def plot_features():
train_feat, test_feat = make_data_feat()
aa = train_feat['Urea'].value_counts()
aa = aa.to_frame()
aa['num'] = aa.index
# plt.hist(train_feat['Age'], 100)
plt.scatter(train_feat['TG/UA'], train_feat['Blood_Sugar'])
plt.show()
def data_corr():
train_feat, test_feat = make_data_feat()
del train_feat['id']
corr = train_feat.corr()
train_feat_temp = (train_feat - train_feat.min()) / (train_feat.max() -
train_feat.min())
corr_temp = train_feat_temp.corr()
print(0)
def mean_value():
train_feat, test_feat = make_data_feat()
train_feat = train_feat.sort_values('Blood_Sugar', ascending=False)
train1 = train_feat[0:1410]
train2 = train_feat[1410:2820]
train3 = train_feat[2820:4230]
train4 = train_feat[4230:5640]
mean1 = train1.mean().to_frame()
mean2 = train2.mean().to_frame()
mean3 = train3.mean().to_frame()
mean4 = train4.mean().to_frame()
result = pd.DataFrame({'feat': mean1.index})
result['1'] = mean1.values
result['2'] = mean2.values
result['3'] = mean3.values
result['4'] = mean4.values
print(0)
# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error
import time
from xgb_make import xgboost_make
from lgb_make import lightgbm_make
from rf_make import randomforest_make
from feature_extract import make_data_feat
if __name__ == '__main__':
t1 = time.time()
train_feat, test_feat = make_data_feat()
lgb_label, lgb_pred = lightgbm_make(train_feat, test_feat)
xgb_label, xgb_pred = xgboost_make(train_feat, test_feat)
rf_label, rf_pred = randomforest_make(train_feat, test_feat)
print('线下得分： {}'.format(mean_squared_error(lgb_label, lgb_pred) * 0.5))
print('线下得分： {}'.format(mean_squared_error(xgb_label, xgb_pred) * 0.5))
print('线下得分： {}'.format(
mean_squared_error(xgb_label, (
(lgb_pred * 0.8 + xgb_pred * 0.2) * 1 + rf_pred * 0)) * 0.5))
#
# df = lgb_label.to_frame()
# df['pred'] = (lgb_pred * 0.8 + xgb_pred * 0.2)*0.9 + rf_pred*0.1
# df = df.sort_values('pred', ascending=True)
