机器学习预测时label错位对未来数据做预测

前言

　　这篇文章时承继上一篇机器学习经典模型使用归一化的影响。这次又有了新的任务，通过将label错位来对未来数据做预测。

实验过程

　　使用不同的归一化方法，不同得模型将测试集label错位，计算出MSE的大小；

　　不断增大错位的数据的个数，并计算出MSE，并画图。通过比较MSE（均方误差，mean-square error）的大小来得出结论

过程及结果

数据处理(和上一篇的处理方式相同)：

test_sort_data = sort_data[:5000]
test_sort_target = sort_target[:5000]

sort_data1 = _sort_data[5000:16060]
sort_data2 = _sort_data[16060:]
sort_target1 = _sort_target[5000:16060]
sort_target2 = _sort_target[16060:]

完整数据处理代码：

#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]

from sklearn.model_selection import train_test_split
test_sort_data = sort_data[:5000]
test_sort_target = sort_target[:5000]

sort_data1 = _sort_data[5000:16060]
sort_data2 = _sort_data[16060:]
sort_target1 = _sort_target[5000:16060]
sort_target2 = _sort_target[16060:]

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)
dict_corr.describe()

选取25%以上的；

new_fea = list(dict_corr[(dict_corr['pearson']>0.41) & (dict_corr['spearman']>0.45) & (dict_corr['kendall']>0.29)]['columns'].values)

包含下面的用来画图：

import matplotlib.pyplot as plt 
lr_plt=[]
ridge_plt=[]
svr_plt=[]
RF_plt=[]

正常的计算mse（label没有移动）：

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]))
lr_mse=mse(lr_ans,sort_target2)
lr_plt.append(lr_mse)
print('lr:',lr_mse)

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]))
ridge_mse=mse(ridge_ans,sort_target2)
ridge_plt.append(ridge_mse)
print('ridge:',ridge_mse)

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]))
svr_mse=mse(svr_ans,sort_target2)
svr_plt.append(svr_mse)
print('svr:',svr_mse)

estimator_RF = RandomForestRegressor().fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
predict_RF = estimator_RF.predict(mm.transform(sort_data2[new_fea]))
RF_mse=mse(predict_RF,sort_target2)
RF_plt.append(RF_mse)
print('RF:',RF_mse)

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))

先让label移动5个：

change_sort_data2 = sort_data2.shift(periods=5,axis=0)
change_sort_target2 = sort_target2.shift(periods=-5,axis=0)
change_sort_data2.dropna(inplace=True)
change_sort_target2.dropna(inplace=True)

让label以5的倍数移动：

mm = MinMaxScaler()

for i in range(0,45,5):
    print(i)
    lr = Lasso(alpha=0.5)
    lr.fit(mm.fit_transform(sort_data1[new_fea]), sort_target1)
    lr_ans = lr.predict(mm.transform(change_sort_data2[new_fea]))
    lr_mse=mse(lr_ans,change_sort_target2)
    lr_plt.append(lr_mse)
    print('lr:',lr_mse)
    
    ridge = Ridge(alpha=0.5)
    ridge.fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
    ridge_ans = ridge.predict(mm.transform(change_sort_data2[new_fea]))
    ridge_mse=mse(ridge_ans,change_sort_target2)
    ridge_plt.append(ridge_mse)
    print('ridge:',ridge_mse)
    
    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(change_sort_data2[new_fea]))
    svr_mse=mse(svr_ans,change_sort_target2)
    svr_plt.append(svr_mse)
    print('svr:',svr_mse)
    
    estimator_RF = RandomForestRegressor().fit(mm.fit_transform(sort_data1[new_fea]),sort_target1)
    predict_RF = estimator_RF.predict(mm.transform(change_sort_data2[new_fea]))
    RF_mse=mse(predict_RF,change_sort_target2)
    RF_plt.append(RF_mse)
    print('RF:',RF_mse)
    
#     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(change_sort_data2[new_fea]))
#     print('bst:',mse(bst_ans,change_sort_target2))
    
    change_sort_target2=change_sort_target2.shift(periods=-5,axis=0)
    change_sort_target2.dropna(inplace=True)
    change_sort_data2 = change_sort_data2.shift(periods=5,axis=0)
    change_sort_data2.dropna(inplace=True)

结果如图：

然后就是画图了；

plt.plot(x,lr_plt,label='lr',color='r',marker='o')
plt.plot(x,ridge_plt,label='ridge',color='b',marker='o')
plt.plot(x,svr_plt,label='svr',color='g',marker='o')
plt.plot(x,RF_plt,label='RF',color='y',marker='o')
plt.legend()
plt.show()

舍去lr，并扩大纵坐标：

#plt.plot(x,lr_plt,label='lr',color='r',marker='o')
plt.plot(x,ridge_plt,label='ridge',color='b',marker='o')
plt.plot(x,svr_plt,label='svr',color='g',marker='o')
plt.plot(x,RF_plt,label='RF',color='y',marker='o')
plt.legend()
plt.show()

其他模型只需将MinMaxScaler改为MaxAbsScaler,standarScaler即可；

总的来说，label的移动会使得mse增加，大约在label=10时候差异最小，结果最理想；