0.111447	0.092404	-0.021190	1.000000

train.corr().shape

(32, 32)

corr_int_sr = train.corr().sort_values(by='SalePrice').iloc[:, -1].sort_values(ascending=False)
train.corr().sort_values(by='SalePrice').iloc[:, -1].sort_values(ascending=False)

SalePrice        1.000000
GrLivArea        0.708624
GarageCars       0.640409
GarageArea       0.623431
TotalBsmtSF      0.613581
1stFlrSF         0.605852
FullBath         0.560664
TotRmsAbvGrd     0.533723
YearBuilt        0.522897
YearRemodAdd     0.507101
MasVnrArea       0.472614
Fireplaces       0.466929
BsmtFinSF1       0.386420
WoodDeckSF       0.324413
2ndFlrSF         0.319334
OpenPorchSF      0.315856
HalfBath         0.284108
LotArea          0.263843
GarageYrBlt      0.261366
BsmtFullBath     0.227122
BsmtUnfSF        0.214479
LotFrontage      0.209624
BedroomAbvGr     0.168213
ScreenPorch      0.111447
PoolArea         0.092404
3SsnPorch        0.044584
BsmtFinSF2      -0.011378
BsmtHalfBath    -0.016844
MiscVal         -0.021190
LowQualFinSF    -0.025606
EnclosedPorch   -0.128578
KitchenAbvGr    -0.135907
Name: SalePrice, dtype: float64

train_int = train.loc[:, train.dtypes != 'object']

train_str = train.loc[:, train.dtypes == 'object']

list(train.loc[:, 'SalePrice'].groupby(train_str.loc[:, 'OverallQual']).mean().sort_values().index)

['1', '2', '3', '4', '5', '6', '7', '8', '9', '10']

train_new = train.copy()
corr_str_list = []
lbl = LabelEncoder()
for col in list(train_str.columns):
    # lbl.fit(train.loc[:, 'OverallQual'])
    lbl.classes_ = list(train.loc[:, 'SalePrice'].groupby(train_str.loc[:, col]).mean().sort_values().index)
    train_new.loc[:, col] = lbl.transform(train.loc[:, col])
    corr_str_list.append(pd.concat([pd.DataFrame(lbl.transform(train.loc[:, col])), np.log1p(train.iloc[:, -1])], axis=1).corr('spearman').iloc[0, 1])
corr_str_sr = pd.Series(data=corr_str_list, index=train_str.columns)
corr_str_sr.sort_values(ascending=False)

OverallQual      0.809829
Neighborhood     0.755779
ExterQual        0.684014
BsmtQual         0.678026
KitchenQual      0.672849
GarageFinish     0.633974
GarageType       0.598814
MSSubClass       0.583130
Foundation       0.573580
FireplaceQu      0.542237
HeatingQC        0.491392
BsmtFinType1     0.454237
Exterior1st      0.435284
MasVnrType       0.433267
Exterior2nd      0.423422
MSZoning         0.422232
OverallCond      0.387181
GarageCond       0.351653
GarageQual       0.351110
BsmtExposure     0.344207
HouseStyle       0.340038
LotShape         0.321184
SaleCondition    0.320496
CentralAir       0.313286
SaleType         0.307845
Electrical       0.297578
PavedDrive       0.280602
BsmtCond         0.269474
Fence            0.209028
Condition1       0.202877
RoofStyle        0.163782
BsmtFinType2     0.155398
LandContour      0.154423
BldgType         0.151785
Functional       0.136477
ExterCond        0.130370
Alley            0.130207
Heating          0.121949
Condition2       0.107173
LotConfig        0.105029
RoofMatl         0.090497
MoSold           0.081074
MiscFeature      0.078318
PoolQC           0.058495
LandSlope        0.050310
Street           0.045814
YrSold           0.024302
Utilities        0.016710
dtype: float64

pd.concat([corr_int_sr, corr_str_sr], axis=0).sort_values(ascending=False)

SalePrice        1.000000
OverallQual      0.809829
Neighborhood     0.755779
GrLivArea        0.708624
ExterQual        0.684014
BsmtQual         0.678026
KitchenQual      0.672849
GarageCars       0.640409
GarageFinish     0.633974
GarageArea       0.623431
TotalBsmtSF      0.613581
1stFlrSF         0.605852
GarageType       0.598814
MSSubClass       0.583130
Foundation       0.573580
FullBath         0.560664
FireplaceQu      0.542237
TotRmsAbvGrd     0.533723
YearBuilt        0.522897
YearRemodAdd     0.507101
HeatingQC        0.491392
MasVnrArea       0.472614
Fireplaces       0.466929
BsmtFinType1     0.454237
Exterior1st      0.435284
MasVnrType       0.433267
Exterior2nd      0.423422
MSZoning         0.422232
OverallCond      0.387181
BsmtFinSF1       0.386420
GarageCond       0.351653
GarageQual       0.351110
BsmtExposure     0.344207
HouseStyle       0.340038
WoodDeckSF       0.324413
LotShape         0.321184
SaleCondition    0.320496
2ndFlrSF         0.319334
OpenPorchSF      0.315856
CentralAir       0.313286
SaleType         0.307845
Electrical       0.297578
HalfBath         0.284108
PavedDrive       0.280602
BsmtCond         0.269474
LotArea          0.263843
GarageYrBlt      0.261366
BsmtFullBath     0.227122
BsmtUnfSF        0.214479
LotFrontage      0.209624
Fence            0.209028
Condition1       0.202877
BedroomAbvGr     0.168213
RoofStyle        0.163782
BsmtFinType2     0.155398
LandContour      0.154423
BldgType         0.151785
Functional       0.136477
ExterCond        0.130370
Alley            0.130207
Heating          0.121949
ScreenPorch      0.111447
Condition2       0.107173
LotConfig        0.105029
PoolArea         0.092404
RoofMatl         0.090497
MoSold           0.081074
MiscFeature      0.078318
PoolQC           0.058495
LandSlope        0.050310
Street           0.045814
3SsnPorch        0.044584
YrSold           0.024302
Utilities        0.016710
BsmtFinSF2      -0.011378
BsmtHalfBath    -0.016844
MiscVal         -0.021190
LowQualFinSF    -0.025606
EnclosedPorch   -0.128578
KitchenAbvGr    -0.135907
dtype: float64

feature_list = list(pd.concat([corr_int_sr, corr_str_sr], axis=0).sort_values(ascending=False).index[0:41])
feature_list.reverse()
feature_list

['SaleType',
 'CentralAir',
 'OpenPorchSF',
 '2ndFlrSF',
 'SaleCondition',
 'LotShape',
 'WoodDeckSF',
 'HouseStyle',
 'BsmtExposure',
 'GarageQual',
 'GarageCond',
 'BsmtFinSF1',
 'OverallCond',
 'MSZoning',
 'Exterior2nd',
 'MasVnrType',
 'Exterior1st',
 'BsmtFinType1',
 'Fireplaces',
 'MasVnrArea',
 'HeatingQC',
 'YearRemodAdd',
 'YearBuilt',
 'TotRmsAbvGrd',
 'FireplaceQu',
 'FullBath',
 'Foundation',
 'MSSubClass',
 'GarageType',
 '1stFlrSF',
 'TotalBsmtSF',
 'GarageArea',
 'GarageFinish',
 'GarageCars',
 'KitchenQual',
 'BsmtQual',
 'ExterQual',
 'GrLivArea',
 'Neighborhood',
 'OverallQual',
 'SalePrice']

train_last = train_new.loc[:, feature_list]
train_last

	SaleType	CentralAir	OpenPorchSF	2ndFlrSF	SaleCondition	LotShape	WoodDeckSF	HouseStyle	BsmtExposure	GarageQual	GarageCond	BsmtFinSF1	OverallCond	MSZoning	Exterior2nd	MasVnrType	Exterior1st	BsmtFinType1	Fireplaces	MasVnrArea	HeatingQC	YearRemodAdd	YearBuilt	TotRmsAbvGrd	FireplaceQu	FullBath	Foundation	MSSubClass	GarageType	1stFlrSF	TotalBsmtSF	GarageArea	GarageFinish	GarageCars	KitchenQual	BsmtQual	ExterQual	GrLivArea	Neighborhood	OverallQual	SalePrice
0	4	1	61	854	4	0	0	6	1	3	5	706	7	3	12	2	11	6	0	196.0	4	2003	2003	8	1	2	5	14	5	856	856	548	2	2	2	3	2	1710	16	6	208500
1	4	1	0	0	4	0	298	5	4	3	5	978	5	3	5	1	4	4	1	0.0	4	1976	1976	6	3	2	2	11	5	1262	1262	460	2	2	1	3	1	1262	20	5	181500
2	4	1	42	866	4	1	0	6	2	3	5	486	7	3	12	2	11	6	1	162.0	4	2002	2001	6	3	2	5	14	5	920	920	608	2	2	2	3	2	1786	16	6	223500
3	4	1	35	756	1	1	0	6	1	3	5	216	7	3	8	1	5	4	1	0.0	3	1970	1915	7	4	1	1	9	2	961	756	642	1	3	2	2	1	1717	17	6	140000
4	4	1	84	1053	4	1	192	6	3	3	5	655	7	3	12	2	11	6	1	350.0	4	2000	2000	9	3	2	5	14	5	1145	1145	836	2	3	2	3	2	2198	24	7	250000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1455	4	1	40	694	4	0	0	6	1	3	5	0	7	3	12	1	11	5	1	0.0	4	2000	1999	7	3	2	5	14	5	953	953	460	2	2	1	3	1	1647	14	5	175000
1456	4	1	0	0	4	0	349	5	1	3	5	790	4	3	10	4	9	4	2	119.0	2	1988	1978	7	3	2	2	11	5	2073	1542	500	1	2	1	3	1	2073	13	5	210000
1457	4	1	60	1152	4	0	0	6	1	3	5	275	8	3	13	1	12	6	2	0.0	4	2006	1941	9	4	2	3	9	5	1188	1152	252	2	1	2	2	3	2340	17	6	266500
1458	4	1	0	0	4	0	366	5	2	3	5	49	4	3	5	1	4	6	0	0.0	3	1996	1950	5	1	1	2	11	5	1078	1078	240	1	1	2	2	1	1078	10	4	142125
1459	4	1	68	0	4	0	736	5	1	3	5	830	4	3	9	1	8	2	0	0.0	3	1965	1965	6	1	1	2	11	5	1256	1256	276	3	1	1	2	2	1256	4	4	147500

1460 rows × 41 columns

X_train, X_test, y_train, y_test = train_test_split(train_last.iloc[:, 0:-1], train_last.iloc[:, [-1]], test_size=0.2, random_state=7)

lr = LinearRegression()
lr.fit(X_train, y_train)
print(lr.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(lr.score(X_test, y_test))
print(lr.score(X_train, y_train))

[[127789.21407131]]
    SalePrice
99     128950
0.8449398174883179
0.8236402408131976

ls = Lasso(alpha=1, max_iter=100000)
ls.fit(X_train, y_train)
print(ls.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(ls.score(X_test, y_test))
print(ls.score(X_train, y_train))

[127780.18771703]
    SalePrice
99     128950
0.8449411977832546
0.8236402205170005

rg = Ridge(alpha=50)
rg.fit(X_train, y_train)
print(rg.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(rg.score(X_test, y_test))
print(rg.score(X_train, y_train))

[[126604.3116898]]
    SalePrice
99     128950
0.8453340855508833
0.8230610246916847

xgb = XGBRegressor()
xgb.fit(X_train, y_train)
print(xgb.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(xgb.score(X_test, y_test))
print(xgb.score(X_train, y_train))

[125012.68]
    SalePrice
99     128950
0.8980734270131909
0.9997334320624469

rfr.fit(train_new.iloc[:, 0:-1], train_new.iloc[:, -1])

RandomForestRegressor(bootstrap=True, ccp_alpha=0.0, criterion='mse',
                      max_depth=None, max_features='auto', max_leaf_nodes=None,
                      max_samples=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=500, n_jobs=-1, oob_score=False,
                      random_state=42, verbose=0, warm_start=False)

rfr.feature_importances_

array([4.02810692e-03, 9.87158518e-04, 5.80719799e-03, 1.10726065e-02,
       5.66349085e-06, 3.40831981e-04, 8.68797202e-04, 1.09590646e-03,
       1.03940738e-06, 7.77616131e-04, 4.06918767e-04, 8.89175416e-02,
       5.44486278e-04, 1.69459949e-04, 3.63927429e-04, 4.60310666e-04,
       5.27892083e-01, 2.88893586e-03, 4.78030371e-03, 6.30284045e-03,
       8.49322248e-04, 3.16173901e-04, 1.74585304e-03, 1.86844967e-03,
       1.08696824e-03, 4.68242529e-03, 3.20662289e-03, 5.49993600e-04,
       4.63504712e-04, 5.21659255e-03, 1.15031549e-03, 2.90474717e-03,
       1.12174740e-03, 2.55563048e-02, 3.60971127e-04, 5.25565579e-04,
       5.10778467e-03, 3.30246235e-02, 7.82016430e-05, 7.70467614e-04,
       1.72899855e-03, 2.09468873e-04, 2.69327020e-02, 3.60331201e-02,
       1.05300010e-04, 1.01772805e-01, 1.08479918e-03, 3.05482508e-04,
       4.48049307e-03, 8.98748530e-04, 1.90311062e-03, 3.47992453e-04,
       4.37312822e-03, 6.27560636e-03, 4.09108527e-04, 1.61260129e-03,
       2.74604972e-03, 2.35392831e-03, 4.44715688e-03, 1.67374818e-03,
       1.84101275e-02, 1.33559120e-02, 4.84571362e-04, 3.86757072e-04,
       4.28789849e-04, 4.46564334e-03, 4.28807668e-03, 8.05120185e-04,
       3.47685029e-04, 1.19347586e-03, 3.37271377e-04, 4.24336200e-04,
       4.46354910e-04, 3.06589136e-05, 4.68966462e-05, 2.26130147e-03,
       1.70978149e-03, 1.15257113e-03, 1.43195285e-03])

plt.bar(np.arange(train_new.shape[1]-1), rfr.feature_importances_)

<BarContainer object of 79 artists>

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-uq8E0y1k-1615021016029)(output_38_1.png)]

imp_sr = pd.Series(data=rfr.feature_importances_, index=train_new.columns[0:-1]).sort_values(ascending=False)

imp_sr_list = imp_sr.index[0:40]
feature_list = list(pd.concat([corr_int_sr, corr_str_sr], axis=0).sort_values(ascending=False).index[0:41])
feature_list.pop(0)

'SalePrice'

# 非相关性的重要特征
non_corr_imp_list = set(imp_sr_list) - set(feature_list)
set(imp_sr_list) - set(feature_list)

{'BedroomAbvGr',
 'BsmtCond',
 'BsmtUnfSF',
 'GarageYrBlt',
 'LotArea',
 'LotFrontage',
 'MoSold',
 'ScreenPorch',
 'YrSold'}

# 重要特征和相关特征
corr_imp_list = set(list(imp_sr_list) + list(feature_list))
set(list(imp_sr_list) + list(feature_list))

{'1stFlrSF',
 '2ndFlrSF',
 'BedroomAbvGr',
 'BsmtCond',
 'BsmtExposure',
 'BsmtFinSF1',
 'BsmtFinType1',
 'BsmtQual',
 'BsmtUnfSF',
 'CentralAir',
 'ExterQual',
 'Exterior1st',
 'Exterior2nd',
 'FireplaceQu',
 'Fireplaces',
 'Foundation',
 'FullBath',
 'GarageArea',
 'GarageCars',
 'GarageCond',
 'GarageFinish',
 'GarageQual',
 'GarageType',
 'GarageYrBlt',
 'GrLivArea',
 'HeatingQC',
 'HouseStyle',
 'KitchenQual',
 'LotArea',
 'LotFrontage',
 'LotShape',
 'MSSubClass',
 'MSZoning',
 'MasVnrArea',
 'MasVnrType',
 'MoSold',
 'Neighborhood',
 'OpenPorchSF',
 'OverallCond',
 'OverallQual',
 'SaleCondition',
 'SaleType',
 'ScreenPorch',
 'TotRmsAbvGrd',
 'TotalBsmtSF',
 'WoodDeckSF',
 'YearBuilt',
 'YearRemodAdd',
 'YrSold'}

train_last = train_new.loc[:,list(corr_imp_list) + ['SalePrice']]
train_last

	MoSold	MSZoning	BsmtFinSF1	GarageCond	MSSubClass	LotArea	WoodDeckSF	GarageFinish	SaleCondition	SaleType	YearBuilt	GarageArea	BedroomAbvGr	Foundation	CentralAir	BsmtFinType1	Exterior1st	FullBath	GarageType	GarageQual	ExterQual	Fireplaces	KitchenQual	1stFlrSF	BsmtCond	GrLivArea	HeatingQC	HouseStyle	LotFrontage	BsmtExposure	OpenPorchSF	BsmtQual	LotShape	MasVnrType	OverallQual	MasVnrArea	TotalBsmtSF	YrSold	BsmtUnfSF	Neighborhood	2ndFlrSF	Exterior2nd	TotRmsAbvGrd	ScreenPorch	GarageCars	FireplaceQu	GarageYrBlt	OverallCond	YearRemodAdd	SalePrice
0	3	3	706	5	14	8450	0	2	4	4	2003	548	3	5	1	6	11	2	5	3	2	0	2	856	3	1710	4	6	65.0	1	61	3	0	2	6	196.0	856	0	150	16	854	12	8	0	2	1	2003.0	7	2003	208500
1	1	3	978	5	11	9600	298	2	4	4	1976	460	3	2	1	4	4	2	5	3	1	1	1	1262	3	1262	4	5	80.0	4	0	3	0	1	5	0.0	1262	4	284	20	0	5	6	0	2	3	1976.0	5	1976	181500
2	11	3	486	5	14	11250	0	2	4	4	2001	608	3	5	1	6	11	2	5	3	2	1	2	920	3	1786	4	6	68.0	2	42	3	1	2	6	162.0	920	0	434	16	866	12	6	0	2	3	2001.0	7	2002	223500
3	3	3	216	5	9	9550	0	1	1	4	1915	642	3	1	1	4	5	1	2	3	1	1	2	961	4	1717	3	6	60.0	1	35	2	1	1	6	0.0	756	3	540	17	756	8	7	0	3	4	1998.0	7	1970	140000
4	9	3	655	5	14	14260	192	2	4	4	2000	836	4	5	1	6	11	2	5	3	2	1	2	1145	3	2198	4	6	84.0	3	84	3	1	2	7	350.0	1145	0	490	24	1053	12	9	0	3	3	2000.0	7	2000	250000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1455	7	3	0	5	14	7917	0	2	4	4	1999	460	3	5	1	5	11	2	5	3	1	1	1	953	3	1647	4	6	62.0	1	40	3	0	1	5	0.0	953	4	953	14	694	12	7	0	2	3	1999.0	7	2000	175000
1456	3	3	790	5	11	13175	349	1	4	4	1978	500	3	2	1	4	9	2	5	3	1	2	1	2073	3	2073	2	5	85.0	1	0	3	0	4	5	119.0	1542	1	589	13	0	10	7	0	2	3	1978.0	4	1988	210000
1457	1	3	275	5	9	9042	0	2	4	4	1941	252	4	3	1	6	12	2	5	3	3	2	2	1188	4	2340	4	6	66.0	1	60	2	0	1	6	0.0	1152	1	877	17	1152	13	9	0	1	4	1941.0	8	2006	266500
1458	0	3	49	5	11	9717	366	1	4	4	1950	240	2	2	1	6	4	1	5	3	1	0	2	1078	3	1078	3	5	68.0	2	0	2	0	1	4	0.0	1078	1	0	10	0	5	5	0	1	1	1950.0	4	1996	142125
1459	2	3	830	5	11	9937	736	3	4	4	1965	276	3	2	1	2	8	1	5	3	2	0	1	1256	3	1256	3	5	75.0	1	68	2	0	1	4	0.0	1256	0	136	4	0	9	6	0	1	1	1965.0	4	1965	147500

1460 rows × 50 columns

X_train, X_test, y_train, y_test = train_test_split(train_last.iloc[:, 0:-1], train_last.iloc[:, [-1]], test_size=0.2, random_state=7)

lr = LinearRegression()
lr.fit(X_train, y_train)
print(lr.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(lr.score(X_test, y_test))
print(lr.score(X_train, y_train))

[[128705.97633884]]
    SalePrice
99     128950
0.8519543734556843
0.8266965527930652

ls = Lasso(alpha=100, max_iter=100000)
ls.fit(X_train, y_train)
print(ls.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(ls.score(X_test, y_test))
print(ls.score(X_train, y_train))

[128194.41905277]
    SalePrice
99     128950
0.8524312721810778
0.8264674896727493

xgb = XGBRegressor()
xgb.fit(X_train, y_train)
print(xgb.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(xgb.score(X_test, y_test))
print(xgb.score(X_train, y_train))

[137806.88]
    SalePrice
99     128950
0.9013816373209745
0.99986585398344

rg = Ridge(alpha=50)
rg.fit(X_train, y_train)
print(rg.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(rg.score(X_test, y_test))
print(rg.score(X_train, y_train))

[[128224.40637062]]
    SalePrice
99     128950
0.8519237019479504
0.8260130780293145

lgbm = LGBMRegressor()
lgbm.fit(X_train, y_train)
print(lgbm.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(lgbm.score(X_test, y_test))
print(lgbm.score(X_train, y_train))

[122699.63086328]
    SalePrice
99     128950
0.9084717579343212
0.9805903170794543

stack = regressor.StackingRegressor(regressors=[ls, xgb, lgbm], meta_regressor=rg)
stack.fit(X_train, y_train)
print(stack.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(stack.score(X_test, y_test))
print(stack.score(X_train, y_train))

[[137983.58172137]]
    SalePrice
99     128950
0.9008161248536086
0.9998717981042333

X_train, X_test, y_train, y_test = train_test_split(train_last.iloc[:, 0:-1], np.log1p(train_last.iloc[:, [-1]]), test_size=0.2, random_state=7)

lr = LinearRegression()
lr.fit(X_train, y_train)
print(lr.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(lr.score(X_test, y_test))
print(lr.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(lr.predict(X_test)))))
# time_1 = time.time()
# error_list = np.sqrt(-cross_val_score(lr, X_train, y_train, scoring='neg_mean_squared_error', cv=len(X_train)))
# print(error_list)
# time_2 = time.time()
# print(time_2-time_1)
print(np.sqrt(cross_val_score(lr, X_train, y_train, scoring='r2', cv=5)))

[[11.6323596]]
    SalePrice
99  11.767188
0.9014287370300434
0.8814179338517563
27407.459338824414
[0.94578428 0.76389078 0.93094413 0.94086894 0.95391384]

ls = Lasso(alpha=0.002, max_iter=100000)
ls.fit(X_train, y_train)
print(ls.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(ls.score(X_test, y_test))
print(ls.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(ls.predict(X_test)))))
time_1 = time.time()
error_list = np.sqrt(-cross_val_score(lr, X_train, y_train, scoring='neg_mean_squared_error', cv=len(X_train)))
print(error_list)
time_2 = time.time()
print(time_2-time_1)
print(np.sqrt(cross_val_score(ls, X_train, y_train, scoring='r2', cv=5)))

[11.6227277]
    SalePrice
99  11.767188
0.9023902700479108
0.8795640077417723
27517.076624711135
[0.07372533 0.05254256 0.06465484 ... 0.09983587 0.04480408 0.20046456]
12.748914957046509
[0.94626087 0.75131723 0.92972572 0.94094776 0.95548991]

rg = Ridge(alpha=1)
rg.fit(X_train, y_train)
print(rg.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(rg.score(X_test, y_test))
print(rg.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(rg.predict(X_test)))))
print(np.sqrt(-cross_val_score(rg, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(rg, X_train, y_train, scoring='r2', cv=5)))

[[11.63177696]]
    SalePrice
99  11.767188
0.9015510582176212
0.8814164537644407
27409.814767861015
[0.12599009 0.24197056 0.14567151 0.12624434 0.13110084]
[0.9457901  0.76392329 0.93089761 0.9408726  0.9540249 ]

# xgb = XGBRegressor()
xgb = XGBRegressor(learning_rate=0.02, max_depth=3, n_estimators=1000)
xgb.fit(X_train, y_train)
print(xgb.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(xgb.score(X_test, y_test))
print(xgb.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(xgb.predict(X_test)))))
print(np.sqrt(mean_squared_error(np.expm1(y_train), np.expm1(xgb.predict(X_train)))))
print(np.sqrt(-cross_val_score(xgb, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(xgb, X_train, y_train, scoring='r2', cv=5)))

[11.665708]
    SalePrice
99  11.767188
0.9192435376855344
0.9698160291558459
25198.975648759053
12138.937999540736
[0.12729575 0.15484294 0.14307831 0.1093134  0.11721916]
[0.94462762 0.91075464 0.93342307 0.95601169 0.96342153]

lgbm = LGBMRegressor(num_leaves=7, learning_rate=0.01, n_estimators=1000)
lgbm.fit(X_train, y_train)
print(lgbm.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(lgbm.score(X_test, y_test))
print(lgbm.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(lgbm.predict(X_test)))))
print(np.sqrt(-cross_val_score(lgbm, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(lgbm, X_train, y_train, scoring='r2', cv=5)))

[11.67980588]
    SalePrice
99  11.767188
0.9123717713040634
0.9507868084209785
27571.85575283145
[0.12858805 0.15503547 0.14073726 0.11536931 0.12916114]
[0.94346381 0.91052166 0.9356583  0.95087378 0.95540682]

stack = regressor.StackingRegressor(regressors=[ls, xgb, lgbm], meta_regressor=rg)
stack.fit(X_train, y_train)
print(stack.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(stack.score(X_test, y_test))
print(stack.score(X_train, y_train))
print(np.sqrt(-cross_val_score(stack, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(stack, X_train, y_train, scoring='r2', cv=5)))

[[11.67493043]]
    SalePrice
99  11.767188
0.9161487095970527
0.9711736239829509
[0.12989797 0.14590182 0.14341223 0.10997372 0.12084481]
[0.94227063 0.92119425 0.93310079 0.95546623 0.96107729]

X_train

	MoSold	MSZoning	BsmtFinSF1	GarageCond	MSSubClass	LotArea	WoodDeckSF	GarageFinish	SaleCondition	SaleType	YearBuilt	GarageArea	BedroomAbvGr	Foundation	CentralAir	BsmtFinType1	Exterior1st	FullBath	GarageType	GarageQual	ExterQual	Fireplaces	KitchenQual	1stFlrSF	BsmtCond	GrLivArea	HeatingQC	HouseStyle	LotFrontage	BsmtExposure	OpenPorchSF	BsmtQual	LotShape	MasVnrType	OverallQual	MasVnrArea	TotalBsmtSF	YrSold	BsmtUnfSF	Neighborhood	2ndFlrSF	Exterior2nd	TotRmsAbvGrd	ScreenPorch	GarageCars	FireplaceQu	GarageYrBlt	OverallCond	YearRemodAdd
1087	1	4	0	5	14	10574	160	2	4	4	2005	1043	3	5	1	5	11	2	5	3	2	1	2	1082	3	1953	4	6	85.0	2	50	3	0	1	7	0.0	1082	2	1082	19	871	12	9	0	3	4	2005.0	7	2006
187	7	3	0	2	6	10410	0	1	4	4	1916	180	3	2	1	5	8	2	2	2	1	0	1	808	3	1656	4	2	60.0	1	0	1	0	1	4	0.0	660	2	660	5	704	9	8	0	1	1	1916.0	6	1987
671	8	2	551	5	9	6629	147	1	4	4	1925	300	3	1	0	2	5	2	2	3	1	0	1	697	3	1369	2	6	54.0	1	0	2	0	1	5	0.0	672	2	121	4	672	4	6	0	1	1	1930.0	4	1950
652	8	3	0	5	14	8750	0	2	4	4	1996	512	2	5	1	5	11	2	5	3	2	1	2	909	3	1716	4	6	70.0	1	120	3	0	1	6	0.0	880	2	880	16	807	12	7	0	2	3	1996.0	7	1996
1266	6	1	0	5	3	10120	0	1	4	4	1910	308	4	2	0	5	5	1	2	3	0	1	1	964	3	1889	2	3	60.0	1	0	2	1	1	6	0.0	925	4	925	5	925	4	9	0	1	4	1960.0	2	1950
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
211	5	3	36	5	11	10420	100	2	4	4	2009	460	3	5	1	6	11	2	5	3	1	0	2	1212	3	1212	4	5	83.0	2	22	3	0	1	5	0.0	1212	1	1176	4	0	12	6	0	2	1	2009.0	7	2009
502	0	3	698	2	11	9170	0	1	4	4	1965	461	2	2	1	4	4	1	2	2	1	0	1	1214	3	1214	4	5	70.0	1	0	2	0	1	4	0.0	1214	4	420	4	0	5	6	0	2	1	1965.0	6	1965
537	0	3	600	5	11	12735	216	1	4	3	1972	576	3	2	1	2	4	1	2	3	1	0	1	864	3	864	2	5	0.0	1	0	2	1	1	3	0.0	864	0	264	10	0	5	5	0	2	1	1980.0	7	1972
1220	10	3	312	5	11	7800	0	1	1	4	1964	288	2	2	1	1	5	1	5	3	1	0	1	912	3	912	2	5	66.0	1	0	2	1	1	4	0.0	912	3	0	10	0	4	5	0	1	1	1964.0	7	1964
175	2	3	477	5	11	12615	0	1	4	4	1950	576	4	2	1	4	6	2	5	3	1	1	2	2158	4	2158	2	5	84.0	3	29	2	0	1	5	0.0	1202	4	725	4	0	8	7	0	2	4	1950.0	6	2001

1168 rows × 49 columns

def cross_test_score(X_train, y_train):
    mean_list = []
    lr = LinearRegression()
    cv=len(X_train)
    for index in [x for x in range(cv)]:
        if index == 0:
            lr.fit(X_train.iloc[1:cv, :], y_train.iloc[1:cv, :])
        elif index == (cv-1):
            lr.fit(X_train.iloc[0:cv, :], y_train.iloc[0:cv, :])
        else:
            a = np.arange(X_train.shape[0]).tolist()
            a.pop(index)
            lr.fit(X_train.iloc[a, :], y_train.iloc[a, :])
        y_pred = lr.predict(X_train.iloc[[index], :])
        mean_abs_error = np.sqrt(mean_squared_error(y_train.iloc[[index], :], y_pred))
        mean_list.append(mean_abs_error)
    return mean_list

X_train.index = range(X_train.shape[0])
y_train.index = range(y_train.shape[0])

mean_list = cross_test_score(X_train, y_train)

plt.plot(range(len(mean_list)), mean_list)

[<matplotlib.lines.Line2D at 0x16af3208d68>]

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-R3M1If7S-1615021016040)(output_62_1.png)]

a = pd.Series(mean_list, index=range(len(mean_list))).sort_values()
a

212     0.000084
816     0.000101
312     0.000261
983     0.000311
111     0.000443
          ...   
1061    0.695339
515     0.750419
437     0.761170
342     1.269573
464     2.359217
Length: 1168, dtype: float64

X_train.iloc[[342, 464], :]

	MoSold	MSZoning	BsmtFinSF1	GarageCond	MSSubClass	LotArea	WoodDeckSF	GarageFinish	SaleCondition	SaleType	YearBuilt	GarageArea	BedroomAbvGr	Foundation	CentralAir	BsmtFinType1	Exterior1st	FullBath	GarageType	GarageQual	ExterQual	Fireplaces	KitchenQual	1stFlrSF	BsmtCond	GrLivArea	HeatingQC	HouseStyle	LotFrontage	BsmtExposure	OpenPorchSF	BsmtQual	LotShape	MasVnrType	OverallQual	MasVnrArea	TotalBsmtSF	YrSold	BsmtUnfSF	Neighborhood	2ndFlrSF	Exterior2nd	TotRmsAbvGrd	ScreenPorch	GarageCars	FireplaceQu	GarageYrBlt	OverallCond	YearRemodAdd
342	4	3	2260	5	14	40094	208	3	5	8	2007	884	3	5	1	6	12	3	6	3	3	1	3	3138	3	4676	4	6	130.0	4	406	4	1	4	9	762.0	3138	4	878	4	1538	13	11	0	3	4	2007.0	7	2008
464	6	3	5644	5	14	63887	214	3	5	8	2008	1418	3	5	1	6	7	2	5	3	3	3	3	4692	3	5642	4	6	313.0	4	292	4	2	4	9	796.0	6110	0	466	4	950	6	12	0	2	4	2008.0	7	2008

X_train.drop([342, 464], axis=0, inplace=True)

y_train.drop([342, 464], axis=0, inplace=True)

rg = Ridge(alpha=1)
rg.fit(X_train, y_train)
print(rg.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(rg.score(X_test, y_test))
print(rg.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(rg.predict(X_test)))))
print(np.sqrt(-cross_val_score(rg, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(rg, X_train, y_train, scoring='r2', cv=5)))    
# 目前最优的，剩下的都是尝试，但证明达不到这个效果。

[[11.64851484]]
    SalePrice
99  11.767188
0.9151227578383072
0.9144284746375823
21680.19889202489
[0.11325024 0.12770313 0.13376579 0.11558958 0.12319022]
[0.95643737 0.94056018 0.94224296 0.95068114 0.95951961]

ls = Lasso(alpha=0.002, max_iter=100000)
ls.fit(X_train, y_train)
print(ls.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(ls.score(X_test, y_test))
print(ls.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(ls.predict(X_test)))))
time_1 = time.time()
error_list = np.sqrt(-cross_val_score(lr, X_train, y_train, scoring='neg_mean_squared_error', cv=len(X_train)))
print(error_list)
time_2 = time.time()
print(time_2-time_1)
print(np.sqrt(cross_val_score(ls, X_train, y_train, scoring='r2', cv=5)))

[11.63326364]
    SalePrice
99  11.767188
0.9143217824770862
0.912713281276043
22220.831580976675
[0.04530086 0.04875491 0.07250084 ... 0.06706882 0.04069486 0.16519963]
12.84067153930664
[0.95639987 0.94282027 0.94192452 0.9501967  0.9602258 ]

# xgb = XGBRegressor()
xgb = XGBRegressor(learning_rate=0.02, max_depth=3, n_estimators=1000)
xgb.fit(X_train, y_train)
print(xgb.predict(X_test.iloc[[142], :]))
print(y_test.iloc[[142], :])
print(xgb.score(X_test, y_test))
print(xgb.score(X_train, y_train))
print(np.sqrt(mean_squared_error(np.expm1(y_test), np.expm1(xgb.predict(X_test)))))
print(np.sqrt(mean_squared_error(np.expm1(y_train), np.expm1(xgb.predict(X_train)))))
print(np.sqrt(-cross_val_score(xgb, X_train, y_train, scoring='neg_mean_squared_error', cv=5)))
print(np.sqrt(cross_val_score(xgb, X_train, y_train, scoring='r2', cv=5)))

[11.663737]
    SalePrice
99  11.767188
0.92229859972357
0.9710584050678127
23644.2496823488
11613.610958582125
[0.12072391 0.1213991  0.13657591 0.10816418 0.11720516]
[0.95034336 0.94644622 0.93971222 0.95695243 0.96343044]

train_concat = pd.concat([X_train, y_train], axis=1)
train_concat

	MoSold	MSZoning	BsmtFinSF1	GarageCond	MSSubClass	LotArea	WoodDeckSF	GarageFinish	SaleCondition	SaleType	YearBuilt	GarageArea	BedroomAbvGr	Foundation	CentralAir	BsmtFinType1	Exterior1st	FullBath	GarageType	GarageQual	ExterQual	Fireplaces	KitchenQual	1stFlrSF	BsmtCond	GrLivArea	HeatingQC	HouseStyle	LotFrontage	BsmtExposure	OpenPorchSF	BsmtQual	LotShape	MasVnrType	OverallQual	MasVnrArea	TotalBsmtSF	YrSold	BsmtUnfSF	Neighborhood	2ndFlrSF	Exterior2nd	TotRmsAbvGrd	ScreenPorch	GarageCars	FireplaceQu	GarageYrBlt	OverallCond	YearRemodAdd	SalePrice
0	1	4	0	5	14	10574	160	2	4	4	2005	1043	3	5	1	5	11	2	5	3	2	1	2	1082	3	1953	4	6	85.0	2	50	3	0	1	7	0.0	1082	2	1082	19	871	12	9	0	3	4	2005.0	7	2006	12.437188
1	7	3	0	2	6	10410	0	1	4	4	1916	180	3	2	1	5	8	2	2	2	1	0	1	808	3	1656	4	2	60.0	1	0	1	0	1	4	0.0	660	2	660	5	704	9	8	0	1	1	1916.0	6	1987	11.813037
2	8	2	551	5	9	6629	147	1	4	4	1925	300	3	1	0	2	5	2	2	3	1	0	1	697	3	1369	2	6	54.0	1	0	2	0	1	5	0.0	672	2	121	4	672	4	6	0	1	1	1930.0	4	1950	11.548302
3	8	3	0	5	14	8750	0	2	4	4	1996	512	2	5	1	5	11	2	5	3	2	1	2	909	3	1716	4	6	70.0	1	120	3	0	1	6	0.0	880	2	880	16	807	12	7	0	2	3	1996.0	7	1996	12.160034
4	6	1	0	5	3	10120	0	1	4	4	1910	308	4	2	0	5	5	1	2	3	0	1	1	964	3	1889	2	3	60.0	1	0	2	1	1	6	0.0	925	4	925	5	925	4	9	0	1	4	1960.0	2	1950	11.711785
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1163	5	3	36	5	11	10420	100	2	4	4	2009	460	3	5	1	6	11	2	5	3	1	0	2	1212	3	1212	4	5	83.0	2	22	3	0	1	5	0.0	1212	1	1176	4	0	12	6	0	2	1	2009.0	7	2009	12.133507
1164	0	3	698	2	11	9170	0	1	4	4	1965	461	2	2	1	4	4	1	2	2	1	0	1	1214	3	1214	4	5	70.0	1	0	2	0	1	4	0.0	1214	4	420	4	0	5	6	0	2	1	1965.0	6	1965	11.849405
1165	0	3	600	5	11	12735	216	1	4	3	1972	576	3	2	1	2	4	1	2	3	1	0	1	864	3	864	2	5	0.0	1	0	2	1	1	3	0.0	864	0	264	10	0	5	5	0	2	1	1980.0	7	1972	11.619544
1166	10	3	312	5	11	7800	0	1	1	4	1964	288	2	2	1	1	5	1	5	3	1	0	1	912	3	912	2	5	66.0	1	0	2	1	1	4	0.0	912	3	0	10	0	4	5	0	1	1	1964.0	7	1964	11.652696
1167	2	3	477	5	11	12615	0	1	4	4	1950	576	4	2	1	4	6	2	5	3	1	1	2	2158	4	2158	2	5	84.0	3	29	2	0	1	5	0.0	1202	4	725	4	0	8	7	0	2	4	1950.0	6	2001	12.400821

1166 rows × 50 columns

corr_last_list = train_concat.corr().iloc[:, -1].sort_values(ascending=False)
corr_last_list

SalePrice        1.000000
OverallQual      0.818545
Neighborhood     0.743155
GrLivArea        0.724649
GarageCars       0.687718
ExterQual        0.679473
KitchenQual      0.664916
GarageArea       0.660270
BsmtQual         0.637945
TotalBsmtSF      0.633197
1stFlrSF         0.605800
FullBath         0.602931
GarageFinish     0.599941
YearBuilt        0.586915
GarageType       0.580333
YearRemodAdd     0.569444
MSSubClass       0.553671
TotRmsAbvGrd     0.545820
Foundation       0.542097
FireplaceQu      0.537695
Fireplaces       0.478249
HeatingQC        0.469827
MasVnrType       0.441539
MasVnrArea       0.414464
MSZoning         0.405073
Exterior1st      0.404112
GarageCond       0.391892
Exterior2nd      0.391754
OverallCond      0.389876
BsmtFinType1     0.381671
BsmtFinSF1       0.375696
GarageQual       0.372400
CentralAir       0.371996
GarageYrBlt      0.368714
WoodDeckSF       0.342925
BsmtExposure     0.334175
2ndFlrSF         0.332800
SaleType         0.324187
OpenPorchSF      0.308198
BsmtCond         0.292069
LotArea          0.291945
HouseStyle       0.291766
LotShape         0.287286
SaleCondition    0.264004
BedroomAbvGr     0.236127
BsmtUnfSF        0.230587
LotFrontage      0.177707
ScreenPorch      0.098918
MoSold           0.075277
YrSold           0.048146
Name: SalePrice, dtype: float64

pf = PolynomialFeatures()

pd.DataFrame(pf.fit_transform(X_train))

	0	1	2	3	4	5	6	7	8	9	10	11	12	13	14	15	16	17	18	19	20	21	22	23	24	25	26	27	28	29	30	31	32	33	34	35	36	37	38	39	40	41	42	43	44	45	46	47	48	49	50	51	52	53	54	55	56	57	58	59	60	61	62	63	64	65	66	67	68	69	70	71	72	73	74	75	76	77	78	79	80	81	82	83	84	85	86	87	88	89	90	91	92	93	94	95	96	97	98	99	100	101	102	103	104	105	106	107	108	109	110	111	112	113	114	115	116	117	118	119	120	121	122	123	124	125	126	127	128	129	130	131	132	133	134	135	136	137	138	139	140	141	142	143	144	145	146	147	148	149	150	151	152	153	154	155	156	157	158	159	160	161	162	163	164	165	166	167	168	169	170	171	172	173	174	175	176	177	178	179	180	181	182	183	184	185	186	187	188	189	190	191	192	193	194	195	196	197	198	199	200	201	202	203	204	205	206	207	208	209	210	211	212	213	214	215	216	217	218	219	220	221	222	223	224	225	226	227	228	229	230	231	232	233	234	235	236	237	238	239	240	241	242	243	244	245	246	247	248	249	...	1025	1026	1027	1028	1029	1030	1031	1032	1033	1034	1035	1036	1037	1038	1039	1040	1041	1042	1043	1044	1045	1046	1047	1048	1049	1050	1051	1052	1053	1054	1055	1056	1057	1058	1059	1060	1061	1062	1063	1064	1065	1066	1067	1068	1069	1070	1071	1072	1073	1074	1075	1076	1077	1078	1079	1080	1081	1082	1083	1084	1085	1086	1087	1088	1089	1090	1091	1092	1093	1094	1095	1096	1097	1098	1099	1100	1101	1102	1103	1104	1105	1106	1107	1108	1109	1110	1111	1112	1113	1114	1115	1116	1117	1118	1119	1120	1121	1122	1123	1124	1125	1126	1127	1128	1129	1130	1131	1132	1133	1134	1135	1136	1137	1138	1139	1140	1141	1142	1143	1144	1145	1146	1147	1148	1149	1150	1151	1152	1153	1154	1155	1156	1157	1158	1159	1160	1161	1162	1163	1164	1165	1166	1167	1168	1169	1170	1171	1172	1173	1174	1175	1176	1177	1178	1179	1180	1181	1182	1183	1184	1185	1186	1187	1188	1189	1190	1191	1192	1193	1194	1195	1196	1197	1198	1199	1200	1201	1202	1203	1204	1205	1206	1207	1208	1209	1210	1211	1212	1213	1214	1215	1216	1217	1218	1219	1220	1221	1222	1223	1224	1225	1226	1227	1228	1229	1230	1231	1232	1233	1234	1235	1236	1237	1238	1239	1240	1241	1242	1243	1244	1245	1246	1247	1248	1249	1250	1251	1252	1253	1254	1255	1256	1257	1258	1259	1260	1261	1262	1263	1264	1265	1266	1267	1268	1269	1270	1271	1272	1273	1274
0	1.0	1.0	4.0	0.0	5.0	14.0	10574.0	160.0	2.0	4.0	4.0	2005.0	1043.0	3.0	5.0	1.0	5.0	11.0	2.0	5.0	3.0	2.0	1.0	2.0	1082.0	3.0	1953.0	4.0	6.0	85.0	2.0	50.0	3.0	0.0	1.0	7.0	0.0	1082.0	2.0	1082.0	19.0	871.0	12.0	9.0	0.0	3.0	4.0	2005.0	7.0	2006.0	1.0	4.0	0.0	5.0	14.0	10574.0	160.0	2.0	4.0	4.0	2005.0	1043.0	3.0	5.0	1.0	5.0	11.0	2.0	5.0	3.0	2.0	1.0	2.0	1082.0	3.0	1953.0	4.0	6.0	85.0	2.0	50.0	3.0	0.0	1.0	7.0	0.0	1082.0	2.0	1082.0	19.0	871.0	12.0	9.0	0.0	3.0	4.0	2005.0	7.0	2006.0	16.0	0.0	20.0	56.0	42296.0	640.0	8.0	16.0	16.0	8020.0	4172.0	12.0	20.0	4.0	20.0	44.0	8.0	20.0	12.0	8.0	4.0	8.0	4328.0	12.0	7812.0	16.0	24.0	340.0	8.0	200.0	12.0	0.0	4.0	28.0	0.0	4328.0	8.0	4328.0	76.0	3484.0	48.0	36.0	0.0	12.0	16.0	8020.0	28.0	8024.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	25.0	70.0	52870.0	800.0	10.0	20.0	20.0	10025.0	5215.0	15.0	25.0	5.0	25.0	55.0	10.0	25.0	15.0	10.0	5.0	10.0	5410.0	15.0	9765.0	20.0	30.0	425.0	10.0	250.0	15.0	0.0	5.0	35.0	0.0	5410.0	10.0	5410.0	95.0	4355.0	60.0	45.0	0.0	15.0	20.0	10025.0	35.0	10030.0	196.0	148036.0	2240.0	28.0	56.0	56.0	28070.0	14602.0	42.0	70.0	...	300.0	18.0	0.0	6.0	42.0	0.0	6492.0	12.0	6492.0	114.0	5226.0	72.0	54.0	0.0	18.0	24.0	12030.0	42.0	12036.0	7225.0	170.0	4250.0	255.0	0.0	85.0	595.0	0.0	91970.0	170.0	91970.0	1615.0	74035.0	1020.0	765.0	0.0	255.0	340.0	170425.0	595.0	170510.0	4.0	100.0	6.0	0.0	2.0	14.0	0.0	2164.0	4.0	2164.0	38.0	1742.0	24.0	18.0	0.0	6.0	8.0	4010.0	14.0	4012.0	2500.0	150.0	0.0	50.0	350.0	0.0	54100.0	100.0	54100.0	950.0	43550.0	600.0	450.0	0.0	150.0	200.0	100250.0	350.0	100300.0	9.0	0.0	3.0	21.0	0.0	3246.0	6.0	3246.0	57.0	2613.0	36.0	27.0	0.0	9.0	12.0	6015.0	21.0	6018.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	7.0	0.0	1082.0	2.0	1082.0	19.0	871.0	12.0	9.0	0.0	3.0	4.0	2005.0	7.0	2006.0	49.0	0.0	7574.0	14.0	7574.0	133.0	6097.0	84.0	63.0	0.0	21.0	28.0	14035.0	49.0	14042.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1170724.0	2164.0	1170724.0	20558.0	942422.0	12984.0	9738.0	0.0	3246.0	4328.0	2169410.0	7574.0	2170492.0	4.0	2164.0	38.0	1742.0	24.0	18.0	0.0	6.0	8.0	4010.0	14.0	4012.0	1170724.0	20558.0	942422.0	12984.0	9738.0	0.0	3246.0	4328.0	2169410.0	7574.0	2170492.0	361.0	16549.0	228.0	171.0	0.0	57.0	76.0	38095.0	133.0	38114.0	758641.0	10452.0	7839.0	0.0	2613.0	3484.0	1746355.0	6097.0	1747226.0	144.0	108.0	0.0	36.0	48.0	24060.0	84.0	24072.0	81.0	0.0	27.0	36.0	18045.0	63.0	18054.0	0.0	0.0	0.0	0.0	0.0	0.0	9.0	12.0	6015.0	21.0	6018.0	16.0	8020.0	28.0	8024.0	4020025.0	14035.0	4022030.0	49.0	14042.0	4024036.0
1	1.0	7.0	3.0	0.0	2.0	6.0	10410.0	0.0	1.0	4.0	4.0	1916.0	180.0	3.0	2.0	1.0	5.0	8.0	2.0	2.0	2.0	1.0	0.0	1.0	808.0	3.0	1656.0	4.0	2.0	60.0	1.0	0.0	1.0	0.0	1.0	4.0	0.0	660.0	2.0	660.0	5.0	704.0	9.0	8.0	0.0	1.0	1.0	1916.0	6.0	1987.0	49.0	21.0	0.0	14.0	42.0	72870.0	0.0	7.0	28.0	28.0	13412.0	1260.0	21.0	14.0	7.0	35.0	56.0	14.0	14.0	14.0	7.0	0.0	7.0	5656.0	21.0	11592.0	28.0	14.0	420.0	7.0	0.0	7.0	0.0	7.0	28.0	0.0	4620.0	14.0	4620.0	35.0	4928.0	63.0	56.0	0.0	7.0	7.0	13412.0	42.0	13909.0	9.0	0.0	6.0	18.0	31230.0	0.0	3.0	12.0	12.0	5748.0	540.0	9.0	6.0	3.0	15.0	24.0	6.0	6.0	6.0	3.0	0.0	3.0	2424.0	9.0	4968.0	12.0	6.0	180.0	3.0	0.0	3.0	0.0	3.0	12.0	0.0	1980.0	6.0	1980.0	15.0	2112.0	27.0	24.0	0.0	3.0	3.0	5748.0	18.0	5961.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	12.0	20820.0	0.0	2.0	8.0	8.0	3832.0	360.0	6.0	4.0	2.0	10.0	16.0	4.0	4.0	4.0	2.0	0.0	2.0	1616.0	6.0	3312.0	8.0	4.0	120.0	2.0	0.0	2.0	0.0	2.0	8.0	0.0	1320.0	4.0	1320.0	10.0	1408.0	18.0	16.0	0.0	2.0	2.0	3832.0	12.0	3974.0	36.0	62460.0	0.0	6.0	24.0	24.0	11496.0	1080.0	18.0	12.0	...	0.0	2.0	0.0	2.0	8.0	0.0	1320.0	4.0	1320.0	10.0	1408.0	18.0	16.0	0.0	2.0	2.0	3832.0	12.0	3974.0	3600.0	60.0	0.0	60.0	0.0	60.0	240.0	0.0	39600.0	120.0	39600.0	300.0	42240.0	540.0	480.0	0.0	60.0	60.0	114960.0	360.0	119220.0	1.0	0.0	1.0	0.0	1.0	4.0	0.0	660.0	2.0	660.0	5.0	704.0	9.0	8.0	0.0	1.0	1.0	1916.0	6.0	1987.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	1.0	4.0	0.0	660.0	2.0	660.0	5.0	704.0	9.0	8.0	0.0	1.0	1.0	1916.0	6.0	1987.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	4.0	0.0	660.0	2.0	660.0	5.0	704.0	9.0	8.0	0.0	1.0	1.0	1916.0	6.0	1987.0	16.0	0.0	2640.0	8.0	2640.0	20.0	2816.0	36.0	32.0	0.0	4.0	4.0	7664.0	24.0	7948.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	435600.0	1320.0	435600.0	3300.0	464640.0	5940.0	5280.0	0.0	660.0	660.0	1264560.0	3960.0	1311420.0	4.0	1320.0	10.0	1408.0	18.0	16.0	0.0	2.0	2.0	3832.0	12.0	3974.0	435600.0	3300.0	464640.0	5940.0	5280.0	0.0	660.0	660.0	1264560.0	3960.0	1311420.0	25.0	3520.0	45.0	40.0	0.0	5.0	5.0	9580.0	30.0	9935.0	495616.0	6336.0	5632.0	0.0	704.0	704.0	1348864.0	4224.0	1398848.0	81.0	72.0	0.0	9.0	9.0	17244.0	54.0	17883.0	64.0	0.0	8.0	8.0	15328.0	48.0	15896.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	1.0	1916.0	6.0	1987.0	1.0	1916.0	6.0	1987.0	3671056.0	11496.0	3807092.0	36.0	11922.0	3948169.0
2	1.0	8.0	2.0	551.0	5.0	9.0	6629.0	147.0	1.0	4.0	4.0	1925.0	300.0	3.0	1.0	0.0	2.0	5.0	2.0	2.0	3.0	1.0	0.0	1.0	697.0	3.0	1369.0	2.0	6.0	54.0	1.0	0.0	2.0	0.0	1.0	5.0	0.0	672.0	2.0	121.0	4.0	672.0	4.0	6.0	0.0	1.0	1.0	1930.0	4.0	1950.0	64.0	16.0	4408.0	40.0	72.0	53032.0	1176.0	8.0	32.0	32.0	15400.0	2400.0	24.0	8.0	0.0	16.0	40.0	16.0	16.0	24.0	8.0	0.0	8.0	5576.0	24.0	10952.0	16.0	48.0	432.0	8.0	0.0	16.0	0.0	8.0	40.0	0.0	5376.0	16.0	968.0	32.0	5376.0	32.0	48.0	0.0	8.0	8.0	15440.0	32.0	15600.0	4.0	1102.0	10.0	18.0	13258.0	294.0	2.0	8.0	8.0	3850.0	600.0	6.0	2.0	0.0	4.0	10.0	4.0	4.0	6.0	2.0	0.0	2.0	1394.0	6.0	2738.0	4.0	12.0	108.0	2.0	0.0	4.0	0.0	2.0	10.0	0.0	1344.0	4.0	242.0	8.0	1344.0	8.0	12.0	0.0	2.0	2.0	3860.0	8.0	3900.0	303601.0	2755.0	4959.0	3652579.0	80997.0	551.0	2204.0	2204.0	1060675.0	165300.0	1653.0	551.0	0.0	1102.0	2755.0	1102.0	1102.0	1653.0	551.0	0.0	551.0	384047.0	1653.0	754319.0	1102.0	3306.0	29754.0	551.0	0.0	1102.0	0.0	551.0	2755.0	0.0	370272.0	1102.0	66671.0	2204.0	370272.0	2204.0	3306.0	0.0	551.0	551.0	1063430.0	2204.0	1074450.0	25.0	45.0	33145.0	735.0	5.0	20.0	20.0	9625.0	1500.0	15.0	5.0	0.0	10.0	25.0	10.0	10.0	15.0	5.0	0.0	5.0	3485.0	15.0	6845.0	10.0	30.0	270.0	5.0	0.0	10.0	0.0	5.0	25.0	0.0	3360.0	10.0	605.0	20.0	3360.0	20.0	30.0	0.0	5.0	5.0	9650.0	20.0	9750.0	81.0	59661.0	1323.0	9.0	36.0	36.0	17325.0	2700.0	27.0	9.0	...	0.0	12.0	0.0	6.0	30.0	0.0	4032.0	12.0	726.0	24.0	4032.0	24.0	36.0	0.0	6.0	6.0	11580.0	24.0	11700.0	2916.0	54.0	0.0	108.0	0.0	54.0	270.0	0.0	36288.0	108.0	6534.0	216.0	36288.0	216.0	324.0	0.0	54.0	54.0	104220.0	216.0	105300.0	1.0	0.0	2.0	0.0	1.0	5.0	0.0	672.0	2.0	121.0	4.0	672.0	4.0	6.0	0.0	1.0	1.0	1930.0	4.0	1950.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	0.0	2.0	10.0	0.0	1344.0	4.0	242.0	8.0	1344.0	8.0	12.0	0.0	2.0	2.0	3860.0	8.0	3900.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	5.0	0.0	672.0	2.0	121.0	4.0	672.0	4.0	6.0	0.0	1.0	1.0	1930.0	4.0	1950.0	25.0	0.0	3360.0	10.0	605.0	20.0	3360.0	20.0	30.0	0.0	5.0	5.0	9650.0	20.0	9750.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	451584.0	1344.0	81312.0	2688.0	451584.0	2688.0	4032.0	0.0	672.0	672.0	1296960.0	2688.0	1310400.0	4.0	242.0	8.0	1344.0	8.0	12.0	0.0	2.0	2.0	3860.0	8.0	3900.0	14641.0	484.0	81312.0	484.0	726.0	0.0	121.0	121.0	233530.0	484.0	235950.0	16.0	2688.0	16.0	24.0	0.0	4.0	4.0	7720.0	16.0	7800.0	451584.0	2688.0	4032.0	0.0	672.0	672.0	1296960.0	2688.0	1310400.0	16.0	24.0	0.0	4.0	4.0	7720.0	16.0	7800.0	36.0	0.0	6.0	6.0	11580.0	24.0	11700.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	1.0	1930.0	4.0	1950.0	1.0	1930.0	4.0	1950.0	3724900.0	7720.0	3763500.0	16.0	7800.0	3802500.0
3	1.0	8.0	3.0	0.0	5.0	14.0	8750.0	0.0	2.0	4.0	4.0	1996.0	512.0	2.0	5.0	1.0	5.0	11.0	2.0	5.0	3.0	2.0	1.0	2.0	909.0	3.0	1716.0	4.0	6.0	70.0	1.0	120.0	3.0	0.0	1.0	6.0	0.0	880.0	2.0	880.0	16.0	807.0	12.0	7.0	0.0	2.0	3.0	1996.0	7.0	1996.0	64.0	24.0	0.0	40.0	112.0	70000.0	0.0	16.0	32.0	32.0	15968.0	4096.0	16.0	40.0	8.0	40.0	88.0	16.0	40.0	24.0	16.0	8.0	16.0	7272.0	24.0	13728.0	32.0	48.0	560.0	8.0	960.0	24.0	0.0	8.0	48.0	0.0	7040.0	16.0	7040.0	128.0	6456.0	96.0	56.0	0.0	16.0	24.0	15968.0	56.0	15968.0	9.0	0.0	15.0	42.0	26250.0	0.0	6.0	12.0	12.0	5988.0	1536.0	6.0	15.0	3.0	15.0	33.0	6.0	15.0	9.0	6.0	3.0	6.0	2727.0	9.0	5148.0	12.0	18.0	210.0	3.0	360.0	9.0	0.0	3.0	18.0	0.0	2640.0	6.0	2640.0	48.0	2421.0	36.0	21.0	0.0	6.0	9.0	5988.0	21.0	5988.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	25.0	70.0	43750.0	0.0	10.0	20.0	20.0	9980.0	2560.0	10.0	25.0	5.0	25.0	55.0	10.0	25.0	15.0	10.0	5.0	10.0	4545.0	15.0	8580.0	20.0	30.0	350.0	5.0	600.0	15.0	0.0	5.0	30.0	0.0	4400.0	10.0	4400.0	80.0	4035.0	60.0	35.0	0.0	10.0	15.0	9980.0	35.0	9980.0	196.0	122500.0	0.0	28.0	56.0	56.0	27944.0	7168.0	28.0	70.0	...	720.0	18.0	0.0	6.0	36.0	0.0	5280.0	12.0	5280.0	96.0	4842.0	72.0	42.0	0.0	12.0	18.0	11976.0	42.0	11976.0	4900.0	70.0	8400.0	210.0	0.0	70.0	420.0	0.0	61600.0	140.0	61600.0	1120.0	56490.0	840.0	490.0	0.0	140.0	210.0	139720.0	490.0	139720.0	1.0	120.0	3.0	0.0	1.0	6.0	0.0	880.0	2.0	880.0	16.0	807.0	12.0	7.0	0.0	2.0	3.0	1996.0	7.0	1996.0	14400.0	360.0	0.0	120.0	720.0	0.0	105600.0	240.0	105600.0	1920.0	96840.0	1440.0	840.0	0.0	240.0	360.0	239520.0	840.0	239520.0	9.0	0.0	3.0	18.0	0.0	2640.0	6.0	2640.0	48.0	2421.0	36.0	21.0	0.0	6.0	9.0	5988.0	21.0	5988.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	6.0	0.0	880.0	2.0	880.0	16.0	807.0	12.0	7.0	0.0	2.0	3.0	1996.0	7.0	1996.0	36.0	0.0	5280.0	12.0	5280.0	96.0	4842.0	72.0	42.0	0.0	12.0	18.0	11976.0	42.0	11976.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	774400.0	1760.0	774400.0	14080.0	710160.0	10560.0	6160.0	0.0	1760.0	2640.0	1756480.0	6160.0	1756480.0	4.0	1760.0	32.0	1614.0	24.0	14.0	0.0	4.0	6.0	3992.0	14.0	3992.0	774400.0	14080.0	710160.0	10560.0	6160.0	0.0	1760.0	2640.0	1756480.0	6160.0	1756480.0	256.0	12912.0	192.0	112.0	0.0	32.0	48.0	31936.0	112.0	31936.0	651249.0	9684.0	5649.0	0.0	1614.0	2421.0	1610772.0	5649.0	1610772.0	144.0	84.0	0.0	24.0	36.0	23952.0	84.0	23952.0	49.0	0.0	14.0	21.0	13972.0	49.0	13972.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	6.0	3992.0	14.0	3992.0	9.0	5988.0	21.0	5988.0	3984016.0	13972.0	3984016.0	49.0	13972.0	3984016.0
4	1.0	6.0	1.0	0.0	5.0	3.0	10120.0	0.0	1.0	4.0	4.0	1910.0	308.0	4.0	2.0	0.0	5.0	5.0	1.0	2.0	3.0	0.0	1.0	1.0	964.0	3.0	1889.0	2.0	3.0	60.0	1.0	0.0	2.0	1.0	1.0	6.0	0.0	925.0	4.0	925.0	5.0	925.0	4.0	9.0	0.0	1.0	4.0	1960.0	2.0	1950.0	36.0	6.0	0.0	30.0	18.0	60720.0	0.0	6.0	24.0	24.0	11460.0	1848.0	24.0	12.0	0.0	30.0	30.0	6.0	12.0	18.0	0.0	6.0	6.0	5784.0	18.0	11334.0	12.0	18.0	360.0	6.0	0.0	12.0	6.0	6.0	36.0	0.0	5550.0	24.0	5550.0	30.0	5550.0	24.0	54.0	0.0	6.0	24.0	11760.0	12.0	11700.0	1.0	0.0	5.0	3.0	10120.0	0.0	1.0	4.0	4.0	1910.0	308.0	4.0	2.0	0.0	5.0	5.0	1.0	2.0	3.0	0.0	1.0	1.0	964.0	3.0	1889.0	2.0	3.0	60.0	1.0	0.0	2.0	1.0	1.0	6.0	0.0	925.0	4.0	925.0	5.0	925.0	4.0	9.0	0.0	1.0	4.0	1960.0	2.0	1950.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	25.0	15.0	50600.0	0.0	5.0	20.0	20.0	9550.0	1540.0	20.0	10.0	0.0	25.0	25.0	5.0	10.0	15.0	0.0	5.0	5.0	4820.0	15.0	9445.0	10.0	15.0	300.0	5.0	0.0	10.0	5.0	5.0	30.0	0.0	4625.0	20.0	4625.0	25.0	4625.0	20.0	45.0	0.0	5.0	20.0	9800.0	10.0	9750.0	9.0	30360.0	0.0	3.0	12.0	12.0	5730.0	924.0	12.0	6.0	...	0.0	6.0	3.0	3.0	18.0	0.0	2775.0	12.0	2775.0	15.0	2775.0	12.0	27.0	0.0	3.0	12.0	5880.0	6.0	5850.0	3600.0	60.0	0.0	120.0	60.0	60.0	360.0	0.0	55500.0	240.0	55500.0	300.0	55500.0	240.0	540.0	0.0	60.0	240.0	117600.0	120.0	117000.0	1.0	0.0	2.0	1.0	1.0	6.0	0.0	925.0	4.0	925.0	5.0	925.0	4.0	9.0	0.0	1.0	4.0	1960.0	2.0	1950.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	2.0	12.0	0.0	1850.0	8.0	1850.0	10.0	1850.0	8.0	18.0	0.0	2.0	8.0	3920.0	4.0	3900.0	1.0	1.0	6.0	0.0	925.0	4.0	925.0	5.0	925.0	4.0	9.0	0.0	1.0	4.0	1960.0	2.0	1950.0	1.0	6.0	0.0	925.0	4.0	925.0	5.0	925.0	4.0	9.0	0.0	1.0	4.0	1960.0	2.0	1950.0	36.0	0.0	5550.0	24.0	5550.0	30.0	5550.0	24.0	54.0	0.0	6.0	24.0	11760.0	12.0	11700.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	855625.0	3700.0	855625.0	4625.0	855625.0	3700.0	8325.0	0.0	925.0	3700.0	1813000.0	1850.0	1803750.0	16.0	3700.0	20.0	3700.0	16.0	36.0	0.0	4.0	16.0	7840.0	8.0	7800.0	855625.0	4625.0	855625.0	3700.0	8325.0	0.0	925.0	3700.0	1813000.0	1850.0	1803750.0	25.0	4625.0	20.0	45.0	0.0	5.0	20.0	9800.0	10.0	9750.0	855625.0	3700.0	8325.0	0.0	925.0	3700.0	1813000.0	1850.0	1803750.0	16.0	36.0	0.0	4.0	16.0	7840.0	8.0	7800.0	81.0	0.0	9.0	36.0	17640.0	18.0	17550.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	4.0	1960.0	2.0	1950.0	16.0	7840.0	8.0	7800.0	3841600.0	3920.0	3822000.0	4.0	3900.0	3802500.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1161	1.0	5.0	3.0	36.0	5.0	11.0	10420.0	100.0	2.0	4.0	4.0	2009.0	460.0	3.0	5.0	1.0	6.0	11.0	2.0	5.0	3.0	1.0	0.0	2.0	1212.0	3.0	1212.0	4.0	5.0	83.0	2.0	22.0	3.0	0.0	1.0	5.0	0.0	1212.0	1.0	1176.0	4.0	0.0	12.0	6.0	0.0	2.0	1.0	2009.0	7.0	2009.0	25.0	15.0	180.0	25.0	55.0	52100.0	500.0	10.0	20.0	20.0	10045.0	2300.0	15.0	25.0	5.0	30.0	55.0	10.0	25.0	15.0	5.0	0.0	10.0	6060.0	15.0	6060.0	20.0	25.0	415.0	10.0	110.0	15.0	0.0	5.0	25.0	0.0	6060.0	5.0	5880.0	20.0	0.0	60.0	30.0	0.0	10.0	5.0	10045.0	35.0	10045.0	9.0	108.0	15.0	33.0	31260.0	300.0	6.0	12.0	12.0	6027.0	1380.0	9.0	15.0	3.0	18.0	33.0	6.0	15.0	9.0	3.0	0.0	6.0	3636.0	9.0	3636.0	12.0	15.0	249.0	6.0	66.0	9.0	0.0	3.0	15.0	0.0	3636.0	3.0	3528.0	12.0	0.0	36.0	18.0	0.0	6.0	3.0	6027.0	21.0	6027.0	1296.0	180.0	396.0	375120.0	3600.0	72.0	144.0	144.0	72324.0	16560.0	108.0	180.0	36.0	216.0	396.0	72.0	180.0	108.0	36.0	0.0	72.0	43632.0	108.0	43632.0	144.0	180.0	2988.0	72.0	792.0	108.0	0.0	36.0	180.0	0.0	43632.0	36.0	42336.0	144.0	0.0	432.0	216.0	0.0	72.0	36.0	72324.0	252.0	72324.0	25.0	55.0	52100.0	500.0	10.0	20.0	20.0	10045.0	2300.0	15.0	25.0	5.0	30.0	55.0	10.0	25.0	15.0	5.0	0.0	10.0	6060.0	15.0	6060.0	20.0	25.0	415.0	10.0	110.0	15.0	0.0	5.0	25.0	0.0	6060.0	5.0	5880.0	20.0	0.0	60.0	30.0	0.0	10.0	5.0	10045.0	35.0	10045.0	121.0	114620.0	1100.0	22.0	44.0	44.0	22099.0	5060.0	33.0	55.0	...	110.0	15.0	0.0	5.0	25.0	0.0	6060.0	5.0	5880.0	20.0	0.0	60.0	30.0	0.0	10.0	5.0	10045.0	35.0	10045.0	6889.0	166.0	1826.0	249.0	0.0	83.0	415.0	0.0	100596.0	83.0	97608.0	332.0	0.0	996.0	498.0	0.0	166.0	83.0	166747.0	581.0	166747.0	4.0	44.0	6.0	0.0	2.0	10.0	0.0	2424.0	2.0	2352.0	8.0	0.0	24.0	12.0	0.0	4.0	2.0	4018.0	14.0	4018.0	484.0	66.0	0.0	22.0	110.0	0.0	26664.0	22.0	25872.0	88.0	0.0	264.0	132.0	0.0	44.0	22.0	44198.0	154.0	44198.0	9.0	0.0	3.0	15.0	0.0	3636.0	3.0	3528.0	12.0	0.0	36.0	18.0	0.0	6.0	3.0	6027.0	21.0	6027.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	5.0	0.0	1212.0	1.0	1176.0	4.0	0.0	12.0	6.0	0.0	2.0	1.0	2009.0	7.0	2009.0	25.0	0.0	6060.0	5.0	5880.0	20.0	0.0	60.0	30.0	0.0	10.0	5.0	10045.0	35.0	10045.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1468944.0	1212.0	1425312.0	4848.0	0.0	14544.0	7272.0	0.0	2424.0	1212.0	2434908.0	8484.0	2434908.0	1.0	1176.0	4.0	0.0	12.0	6.0	0.0	2.0	1.0	2009.0	7.0	2009.0	1382976.0	4704.0	0.0	14112.0	7056.0	0.0	2352.0	1176.0	2362584.0	8232.0	2362584.0	16.0	0.0	48.0	24.0	0.0	8.0	4.0	8036.0	28.0	8036.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	144.0	72.0	0.0	24.0	12.0	24108.0	84.0	24108.0	36.0	0.0	12.0	6.0	12054.0	42.0	12054.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	4018.0	14.0	4018.0	1.0	2009.0	7.0	2009.0	4036081.0	14063.0	4036081.0	49.0	14063.0	4036081.0
1162	1.0	0.0	3.0	698.0	2.0	11.0	9170.0	0.0	1.0	4.0	4.0	1965.0	461.0	2.0	2.0	1.0	4.0	4.0	1.0	2.0	2.0	1.0	0.0	1.0	1214.0	3.0	1214.0	4.0	5.0	70.0	1.0	0.0	2.0	0.0	1.0	4.0	0.0	1214.0	4.0	420.0	4.0	0.0	5.0	6.0	0.0	2.0	1.0	1965.0	6.0	1965.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	9.0	2094.0	6.0	33.0	27510.0	0.0	3.0	12.0	12.0	5895.0	1383.0	6.0	6.0	3.0	12.0	12.0	3.0	6.0	6.0	3.0	0.0	3.0	3642.0	9.0	3642.0	12.0	15.0	210.0	3.0	0.0	6.0	0.0	3.0	12.0	0.0	3642.0	12.0	1260.0	12.0	0.0	15.0	18.0	0.0	6.0	3.0	5895.0	18.0	5895.0	487204.0	1396.0	7678.0	6400660.0	0.0	698.0	2792.0	2792.0	1371570.0	321778.0	1396.0	1396.0	698.0	2792.0	2792.0	698.0	1396.0	1396.0	698.0	0.0	698.0	847372.0	2094.0	847372.0	2792.0	3490.0	48860.0	698.0	0.0	1396.0	0.0	698.0	2792.0	0.0	847372.0	2792.0	293160.0	2792.0	0.0	3490.0	4188.0	0.0	1396.0	698.0	1371570.0	4188.0	1371570.0	4.0	22.0	18340.0	0.0	2.0	8.0	8.0	3930.0	922.0	4.0	4.0	2.0	8.0	8.0	2.0	4.0	4.0	2.0	0.0	2.0	2428.0	6.0	2428.0	8.0	10.0	140.0	2.0	0.0	4.0	0.0	2.0	8.0	0.0	2428.0	8.0	840.0	8.0	0.0	10.0	12.0	0.0	4.0	2.0	3930.0	12.0	3930.0	121.0	100870.0	0.0	11.0	44.0	44.0	21615.0	5071.0	22.0	22.0	...	0.0	10.0	0.0	5.0	20.0	0.0	6070.0	20.0	2100.0	20.0	0.0	25.0	30.0	0.0	10.0	5.0	9825.0	30.0	9825.0	4900.0	70.0	0.0	140.0	0.0	70.0	280.0	0.0	84980.0	280.0	29400.0	280.0	0.0	350.0	420.0	0.0	140.0	70.0	137550.0	420.0	137550.0	1.0	0.0	2.0	0.0	1.0	4.0	0.0	1214.0	4.0	420.0	4.0	0.0	5.0	6.0	0.0	2.0	1.0	1965.0	6.0	1965.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	0.0	2.0	8.0	0.0	2428.0	8.0	840.0	8.0	0.0	10.0	12.0	0.0	4.0	2.0	3930.0	12.0	3930.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	4.0	0.0	1214.0	4.0	420.0	4.0	0.0	5.0	6.0	0.0	2.0	1.0	1965.0	6.0	1965.0	16.0	0.0	4856.0	16.0	1680.0	16.0	0.0	20.0	24.0	0.0	8.0	4.0	7860.0	24.0	7860.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1473796.0	4856.0	509880.0	4856.0	0.0	6070.0	7284.0	0.0	2428.0	1214.0	2385510.0	7284.0	2385510.0	16.0	1680.0	16.0	0.0	20.0	24.0	0.0	8.0	4.0	7860.0	24.0	7860.0	176400.0	1680.0	0.0	2100.0	2520.0	0.0	840.0	420.0	825300.0	2520.0	825300.0	16.0	0.0	20.0	24.0	0.0	8.0	4.0	7860.0	24.0	7860.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	25.0	30.0	0.0	10.0	5.0	9825.0	30.0	9825.0	36.0	0.0	12.0	6.0	11790.0	36.0	11790.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	3930.0	12.0	3930.0	1.0	1965.0	6.0	1965.0	3861225.0	11790.0	3861225.0	36.0	11790.0	3861225.0
1163	1.0	0.0	3.0	600.0	5.0	11.0	12735.0	216.0	1.0	4.0	3.0	1972.0	576.0	3.0	2.0	1.0	2.0	4.0	1.0	2.0	3.0	1.0	0.0	1.0	864.0	3.0	864.0	2.0	5.0	0.0	1.0	0.0	2.0	1.0	1.0	3.0	0.0	864.0	0.0	264.0	10.0	0.0	5.0	5.0	0.0	2.0	1.0	1980.0	7.0	1972.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	9.0	1800.0	15.0	33.0	38205.0	648.0	3.0	12.0	9.0	5916.0	1728.0	9.0	6.0	3.0	6.0	12.0	3.0	6.0	9.0	3.0	0.0	3.0	2592.0	9.0	2592.0	6.0	15.0	0.0	3.0	0.0	6.0	3.0	3.0	9.0	0.0	2592.0	0.0	792.0	30.0	0.0	15.0	15.0	0.0	6.0	3.0	5940.0	21.0	5916.0	360000.0	3000.0	6600.0	7641000.0	129600.0	600.0	2400.0	1800.0	1183200.0	345600.0	1800.0	1200.0	600.0	1200.0	2400.0	600.0	1200.0	1800.0	600.0	0.0	600.0	518400.0	1800.0	518400.0	1200.0	3000.0	0.0	600.0	0.0	1200.0	600.0	600.0	1800.0	0.0	518400.0	0.0	158400.0	6000.0	0.0	3000.0	3000.0	0.0	1200.0	600.0	1188000.0	4200.0	1183200.0	25.0	55.0	63675.0	1080.0	5.0	20.0	15.0	9860.0	2880.0	15.0	10.0	5.0	10.0	20.0	5.0	10.0	15.0	5.0	0.0	5.0	4320.0	15.0	4320.0	10.0	25.0	0.0	5.0	0.0	10.0	5.0	5.0	15.0	0.0	4320.0	0.0	1320.0	50.0	0.0	25.0	25.0	0.0	10.0	5.0	9900.0	35.0	9860.0	121.0	140085.0	2376.0	11.0	44.0	33.0	21692.0	6336.0	33.0	22.0	...	0.0	10.0	5.0	5.0	15.0	0.0	4320.0	0.0	1320.0	50.0	0.0	25.0	25.0	0.0	10.0	5.0	9900.0	35.0	9860.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	2.0	1.0	1.0	3.0	0.0	864.0	0.0	264.0	10.0	0.0	5.0	5.0	0.0	2.0	1.0	1980.0	7.0	1972.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	2.0	6.0	0.0	1728.0	0.0	528.0	20.0	0.0	10.0	10.0	0.0	4.0	2.0	3960.0	14.0	3944.0	1.0	1.0	3.0	0.0	864.0	0.0	264.0	10.0	0.0	5.0	5.0	0.0	2.0	1.0	1980.0	7.0	1972.0	1.0	3.0	0.0	864.0	0.0	264.0	10.0	0.0	5.0	5.0	0.0	2.0	1.0	1980.0	7.0	1972.0	9.0	0.0	2592.0	0.0	792.0	30.0	0.0	15.0	15.0	0.0	6.0	3.0	5940.0	21.0	5916.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	746496.0	0.0	228096.0	8640.0	0.0	4320.0	4320.0	0.0	1728.0	864.0	1710720.0	6048.0	1703808.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	69696.0	2640.0	0.0	1320.0	1320.0	0.0	528.0	264.0	522720.0	1848.0	520608.0	100.0	0.0	50.0	50.0	0.0	20.0	10.0	19800.0	70.0	19720.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	25.0	25.0	0.0	10.0	5.0	9900.0	35.0	9860.0	25.0	0.0	10.0	5.0	9900.0	35.0	9860.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	3960.0	14.0	3944.0	1.0	1980.0	7.0	1972.0	3920400.0	13860.0	3904560.0	49.0	13804.0	3888784.0
1164	1.0	10.0	3.0	312.0	5.0	11.0	7800.0	0.0	1.0	1.0	4.0	1964.0	288.0	2.0	2.0	1.0	1.0	5.0	1.0	5.0	3.0	1.0	0.0	1.0	912.0	3.0	912.0	2.0	5.0	66.0	1.0	0.0	2.0	1.0	1.0	4.0	0.0	912.0	3.0	0.0	10.0	0.0	4.0	5.0	0.0	1.0	1.0	1964.0	7.0	1964.0	100.0	30.0	3120.0	50.0	110.0	78000.0	0.0	10.0	10.0	40.0	19640.0	2880.0	20.0	20.0	10.0	10.0	50.0	10.0	50.0	30.0	10.0	0.0	10.0	9120.0	30.0	9120.0	20.0	50.0	660.0	10.0	0.0	20.0	10.0	10.0	40.0	0.0	9120.0	30.0	0.0	100.0	0.0	40.0	50.0	0.0	10.0	10.0	19640.0	70.0	19640.0	9.0	936.0	15.0	33.0	23400.0	0.0	3.0	3.0	12.0	5892.0	864.0	6.0	6.0	3.0	3.0	15.0	3.0	15.0	9.0	3.0	0.0	3.0	2736.0	9.0	2736.0	6.0	15.0	198.0	3.0	0.0	6.0	3.0	3.0	12.0	0.0	2736.0	9.0	0.0	30.0	0.0	12.0	15.0	0.0	3.0	3.0	5892.0	21.0	5892.0	97344.0	1560.0	3432.0	2433600.0	0.0	312.0	312.0	1248.0	612768.0	89856.0	624.0	624.0	312.0	312.0	1560.0	312.0	1560.0	936.0	312.0	0.0	312.0	284544.0	936.0	284544.0	624.0	1560.0	20592.0	312.0	0.0	624.0	312.0	312.0	1248.0	0.0	284544.0	936.0	0.0	3120.0	0.0	1248.0	1560.0	0.0	312.0	312.0	612768.0	2184.0	612768.0	25.0	55.0	39000.0	0.0	5.0	5.0	20.0	9820.0	1440.0	10.0	10.0	5.0	5.0	25.0	5.0	25.0	15.0	5.0	0.0	5.0	4560.0	15.0	4560.0	10.0	25.0	330.0	5.0	0.0	10.0	5.0	5.0	20.0	0.0	4560.0	15.0	0.0	50.0	0.0	20.0	25.0	0.0	5.0	5.0	9820.0	35.0	9820.0	121.0	85800.0	0.0	11.0	11.0	44.0	21604.0	3168.0	22.0	22.0	...	0.0	10.0	5.0	5.0	20.0	0.0	4560.0	15.0	0.0	50.0	0.0	20.0	25.0	0.0	5.0	5.0	9820.0	35.0	9820.0	4356.0	66.0	0.0	132.0	66.0	66.0	264.0	0.0	60192.0	198.0	0.0	660.0	0.0	264.0	330.0	0.0	66.0	66.0	129624.0	462.0	129624.0	1.0	0.0	2.0	1.0	1.0	4.0	0.0	912.0	3.0	0.0	10.0	0.0	4.0	5.0	0.0	1.0	1.0	1964.0	7.0	1964.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	2.0	2.0	8.0	0.0	1824.0	6.0	0.0	20.0	0.0	8.0	10.0	0.0	2.0	2.0	3928.0	14.0	3928.0	1.0	1.0	4.0	0.0	912.0	3.0	0.0	10.0	0.0	4.0	5.0	0.0	1.0	1.0	1964.0	7.0	1964.0	1.0	4.0	0.0	912.0	3.0	0.0	10.0	0.0	4.0	5.0	0.0	1.0	1.0	1964.0	7.0	1964.0	16.0	0.0	3648.0	12.0	0.0	40.0	0.0	16.0	20.0	0.0	4.0	4.0	7856.0	28.0	7856.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	831744.0	2736.0	0.0	9120.0	0.0	3648.0	4560.0	0.0	912.0	912.0	1791168.0	6384.0	1791168.0	9.0	0.0	30.0	0.0	12.0	15.0	0.0	3.0	3.0	5892.0	21.0	5892.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	100.0	0.0	40.0	50.0	0.0	10.0	10.0	19640.0	70.0	19640.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	16.0	20.0	0.0	4.0	4.0	7856.0	28.0	7856.0	25.0	0.0	5.0	5.0	9820.0	35.0	9820.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	1.0	1964.0	7.0	1964.0	1.0	1964.0	7.0	1964.0	3857296.0	13748.0	3857296.0	49.0	13748.0	3857296.0
1165	1.0	2.0	3.0	477.0	5.0	11.0	12615.0	0.0	1.0	4.0	4.0	1950.0	576.0	4.0	2.0	1.0	4.0	6.0	2.0	5.0	3.0	1.0	1.0	2.0	2158.0	4.0	2158.0	2.0	5.0	84.0	3.0	29.0	2.0	0.0	1.0	5.0	0.0	1202.0	4.0	725.0	4.0	0.0	8.0	7.0	0.0	2.0	4.0	1950.0	6.0	2001.0	4.0	6.0	954.0	10.0	22.0	25230.0	0.0	2.0	8.0	8.0	3900.0	1152.0	8.0	4.0	2.0	8.0	12.0	4.0	10.0	6.0	2.0	2.0	4.0	4316.0	8.0	4316.0	4.0	10.0	168.0	6.0	58.0	4.0	0.0	2.0	10.0	0.0	2404.0	8.0	1450.0	8.0	0.0	16.0	14.0	0.0	4.0	8.0	3900.0	12.0	4002.0	9.0	1431.0	15.0	33.0	37845.0	0.0	3.0	12.0	12.0	5850.0	1728.0	12.0	6.0	3.0	12.0	18.0	6.0	15.0	9.0	3.0	3.0	6.0	6474.0	12.0	6474.0	6.0	15.0	252.0	9.0	87.0	6.0	0.0	3.0	15.0	0.0	3606.0	12.0	2175.0	12.0	0.0	24.0	21.0	0.0	6.0	12.0	5850.0	18.0	6003.0	227529.0	2385.0	5247.0	6017355.0	0.0	477.0	1908.0	1908.0	930150.0	274752.0	1908.0	954.0	477.0	1908.0	2862.0	954.0	2385.0	1431.0	477.0	477.0	954.0	1029366.0	1908.0	1029366.0	954.0	2385.0	40068.0	1431.0	13833.0	954.0	0.0	477.0	2385.0	0.0	573354.0	1908.0	345825.0	1908.0	0.0	3816.0	3339.0	0.0	954.0	1908.0	930150.0	2862.0	954477.0	25.0	55.0	63075.0	0.0	5.0	20.0	20.0	9750.0	2880.0	20.0	10.0	5.0	20.0	30.0	10.0	25.0	15.0	5.0	5.0	10.0	10790.0	20.0	10790.0	10.0	25.0	420.0	15.0	145.0	10.0	0.0	5.0	25.0	0.0	6010.0	20.0	3625.0	20.0	0.0	40.0	35.0	0.0	10.0	20.0	9750.0	30.0	10005.0	121.0	138765.0	0.0	11.0	44.0	44.0	21450.0	6336.0	44.0	22.0	...	145.0	10.0	0.0	5.0	25.0	0.0	6010.0	20.0	3625.0	20.0	0.0	40.0	35.0	0.0	10.0	20.0	9750.0	30.0	10005.0	7056.0	252.0	2436.0	168.0	0.0	84.0	420.0	0.0	100968.0	336.0	60900.0	336.0	0.0	672.0	588.0	0.0	168.0	336.0	163800.0	504.0	168084.0	9.0	87.0	6.0	0.0	3.0	15.0	0.0	3606.0	12.0	2175.0	12.0	0.0	24.0	21.0	0.0	6.0	12.0	5850.0	18.0	6003.0	841.0	58.0	0.0	29.0	145.0	0.0	34858.0	116.0	21025.0	116.0	0.0	232.0	203.0	0.0	58.0	116.0	56550.0	174.0	58029.0	4.0	0.0	2.0	10.0	0.0	2404.0	8.0	1450.0	8.0	0.0	16.0	14.0	0.0	4.0	8.0	3900.0	12.0	4002.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	5.0	0.0	1202.0	4.0	725.0	4.0	0.0	8.0	7.0	0.0	2.0	4.0	1950.0	6.0	2001.0	25.0	0.0	6010.0	20.0	3625.0	20.0	0.0	40.0	35.0	0.0	10.0	20.0	9750.0	30.0	10005.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1444804.0	4808.0	871450.0	4808.0	0.0	9616.0	8414.0	0.0	2404.0	4808.0	2343900.0	7212.0	2405202.0	16.0	2900.0	16.0	0.0	32.0	28.0	0.0	8.0	16.0	7800.0	24.0	8004.0	525625.0	2900.0	0.0	5800.0	5075.0	0.0	1450.0	2900.0	1413750.0	4350.0	1450725.0	16.0	0.0	32.0	28.0	0.0	8.0	16.0	7800.0	24.0	8004.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	64.0	56.0	0.0	16.0	32.0	15600.0	48.0	16008.0	49.0	0.0	14.0	28.0	13650.0	42.0	14007.0	0.0	0.0	0.0	0.0	0.0	0.0	4.0	8.0	3900.0	12.0	4002.0	16.0	7800.0	24.0	8004.0	3802500.0	11700.0	3901950.0	36.0	12006.0	4004001.0

1166 rows × 1275 columns

# std = StandardScaler()
X_train_new = X_train.copy()
# X_train_new = pd.DataFrame(std.fit_transform(X_train_new), columns=X_train_new.columns)
pf = PolynomialFeatures(include_bias=False)
for index_1, col_1 in enumerate(X_train.columns):
    for index_2, col_2 in enumerate(X_train.columns):
        if index_1 >= index_2:
            continue
#         print(col_1, col_2)
        col_corr = max(corr_last_list[col_1], corr_last_list[col_2])
#         print(col_corr)
        pd_df = pd.concat([pd.DataFrame(pf.fit_transform(X_train.loc[:, [col_1, col_2]])), y_train], axis=1)
#         print(pd_df)
#         print(pd_df.corr())
#         print(1)
        a = ((pd_df.corr().iloc[:, -1] - col_corr)>0).value_counts()
#         print(a)
#         print(a[True])
        if a[True] > 1 :
#             print(max((pd_df.corr().iloc[0: -1, -1])))
            index_3 = (pd_df.corr().iloc[0: -1, -1])[(pd_df.corr().iloc[0: -1, -1]).values == max((pd_df.corr().iloc[0: -1, -1]))].index
#             print(index_3)
            X_train_new[col_1 + 'PnFt' + col_2] = pd_df.iloc[:, index_3[0]]

X_train_new

	MoSold	MSZoning	BsmtFinSF1	GarageCond	MSSubClass	LotArea	WoodDeckSF	GarageFinish	SaleCondition	SaleType	YearBuilt	GarageArea	BedroomAbvGr	Foundation	CentralAir	BsmtFinType1	Exterior1st	FullBath	GarageType	GarageQual	ExterQual	Fireplaces	KitchenQual	1stFlrSF	BsmtCond	GrLivArea	HeatingQC	HouseStyle	LotFrontage	BsmtExposure	OpenPorchSF	BsmtQual	LotShape	MasVnrType	OverallQual	MasVnrArea	TotalBsmtSF	YrSold	BsmtUnfSF	Neighborhood	2ndFlrSF	Exterior2nd	TotRmsAbvGrd	ScreenPorch	GarageCars	FireplaceQu	GarageYrBlt	OverallCond	YearRemodAdd
0	1	4	0	5	14	10574	160	2	4	4	2005	1043	3	5	1	5	11	2	5	3	2	1	2	1082	3	1953	4	6	85.0	2	50	3	0	1	7	0.0	1082	2	1082	19	871	12	9	0	3	4	2005.0	7	2006
1	7	3	0	2	6	10410	0	1	4	4	1916	180	3	2	1	5	8	2	2	2	1	0	1	808	3	1656	4	2	60.0	1	0	1	0	1	4	0.0	660	2	660	5	70