#按时间排序
sort_data = data.sort_values(by = 'time',ascending = True)
sort_data.reset_index(inplace = True,drop = True)
target = data['T1AOMW_AV']
sort_target = sort_data['T1AOMW_AV']
del data['T1AOMW_AV']
del sort_data['T1AOMW_AV']
from sklearn.model_selection import train_test_split
test_sort_data = sort_data[16160:]
test_sort_target = sort_target[16160:]_sort_data = sort_data[:16160]
_sort_target = sort_target[:16160]
sort_data1 = _sort_data[:(int)(len(_sort_data)*0.75)]
sort_data2 = _sort_data[(int)(len(_sort_data)*0.75):]
sort_target1 = _sort_target[:(int)(len(_sort_target)*0.75)]
sort_target2 = _sort_target[(int)(len(_sort_target)*0.75):]import scipy.stats as stats
dict_corr = {'spearman' : [],'pearson' : [],'kendall' : [],'columns' : []
}for i in data.columns:corr_pear,pval = stats.pearsonr(sort_data[i],sort_target)corr_spear,pval = stats.spearmanr(sort_data[i],sort_target)corr_kendall,pval = stats.kendalltau(sort_data[i],sort_target)dict_corr['pearson'].append(abs(corr_pear))dict_corr['spearman'].append(abs(corr_spear))dict_corr['kendall'].append(abs(corr_kendall))dict_corr['columns'].append(i)# 筛选新属性
dict_corr =pd.DataFrame(dict_corr)
new_fea = list(dict_corr[(dict_corr['pearson']>0.41) & (dict_corr['spearman']>0.45) & (dict_corr['kendall']>0.29)]['columns'].values)
# 选取原则，选取25%分位数 以上的相关性系数

from sklearn.linear_model import LinearRegression,Lasso,Ridge
from sklearn.preprocessing import MinMaxScaler,StandardScaler,MaxAbsScaler
from sklearn.metrics import mean_squared_error as mse
from sklearn.svm import SVR
from sklearn.ensemble import RandomForestRegressor
import xgboost as xgb
#最大最小归一化
mm = MinMaxScaler()lr = Lasso(alpha=0.5)
lr.fit(mm.fit_transform(sort_data1[new_fea]), sort_target1)
lr_ans = lr.predict(mm.transform(sort_data2[new_fea]))
print('lr:',mse(lr_ans,sort_target2))ridge = Ridge(alpha=0.5)
ridge.fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
ridge_ans = ridge.predict(mm.transform(sort_data2[new_fea]))
print('ridge:',mse(ridge_ans,sort_target2))svr = SVR(kernel='rbf',C=100,epsilon=0.1).fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
svr_ans = svr.predict(mm.transform(sort_data2[new_fea]))
print('svr:',mse(svr_ans,sort_target2))estimator_RF = RandomForestRegressor().fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
predict_RF = estimator_RF.predict(mm.transform(sort_data2[new_fea]))
print('RF:',mse(predict_RF,sort_target2))bst = xgb.XGBRegressor(learning_rate=0.1, n_estimators=550, max_depth=4, min_child_weight=5, seed=0,subsample=0.7, colsample_bytree=0.7, gamma=0.1, reg_alpha=1, reg_lambda=1)
bst.fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
bst_ans = bst.predict(mm.transform(sort_data2[new_fea]))
print('bst:',mse(bst_ans,sort_target2))

lr: 7.736200563088036
ridge: 3.264150764935616
svr: 3.505799850945091
RF: 0.24087179220636037
bst: 0.9945862722591914