挖掘幸福感赛题

赛题背景

在社会科学领域，幸福感的研究占有重要的位置。这个涉及了哲学、心理学、社会学、经济学等多方学科的话题复杂而有趣；同时与大家生活息息相关，每个人对幸福感都有自己的衡量标准。如果能发现影响幸福感的共性，生活中是不是将多一些乐趣；如果能找到影响幸福感的政策因素，便能优化资源配置来提升国民的幸福感。目前社会科学研究注重变量的可解释性和未来政策的落地，主要采用了线性回归和逻辑回归的方法，在收入、健康、职业、社交关系、休闲方式等经济人口因素；以及政府公共服务、宏观经济环境、税负等宏观因素上有了一系列的推测和发现。

赛题尝试了幸福感预测这一经典课题，希望在现有社会科学研究外有其他维度的算法尝试，结合多学科各自优势，挖掘潜在的影响因素，发现更多可解释、可理解的相关关系。

赛题说明

赛题使用公开数据的问卷调查结果，选取其中多组变量，包括个体变量（性别、年龄、地域、职业、健康、婚姻与政治面貌等等）、家庭变量（父母、配偶、子女、家庭资本等等）、社会态度（公平、信用、公共服务等等），来预测其对幸福感的评价。

代码

%matplotlib inline
import os
import time
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import lightgbm as lgb
from sklearn.metrics import roc_auc_score, roc_curve
from sklearn.model_selection import KFold
from sklearn.model_selection import train_test_split
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.model_selection import GridSearchCV
from sklearn import metrics
from sklearn.metrics import mean_squared_error

train = pd.read_csv('/Users/Desktop/happiness_train_complete.csv',parse_dates=["survey_time"], encoding='latin-1')
test = pd.read_csv('/Users/happiness_test_complete.csv',parse_dates=["survey_time"], encoding='latin-1')
train.head()

train.describe()

train.info()

train.isnull().sum()

train = train.loc[train['happiness'] != -8]

train.shape

f,ax = plt.subplots(1,2,figsize = (15,6))
train['happiness'].value_counts().plot.pie(autopct='%1.1f%%',ax=ax[0],shadow=False)
ax[0].set_title('happiness')
ax[0].set_ylabel('')
train['happiness'].value_counts().plot.bar(ax=ax[1])
ax[1].set_title('happiness')
plt.show()

sns.countplot('gender',hue='happiness',data=train)
ax[1].set_title('Sex:happiness')
#1=男，2=女

print(train['survey_time'][0])
train['survey_time'] = pd.to_datetime(train['survey_time'], format='%Y/%m/%d %H:%M')
test['survey_time'] = pd.to_datetime(test['survey_time'], format='%Y/%m/%d %H:%M')

# 探究年龄和幸福感的关系
train['survey_time'] = train['survey_time'].dt.year
test['survey_time'] = test['survey_time'].dt.year
train['Age'] = train['survey_time']-train['birth']
test['Age'] = test['survey_time']-test['birth']
del_list=['survey_time','birth']
figure,ax = plt.subplots(1,1)
train['Age'].plot.hist(ax=ax,color='blue')

combine=[train,test]

for dataset in combine:
    dataset.loc[dataset['Age']<=16,'Age']=0
    dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
    dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
    dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
    dataset.loc[(dataset['Age'] > 64) & (dataset['Age'] <= 80), 'Age'] = 4
    dataset.loc[ dataset['Age'] > 80, 'Age'] = 5
sns.countplot('Age', hue='happiness', data=train)

figure1,ax1 = plt.subplots(1,5,figsize=(18,4))
train['happiness'][train['Age']==1].value_counts().plot.pie(autopct='%1.1f%%',ax=ax1[0],shadow=False)
train['happiness'][train['Age']==2].value_counts().plot.pie(autopct='%1.1f%%',ax=ax1[1],shadow=False)
train['happiness'][train['Age']==3].value_counts().plot.pie(autopct='%1.1f%%',ax=ax1[2],shadow=False)
train['happiness'][train['Age']==4].value_counts().plot.pie(autopct='%1.1f%%',ax=ax1[3],shadow=False)
train['happiness'][train['Age']==5].value_counts().plot.pie(autopct='%1.1f%%',ax=ax1[4],shadow=False)

# 目前只考虑通过相关性选择特征
train.corr()['happiness'][abs(train.corr()['happiness'])>0.05]

features = (train.corr()['happiness'][abs(train.corr()['happiness'])>0.05]).index
features = features.values.tolist()
features.extend(['Age', 'work_exper'])
features.remove('happiness')
len(features)

# 生成数据和标签
target = train['happiness']
train_selected = train[features]
test = test[features]
feature_importance_df = pd.DataFrame()
oof = np.zeros(len(train))
predictions = np.zeros(len(test))

params = {'num_leaves': 9,
         'min_data_in_leaf': 40,
         'objective': 'regression',
         'max_depth': 16,
         'learning_rate': 0.01,
         'boosting': 'gbdt',
         'bagging_freq': 5,
         'bagging_fraction': 0.8,   # 每次迭代时用的数据比例
         'feature_fraction': 0.8201,# 每次迭代中随机选择80％的参数来建树
         'bagging_seed': 11,
         'reg_alpha': 1.728910519108444,
         'reg_lambda': 4.9847051755586085,
         'random_state': 42,
         'metric': 'rmse',
         'verbosity': -1,
         'subsample': 0.81,
         'min_gain_to_split': 0.01077313523861969,
         'min_child_weight': 19.428902804238373,
         'num_threads': 4}

kfolds = KFold(n_splits=5,shuffle=True,random_state=15)
predictions = np.zeros(len(test))

for fold_n,(trn_index,val_index) in enumerate(kfolds.split(train_selected,target)):
    print("fold_n {}".format(fold_n))
    trn_data = lgb.Dataset(train_selected.iloc[trn_index],label=target.iloc[trn_index])
    val_data = lgb.Dataset(train_selected.iloc[val_index],label=target.iloc[val_index])
    num_round=10000
    clf = lgb.train(params, trn_data, num_round, valid_sets = [trn_data, val_data], verbose_eval=1000, early_stopping_rounds = 100)
    oof[val_index] = clf.predict(train_selected.iloc[val_index], num_iteration=clf.best_iteration)
    predictions += clf.predict(test,num_iteration=clf.best_iteration)/5
    fold_importance_df = pd.DataFrame()
    fold_importance_df["feature"] = features
    fold_importance_df["importance"] = clf.feature_importance()
    fold_importance_df["fold"] = fold_n + 1
    feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)
    print("CV score: {:<8.5f}".format(mean_squared_error(target, oof)**0.5))

cols = (feature_importance_df[["feature", "importance"]]
        .groupby("feature")
        .mean()
        .sort_values(by="importance", ascending=False)[:1000].index)
best_features = feature_importance_df.loc[feature_importance_df.feature.isin(cols)]

plt.figure(figsize=(14,26))
sns.barplot(x="importance", y="feature", data=best_features.sort_values(by="importance",ascending=False))
plt.title('LightGBM Features (averaged over folds)')
plt.tight_layout()

# 计算结果
submit = pd.read_csv("/Users/chensijie/Desktop/阿里云天池/幸福感挖掘/happiness_submit.csv")
submision_lgb1  = pd.DataFrame({"id":submit['id'].values})
submision_lgb1["happiness"]=predictions
submision_lgb1.head(5)