Datawhale 202104 集成学习（下）| 幸福感预测实例

背景介绍

数据介绍

数据具有139维特征，使用8000余组数据惊醒个人幸福感的预测，标记为[1，2，3，4，5]的几个级别；

评价指标

评价指标为MSE：
$$Score=\frac{1}{n}\sum _1^n(y_i-y^{\ast }{)}^2$$

竞赛思路

S1. 数据预处理

• 异常值处理：补全
• 缺失值处理：0填充、均值填充
• 特殊格式处理：分层、主观设定值
  S2. 数据增广
• 连续变量：加减乘除
• 离散变量：分层
• 特殊变量：如字符进行One-hot编码
  S3. 特征建模

S4. 模型融合

S5. 保存结果

数据准备

函数准备

使用函数库：sklearn、seaborn、lgb、xgBoost

import os
import time 
import pandas as pd
import numpy as np
from datetime import datetime

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn import metrics
from sklearn.metrics import roc_auc_score, roc_curve, mean_squared_error,mean_absolute_error, f1_score

from sklearn import preprocessing
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet as en
from sklearn.linear_model import BayesianRidge as br
from sklearn.linear_model import LinearRegression as lr
from sklearn.ensemble import ExtraTreesRegressor as etr
from sklearn.ensemble import RandomForestRegressor as rfr
from sklearn.ensemble import GradientBoostingRegressor as gbr
from sklearn.kernel_ridge import KernelRidge as kr
from sklearn.model_selection import  KFold, StratifiedKFold,GroupKFold, RepeatedKFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV

import seaborn as sns
import matplotlib.pyplot as plt

import lightgbm as lgb
import xgboost as xgb

import logging
import warnings
import pandas_profiling as pp

warnings.filterwarnings('ignore') #消除warning

导入数据集

# 导入数据集
train = pd.read_csv("train.csv", parse_dates=['survey_time'],encoding='latin-1') 
test = pd.read_csv("test.csv", parse_dates=['survey_time'],encoding='latin-1') #latin-1向下兼容ASCII

train = train[train["happiness"]!=-8].reset_index(drop=True)
train_data_copy = train.copy() #删去"happiness" 为-8的行
target_col = "happiness" #目标列
target = train_data_copy[target_col]
del train_data_copy[target_col] #去除目标列

data = pd.concat([train_data_copy,test], axis=0, ignore_index=True)

查看数据的基本信息

train.happiness.describe()

共包含
count 7988.000000
mean 3.867927
std 0.818717
min 1.000000
25% 4.000000
50% 4.000000
75% 4.000000
max 5.000000
Name: happiness, dtype: float64

数据预处理

处理数据中连续出现的负数值，负数值仅出现-1，-2，-3，-8，对集中数值分别操作；

# make feature +5
#csv中有复数值：-1、-2、-3、-8，将他们视为有问题的特征，但是不删去
def getres1(row):
    return len([x for x in row.values if type(x)==int and x<0])

def getres2(row):
    return len([x for x in row.values if type(x)==int and x==-8])

def getres3(row):
    return len([x for x in row.values if type(x)==int and x==-1])

def getres4(row):
    return len([x for x in row.values if type(x)==int and x==-2])

def getres5(row):
    return len([x for x in row.values if type(x)==int and x==-3])

#检查数据
data['neg1'] = data[data.columns].apply(lambda row:getres1(row),axis=1)
data.loc[data['neg1']>20,'neg1'] = 20  #平滑处理,最多出现20次

data['neg2'] = data[data.columns].apply(lambda row:getres2(row),axis=1)
data['neg3'] = data[data.columns].apply(lambda row:getres3(row),axis=1)
data['neg4'] = data[data.columns].apply(lambda row:getres4(row),axis=1)
data['neg5'] = data[data.columns].apply(lambda row:getres5(row),axis=1)

填充缺失值，使用fillna(value)补全，将大部分缺失信息认为是零，根据常识补全缺失信息。

# 填充缺失信息 共25列 去掉4列 填充21列
data['work_status'] = data['work_status'].fillna(0)
data['work_yr'] = data['work_yr'].fillna(0)
data['work_manage'] = data['work_manage'].fillna(0)
data['work_type'] = data['work_type'].fillna(0)

data['edu_yr'] = data['edu_yr'].fillna(0)
data['edu_status'] = data['edu_status'].fillna(0)

data['s_work_type'] = data['s_work_type'].fillna(0)
data['s_work_status'] = data['s_work_status'].fillna(0)
data['s_political'] = data['s_political'].fillna(0)
data['s_hukou'] = data['s_hukou'].fillna(0)
data['s_income'] = data['s_income'].fillna(0)
data['s_birth'] = data['s_birth'].fillna(0)
data['s_edu'] = data['s_edu'].fillna(0)
data['s_work_exper'] = data['s_work_exper'].fillna(0)

data['minor_child'] = data['minor_child'].fillna(0)
data['marital_now'] = data['marital_now'].fillna(0)
data['marital_1st'] = data['marital_1st'].fillna(0)
data['social_neighbor']=data['social_neighbor'].fillna(0)
data['social_friend']=data['social_friend'].fillna(0)
data['hukou_loc']=data['hukou_loc'].fillna(1) #最少为1，表示户口
data['family_income']=data['family_income'].fillna(66365) #删除问题值后的平均值

特殊格式处理

• 年龄分层处理：根据出生年月和调查事件计算得到；
• 家庭收入：由于是连续值，所以不适用众数，改为均值进行缺失值补全。
• 宗教：通过主观判断，数值为1，即没有参加过宗教活动。

# 144 + 1 = 145 年龄分层处理
# 进行特殊的列进行数据处理
# 读happiness_index。xlsx
data['survey_time'] = pd.to_datetime(data['survey_time'], 
                                     format = '%Y-%m-%d', errors = 'coerce')    # 防止时间格式不同报错
data['survey_time'] = data['survey_time'].dt.year    # 得到year 计算年龄
data['age'] = data['survey_time'] - data['birth']

# 年龄分层
bins = [0, 17, 26, 34, 50, 63, 100]
data['age_bin'] = pd.cut(data['age'], bins, labels=[0, 1, 2, 3 ,4 ,5])

# 对‘宗教’处理
data.loc[data['religion']<0, 'religion'] = 1    # 1为不信仰宗教
data.loc[data['religion_freq']<0, 'religion_freq'] =1    # 1为从来没有参加过
# 对‘教育程度’处理
data.loc[data['edu']<0, 'edu'] = 4
data.loc[data['edu_status']<0, 'edu_status'] = 0
data.loc[data['edu_yr']<0,'edu_yr'] = 0
#对‘个人收入’处理
data.loc[data['income']<0,'income'] = 0 #认为无收入
#对‘政治面貌’处理
data.loc[data['political']<0,'political'] = 1 #认为是群众
#对体重处理
data.loc[(data['weight_jin']<=80)&(data['height_cm']>=160),'weight_jin']= data['weight_jin']*2
data.loc[data['weight_jin']<=60,'weight_jin']= data['weight_jin']*2  #个人的想法，哈哈哈，没有60斤的成年人吧
#对身高处理
data.loc[data['height_cm']<150,'height_cm'] = 150 #成年人的实际情况
#对‘健康’处理
data.loc[data['health']<0,'health'] = 4 #认为是比较健康
data.loc[data['health_problem']<0,'health_problem'] = 4
#对‘沮丧’处理
data.loc[data['depression']<0,'depression'] = 4 #一般人都是很少吧
#对‘媒体’处理
data.loc[data['media_1']<0,'media_1'] = 1 #都是从不
data.loc[data['media_2']<0,'media_2'] = 1
data.loc[data['media_3']<0,'media_3'] = 1
data.loc[data['media_4']<0,'media_4'] = 1
data.loc[data['media_5']<0,'media_5'] = 1
data.loc[data['media_6']<0,'media_6'] = 1
#对‘空闲活动’处理
data.loc[data['leisure_1']<0,'leisure_1'] = 1 #都是根据自己的想法
data.loc[data['leisure_2']<0,'leisure_2'] = 5
data.loc[data['leisure_3']<0,'leisure_3'] = 3

使用众数，代码中的mode实现异常值修正，这里的特征是空闲活动，采用众数对缺失值处理。

# 异常值取众数
data.loc[data['leisure_4']<0,'leisure_4'] = data['leisure_4'].mode() #取众数
data.loc[data['leisure_5']<0,'leisure_5'] = data['leisure_5'].mode()
data.loc[data['leisure_6']<0,'leisure_6'] = data['leisure_6'].mode()
data.loc[data['leisure_7']<0,'leisure_7'] = data['leisure_7'].mode()
data.loc[data['leisure_8']<0,'leisure_8'] = data['leisure_8'].mode()
data.loc[data['leisure_9']<0,'leisure_9'] = data['leisure_9'].mode()
data.loc[data['leisure_10']<0,'leisure_10'] = data['leisure_10'].mode()
data.loc[data['leisure_11']<0,'leisure_11'] = data['leisure_11'].mode()
data.loc[data['leisure_12']<0,'leisure_12'] = data['leisure_12'].mode()
data.loc[data['socialize']<0,'socialize'] = 2 #很少
data.loc[data['relax']<0,'relax'] = 4 #经常
data.loc[data['learn']<0,'learn'] = 1 #从不

# ‘社交’处理
data.loc[data['social_neighbor']<0, 'social_neighbor'] = 0
data.loc[data['social_friend']<0, 'social_friend'] = 0
data.loc[data['socia_outing']<0,'socia_outing'] = 1
data.loc[data['neighbor_familiarity']<0,'social_neighbor']= 4

# '社会公平性'处理
data.loc[data['equity']<0,'equity'] = 4
#对‘社会等级’处理
data.loc[data['class_10_before']<0,'class_10_before'] = 3
data.loc[data['class']<0,'class'] = 5
data.loc[data['class_10_after']<0,'class_10_after'] = 5
data.loc[data['class_14']<0,'class_14'] = 2
#对‘工作情况’处理
data.loc[data['work_status']<0,'work_status'] = 0
data.loc[data['work_yr']<0,'work_yr'] = 0
data.loc[data['work_manage']<0,'work_manage'] = 0
data.loc[data['work_type']<0,'work_type'] = 0
#对‘社会保障’处理
data.loc[data['insur_1']<0,'insur_1'] = 1
data.loc[data['insur_2']<0,'insur_2'] = 1
data.loc[data['insur_3']<0,'insur_3'] = 1
data.loc[data['insur_4']<0,'insur_4'] = 1
data.loc[data['insur_1']==0,'insur_1'] = 0
data.loc[data['insur_2']==0,'insur_2'] = 0
data.loc[data['insur_3']==0,'insur_3'] = 0
data.loc[data['insur_4']==0,'insur_4'] = 0

使用平均值进行补全，代码为mean()，家庭收入是连续值，不能使用众数。

#对家庭情况处理
family_income_mean = data['family_income'].mean()
data.loc[data['family_income']<0,'family_income'] = family_income_mean
data.loc[data['family_m']<0,'family_m'] = 2
data.loc[data['family_status']<0,'family_status'] = 3
data.loc[data['house']<0,'house'] = 1
data.loc[data['car']<0,'car'] = 0
data.loc[data['car']==2,'car'] = 0
data.loc[data['son']<0,'son'] = 1
data.loc[data['daughter']<0,'daughter'] = 0
data.loc[data['minor_child']<0,'minor_child'] = 0
#对‘婚姻’处理
data.loc[data['marital_1st']<0,'marital_1st'] = 0
data.loc[data['marital_now']<0,'marital_now'] = 0
#对‘配偶’处理
data.loc[data['s_birth']<0,'s_birth'] = 0
data.loc[data['s_edu']<0,'s_edu'] = 0
data.loc[data['s_political']<0,'s_political'] = 0
data.loc[data['s_hukou']<0,'s_hukou'] = 0
data.loc[data['s_income']<0,'s_income'] = 0
data.loc[data['s_work_type']<0,'s_work_type'] = 0
data.loc[data['s_work_status']<0,'s_work_status'] = 0
data.loc[data['s_work_exper']<0,'s_work_exper'] = 0
#对‘父母情况’处理
data.loc[data['f_birth']<0,'f_birth'] = 1945
data.loc[data['f_edu']<0,'f_edu'] = 1
data.loc[data['f_political']<0,'f_political'] = 1
data.loc[data['f_work_14']<0,'f_work_14'] = 2
data.loc[data['m_birth']<0,'m_birth'] = 1940
data.loc[data['m_edu']<0,'m_edu'] = 1
data.loc[data['m_political']<0,'m_political'] = 1
data.loc[data['m_work_14']<0,'m_work_14'] = 2
#和同龄人相比社会经济地位
data.loc[data['status_peer']<0,'status_peer'] = 2
#和3年前比社会经济地位
data.loc[data['status_3_before']<0,'status_3_before'] = 2
#对‘观点’处理
data.loc[data['view']<0,'view'] = 4
#对期望年收入处理
data.loc[data['inc_ability']<=0,'inc_ability']= 2
inc_exp_mean = data['inc_exp'].mean()
data.loc[data['inc_exp']<=0,'inc_exp']= inc_exp_mean #取均值

#部分特征处理，取众数
for i in range(1,9+1):
    data.loc[data['public_service_'+str(i)]<0,'public_service_'+str(i)] = data['public_service_'+str(i)].dropna().mode()[0]

for i in range(1,13+1):
    data.loc[data['trust_'+str(i)]<0,'trust_'+str(i)] = data['trust_'+str(i)].dropna().mode()[0]

数据增广

处理各个特征关系，进行数据增广，处理以下信息：

• 第一次结婚年龄
• 最近结婚年龄
• 是否再婚
• 配偶年龄
• 配偶年龄差
• 各种收入比（与配偶之间的收入比、十年后预期收入与现在收入之比）
• 收入与住房面积比（10年后期望收入）
• 社会阶级（10年后的社会阶级、14年后的社会阶级）
• 悠闲指数
• 满意指数
• 信任指数
• 同一省市内的收入平均值 一个个体相对于同省、市、县
• 同龄人之间 收入情况、健康情况等

#第一次结婚年龄 147
data['marital_1stbir'] = data['marital_1st'] - data['birth'] 
#最近结婚年龄 148
data['marital_nowtbir'] = data['marital_now'] - data['birth'] 
#是否再婚 149
data['mar'] = data['marital_nowtbir'] - data['marital_1stbir']
#配偶年龄 150
data['marital_sbir'] = data['marital_now']-data['s_birth']
#配偶年龄差 151
data['age_'] = data['marital_nowtbir'] - data['marital_sbir'] 

#收入比 151+7 =158
data['income/s_income'] = data['income']/(data['s_income']+1)
data['income+s_income'] = data['income']+(data['s_income']+1)
data['income/family_income'] = data['income']/(data['family_income']+1)
data['all_income/family_income'] = (data['income']+data['s_income'])/(data['family_income']+1)
data['income/inc_exp'] = data['income']/(data['inc_exp']+1)
data['family_income/m'] = data['family_income']/(data['family_m']+0.01)
data['income/m'] = data['income']/(data['family_m']+0.01)

#收入/面积比 158+4=162
data['income/floor_area'] = data['income']/(data['floor_area']+0.01)
data['all_income/floor_area'] = (data['income']+data['s_income'])/(data['floor_area']+0.01)
data['family_income/floor_area'] = data['family_income']/(data['floor_area']+0.01)
data['floor_area/m'] = data['floor_area']/(data['family_m']+0.01)

#class 162+3=165
data['class_10_diff'] = (data['class_10_after'] - data['class'])
data['class_diff'] = data['class'] - data['class_10_before']
data['class_14_diff'] = data['class'] - data['class_14']
#悠闲指数 166
leisure_fea_lis = ['leisure_'+str(i) for i in range(1,13)]
data['leisure_sum'] = data[leisure_fea_lis].sum(axis=1) #skew
#满意指数 167
public_service_fea_lis = ['public_service_'+str(i) for i in range(1,10)]
data['public_service_sum'] = data[public_service_fea_lis].sum(axis=1) #skew

#信任指数 168
trust_fea_lis = ['trust_'+str(i) for i in range(1,14)]
data['trust_sum'] = data[trust_fea_lis].sum(axis=1) #skew

#province mean 168+13=181
data['province_income_mean'] = data.groupby(['province'])['income'].transform('mean').values
data['province_family_income_mean'] = data.groupby(['province'])['family_income'].transform('mean').values
data['province_equity_mean'] = data.groupby(['province'])['equity'].transform('mean').values
data['province_depression_mean'] = data.groupby(['province'])['depression'].transform('mean').values
data['province_floor_area_mean'] = data.groupby(['province'])['floor_area'].transform('mean').values
data['province_health_mean'] = data.groupby(['province'])['health'].transform('mean').values
data['province_class_10_diff_mean'] = data.groupby(['province'])['class_10_diff'].transform('mean').values
data['province_class_mean'] = data.groupby(['province'])['class'].transform('mean').values
data['province_health_problem_mean'] = data.groupby(['province'])['health_problem'].transform('mean').values
data['province_family_status_mean'] = data.groupby(['province'])['family_status'].transform('mean').values
data['province_leisure_sum_mean'] = data.groupby(['province'])['leisure_sum'].transform('mean').values
data['province_public_service_sum_mean'] = data.groupby(['province'])['public_service_sum'].transform('mean').values
data['province_trust_sum_mean'] = data.groupby(['province'])['trust_sum'].transform('mean').values

#city   mean 181+13=194
data['city_income_mean'] = data.groupby(['city'])['income'].transform('mean').values
data['city_family_income_mean'] = data.groupby(['city'])['family_income'].transform('mean').values
data['city_equity_mean'] = data.groupby(['city'])['equity'].transform('mean').values
data['city_depression_mean'] = data.groupby(['city'])['depression'].transform('mean').values
data['city_floor_area_mean'] = data.groupby(['city'])['floor_area'].transform('mean').values
data['city_health_mean'] = data.groupby(['city'])['health'].transform('mean').values
data['city_class_10_diff_mean'] = data.groupby(['city'])['class_10_diff'].transform('mean').values
data['city_class_mean'] = data.groupby(['city'])['class'].transform('mean').values
data['city_health_problem_mean'] = data.groupby(['city'])['health_problem'].transform('mean').values
data['city_family_status_mean'] = data.groupby(['city'])['family_status'].transform('mean').values
data['city_leisure_sum_mean'] = data.groupby(['city'])['leisure_sum'].transform('mean').values
data['city_public_service_sum_mean'] = data.groupby(['city'])['public_service_sum'].transform('mean').values
data['city_trust_sum_mean'] = data.groupby(['city'])['trust_sum'].transform('mean').values

#county  mean 194 + 13 = 207
data['county_income_mean'] = data.groupby(['county'])['income'].transform('mean').values
data['county_family_income_mean'] = data.groupby(['county'])['family_income'].transform('mean').values
data['county_equity_mean'] = data.groupby(['county'])['equity'].transform('mean').values
data['county_depression_mean'] = data.groupby(['county'])['depression'].transform('mean').values
data['county_floor_area_mean'] = data.groupby(['county'])['floor_area'].transform('mean').values
data['county_health_mean'] = data.groupby(['county'])['health'].transform('mean').values
data['county_class_10_diff_mean'] = data.groupby(['county'])['class_10_diff'].transform('mean').values
data['county_class_mean'] = data.groupby(['county'])['class'].transform('mean').values
data['county_health_problem_mean'] = data.groupby(['county'])['health_problem'].transform('mean').values
data['county_family_status_mean'] = data.groupby(['county'])['family_status'].transform('mean').values
data['county_leisure_sum_mean'] = data.groupby(['county'])['leisure_sum'].transform('mean').values
data['county_public_service_sum_mean'] = data.groupby(['county'])['public_service_sum'].transform('mean').values
data['county_trust_sum_mean'] = data.groupby(['county'])['trust_sum'].transform('mean').values

#ratio 相比同省 207 + 13 =220
data['income/province'] = data['income']/(data['province_income_mean'])                                      
data['family_income/province'] = data['family_income']/(data['province_family_income_mean'])   
data['equity/province'] = data['equity']/(data['province_equity_mean'])       
data['depression/province'] = data['depression']/(data['province_depression_mean'])                                                
data['floor_area/province'] = data['floor_area']/(data['province_floor_area_mean'])
data['health/province'] = data['health']/(data['province_health_mean'])
data['class_10_diff/province'] = data['class_10_diff']/(data['province_class_10_diff_mean'])
data['class/province'] = data['class']/(data['province_class_mean'])
data['health_problem/province'] = data['health_problem']/(data['province_health_problem_mean'])
data['family_status/province'] = data['family_status']/(data['province_family_status_mean'])
data['leisure_sum/province'] = data['leisure_sum']/(data['province_leisure_sum_mean'])
data['public_service_sum/province'] = data['public_service_sum']/(data['province_public_service_sum_mean'])
data['trust_sum/province'] = data['trust_sum']/(data['province_trust_sum_mean']+1)

#ratio 相比同市 220 + 13 =233
data['income/city'] = data['income']/(data['city_income_mean'])                                      
data['family_income/city'] = data['family_income']/(data['city_family_income_mean'])   
data['equity/city'] = data['equity']/(data['city_equity_mean'])       
data['depression/city'] = data['depression']/(data['city_depression_mean'])                                                
data['floor_area/city'] = data['floor_area']/(data['city_floor_area_mean'])
data['health/city'] = data['health']/(data['city_health_mean'])
data['class_10_diff/city'] = data['class_10_diff']/(data['city_class_10_diff_mean'])
data['class/city'] = data['class']/(data['city_class_mean'])
data['health_problem/city'] = data['health_problem']/(data['city_health_problem_mean'])
data['family_status/city'] = data['family_status']/(data['city_family_status_mean'])
data['leisure_sum/city'] = data['leisure_sum']/(data['city_leisure_sum_mean'])
data['public_service_sum/city'] = data['public_service_sum']/(data['city_public_service_sum_mean'])
data['trust_sum/city'] = data['trust_sum']/(data['city_trust_sum_mean'])

#ratio 相比同个地区 233 + 13 =246
data['income/county'] = data['income']/(data['county_income_mean'])                                      
data['family_income/county'] = data['family_income']/(data['county_family_income_mean'])   
data['equity/county'] = data['equity']/(data['county_equity_mean'])       
data['depression/county'] = data['depression']/(data['county_depression_mean'])                                                
data['floor_area/county'] = data['floor_area']/(data['county_floor_area_mean'])
data['health/county'] = data['health']/(data['county_health_mean'])
data['class_10_diff/county'] = data['class_10_diff']/(data['county_class_10_diff_mean'])
data['class/county'] = data['class']/(data['county_class_mean'])
data['health_problem/county'] = data['health_problem']/(data['county_health_problem_mean'])
data['family_status/county'] = data['family_status']/(data['county_family_status_mean'])
data['leisure_sum/county'] = data['leisure_sum']/(data['county_leisure_sum_mean'])
data['public_service_sum/county'] = data['public_service_sum']/(data['county_public_service_sum_mean'])
data['trust_sum/county'] = data['trust_sum']/(data['county_trust_sum_mean'])

#age   mean 246+ 13 =259
data['age_income_mean'] = data.groupby(['age'])['income'].transform('mean').values
data['age_family_income_mean'] = data.groupby(['age'])['family_income'].transform('mean').values
data['age_equity_mean'] = data.groupby(['age'])['equity'].transform('mean').values
data['age_depression_mean'] = data.groupby(['age'])['depression'].transform('mean').values
data['age_floor_area_mean'] = data.groupby(['age'])['floor_area'].transform('mean').values
data['age_health_mean'] = data.groupby(['age'])['health'].transform('mean').values
data['age_class_10_diff_mean'] = data.groupby(['age'])['class_10_diff'].transform('mean').values
data['age_class_mean'] = data.groupby(['age'])['class'].transform('mean').values
data['age_health_problem_mean'] = data.groupby(['age'])['health_problem'].transform('mean').values
data['age_family_status_mean'] = data.groupby(['age'])['family_status'].transform('mean').values
data['age_leisure_sum_mean'] = data.groupby(['age'])['leisure_sum'].transform('mean').values
data['age_public_service_sum_mean'] = data.groupby(['age'])['public_service_sum'].transform('mean').values
data['age_trust_sum_mean'] = data.groupby(['age'])['trust_sum'].transform('mean').values

# 和同龄人相比259 + 13 =272
data['income/age'] = data['income']/(data['age_income_mean'])                                      
data['family_income/age'] = data['family_income']/(data['age_family_income_mean'])   
data['equity/age'] = data['equity']/(data['age_equity_mean'])       
data['depression/age'] = data['depression']/(data['age_depression_mean'])                                                
data['floor_area/age'] = data['floor_area']/(data['age_floor_area_mean'])
data['health/age'] = data['health']/(data['age_health_mean'])
data['class_10_diff/age'] = data['class_10_diff']/(data['age_class_10_diff_mean'])
data['class/age'] = data['class']/(data['age_class_mean'])
data['health_problem/age'] = data['health_problem']/(data['age_health_problem_mean'])
data['family_status/age'] = data['family_status']/(data['age_family_status_mean'])
data['leisure_sum/age'] = data['leisure_sum']/(data['age_leisure_sum_mean'])
data['public_service_sum/age'] = data['public_service_sum']/(data['age_public_service_sum_mean'])
data['trust_sum/age'] = data['trust_sum']/(data['age_trust_sum_mean'])

此外应该山区有效样本数少的特征，例如负值多或者缺失值太多的特征； 观察数据特征维度，考虑特征工程、训练模型以及模型融合的工作：

print('shape',data.shape)
data.head()

#272-9=263
#删除数值特别少的和之前用过的特征
del_list=['id','survey_time','edu_other','invest_other','property_other','join_party','province','city','county']
use_feature = [clo for clo in data.columns if clo not in del_list]
data.fillna(0,inplace=True) #还是补0
train_shape = train.shape[0] #一共的数据量，训练集
features = data[use_feature].columns #删除后所有的特征
X_train_263 = data[:train_shape][use_feature].values
y_train = target
X_test_263 = data[train_shape:][use_feature].values
X_train_263.shape #最终一种263个特征

# 选择最重要的49个特征
imp_fea_49 = ['equity','depression','health','class','family_status','health_problem','class_10_after',
               'equity/province','equity/city','equity/county',
               'depression/province','depression/city','depression/county',
               'health/province','health/city','health/county',
               'class/province','class/city','class/county',
               'family_status/province','family_status/city','family_status/county',
               'family_income/province','family_income/city','family_income/county',
               'floor_area/province','floor_area/city','floor_area/county',
               'leisure_sum/province','leisure_sum/city','leisure_sum/county',
               'public_service_sum/province','public_service_sum/city','public_service_sum/county',
               'trust_sum/province','trust_sum/city','trust_sum/county',
               'income/m','public_service_sum','class_diff','status_3_before','age_income_mean','age_floor_area_mean',
               'weight_jin','height_cm',
               'health/age','depression/age','equity/age','leisure_sum/age'
              ]
train_shape = train.shape[0]
X_train_49 = data[:train_shape][imp_fea_49].values
X_test_49 = data[train_shape:][imp_fea_49].values
X_train_49.shape #最重要的49个特征

对离散变量进行one-hot编码 合成第三类特征

cat_fea = ['survey_type','gender','nationality','edu_status','political','hukou','hukou_loc','work_exper','work_status','work_type',
           'work_manage','marital','s_political','s_hukou','s_work_exper','s_work_status','s_work_type','f_political','f_work_14',
           'm_political','m_work_14']
noc_fea = [clo for clo in use_feature if clo not in cat_fea]

onehot_data = data[cat_fea].values
enc = preprocessing.OneHotEncoder(categories = 'auto')
oh_data=enc.fit_transform(onehot_data).toarray()
oh_data.shape #变为onehot编码格式

X_train_oh = oh_data[:train_shape,:]
X_test_oh = oh_data[train_shape:,:]
X_train_oh.shape #其中的训练集

X_train_383 = np.column_stack([data[:train_shape][noc_fea].values,X_train_oh])#先是noc，再是cat_fea
X_test_383 = np.column_stack([data[train_shape:][noc_fea].values,X_test_oh])
X_train_383.shape

基于此，我们构建完成了三种特征工程（训练数据集）：

• 其一是上面提取的最重要的49中特征，其中包括健康程度、社会阶级、在同龄人中的收入情况等等特征。
• 其二是扩充后的263维特征（这里可以认为是初始特征）。
• 其三是使用One-hot编码后的特征，这里要使用One-hot进行编码的原因在于，有部分特征为分离值，例如性别中男女，男为1，女为2，我们想使用One-hot将其变为男为0，女为1，来增强机器学习算法的鲁棒性能；再如民族这个特征，原本是1-56这56个数值，如果直接分类会让分类器的鲁棒性变差，所以使用One-hot编码将其变为6个特征进行非零即一的处理。

特征建模

对于原始的263维的特征，使用lightGBM进行处理，这里我们使用5折交叉验证的方法：

1. lightGBM

##### lgb_263 #
#lightGBM决策树
lgb_263_param = {'num_leaves': 7, 
                'min_data_in_leaf': 20, #叶子可能具有的最小记录数
                'objective':'regression',
                'max_depth': -1,
                'learning_rate': 0.003,
                "boosting": "gbdt", #用gbdt算法
                "feature_fraction": 0.18, #例如 0.18时，意味着在每次迭代中随机选择18％的参数来建树
                "bagging_freq": 1,
                "bagging_fraction": 0.55, #每次迭代时用的数据比例
                "bagging_seed": 14,
                "metric": 'mse',
                "lambda_l1": 0.1005,
                "lambda_l2": 0.1996, 
                "verbosity": -1}
folds = StratifiedKFold(n_splits=5, shuffle=True, random_state=4)   #交叉切分：5
oof_lgb_263 = np.zeros(len(X_train_263))
predictions_lgb_263 = np.zeros(len(X_test_263))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_263, y_train)):

    print("fold n°{}".format(fold_+1))
    trn_data = lgb.Dataset(X_train_263[trn_idx], y_train[trn_idx])
    val_data = lgb.Dataset(X_train_263[val_idx], y_train[val_idx])#train:val=4:1

    num_round = 10000
    lgb_263 = lgb.train(lgb_263_param, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=500, early_stopping_rounds = 800)
    oof_lgb_263[val_idx] = lgb_263.predict(X_train_263[val_idx], num_iteration=lgb_263.best_iteration)
    predictions_lgb_263 += lgb_263.predict(X_test_263, num_iteration=lgb_263.best_iteration) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_lgb_263, target)))

CV score: 0.46473870

训练完lightGBM，通过结果看出看出特征的重要性

#---------------特征重要性
pd.set_option('display.max_columns', None)
#显示所有行
pd.set_option('display.max_rows', None)
#设置value的显示长度为100，默认为50
pd.set_option('max_colwidth',100)
df = pd.DataFrame(data[use_feature].columns.tolist(), columns=['feature'])
df['importance']=list(lgb_263.feature_importance())
df = df.sort_values(by='importance',ascending=False)
plt.figure(figsize=(14,28))
sns.barplot(x="importance", y="feature", data=df.head(50))
plt.title('Features importance (averaged/folds)')
plt.tight_layout()

使用常见的机器学习方法，对263维特征进行建模：

# 2. xgboost
##### xgb_263
#xgboost
xgb_263_params = {'eta': 0.02,  #lr
              'max_depth': 6,  
              'min_child_weight':3,#最小叶子节点样本权重和
              'gamma':0, #指定节点分裂所需的最小损失函数下降值。
              'subsample': 0.7,  #控制对于每棵树，随机采样的比例
              'colsample_bytree': 0.3,  #用来控制每棵随机采样的列数的占比 (每一列是一个特征)。
              'lambda':2,
              'objective': 'reg:linear', 
              'eval_metric': 'rmse', 
              'silent': True, 
              'nthread': -1}


folds = KFold(n_splits=5, shuffle=True, random_state=2019)
oof_xgb_263 = np.zeros(len(X_train_263))
predictions_xgb_263 = np.zeros(len(X_test_263))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_263, y_train)):
    print("fold n°{}".format(fold_+1))
    trn_data = xgb.DMatrix(X_train_263[trn_idx], y_train[trn_idx])
    val_data = xgb.DMatrix(X_train_263[val_idx], y_train[val_idx])

    watchlist = [(trn_data, 'train'), (val_data, 'valid_data')]
    xgb_263 = xgb.train(dtrain=trn_data, num_boost_round=3000, evals=watchlist, early_stopping_rounds=600, verbose_eval=500, params=xgb_263_params)
    oof_xgb_263[val_idx] = xgb_263.predict(xgb.DMatrix(X_train_263[val_idx]), ntree_limit=xgb_263.best_ntree_limit)
    predictions_xgb_263 += xgb_263.predict(xgb.DMatrix(X_test_263), ntree_limit=xgb_263.best_ntree_limit) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_xgb_263, target)))

CV score: 0.46446058

# 3. RandomForestRegressor随机森林
folds = KFold(n_splits=5, shuffle=True, random_state=2019)
oof_rfr_263 = np.zeros(len(X_train_263))
predictions_rfr_263 = np.zeros(len(X_test_263))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_263, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_263[trn_idx]
    tr_y = y_train[trn_idx]
    rfr_263 = rfr(n_estimators=1600,max_depth=9, min_samples_leaf=9, min_weight_fraction_leaf=0.0,
            max_features=0.25,verbose=1,n_jobs=-1)
    #verbose = 0 为不在标准输出流输出日志信息
#verbose = 1 为输出进度条记录
#verbose = 2 为每个epoch输出一行记录
    rfr_263.fit(tr_x,tr_y)
    oof_rfr_263[val_idx] = rfr_263.predict(X_train_263[val_idx])
    
    predictions_rfr_263 += rfr_263.predict(X_test_263) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_rfr_263, target)))

CV score: 0.48584807

# 4. GradientBoostingRegressor梯度提升决策树
folds = StratifiedKFold(n_splits=5, shuffle=True, random_state=2018)
oof_gbr_263 = np.zeros(train_shape)
predictions_gbr_263 = np.zeros(len(X_test_263))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_263, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_263[trn_idx]
    tr_y = y_train[trn_idx]
    gbr_263 = gbr(n_estimators=400, learning_rate=0.01,subsample=0.65,max_depth=7, min_samples_leaf=20,
            max_features=0.22,verbose=1)
    gbr_263.fit(tr_x,tr_y)
    oof_gbr_263[val_idx] = gbr_263.predict(X_train_263[val_idx])
    
    predictions_gbr_263 += gbr_263.predict(X_test_263) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_gbr_263, target)))

CV score: 0.46177263

# 5. ExtraTreesRegressor 极端随机森林回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_etr_263 = np.zeros(train_shape)
predictions_etr_263 = np.zeros(len(X_test_263))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_263, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_263[trn_idx]
    tr_y = y_train[trn_idx]
    etr_263 = etr(n_estimators=1000,max_depth=8, min_samples_leaf=12, min_weight_fraction_leaf=0.0,
            max_features=0.4,verbose=1,n_jobs=-1)
    etr_263.fit(tr_x,tr_y)
    oof_etr_263[val_idx] = etr_263.predict(X_train_263[val_idx])
    
    predictions_etr_263 += etr_263.predict(X_test_263) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_etr_263, target)))

CV score: 0.49117365

以上5种模型的预测结果以及模型架构参数，进行5折交叉验证并重复两次（核脊回归）的结果如下。

train_stack2 = np.vstack([oof_lgb_263,oof_xgb_263,oof_gbr_263,oof_rfr_263,oof_etr_263]).transpose()
# transpose()函数的作用就是调换x,y,z的位置,也就是数组的索引值
test_stack2 = np.vstack([predictions_lgb_263, predictions_xgb_263,predictions_gbr_263,predictions_rfr_263,predictions_etr_263]).transpose()

#交叉验证:5折，重复2次
folds_stack = RepeatedKFold(n_splits=5, n_repeats=2, random_state=7)
oof_stack2 = np.zeros(train_stack2.shape[0])
predictions_lr2 = np.zeros(test_stack2.shape[0])

for fold_, (trn_idx, val_idx) in enumerate(folds_stack.split(train_stack2,target)):
    print("fold {}".format(fold_))
    trn_data, trn_y = train_stack2[trn_idx], target.iloc[trn_idx].values
    val_data, val_y = train_stack2[val_idx], target.iloc[val_idx].values
    #Kernel Ridge Regression
    lr2 = kr()
    lr2.fit(trn_data, trn_y)
    
    oof_stack2[val_idx] = lr2.predict(val_data)
    predictions_lr2 += lr2.predict(test_stack2) / 10
    
mean_squared_error(target.values, oof_stack2) 

接下来我们对49维的数据进行与上述263维数据相同的操作

# 1. Kernel ridge Regression 基于核的岭回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_kr_383 = np.zeros(train_shape)
predictions_kr_383 = np.zeros(len(X_test_383))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_383, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_383[trn_idx]
    tr_y = y_train[trn_idx]
    #Kernel Ridge Regression 岭回归
    kr_383 = kr()
    kr_383.fit(tr_x,tr_y)
    oof_kr_383[val_idx] = kr_383.predict(X_train_383[val_idx])
    
    predictions_kr_383 += kr_383.predict(X_test_383) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_kr_383, target)))

CV score: 0.49538047

# 2. 使用普通岭回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_ridge_383 = np.zeros(train_shape)
predictions_ridge_383 = np.zeros(len(X_test_383))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_383, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_383[trn_idx]
    tr_y = y_train[trn_idx]
    #使用岭回归
    ridge_383 = Ridge(alpha=1200)
    ridge_383.fit(tr_x,tr_y)
    oof_ridge_383[val_idx] = ridge_383.predict(X_train_383[val_idx])
    
    predictions_ridge_383 += ridge_383.predict(X_test_383) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_ridge_383, target)))

CV score: 0.48257451

# 3. 使用ElasticNet 弹性网络
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_en_383 = np.zeros(train_shape)
predictions_en_383 = np.zeros(len(X_test_383))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_383, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_383[trn_idx]
    tr_y = y_train[trn_idx]
    #ElasticNet 弹性网络
    en_383 = en(alpha=1.0,l1_ratio=0.06)
    en_383.fit(tr_x,tr_y)
    oof_en_383[val_idx] = en_383.predict(X_train_383[val_idx])
    
    predictions_en_383 += en_383.predict(X_test_383) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_en_383, target)))

CV score: 0.53756165

# 4. 使用BayesianRidge 贝叶斯岭回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_br_383 = np.zeros(train_shape)
predictions_br_383 = np.zeros(len(X_test_383))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_383, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_383[trn_idx]
    tr_y = y_train[trn_idx]
    #BayesianRidge 贝叶斯回归
    br_383 = br()
    br_383.fit(tr_x,tr_y)
    oof_br_383[val_idx] = br_383.predict(X_train_383[val_idx])
    
    predictions_br_383 += br_383.predict(X_test_383) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_br_383, target)))

CV score: 0.48154234

四种模型的基于383个特征的预测结果以及模型架构及参数，通过五折交叉验证，重复两次线性回归，得到每个特征数下的模型结果。

train_stack3 = np.vstack([oof_lgb_49,oof_xgb_49,oof_gbr_49]).transpose()
test_stack3 = np.vstack([predictions_lgb_49, predictions_xgb_49,predictions_gbr_49]).transpose()
#
folds_stack = RepeatedKFold(n_splits=5, n_repeats=2, random_state=7)
oof_stack3 = np.zeros(train_stack3.shape[0])
predictions_lr3 = np.zeros(test_stack3.shape[0])

for fold_, (trn_idx, val_idx) in enumerate(folds_stack.split(train_stack3,target)):
    print("fold {}".format(fold_))
    trn_data, trn_y = train_stack3[trn_idx], target.iloc[trn_idx].values
    val_data, val_y = train_stack3[val_idx], target.iloc[val_idx].values
        #Kernel Ridge Regression
    lr3 = kr()
    lr3.fit(trn_data, trn_y)
    
    oof_stack3[val_idx] = lr3.predict(val_data)
    predictions_lr3 += lr3.predict(test_stack3) / 10
    
mean_squared_error(target.values, oof_stack3) 

49维特征作为重要特征，考虑增加更多模型对数据构建工作。

# 1. KernelRidge核岭回归
flods = KFold(n_splits=5, shuffle=True, random_state=13)
oof_kr_49 = np.zeros(train_shape)
predictions_kr_49 = np.zeros(len(X_test_49))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_49, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_49[trn_idx]
    tr_y = y_train[trn_idx]
    kr_49 = kr()
    kr_49.fit(tr_x,tr_y)
    oof_kr_49[val_idx] = kr_49.predict(X_train_49[val_idx])
    
    predictions_kr_49 += kr_49.predict(X_test_49) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_kr_49, target)))

CV score: 0.50260307

# 2. Ridge 岭回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_ridge_49 = np.zeros(train_shape)
predictions_ridge_49 = np.zeros(len(X_test_49))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_49, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_49[trn_idx]
    tr_y = y_train[trn_idx]
    ridge_49 = Ridge(alpha=6)
    ridge_49.fit(tr_x,tr_y)
    oof_ridge_49[val_idx] = ridge_49.predict(X_train_49[val_idx])
    
    predictions_ridge_49 += ridge_49.predict(X_test_49) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_ridge_49, target)))

CV score: 0.49457774

# 3. BayesianRidge 贝叶斯岭回归
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_br_49 = np.zeros(train_shape)
predictions_br_49 = np.zeros(len(X_test_49))

for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_49, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_49[trn_idx]
    tr_y = y_train[trn_idx]
    br_49 = br()
    br_49.fit(tr_x,tr_y)
    oof_br_49[val_idx] = br_49.predict(X_train_49[val_idx])
    
    predictions_br_49 += br_49.predict(X_test_49) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_br_49, target)))

CV score: 0.49538223

# 4. ElasticNet 弹性网络
folds = KFold(n_splits=5, shuffle=True, random_state=13)
oof_en_49 = np.zeros(train_shape)
predictions_en_49 = np.zeros(len(X_test_49))
#
for fold_, (trn_idx, val_idx) in enumerate(folds.split(X_train_49, y_train)):
    print("fold n°{}".format(fold_+1))
    tr_x = X_train_49[trn_idx]
    tr_y = y_train[trn_idx]
    en_49 = en(alpha=1.0,l1_ratio=0.05)
    en_49.fit(tr_x,tr_y)
    oof_en_49[val_idx] = en_49.predict(X_train_49[val_idx])
    
    predictions_en_49 += en_49.predict(X_test_49) / folds.n_splits

print("CV score: {:<8.8f}".format(mean_squared_error(oof_en_49, target)))

CV score: 0.53831897

得到49个特征的预测结果以及模型架构及参数，对每种特征工程进行5折交叉验证，重复两次线性回归，得到每一个特征数下的模型结果。

train_stack4 = np.vstack([oof_br_49,oof_kr_49,oof_en_49,oof_ridge_49]).transpose()
test_stack4 = np.vstack([predictions_br_49, predictions_kr_49,predictions_en_49,predictions_ridge_49]).transpose()

folds_stack = RepeatedKFold(n_splits=5, n_repeats=2, random_state=7)
oof_stack4 = np.zeros(train_stack4.shape[0])
predictions_lr4 = np.zeros(test_stack4.shape[0])

for fold_, (trn_idx, val_idx) in enumerate(folds_stack.split(train_stack4,target)):
    print("fold {}".format(fold_))
    trn_data, trn_y = train_stack4[trn_idx], target.iloc[trn_idx].values
    val_data, val_y = train_stack4[val_idx], target.iloc[val_idx].values
    #LinearRegression
    lr4 = lr()
    lr4.fit(trn_data, trn_y)
    
    oof_stack4[val_idx] = lr4.predict(val_data)
    predictions_lr4 += lr4.predict(test_stack1) / 10
    
mean_squared_error(target.values, oof_stack4) 

CV：0.49497245370527776

模型融合

#和下面作对比
mean_squared_error(target.values, 0.7*(0.6*oof_stack2 + 0.4*oof_stack3)+0.3*(0.55*oof_stack1+0.45*oof_stack4))

CV：0.455987412131992

将以上的4种集成学习模型再次进行集成学习训练，直接用LinearRegression简单线性回归进行集成。

train_stack5 = np.vstack([oof_stack1,oof_stack2,oof_stack3,oof_stack4]).transpose()
test_stack5 = np.vstack([predictions_lr1, predictions_lr2,predictions_lr3,predictions_lr4]).transpose()

folds_stack = RepeatedKFold(n_splits=5, n_repeats=2, random_state=7)
oof_stack5 = np.zeros(train_stack5.shape[0])
predictions_lr5= np.zeros(test_stack5.shape[0])

for fold_, (trn_idx, val_idx) in enumerate(folds_stack.split(train_stack5,target)):
    print("fold {}".format(fold_))
    trn_data, trn_y = train_stack5[trn_idx], target.iloc[trn_idx].values
    val_data, val_y = train_stack5[val_idx], target.iloc[val_idx].values
    #LinearRegression
    lr5 = lr()
    lr5.fit(trn_data, trn_y)
    
    oof_stack5[val_idx] = lr5.predict(val_data)
    predictions_lr5 += lr5.predict(test_stack5) / 10
    
mean_squared_error(target.values, oof_stack5) 

CV：0.4514447311895284

结果保存

进行index地读取工作

submit_example = pd.read_csv('submit_example.csv',sep=',',encoding='latin-1')

submit_example['happiness'] = predictions_lr5

submit_example.happiness.describe()

进一步优化并保存为CSV

submit_example.loc[submit_example['happiness']>4.96,'happiness']= 5
submit_example.loc[submit_example['happiness']<=1.04,'happiness']= 1
submit_example.loc[(submit_example['happiness']>1.96)&(submit_example['happiness']<2.04),'happiness']= 2

submit_example.to_csv("submision.csv",index=False)
submit_example.happiness.describe()