Task04：快来一起挖掘幸福感--阿里云天池

赛题相关介绍详见：https://tianchi.aliyun.com/competition/entrance/231702/information
鉴于保密要求，无法提供具体数据下载，敬请报名参加相关赛事。
根据发布的评测标准，当前参数下的RMSE为0.48，后面将会继续调参，争取将RMSE缩减至0.47以下，争取登上前500的排行榜。

import os
import time 
import pandas as pd
import numpy as np
import lightgbm as lgb
import seaborn as sns
import matplotlib.pyplot as plt
import time
from scipy.special import jn
from IPython.display import display, clear_output

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

# 加载数据集 #
train = pd.read_csv("C:/Users/Bai/Python_projects/Ali_Cloud/happiness_train_complete.csv", parse_dates=["survey_time"], encoding='latin-1') 
test = pd.read_csv("C:/Users/Bai/Python_projects/Ali_Cloud/happiness_test_complete.csv", parse_dates=["survey_time"], encoding='latin-1')
train.head()

# 删除训练集中无效的标签对应的数据 #
train = train.loc[train['happiness'] != -8]

print(train.shape)

# 查看各个类别的分布情况 #
f,ax=plt.subplots(1,2,figsize=(18,8))
train['happiness'].value_counts().plot.pie(autopct='%1.1f%%',ax=ax[0],shadow=True)
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()

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

# 选择相关性大于0.05的作为候选特征 #
features = (train.corr()['happiness'][abs(train.corr()['happiness'])>0.05]).index
features = features.values.tolist()
# 额外加入比较重要的特征 # 
features.extend(['Age', 'work_exper'])
features.remove('happiness')
print(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))

# 模型参数设置 #
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,   # 每次迭代时随机选择80％的参数 #
         '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("C:/Users/Bai/Python_projects/Ali_Cloud/happiness_submit.csv")
submision_lgb1  = pd.DataFrame({"id":submit['id'].values})
submision_lgb1["happiness"]=predictions
submision_lgb1.head(5)

# 获取时间 #
time_str = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
out_dir = "C:/Users/Bai/Python_projects/Ali_Cloud/{}/".format(time_str)
os.makedirs(out_dir)

# 保存模型 #
clf.save_model(out_dir + "model.txt")

# 保存结果 #
submision_lgb1.to_csv(out_dir + "submision_lgbm.csv",index=False)