import pandas as pd
import numpy as np
from sklearn. metrics import mean_squared_error
import lightgbm as lgb
import xgboost as xgb
from sklearn. model_selection import train_test_split
from sklearn. preprocessing import OneHotEncoder
from sklearn. model_selection import KFold, RepeatedKFold
from scipy import sparse
pd. set_option( 'display.max_columns' , None )
pd. set_option( 'display.max_rows' , None )
from datetime import datetime
train_abbr= pd. read_csv( "./data/happiness_train_abbr.csv" , encoding= 'ISO-8859-1' )
train= pd. read_csv( "./data/happiness_train_complete.csv" , encoding= 'ISO-8859-1' )
test_abbr= pd. read_csv( "./data/happiness_test_abbr.csv" , encoding= 'ISO-8859-1' )
test= pd. read_csv( "./data/happiness_test_complete.csv" , encoding= 'ISO-8859-1' )
test_sub= pd. read_csv( "./data/happiness_submit.csv" , encoding= 'ISO-8859-1' )
test. shape
(2968, 139)
test_sub. shape
(2968, 2)
train. shape
(8000, 140)
train. head( )
id
happiness
survey_type
province
city
county
survey_time
gender
birth
nationality
religion
religion_freq
edu
edu_other
edu_status
edu_yr
income
political
join_party
floor_area
property_0
property_1
property_2
property_3
property_4
property_5
property_6
property_7
property_8
property_other
height_cm
weight_jin
health
health_problem
depression
hukou
hukou_loc
media_1
media_2
media_3
media_4
media_5
media_6
leisure_1
leisure_2
leisure_3
leisure_4
leisure_5
leisure_6
leisure_7
leisure_8
leisure_9
leisure_10
leisure_11
leisure_12
socialize
relax
learn
social_neighbor
social_friend
socia_outing
equity
class
class_10_before
class_10_after
class_14
work_exper
work_status
work_yr
work_type
work_manage
insur_1
insur_2
insur_3
insur_4
family_income
family_m
family_status
house
car
invest_0
invest_1
invest_2
invest_3
invest_4
invest_5
invest_6
invest_7
invest_8
invest_other
son
daughter
minor_child
marital
marital_1st
s_birth
marital_now
s_edu
s_political
s_hukou
s_income
s_work_exper
s_work_status
s_work_type
f_birth
f_edu
f_political
f_work_14
m_birth
m_edu
m_political
m_work_14
status_peer
status_3_before
view
inc_ability
inc_exp
trust_1
trust_2
trust_3
trust_4
trust_5
trust_6
trust_7
trust_8
trust_9
trust_10
trust_11
trust_12
trust_13
neighbor_familiarity
public_service_1
public_service_2
public_service_3
public_service_4
public_service_5
public_service_6
public_service_7
public_service_8
public_service_9
0
1
4
1
12
32
59
2015/8/4 14:18
1
1959
1
1
1
11
NaN
4.0
-2.0
20000
1
NaN
45.0
0
1
0
0
0
0
0
0
0
NaN
176
155
3
2
5
5
2.0
4
2
5
5
4
3
1
4
3
1
2
3
4
1
4
5
4
1
2
4
3
3.0
3.0
2
3
3
3
3
1
1
3.0
30.0
1.0
2.0
1
1
1
2
60000.0
2
2
1
2
0
1
0
0
0
0
0
0
0
NaN
1
0
0.0
3
1984.0
1958.0
1984.0
6.0
1.0
5.0
40000.0
5.0
NaN
NaN
-2
4
4
1
-2
4
1
1
3
2
4
3
50000.0
4
2
-8
-8
5
3
2
3
4
3
-8
4
1
4
50
60
50
50
30.0
30
50
50
50
1
2
4
2
18
52
85
2015/7/21 15:04
1
1992
1
1
1
12
NaN
4.0
2013.0
20000
1
NaN
110.0
0
0
0
0
1
0
0
0
0
NaN
170
110
5
4
3
1
1.0
2
2
1
3
5
1
2
3
4
3
5
4
3
2
3
4
5
1
2
4
3
6.0
2.0
1
3
6
4
8
5
1
3.0
2.0
1.0
3.0
1
1
1
1
40000.0
3
4
1
2
0
1
0
0
0
0
0
0
0
NaN
0
0
NaN
1
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
1972
3
1
2
1973
3
1
2
1
1
4
2
50000.0
5
4
4
3
5
3
3
3
2
3
3
3
2
3
90
70
70
80
85.0
70
90
60
60
2
3
4
2
29
83
126
2015/7/21 13:24
2
1967
1
0
3
4
NaN
4.0
-2.0
2000
1
NaN
120.0
0
1
1
0
0
0
0
0
0
NaN
160
122
4
4
5
1
1.0
2
2
2
5
1
3
1
4
4
3
5
4
4
2
3
5
5
5
3
4
2
2.0
5.0
2
4
5
4
6
3
2
NaN
NaN
NaN
NaN
1
1
2
2
8000.0
3
3
1
2
0
1
0
0
0
0
0
0
0
NaN
0
2
1.0
3
1990.0
1968.0
1990.0
3.0
1.0
1.0
6000.0
3.0
NaN
NaN
-2
1
1
2
-2
1
1
2
2
1
4
2
80000.0
3
3
3
3
4
3
3
3
3
3
-8
3
1
4
90
80
75
79
80.0
90
90
90
75
3
4
5
2
10
28
51
2015/7/25 17:33
2
1943
1
1
1
3
NaN
4.0
1959.0
6420
1
NaN
78.0
0
0
0
1
0
0
0
0
0
NaN
163
170
4
4
4
1
2.0
2
1
1
5
1
1
1
5
2
4
5
4
5
1
1
5
5
5
2
4
4
1.0
6.0
1
4
5
5
7
2
4
NaN
NaN
NaN
NaN
2
2
2
2
12000.0
3
3
1
1
0
1
0
0
0
0
0
0
0
NaN
1
4
0.0
7
1960.0
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
-2
14
1
2
-2
1
1
2
2
1
3
2
10000.0
3
3
4
3
5
3
3
5
4
3
3
3
2
3
100
90
70
80
80.0
90
90
80
80
4
5
4
1
7
18
36
2015/8/10 9:50
2
1994
1
1
1
12
NaN
1.0
2014.0
-1
2
NaN
70.0
0
0
0
0
1
0
0
0
0
NaN
165
110
5
5
3
2
3.0
1
3
4
2
5
5
3
3
3
2
4
4
3
5
2
5
5
1
4
3
4
7.0
5.0
3
2
1
1
1
4
6
NaN
NaN
NaN
NaN
1
2
2
2
-2.0
4
3
1
1
0
1
0
0
0
0
0
0
0
NaN
0
0
NaN
1
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
1970
6
1
10
1972
4
1
15
3
2
3
-8
200000.0
4
3
3
3
5
5
3
4
3
3
3
3
2
2
50
50
50
50
50.0
50
50
50
50
train. info( verbose= True , show_counts= True )
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8000 entries, 0 to 7999
Data columns (total 140 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 id 8000 non-null int64
1 happiness 8000 non-null int64
2 survey_type 8000 non-null int64
3 province 8000 non-null int64
4 city 8000 non-null int64
5 county 8000 non-null int64
6 survey_time 8000 non-null object
7 gender 8000 non-null int64
8 birth 8000 non-null int64
9 nationality 8000 non-null int64
10 religion 8000 non-null int64
11 religion_freq 8000 non-null int64
12 edu 8000 non-null int64
13 edu_other 3 non-null object
14 edu_status 6880 non-null float64
15 edu_yr 6028 non-null float64
16 income 8000 non-null int64
17 political 8000 non-null int64
18 join_party 824 non-null float64
19 floor_area 8000 non-null float64
20 property_0 8000 non-null int64
21 property_1 8000 non-null int64
22 property_2 8000 non-null int64
23 property_3 8000 non-null int64
24 property_4 8000 non-null int64
25 property_5 8000 non-null int64
26 property_6 8000 non-null int64
27 property_7 8000 non-null int64
28 property_8 8000 non-null int64
29 property_other 66 non-null object
30 height_cm 8000 non-null int64
31 weight_jin 8000 non-null int64
32 health 8000 non-null int64
33 health_problem 8000 non-null int64
34 depression 8000 non-null int64
35 hukou 8000 non-null int64
36 hukou_loc 7996 non-null float64
37 media_1 8000 non-null int64
38 media_2 8000 non-null int64
39 media_3 8000 non-null int64
40 media_4 8000 non-null int64
41 media_5 8000 non-null int64
42 media_6 8000 non-null int64
43 leisure_1 8000 non-null int64
44 leisure_2 8000 non-null int64
45 leisure_3 8000 non-null int64
46 leisure_4 8000 non-null int64
47 leisure_5 8000 non-null int64
48 leisure_6 8000 non-null int64
49 leisure_7 8000 non-null int64
50 leisure_8 8000 non-null int64
51 leisure_9 8000 non-null int64
52 leisure_10 8000 non-null int64
53 leisure_11 8000 non-null int64
54 leisure_12 8000 non-null int64
55 socialize 8000 non-null int64
56 relax 8000 non-null int64
57 learn 8000 non-null int64
58 social_neighbor 7204 non-null float64
59 social_friend 7204 non-null float64
60 socia_outing 8000 non-null int64
61 equity 8000 non-null int64
62 class 8000 non-null int64
63 class_10_before 8000 non-null int64
64 class_10_after 8000 non-null int64
65 class_14 8000 non-null int64
66 work_exper 8000 non-null int64
67 work_status 2951 non-null float64
68 work_yr 2951 non-null float64
69 work_type 2951 non-null float64
70 work_manage 2951 non-null float64
71 insur_1 8000 non-null int64
72 insur_2 8000 non-null int64
73 insur_3 8000 non-null int64
74 insur_4 8000 non-null int64
75 family_income 7999 non-null float64
76 family_m 8000 non-null int64
77 family_status 8000 non-null int64
78 house 8000 non-null int64
79 car 8000 non-null int64
80 invest_0 8000 non-null int64
81 invest_1 8000 non-null int64
82 invest_2 8000 non-null int64
83 invest_3 8000 non-null int64
84 invest_4 8000 non-null int64
85 invest_5 8000 non-null int64
86 invest_6 8000 non-null int64
87 invest_7 8000 non-null int64
88 invest_8 8000 non-null int64
89 invest_other 29 non-null object
90 son 8000 non-null int64
91 daughter 8000 non-null int64
92 minor_child 6934 non-null float64
93 marital 8000 non-null int64
94 marital_1st 7172 non-null float64
95 s_birth 6282 non-null float64
96 marital_now 6230 non-null float64
97 s_edu 6282 non-null float64
98 s_political 6282 non-null float64
99 s_hukou 6282 non-null float64
100 s_income 6282 non-null float64
101 s_work_exper 6282 non-null float64
102 s_work_status 2565 non-null float64
103 s_work_type 2565 non-null float64
104 f_birth 8000 non-null int64
105 f_edu 8000 non-null int64
106 f_political 8000 non-null int64
107 f_work_14 8000 non-null int64
108 m_birth 8000 non-null int64
109 m_edu 8000 non-null int64
110 m_political 8000 non-null int64
111 m_work_14 8000 non-null int64
112 status_peer 8000 non-null int64
113 status_3_before 8000 non-null int64
114 view 8000 non-null int64
115 inc_ability 8000 non-null int64
116 inc_exp 8000 non-null float64
117 trust_1 8000 non-null int64
118 trust_2 8000 non-null int64
119 trust_3 8000 non-null int64
120 trust_4 8000 non-null int64
121 trust_5 8000 non-null int64
122 trust_6 8000 non-null int64
123 trust_7 8000 non-null int64
124 trust_8 8000 non-null int64
125 trust_9 8000 non-null int64
126 trust_10 8000 non-null int64
127 trust_11 8000 non-null int64
128 trust_12 8000 non-null int64
129 trust_13 8
