import time
import numpy as np
import xgboost as xgb
from xgboost import plot_importance,plot_tree
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import matplotlib
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.metrics import mean_squared_error
%matplotlib inline

def dropun(X):
    for x in X.columns:
        if x[:7]=='Unnamed':
            X=X.drop(columns=[x])
    return X

def hist(L):
    kwargs = dict(histtype='stepfilled',density=True,alpha=0.3,bins=40)
    for X in L:
        plt.hist(X, **kwargs)
        
def prediction(y_pred, y_test, plot=True):
    sum_erro = mean_squared_error(y_pred, y_test) 
    # https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_squared_error.html#sklearn.metrics.mean_squared_error
    print ("MSE:", sum_erro)
    
    if plot:
        # 做ROC曲线
        plt.figure()
        plt.plot(range(len(y_pred)), y_pred, 'b', label="predict")
        plt.plot(range(len(y_pred)), y_test, 'r', label="test")
        plt.legend(loc="upper right")  # 显示图中的标签
    
    return sum_erro

X=pd.read_csv('data/factors2013-0-2-1.csv')
Y=pd.read_csv('data/daily2011-2017-1.csv')
X=dropun(X)
Y=dropun(Y)

factors=list(X.columns)
factors.remove('ts_code')
factors.remove('trade_date')

days=set(X['trade_date'])
days=list(days)
days.sort()

def get_split_by_trade_date(date, state=0, remove_factors = []):
    # state=0表示不进行缺失值去除/填充
    # state=1表示直接去除含有缺失值股票的数据
    # state=2表示使用当天的平均值进行填充缺失数据
    
    # '2013-03-01'
    x=X[X['trade_date']==date].drop(columns=['trade_date'] + remove_factors)
    y=Y[Y['trade_date']==date].drop(columns=['trade_date'])
    z=pd.merge(x,y,on='ts_code')
    
    if state==1:
        z.dropna(inplace=True)
    elif state==2:
        z.fillna(value=dict(z.mean()), inplace=True)
        
    x=z[set(factors)-set(remove_factors)]
    y=z['yield']*100
    # 划分数据集
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2) # random_state=0 
    # print('x_train.shape={}\ny_train.shape ={}\nx_test.shape={}\ny_test.shape={}'.format(x_train.shape, y_train.shape, x_test.shape, y_test.shape))
    return x_train, x_test, y_train, y_test

去除无用特征

根据permutaiton importance求在2013年全年各因子对于预测结果的重要性（使用随机random_state）。

首先根据线性模型计算一遍，再用XGBoost计算一遍

如果全年超过一半都为负数，则直接删去该因子

linear模型2013年各因子重要性

def get_linear_importance(date):
    # 划分数据集
    x_train, x_test, y_train, y_test = get_split_by_trade_date(date, 1)

    # 模型训练
    model = LinearRegression()
    model.fit(x_train, y_train)
    
    # 计算排序重要性
    perm = PermutationImportance(model).fit(x_test, y_test)
    
    return perm

perm = get_linear_importance('2013-01-04')
print(pd.DataFrame(perm.feature_importances_, index = factors))
eli5.show_weights(perm, feature_names = factors, top=56)

x_train.shape=(1185, 56)
y_train.shape =(1185,)
x_test.shape=(297, 56)
y_test.shape=(297,)
                  0
size       0.022446
beta       0.000113
betad      0.001902
idvol     -0.003462
total_vol  0.003035
idskew     0.140981
skew      -0.002844
coskew     0.008199
turn      -0.002669
std_turn   0.018550
volumed    0.000761
std_dvol   0.146898
retnmax    0.002345
illq      -0.005696
LM         0.018519
sharechg  -0.000700
age        0.000593
mom12      0.089085
mom6       0.029796
momchg     0.009969
imom       0.005457
lagretn   -0.002747
BM         0.005480
AM        -0.005562
LEV        0.006296
EP         0.012142
CFP        0.031895
OCFP      -0.000878
DP        -0.000697
SP         0.039042
AG         0.027988
LG         0.013685
BVEG       0.004491
INVG      -0.006270
INVchg     0.004587
SG         0.000570
SgINVg    -0.000105
PMG        0.003184
TAXchg     0.010312
ACC        0.065508
ACCP       0.164036
ROE        0.005988
ROA        0.006740
PA         0.003271
CT         0.009938
cash       0.012838
cashpr     0.132102
RD        -0.001856
RDsales    0.002344
CR        -0.004083
QR         0.007043
CFdebt     0.002388
salecash  -0.003473
saleinv    0.086358
CRG        0.025812
QRG       -0.005456






<style>
table.eli5-weights tr:hover {
    filter: brightness(85%);
}

    <table class="eli5-weights eli5-feature-importances" style="border-collapse: collapse; border: none; margin-top: 0em; table-layout: auto;">
<thead>
<tr style="border: none;">
    <th style="padding: 0 1em 0 0.5em; text-align: right; border: none;">Weight</th>
    <th style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">Feature</th>
</tr>
</thead>
<tbody>

    <tr style="background-color: hsl(120, 100.00%, 80.00%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.1640

                &plusmn; 0.0249

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            ACCP
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 81.49%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.1469

                &plusmn; 0.0485

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            std_dvol
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 82.01%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.1410

                &plusmn; 0.0263

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            idskew
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 82.81%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.1321

                &plusmn; 0.0312

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            cashpr
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 86.96%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0891

                &plusmn; 0.0471

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            mom12
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 87.24%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0864

                &plusmn; 0.0665

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            saleinv
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 89.48%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0655

                &plusmn; 0.0407

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            ACC
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 92.68%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0390

                &plusmn; 0.0297

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            SP
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 93.64%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0319

                &plusmn; 0.0159

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            CFP
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 93.94%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0298

                &plusmn; 0.0300

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            mom6
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 94.20%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0280

                &plusmn; 0.0271

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            AG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 94.52%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0258

                &plusmn; 0.0220

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            CRG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 95.03%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0224

                &plusmn; 0.0311

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            size
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 95.65%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0185

                &plusmn; 0.0286

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            std_turn
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 95.66%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0185

                &plusmn; 0.0124

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            LM
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 96.48%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0137

                &plusmn; 0.0407

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            LG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 96.64%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0128

                &plusmn; 0.0083

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            cash
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 96.77%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0121

                &plusmn; 0.0262

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            EP
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.12%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0103

                &plusmn; 0.0119

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            TAXchg
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.18%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0100

                &plusmn; 0.0262

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            momchg
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.19%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0099

                &plusmn; 0.0095

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            CT
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.54%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0082

                &plusmn; 0.0189

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            coskew
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.79%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0070

                &plusmn; 0.0130

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            QR
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.86%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0067

                &plusmn; 0.0082

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            ROA
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 97.96%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0063

                &plusmn; 0.0178

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            LEV
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.03%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0060

                &plusmn; 0.0132

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            ROE
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.15%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0055

                &plusmn; 0.0190

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            BM
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.15%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0055

                &plusmn; 0.0057

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            imom
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.36%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0046

                &plusmn; 0.0078

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            INVchg
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.39%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0045

                &plusmn; 0.0073

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            BVEG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.71%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0033

                &plusmn; 0.0058

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            PA
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.73%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0032

                &plusmn; 0.0051

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            PMG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.78%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0030

                &plusmn; 0.0116

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            total_vol
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.96%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0024

                &plusmn; 0.0032

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            CFdebt
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.98%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0023

                &plusmn; 0.0133

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            retnmax
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 98.98%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0023

                &plusmn; 0.0028

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            RDsales
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 99.12%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0019

                &plusmn; 0.0067

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            betad
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 99.53%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0008

                &plusmn; 0.0018

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            volumed
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 99.61%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0006

                &plusmn; 0.0005

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            age
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 99.62%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0006

                &plusmn; 0.0063

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            SG
        </td>
    </tr>

    <tr style="background-color: hsl(120, 100.00%, 99.88%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            0.0001

                &plusmn; 0.0053

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            beta
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 99.88%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0001

                &plusmn; 0.0010

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            SgINVg
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 99.56%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0007

                &plusmn; 0.0062

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            DP
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 99.56%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0007

                &plusmn; 0.0017

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            sharechg
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 99.49%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0009

                &plusmn; 0.0172

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            OCFP
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 99.13%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0019

                &plusmn; 0.0071

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            RD
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.88%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0027

                &plusmn; 0.0048

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            turn
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.86%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0027

                &plusmn; 0.0026

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            lagretn
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.83%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0028

                &plusmn; 0.0025

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            skew
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.66%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0035

                &plusmn; 0.0107

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            idvol
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.65%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0035

                &plusmn; 0.0025

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            salecash
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.49%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0041

                &plusmn; 0.0069

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            CR
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.15%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0055

                &plusmn; 0.0050

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            QRG
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.13%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0056

                &plusmn; 0.0190

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            AM
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 98.10%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0057

                &plusmn; 0.0074

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            illq
        </td>
    </tr>

    <tr style="background-color: hsl(0, 100.00%, 97.96%); border: none;">
        <td style="padding: 0 1em 0 0.5em; text-align: right; border: none;">
            -0.0063

                &plusmn; 0.0067

        </td>
        <td style="padding: 0 0.5em 0 0.5em; text-align: left; border: none;">
            INVG
        </td>
    </tr>


</tbody>

importance = pd.DataFrame(index = factors)   # 记录每个因子重要性的总和，重要性为负的天数
importance['sum'] = 0
importance['negative'] = 0

for day in days:
    print(day)
    perm = get_linear_importance(day)
    importance['sum']+=perm.feature_importances_
    importance['negative']+=(perm.feature_importances_<0)

2013-01-04
x_train.shape=(1185, 56)
y_train.shape =(1185,)
x_test.shape=(297, 56)
y_test.shape=(297,)
2013-01-07
x_train.shape=(1175, 56)
y_train.shape =(1175,)
x_test.shape=(294, 56)
y_test.shape=(294,)
2013-01-08
x_train.shape=(1176, 56)
y_train.shape =(1176,)
x_test.shape=(294, 56)
y_test.shape=(294,)
2013-01-09
x_train.shape=(1178, 56)
y_train.shape =(1178,)
x_test.shape=(295, 56)
y_test.shape=(295,)
2013-01-10
x_train.shape=(1170, 56)
y_train.shape =(1170,)
x_test.shape=(293, 56)
y_test.shape=(293,)
2013-01-11
x_train.shape=(1172, 56)
y_train.shape =(1172,)
x_test.shape=(293, 56)
y_test.shape=(293,)
2013-01-14
x_train.shape=(1161, 56)
y_train.shape =(1161,)
x_test.shape=(291, 56)
y_test.shape=(291,)
2013-01-15
x_train.shape=(1176, 56)
y_train.shape =(1176,)
x_test.shape=(294, 56)
y_test.shape=(294,)
2013-01-16
x_train.shape=(1164, 56)
y_train.shape =(1164,)
x_test.shape=(291, 56)
y_test.shape=(291,)
2013-01-17
x_train.shape=(1174, 56)
y_train.shape =(1174,)
x_test.shape=(294, 56)
y_test.shape=(294,)
2013-01-18
x_train.shape=(1175, 56)
y_train.shape =(1175,)
x_test.shape=(294, 56)
y_test.shape=(294,)
2013-01-21
x_train.shape=(1186, 56)
y_train.shape =(1186,)
x_test.shape=(297, 56)
y_test.shape=(297,)
2013-01-22
x_train.shape=(1181, 56)
y_train.shape =(1181,)
x_test.shape=(296, 56)
y_test.shape=(296,)
2013-01-23
x_train.shape=(1168, 56)
y_train.shape =(1168,)
x_test.shape=(293, 56)
y_test.shape=(293,)
2013-01-24
x_train.shape=(1184, 56)
y_train.shape =(1184,)
x_test.shape=(297, 56)
y_test.shape=(297,)
2013-01-25
x_train.shape=(1167, 56)
y_train.shape =(1167,)
x_test.shape=(292, 56)
y_test.shape=(292,)

...
2013-12-31
x_train.shape=(1257, 56)
y_train.shape =(1257,)
x_test.shape=(315, 56)
y_test.shape=(315,)

pd.set_option('display.max_columns', None)
importance.sort_values(by="sum" , ascending=False).transpose()

	ROE	mom12	ACCP	std_dvol	momchg	BM	AG	SP	idskew	sharechg	SgINVg	saleinv	CRG	total_vol	ACC	LM	LG	cashpr	LEV	betad	mom6	imom	CFdebt	QRG	std_turn	coskew	PA	beta	ROA	QR	INVchg	size	DP	TAXchg	PMG	volumed	BVEG	CR	CT	OCFP	SG	lagretn	retnmax	illq	cash	CFP	skew	EP	INVG	RDsales	RD	salecash	idvol	age	AM	turn
sum	450.179329	430.119666	74.490326	72.665519	18.17473	18.007253	17.610628	16.867773	15.003665	14.761029	14.236372	14.163207	13.581656	11.512615	10.269702	9.761518	7.554256	6.340006	5.963265	5.642828	3.519301	2.888595	2.681334	2.456618	2.447205	2.4201	2.337622	2.337583	2.138391	2.084859	1.935707	1.856355	1.847884	1.705292	1.395641	1.257528	1.239606	1.188467	1.143138	1.113026	0.890586	0.826029	0.81739	0.780101	0.593657	0.590286	0.501265	0.443186	0.340089	0.211641	0.153811	0.098633	0.090249	0.017987	-0.00769	-0.100969
negative	9.000000	6.000000	12.000000	7.000000	30.00000	26.000000	29.000000	40.000000	36.000000	35.000000	32.000000	17.000000	33.000000	40.000000	28.000000	45.000000	47.000000	50.000000	55.000000	50.000000	62.000000	56.000000	67.000000	60.000000	55.000000	51.0000	59.000000	65.000000	57.000000	64.000000	56.000000	71.000000	64.000000	61.000000	87.000000	76.000000	75.000000	86.000000	67.000000	78.000000	87.000000	84.000000	79.00000	87.000000	95.000000	103.000000	95.000000	96.000000	106.000000	110.000000	108.000000	127.000000	116.000000	120.000000	125.00000	130.000000

importance.sort_values(by="negative" , ascending=True).transpose()

	mom12	std_dvol	ROE	ACCP	saleinv	BM	ACC	AG	momchg	SgINVg	CRG	sharechg	idskew	total_vol	SP	LM	LG	betad	cashpr	coskew	std_turn	LEV	imom	INVchg	ROA	PA	QRG	TAXchg	mom6	DP	QR	beta	CT	CFdebt	size	BVEG	volumed	OCFP	retnmax	lagretn	CR	illq	SG	PMG	skew	cash	EP	CFP	INVG	RD	RDsales	idvol	age	AM	salecash	turn
sum	430.119666	72.665519	450.179329	74.490326	14.163207	18.007253	10.269702	17.610628	18.17473	14.236372	13.581656	14.761029	15.003665	11.512615	16.867773	9.761518	7.554256	5.642828	6.340006	2.4201	2.447205	5.963265	2.888595	1.935707	2.138391	2.337622	2.456618	1.705292	3.519301	1.847884	2.084859	2.337583	1.143138	2.681334	1.856355	1.239606	1.257528	1.113026	0.81739	0.826029	1.188467	0.780101	0.890586	1.395641	0.501265	0.593657	0.443186	0.590286	0.340089	0.153811	0.211641	0.090249	0.017987	-0.00769	0.098633	-0.100969
negative	6.000000	7.000000	9.000000	12.000000	17.000000	26.000000	28.000000	29.000000	30.00000	32.000000	33.000000	35.000000	36.000000	40.000000	40.000000	45.000000	47.000000	50.000000	50.000000	51.0000	55.000000	55.000000	56.000000	56.000000	57.000000	59.000000	60.000000	61.000000	62.000000	64.000000	64.000000	65.000000	67.000000	67.000000	71.000000	75.000000	76.000000	78.000000	79.00000	84.000000	86.000000	87.000000	87.000000	87.000000	95.000000	95.000000	96.000000	103.000000	106.000000	108.000000	110.000000	116.000000	120.000000	125.00000	127.000000	130.000000

def get_last_N(importance, n):
    if n==0:
        return {}
    return set(importance.sort_values(by="sum" , ascending=False).index[-n:]) &  set(importance.sort_values(by="negative" , ascending=True).index[-n:])

remove_factors = list(get_last_N(importance, 10))
remove_factors

['salecash', 'idvol', 'EP', 'INVG', 'turn', 'AM', 'RD', 'RDsales', 'age']

importance["mark"] = 0

i=1
for index, row in importance.sort_values(by="sum" , ascending=False).iterrows():
    importance.loc[index, "mark"] += i
    i+=1
i=1
for index, row in importance.sort_values(by="negative" , ascending=True).iterrows():
    importance.loc[index, "mark"] += i
    i+=1
    
importance.sort_values(by="mark" , ascending=True).transpose()

	mom12	ROE	std_dvol	ACCP	BM	momchg	AG	saleinv	SgINVg	sharechg	ACC	idskew	SP	CRG	total_vol	LM	LG	cashpr	betad	LEV	imom	std_turn	coskew	mom6	QRG	PA	ROA	INVchg	CFdebt	beta	QR	TAXchg	DP	size	CT	volumed	BVEG	OCFP	CR	PMG	lagretn	retnmax	SG	illq	cash	skew	CFP	EP	INVG	RD	RDsales	idvol	age	salecash	AM	turn
sum	430.119666	450.179329	72.665519	74.490326	18.007253	18.17473	17.610628	14.163207	14.236372	14.761029	10.269702	15.003665	16.867773	13.581656	11.512615	9.761518	7.554256	6.340006	5.642828	5.963265	2.888595	2.447205	2.4201	3.519301	2.456618	2.337622	2.138391	1.935707	2.681334	2.337583	2.084859	1.705292	1.847884	1.856355	1.143138	1.257528	1.239606	1.113026	1.188467	1.395641	0.826029	0.81739	0.890586	0.780101	0.593657	0.501265	0.590286	0.443186	0.340089	0.153811	0.211641	0.090249	0.017987	0.098633	-0.00769	-0.100969
negative	6.000000	9.000000	7.000000	12.000000	26.000000	30.00000	29.000000	17.000000	32.000000	35.000000	28.000000	36.000000	40.000000	33.000000	40.000000	45.000000	47.000000	50.000000	50.000000	55.000000	56.000000	55.000000	51.0000	62.000000	60.000000	59.000000	57.000000	56.000000	67.000000	65.000000	64.000000	61.000000	64.000000	71.000000	67.000000	76.000000	75.000000	78.000000	86.000000	87.000000	84.000000	79.00000	87.000000	87.000000	95.000000	95.000000	103.000000	96.000000	106.000000	108.000000	110.000000	116.000000	120.000000	127.000000	125.00000	130.000000
mark	3.000000	4.000000	6.000000	7.000000	12.000000	14.00000	15.000000	17.000000	21.000000	22.000000	22.000000	22.000000	23.000000	24.000000	28.000000	32.000000	34.000000	37.000000	38.000000	41.000000	45.000000	46.000000	46.0000	50.000000	51.000000	53.000000	54.000000	55.000000	57.000000	60.000000	61.000000	62.000000	63.000000	67.000000	72.000000	73.000000	73.000000	78.000000	79.000000	79.000000	82.000000	82.00000	84.000000	86.000000	91.000000	92.000000	94.000000	95.000000	98.000000	101.000000	101.000000	105.000000	107.000000	107.000000	109.00000	112.000000

def get_trivial(n):
    if n==0:
        return []
    return list(importance.sort_values(by="mark" , ascending=False).index[:n])

get_trivial(5)

['turn', 'AM', 'salecash', 'age', 'idvol']

linear模型去除无用特征后计算准确率

linear_err1 = []
for day in days:
    print(day)
    linear_err1.append(linear_train(day, 1, remove_factors))

2013-01-04
x_train.shape=(1284, 47)
y_train.shape =(1284,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 3.8900002458152043
2013-01-07
x_train.shape=(1276, 47)
y_train.shape =(1276,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 3.6450571284258366
2013-01-08
x_train.shape=(1272, 47)
y_train.shape =(1272,)
x_test.shape=(319, 47)
y_test.shape=(319,)
MSE: 3.4844858023817724
2013-01-09
x_train.shape=(1279, 47)
y_train.shape =(1279,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 4.385839023354379
2013-01-10
x_train.shape=(1267, 47)
y_train.shape =(1267,)
x_test.shape=(317, 47)
y_test.shape=(317,)
MSE: 3.2301927988080217
2013-01-11
x_train.shape=(1276, 47)
y_train.shape =(1276,)
x_test.shape=(319, 47)
y_test.shape=(319,)
MSE: 3.3160646057613286
2013-01-14
x_train.shape=(1264, 47)
y_train.shape =(1264,)
x_test.shape=(317, 47)
y_test.shape=(317,)
MSE: 2.6315416654139416
2013-01-15
x_train.shape=(1280, 47)
y_train.shape =(1280,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 3.161195649230965
2013-01-16
x_train.shape=(1267, 47)
y_train.shape =(1267,)
x_test.shape=(317, 47)
y_test.shape=(317,)
MSE: 3.648510598956155
2013-01-17
x_train.shape=(1277, 47)
y_train.shape =(1277,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 3.6928441679882473
2013-01-18
x_train.shape=(1278, 47)
y_train.shape =(1278,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 2.6165099237166096
2013-01-21
x_train.shape=(1288, 47)
y_train.shape =(1288,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 3.894516190209926
2013-01-22
x_train.shape=(1284, 47)
y_train.shape =(1284,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 4.286606469881523
2013-01-23
x_train.shape=(1270, 47)
y_train.shape =(1270,)
x_test.shape=(318, 47)
y_test.shape=(318,)
MSE: 3.5002474096789133
2013-01-24
x_train.shape=(1289, 47)
y_train.shape =(1289,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 4.337442107992211
2013-01-25
x_train.shape=(1268, 47)
y_train.shape =(1268,)
x_test.shape=(317, 47)
y_test.shape=(317,)
MSE: 4.233215798264175
2013-01-28
x_train.shape=(1285, 47)
y_train.shape =(1285,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 2.1029862362265517
2013-01-29
x_train.shape=(1291, 47)
y_train.shape =(1291,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.0675884909138524
2013-01-30
x_train.shape=(1288, 47)
y_train.shape =(1288,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.390301459355334
2013-01-31
x_train.shape=(1298, 47)
y_train.shape =(1298,)
x_test.shape=(325, 47)
y_test.shape=(325,)
MSE: 4.195368336294644
2013-02-01
x_train.shape=(1283, 47)
y_train.shape =(1283,)
x_test.shape=(321, 47)
y_test.shape=(321,)
MSE: 4.275662003906857
2013-02-04
x_train.shape=(1284, 47)
y_train.shape =(1284,)
x_test.shape=(321, 47)
y_test.shape=(321,)
MSE: 4.889704561843679
2013-02-05
x_train.shape=(1287, 47)
y_train.shape =(1287,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 3.308904702025854
2013-02-06
x_train.shape=(1302, 47)
y_train.shape =(1302,)
x_test.shape=(326, 47)
y_test.shape=(326,)
MSE: 2.3231021846206152
2013-02-07
x_train.shape=(1291, 47)
y_train.shape =(1291,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.0897366381997493
2013-02-08
x_train.shape=(1291, 47)
y_train.shape =(1291,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.0095948358334943
2013-02-18
x_train.shape=(1306, 47)
y_train.shape =(1306,)
x_test.shape=(327, 47)
y_test.shape=(327,)
MSE: 3.7638168877810902
2013-02-19
x_train.shape=(1289, 47)
y_train.shape =(1289,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.9436390461992437
2013-02-20
x_train.shape=(1276, 47)
y_train.shape =(1276,)
x_test.shape=(320, 47)
y_test.shape=(320,)
MSE: 2.8167905873185783
2013-02-21
x_train.shape=(1316, 47)
y_train.shape =(1316,)
x_test.shape=(330, 47)
y_test.shape=(330,)
MSE: 4.046686848841419
2013-02-22
x_train.shape=(1298, 47)
y_train.shape =(1298,)
x_test.shape=(325, 47)
y_test.shape=(325,)
MSE: 4.683281982924828
2013-02-25
x_train.shape=(1292, 47)
y_train.shape =(1292,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.465463687553005
2013-02-26
x_train.shape=(1298, 47)
y_train.shape =(1298,)
x_test.shape=(325, 47)
y_test.shape=(325,)
MSE: 3.895290637571066
2013-02-27
x_train.shape=(1298, 47)
y_train.shape =(1298,)
x_test.shape=(325, 47)
y_test.shape=(325,)
MSE: 3.1285588354082488
2013-02-28
x_train.shape=(1304, 47)
y_train.shape =(1304,)
x_test.shape=(326, 47)
y_test.shape=(326,)
MSE: 2.250473626020243
2013-03-01
x_train.shape=(1292, 47)
y_train.shape =(1292,)
x_test.shape=(324, 47)
y_test.shape=(324,)
MSE: 2.8604010827684423
2013-03-04
x_train.shape=(1296, 47)
y_train.shape =(1296,)
x_test.shape=(324, 47)
y_test.shape=(324,)
MSE: 3.6787565887350375
2013-03-05
x_train.shape=(1292, 47)
y_train.shape =(1292,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 2.581324233766885
2013-03-06
x_train.shape=(1291, 47)
y_train.shape =(1291,)
x_test.shape=(323, 47)
y_test.shape=(323,)
MSE: 3.626701292445271
2013-03-07
x_train.shape=(1293, 47)
y_train.shape =(1293,)
x_test.shape=(324, 47)
y_test.shape=(324,)
MSE: 4.545620279447667
2013-03-08
x_train.shape=(1304, 47)
y_train.shape =(1304,)
x_test.shape=(327, 47)
y_test.shape=(327,)
MSE: 3.928400420077943
2013-03-11
x_train.shape=(1316, 47)
y_train.shape =(1316,)
x_test.shape=(329, 47)
y_test.shape=(329,)
MSE: 3.166664175089738
2013-03-12
x_train.shape=(1301, 47)
y_train.shape =(1301,)
x_test.shape=(326, 47)
y_test.shape=(326,)
MSE: 4.5616688994028
2013-03-13
x_train.shape=(1309, 47)
y_train.shape =(1309,)
x_test.shape=(328, 47)
y_test.shape=(328,)
MSE: 4.472122380897298
2013-03-14
x_train.shape=(1284, 47)
y_train.shape =(1284,)
x_test.shape=(322, 47)
y_test.shape=(322,)
MSE: 3.188998539129929
2013-03-15
x_train.shape=(1293, 47)
y_train.shape =(1293,)
x_test.shape=(324, 47)
y_test.shape=(324,)
MSE: 3.040507215859806
2013-03-18
x_train.shape=(1318, 47)
y_train.shape =(1318,)
x_test.shape=(330, 47)
y_test.shape=(330,)
MSE: 4.55967705671932
2013-03-19
x_train.shape=(1320, 47)
y_train.shape =(1320,)
x_test.shape=(331, 47)
y_test.shape=(331,)
MSE: 3.6700105115883552
2013-03-20
x_train.shape=(1322, 47)
y_train.shape =(1322,)
x_test.shape=(331, 47)
y_test.shape=(331,)
MSE: 1.8441303047839912
...
2013-12-31
x_train.shape=(1391, 47)
y_train.shape =(1391,)
x_test.shape=(348, 47)
y_test.shape=(348,)
MSE: 2.682600346871959

np.array(linear_err1).mean()

3.8178624023374335

linear_err2 = []
for day in days:
    print(day)
    linear_err2.append(linear_train(day, 2, remove_factors))

2013-01-04
x_train.shape=(1820, 47)
y_train.shape =(1820,)
x_test.shape=(455, 47)
y_test.shape=(455,)
MSE: 5.068830718368795
2013-01-07
x_train.shape=(1793, 47)
y_train.shape =(1793,)
x_test.shape=(449, 47)
y_test.shape=(449,)
MSE: 3.107165891835445
2013-01-08
x_train.shape=(1797, 47)
y_train.shape =(1797,)
x_test.shape=(450, 47)
y_test.shape=(450,)
MSE: 3.965400340309687
...
2013-12-27
x_train.shape=(1771, 47)
y_train.shape =(1771,)
x_test.shape=(443, 47)
y_test.shape=(443,)
MSE: 2.829811584378174
2013-12-30
x_train.shape=(1783, 47)
y_train.shape =(1783,)
x_test.shape=(446, 47)
y_test.shape=(446,)
MSE: 3.7229692784887587
2013-12-31
x_train.shape=(1781, 47)
y_train.shape =(1781,)
x_test.shape=(446, 47)
y_test.shape=(446,)
MSE: 2.9187787604137077

np.array(linear_err2).mean()

3.9034814254319627

XGBoost模型2013年各因子重要性

def get_XGBoost_importance(date):
    # 划分数据集
    x_train, x_test, y_train, y_test = get_split_by_trade_date(date)

    # 模型训练
    model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=100, objective='reg:squarederror',tree_method='gpu_hist')
    model.fit(x_train, y_train, eval_set=[(x_test, y_test)], eval_metric='rmse', early_stopping_rounds=5)
    
    # 计算排序重要性
    perm = PermutationImportance(model).fit(x_test, y_test)
    
    return perm

importance_XGBoost = pd.DataFrame(index = factors)   # 记录每个因子重要性的总和，重要性为负的天数
importance_XGBoost['sum'] = 0
importance_XGBoost['negative'] = 0

for day in days:
    print(day)
    perm = get_linear_importance(day)
    importance_XGBoost['sum']+=perm.feature_importances_
    importance_XGBoost['negative']+=(perm.feature_importances_<0)

2013-01-04
x_train.shape=(1185, 56)
y_train.shape =(1185,)
x_test.shape=(297, 56)
y_test.shape=(297,)
...
2013-12-30
x_train.shape=(1257, 56)
y_train.shape =(1257,)
x_test.shape=(315, 56)
y_test.shape=(315,)
2013-12-31
x_train.shape=(1257, 56)
y_train.shape =(1257,)
x_test.shape=(315, 56)
y_test.shape=(315,)

pd.set_option('display.max_columns', None)
importance_XGBoost.sort_values(by="sum" , ascending=False).transpose()

	ROE	mom12	ACCP	std_dvol	momchg	BM	AG	SP	idskew	sharechg	saleinv	SgINVg	CRG	total_vol	ACC	LM	LG	cashpr	LEV	betad	mom6	imom	CFdebt	QRG	std_turn	beta	coskew	PA	ROA	QR	size	DP	INVchg	TAXchg	BVEG	PMG	volumed	CT	CR	OCFP	SG	lagretn	illq	retnmax	cash	CFP	skew	EP	INVG	RDsales	RD	idvol	age	salecash	AM	turn
sum	448.405801	429.702717	74.743502	72.6	18.79974	17.990883	17.463805	17.166179	14.967974	14.685136	14.330699	14.089602	13.72714	11.487408	10.214821	9.876215	7.523135	6.356613	5.795162	5.624204	3.459836	3.01425	2.780895	2.529968	2.471124	2.463948	2.385884	2.328784	2.254455	2.201655	1.965896	1.916151	1.891923	1.651909	1.406529	1.3165	1.236694	1.194309	1.187277	1.122339	0.874006	0.854623	0.823669	0.776181	0.64295	0.596978	0.521497	0.438793	0.3598	0.192119	0.139393	0.052621	0.03791	0.015843	-0.000126	-0.101014
negative	7.000000	5.000000	15.000000	13.0	25.00000	23.000000	30.000000	34.000000	41.000000	31.000000	21.000000	41.000000	35.00000	44.000000	28.000000	41.000000	48.000000	53.000000	59.000000	50.000000	63.000000	61.00000	67.000000	59.000000	69.000000	67.000000	54.000000	59.000000	60.000000	64.000000	71.000000	61.000000	57.000000	69.000000	69.000000	79.0000	81.000000	59.000000	90.000000	67.000000	82.000000	94.000000	85.000000	75.000000	88.00000	99.000000	94.000000	89.000000	93.0000	117.000000	110.000000	111.000000	113.00000	137.000000	122.000000	134.000000

importance_XGBoost.sort_values(by="negative" , ascending=True).transpose()

	mom12	ROE	std_dvol	ACCP	saleinv	BM	momchg	ACC	AG	sharechg	SP	CRG	LM	idskew	SgINVg	total_vol	LG	betad	cashpr	coskew	INVchg	PA	LEV	QRG	CT	ROA	DP	imom	mom6	QR	CFdebt	OCFP	beta	BVEG	std_turn	TAXchg	size	retnmax	PMG	volumed	SG	illq	cash	EP	CR	INVG	skew	lagretn	CFP	RD	idvol	age	RDsales	AM	turn	salecash
sum	429.702717	448.405801	72.6	74.743502	14.330699	17.990883	18.79974	10.214821	17.463805	14.685136	17.166179	13.72714	9.876215	14.967974	14.089602	11.487408	7.523135	5.624204	6.356613	2.385884	1.891923	2.328784	5.795162	2.529968	1.194309	2.254455	1.916151	3.01425	3.459836	2.201655	2.780895	1.122339	2.463948	1.406529	2.471124	1.651909	1.965896	0.776181	1.3165	1.236694	0.874006	0.823669	0.64295	0.438793	1.187277	0.3598	0.521497	0.854623	0.596978	0.139393	0.052621	0.03791	0.192119	-0.000126	-0.101014	0.015843
negative	5.000000	7.000000	13.0	15.000000	21.000000	23.000000	25.00000	28.000000	30.000000	31.000000	34.000000	35.00000	41.000000	41.000000	41.000000	44.000000	48.000000	50.000000	53.000000	54.000000	57.000000	59.000000	59.000000	59.000000	59.000000	60.000000	61.000000	61.00000	63.000000	64.000000	67.000000	67.000000	67.000000	69.000000	69.000000	69.000000	71.000000	75.000000	79.0000	81.000000	82.000000	85.000000	88.00000	89.000000	90.000000	93.0000	94.000000	94.000000	99.000000	110.000000	111.000000	113.00000	117.000000	122.000000	134.000000	137.000000

remove_factors_XGBoost = list(get_last_N(importance_XGBoost, 10))

print(get_last_N(importance, 10))
print(get_last_N(importance_XGBoost, 10))

{'salecash', 'idvol', 'INVG', 'turn', 'AM', 'RD', 'RDsales', 'age'}
{'salecash', 'idvol', 'turn', 'skew', 'AM', 'RD', 'RDsales', 'age'}

print(get_last_N(importance, 20))
print(get_last_N(importance_XGBoost, 20))

{'salecash', 'CR', 'volumed', 'CFP', 'SG', 'idvol', 'EP', 'turn', 'INVG', 'lagretn', 'cash', 'skew', 'age', 'retnmax', 'AM', 'illq', 'RDsales', 'RD'}
{'salecash', 'CR', 'volumed', 'CFP', 'SG', 'idvol', 'EP', 'turn', 'INVG', 'lagretn', 'cash', 'skew', 'age', 'retnmax', 'AM', 'illq', 'RDsales', 'RD'}

XGBoost得到的结果与Linear模型不一样：但差别不大

XGBoost去除无用特征

XGBoost_err1 = []
for day in days:
    print(day)
    XGBoost_err1.append(XGBoost_train(day, 0, remove_factors_XGBoost))

2013-01-04
x_train.shape=(1820, 48)
y_train.shape =(1820,)
x_test.shape=(455, 48)
y_test.shape=(455,)
[0]	validation_0-rmse:2.71745
[1]	validation_0-rmse:2.67359
[2]	validation_0-rmse:2.63451
[3]	validation_0-rmse:2.60041
[4]	validation_0-rmse:2.57119
[5]	validation_0-rmse:2.54164
[6]	validation_0-rmse:2.51318
[7]	validation_0-rmse:2.48936
[8]	validation_0-rmse:2.46562
[9]	validation_0-rmse:2.44546
[10]	validation_0-rmse:2.42487
[11]	validation_0-rmse:2.40673
[12]	validation_0-rmse:2.38718
[13]	validation_0-rmse:2.37333
[14]	validation_0-rmse:2.36220
[15]	validation_0-rmse:2.35255
[16]	validation_0-rmse:2.34168
[17]	validation_0-rmse:2.32783
[18]	validation_0-rmse:2.31884
[19]	validation_0-rmse:2.30887
[20]	validation_0-rmse:2.30385
[21]	validation_0-rmse:2.30015
[22]	validation_0-rmse:2.29274
[23]	validation_0-rmse:2.28728
[24]	validation_0-rmse:2.28071
[25]	validation_0-rmse:2.27549
[26]	validation_0-rmse:2.27096
[27]	validation_0-rmse:2.26446
[28]	validation_0-rmse:2.25991
[29]	validation_0-rmse:2.25987
[30]	validation_0-rmse:2.25923
[31]	validation_0-rmse:2.25714
[32]	validation_0-rmse:2.25545
[33]	validation_0-rmse:2.25242
[34]	validation_0-rmse:2.25230
[35]	validation_0-rmse:2.25038
[36]	validation_0-rmse:2.24694
[37]	validation_0-rmse:2.24920
[38]	validation_0-rmse:2.24767
[39]	validation_0-rmse:2.24455
[40]	validation_0-rmse:2.24335
[41]	validation_0-rmse:2.24286
[42]	validation_0-rmse:2.24344
[43]	validation_0-rmse:2.24169
[44]	validation_0-rmse:2.23983
[45]	validation_0-rmse:2.23949
[46]	validation_0-rmse:2.24040
[47]	validation_0-rmse:2.23639
[48]	validation_0-rmse:2.23753
[49]	validation_0-rmse:2.23831
[50]	validation_0-rmse:2.23831
[51]	validation_0-rmse:2.23881
[52]	validation_0-rmse:2.23851
MSE: 5.001454124013577
2013-01-07
x_train.shape=(1793, 48)
y_train.shape =(1793,)
x_test.shape=(449, 48)
y_test.shape=(449,)
[0]	validation_0-rmse:2.00898
[1]	validation_0-rmse:1.98336
[2]	validation_0-rmse:1.96136
[3]	validation_0-rmse:1.93963
[4]	validation_0-rmse:1.92541
[5]	validation_0-rmse:1.90738
[6]	validation_0-rmse:1.89212
[7]	validation_0-rmse:1.87982
[8]	validation_0-rmse:1.87254
[9]	validation_0-rmse:1.86130
[10]	validation_0-rmse:1.85293
[11]	validation_0-rmse:1.84307
[12]	validation_0-rmse:1.83806
[13]	validation_0-rmse:1.83238
[14]	validation_0-rmse:1.82658
[15]	validation_0-rmse:1.82079
[16]	validation_0-rmse:1.81401
[17]	validation_0-rmse:1.81253
[18]	validation_0-rmse:1.80937
[19]	validation_0-rmse:1.80658
[20]	validation_0-rmse:1.80209
[21]	validation_0-rmse:1.79880
[22]	validation_0-rmse:1.79395
[23]	validation_0-rmse:1.79342
[24]	validation_0-rmse:1.79180
[25]	validation_0-rmse:1.78960
[26]	validation_0-rmse:1.79045
[27]	validation_0-rmse:1.79132
[28]	validation_0-rmse:1.78716
[29]	validation_0-rmse:1.78690
[30]	validation_0-rmse:1.78452
[31]	validation_0-rmse:1.78472
[32]	validation_0-rmse:1.78501
[33]	validation_0-rmse:1.78616
[34]	validation_0-rmse:1.78586
[35]	validation_0-rmse:1.78812
MSE: 3.1845212488497667
2013-01-08
x_train.shape=(1797, 48)
y_train.shape =(1797,)
x_test.shape=(450, 48)
y_test.shape=(450,)
[0]	validation_0-rmse:2.21991
[1]	validation_0-rmse:2.19453
[2]	validation_0-rmse:2.17296
[3]	validation_0-rmse:2.15496
[4]	validation_0-rmse:2.14025
[5]	validation_0-rmse:2.12435
[6]	validation_0-rmse:2.11047
[7]	validation_0-rmse:2.09894
[8]	validation_0-rmse:2.08667
[9]	validation_0-rmse:2.07808
[10]	validation_0-rmse:2.07004
[11]	validation_0-rmse:2.06143
[12]	validation_0-rmse:2.05203
[13]	validation_0-rmse:2.04436
[14]	validation_0-rmse:2.03613
[15]	validation_0-rmse:2.03236
[16]	validation_0-rmse:2.02629
[17]	validation_0-rmse:2.02123
[18]	validation_0-rmse:2.02001
[19]	validation_0-rmse:2.01185
[20]	validation_0-rmse:2.01016
[21]	validation_0-rmse:2.00876
[22]	validation_0-rmse:2.00288
[23]	validation_0-rmse:2.00041
[24]	validation_0-rmse:1.99874
[25]	validation_0-rmse:1.99588
[26]	validation_0-rmse:1.99229
[27]	validation_0-rmse:1.98823
[28]	validation_0-rmse:1.98213
[29]	validation_0-rmse:1.98026
[30]	validation_0-rmse:1.97804
[31]	validation_0-rmse:1.97848
[32]	validation_0-rmse:1.97623
[33]	validation_0-rmse:1.97624
[34]	validation_0-rmse:1.97415
[35]	validation_0-rmse:1.97366
[36]	validation_0-rmse:1.97279
[37]	validation_0-rmse:1.97119
[38]	validation_0-rmse:1.97256
[39]	validation_0-rmse:1.97306
[40]	validation_0-rmse:1.97376
[41]	validation_0-rmse:1.97482
MSE: 3.8855736293546372
2013-01-09
x_train.shape=(1791, 48)
y_train.shape =(1791,)
x_test.shape=(448, 48)
y_test.shape=(448,)
[0]	validation_0-rmse:1.90462
[1]	validation_0-rmse:1.90026
[2]	validation_0-rmse:1.89663
[3]	validation_0-rmse:1.89111
[4]	validation_0-rmse:1.88658
[5]	validation_0-rmse:1.88702
[6]	validation_0-rmse:1.88244
[7]	validation_0-rmse:1.88211
[8]	validation_0-rmse:1.87815
[9]	validation_0-rmse:1.87744
[10]	validation_0-rmse:1.87602
[11]	validation_0-rmse:1.87436
[12]	validation_0-rmse:1.87080
[13]	validation_0-rmse:1.86997
[14]	validation_0-rmse:1.86840
[15]	validation_0-rmse:1.86853
[16]	validation_0-rmse:1.86896
[17]	validation_0-rmse:1.86809
[18]	validation_0-rmse:1.86592
[19]	validation_0-rmse:1.86313
[20]	validation_0-rmse:1.86108
[21]	validation_0-rmse:1.86272
[22]	validation_0-rmse:1.86133
[23]	validation_0-rmse:1.85858
[24]	validation_0-rmse:1.85833
[25]	validation_0-rmse:1.85615
[26]	validation_0-rmse:1.85641
[27]	validation_0-rmse:1.85625
[28]	validation_0-rmse:1.85526
[29]	validation_0-rmse:1.85653
[30]	validation_0-rmse:1.85803
[31]	validation_0-rmse:1.85546
[32]	validation_0-rmse:1.85270
[33]	validation_0-rmse:1.85378
[34]	validation_0-rmse:1.85455
[35]	validation_0-rmse:1.85685
[36]	validation_0-rmse:1.85556
MSE: 3.4324928107513224
2013-01-10
x_train.shape=(1791, 48)
y_train.shape =(1791,)
x_test.shape=(448, 48)
y_test.shape=(448,)
[0]	validation_0-rmse:1.74036
[1]	validation_0-rmse:1.73539
[2]	validation_0-rmse:1.72730
[3]	validation_0-rmse:1.72252
[4]	validation_0-rmse:1.71576
[5]	validation_0-rmse:1.71449
[6]	validation_0-rmse:1.70838
[7]	validation_0-rmse:1.70582
[8]	validation_0-rmse:1.70224
[9]	validation_0-rmse:1.70405
[10]	validation_0-rmse:1.70169
[11]	validation_0-rmse:1.70120
[12]	validation_0-rmse:1.69680
[13]	validation_0-rmse:1.69821
[14]	validation_0-rmse:1.69667
[15]	validation_0-rmse:1.69463
[16]	validation_0-rmse:1.69219
[17]	validation_0-rmse:1.68838
[18]	validation_0-rmse:1.68872
[19]	validation_0-rmse:1.68787
[20]	validation_0-rmse:1.68485
[21]	validation_0-rmse:1.68401
[22]	validation_0-rmse:1.68272
[23]	validation_0-rmse:1.68308
[24]	validation_0-rmse:1.68362
[25]	validation_0-rmse:1.68241
[26]	validation_0-rmse:1.68232
[27]	validation_0-rmse:1.68231
[28]	validation_0-rmse:1.68390
[29]	validation_0-rmse:1.68406
[30]	validation_0-rmse:1.68301
[31]	validation_0-rmse:1.68244
MSE: 2.8301813631073527
2013-01-11
x_train.shape=(1798, 48)
y_train.shape =(1798,)
x_test.shape=(450, 48)
y_test.shape=(450,)
[0]	validation_0-rmse:3.31175
[1]	validation_0-rmse:3.21892
[2]	validation_0-rmse:3.13651
[3]	validation_0-rmse:3.06162
[4]	validation_0-rmse:2.98938
[5]	validation_0-rmse:2.92879
[6]	validation_0-rmse:2.86506
[7]	validation_0-rmse:2.81064
[8]	validation_0-rmse:2.76554
[9]	validation_0-rmse:2.71910
[10]	validation_0-rmse:2.67275
[11]	validation_0-rmse:2.62927
[12]	validation_0-rmse:2.58945
[13]	validation_0-rmse:2.55245
[14]	validation_0-rmse:2.51939
[15]	validation_0-rmse:2.49457
[16]	validation_0-rmse:2.47158
[17]	validation_0-rmse:2.44465
[18]	validation_0-rmse:2.42555
[19]	validation_0-rmse:2.41074
[20]	validation_0-rmse:2.39081
[21]	validation_0-rmse:2.37692
[22]	validation_0-rmse:2.36240
[23]	validation_0-rmse:2.34919
[24]	validation_0-rmse:2.33831
[25]	validation_0-rmse:2.32760
[26]	validation_0-rmse:2.31880
[27]	validation_0-rmse:2.30908
[28]	validation_0-rmse:2.29942
[29]	validation_0-rmse:2.29173
[30]	validation_0-rmse:2.28906
[31]	validation_0-rmse:2.28330
[32]	validation_0-rmse:2.27824
[33]	validation_0-rmse:2.27168
[34]	validation_0-rmse:2.26974
[35]	validation_0-rmse:2.26434
[36]	validation_0-rmse:2.26080
[37]	validation_0-rmse:2.25779
[38]	validation_0-rmse:2.25554
[39]	validation_0-rmse:2.25194
[40]	validation_0-rmse:2.24950
[41]	validation_0-rmse:2.24582
[42]	validation_0-rmse:2.24212
[43]	validation_0-rmse:2.23924
[44]	validation_0-rmse:2.23693
[45]	validation_0-rmse:2.23408
[46]	validation_0-rmse:2.23157
[47]	validation_0-rmse:2.22886
[48]	validation_0-rmse:2.22640
[49]	validation_0-rmse:2.22447
[50]	validation_0-rmse:2.22414
[51]	validation_0-rmse:2.22391
[52]	validation_0-rmse:2.22305
[53]	validation_0-rmse:2.22291
[54]	validation_0-rmse:2.22153
[55]	validation_0-rmse:2.21619
[56]	validation_0-rmse:2.21558
[57]	validation_0-rmse:2.21659
[58]	validation_0-rmse:2.21574
[59]	validation_0-rmse:2.21568
[60]	validation_0-rmse:2.21477
[61]	validation_0-rmse:2.21468
[62]	validation_0-rmse:2.21416
[63]	validation_0-rmse:2.21339
[64]	validation_0-rmse:2.21196
[65]	validation_0-rmse:2.21234
[66]	validation_0-rmse:2.21082
[67]	validation_0-rmse:2.20976
[68]	validation_0-rmse:2.20896
[69]	validation_0-rmse:2.20771
[70]	validation_0-rmse:2.20623
[71]	validation_0-rmse:2.20521
[72]	validation_0-rmse:2.20464
[73]	validation_0-rmse:2.20457
[74]	validation_0-rmse:2.20517
[75]	validation_0-rmse:2.20470
[76]	validation_0-rmse:2.20315
[77]	validation_0-rmse:2.20307
[78]	validation_0-rmse:2.20312
[79]	validation_0-rmse:2.20367
[80]	validation_0-rmse:2.20395
[81]	validation_0-rmse:2.20458
MSE: 4.853516475539035
2013-01-14
x_train.shape=(1788, 48)
y_train.shape =(1788,)
x_test.shape=(448, 48)
y_test.shape=(448,)
[0]	validation_0-rmse:3.54992
[1]	validation_0-rmse:3.41347
[2]	validation_0-rmse:3.28376
[3]	validation_0-rmse:3.16036
[4]	validation_0-rmse:3.04717
[5]	validation_0-rmse:2.94013
[6]	validation_0-rmse:2.83867
[7]	validation_0-rmse:2.74747
[8]	validation_0-rmse:2.66053
[9]	validation_0-rmse:2.57977
[10]	validation_0-rmse:2.50311
[11]	validation_0-rmse:2.43331
[12]	validation_0-rmse:2.36710
[13]	validation_0-rmse:2.30966
[14]	validation_0-rmse:2.25344
[15]	validation_0-rmse:2.20568
[16]	validation_0-rmse:2.15862
[17]	validation_0-rmse:2.11274
[18]	validation_0-rmse:2.07126
[19]	validation_0-rmse:2.03326
[20]	validation_0-rmse:1.99911
[21]	validation_0-rmse:1.96901
[22]	validation_0-rmse:1.93961
[23]	validation_0-rmse:1.91477
[24]	validation_0-rmse:1.89042
[25]	validation_0-rmse:1.86812
[26]	validation_0-rmse:1.84573
[27]	validation_0-rmse:1.82862
[28]	validation_0-rmse:1.81004
[29]	validation_0-rmse:1.79396
[30]	validation_0-rmse:1.78030
[31]	validation_0-rmse:1.76868
[32]	validation_0-rmse:1.75735
[33]	validation_0-rmse:1.74560
[34]	validation_0-rmse:1.73647
[35]	validation_0-rmse:1.72792
[36]	validation_0-rmse:1.71951
[37]	validation_0-rmse:1.71065
[38]	validation_0-rmse:1.70197
[39]	validation_0-rmse:1.69403
[40]	validation_0-rmse:1.68678
[41]	validation_0-rmse:1.68097
[42]	validation_0-rmse:1.67777
[43]	validation_0-rmse:1.67243
[44]	validation_0-rmse:1.66799
[45]	validation_0-rmse:1.66378
[46]	validation_0-rmse:1.66015
[47]	validation_0-rmse:1.65685
[48]	validation_0-rmse:1.65420
[49]	validation_0-rmse:1.65186
[50]	validation_0-rmse:1.64992
[51]	validation_0-rmse:1.64827
[52]	validation_0-rmse:1.64639
[53]	validation_0-rmse:1.64575
[54]	validation_0-rmse:1.64446
[55]	validation_0-rmse:1.64233
[56]	validation_0-rmse:1.64053
[57]	validation_0-rmse:1.63897
[58]	validation_0-rmse:1.63678
[59]	validation_0-rmse:1.63496
[60]	validation_0-rmse:1.63408
[61]	validation_0-rmse:1.63270
[62]	validation_0-rmse:1.63197
[63]	validation_0-rmse:1.63001
[64]	validation_0-rmse:1.63058
[65]	validation_0-rmse:1.63124
[66]	validation_0-rmse:1.63046
[67]	validation_0-rmse:1.63053
[68]	validation_0-rmse:1.62815
[69]	validation_0-rmse:1.62808
[70]	validation_0-rmse:1.62787
[71]	validation_0-rmse:1.62731
[72]	validation_0-rmse:1.62736
[73]	validation_0-rmse:1.62676
[74]	validation_0-rmse:1.62728
[75]	validation_0-rmse:1.62717
[76]	validation_0-rmse:1.62791
[77]	validation_0-rmse:1.62786
[78]	validation_0-rmse:1.62667
[79]	validation_0-rmse:1.62613
[80]	validation_0-rmse:1.62612
[81]	validation_0-rmse:1.62547
[82]	validation_0-rmse:1.62677
[83]	validation_0-rmse:1.62850
[84]	validation_0-rmse:1.62882
[85]	validation_0-rmse:1.62957
[86]	validation_0-rmse:1.63227
MSE: 2.642140469381674
...
2013-12-31
x_train.shape=(1781, 48)
y_train.shape =(1781,)
x_test.shape=(446, 48)
y_test.shape=(446,)
[0]	validation_0-rmse:1.88690
[1]	validation_0-rmse:1.86526
[2]	validation_0-rmse:1.85005
[3]	validation_0-rmse:1.84162
[4]	validation_0-rmse:1.83684
[5]	validation_0-rmse:1.82044
[6]	validation_0-rmse:1.80873
[7]	validation_0-rmse:1.79836
[8]	validation_0-rmse:1.79244
[9]	validation_0-rmse:1.78463
[10]	validation_0-rmse:1.77731
[11]	validation_0-rmse:1.77208
[12]	validation_0-rmse:1.76650
[13]	validation_0-rmse:1.76504
[14]	validation_0-rmse:1.76111
[15]	validation_0-rmse:1.76009
[16]	validation_0-rmse:1.75637
[17]	validation_0-rmse:1.75409
[18]	validation_0-rmse:1.75204
[19]	validation_0-rmse:1.75110
[20]	validation_0-rmse:1.74982
[21]	validation_0-rmse:1.74916
[22]	validation_0-rmse:1.74626
[23]	validation_0-rmse:1.74462
[24]	validation_0-rmse:1.74572
[25]	validation_0-rmse:1.74326
[26]	validation_0-rmse:1.74332
[27]	validation_0-rmse:1.74115
[28]	validation_0-rmse:1.73936
[29]	validation_0-rmse:1.73940
[30]	validation_0-rmse:1.73854
[31]	validation_0-rmse:1.73787
[32]	validation_0-rmse:1.73685
[33]	validation_0-rmse:1.73552
[34]	validation_0-rmse:1.73746
[35]	validation_0-rmse:1.73781
[36]	validation_0-rmse:1.73913
[37]	validation_0-rmse:1.73897
MSE: 3.01203762063307

np.array(XGBoost_err1).mean()

3.909562275559899

XGBoost_err2 = []
for day in days:
    print(day)
    XGBoost_err2.append(XGBoost_train(day, 1, remove_factors_XGBoost))

2013-01-04
x_train.shape=(1185, 48)
y_train.shape =(1185,)
x_test.shape=(297, 48)
y_test.shape=(297,)
[0]	validation_0-rmse:2.44807
[1]	validation_0-rmse:2.39745
[2]	validation_0-rmse:2.35292
[3]	validation_0-rmse:2.30882
[4]	validation_0-rmse:2.27245
[5]	validation_0-rmse:2.23914
[6]	validation_0-rmse:2.20729
[7]	validation_0-rmse:2.16935
[8]	validation_0-rmse:2.14256
[9]	validation_0-rmse:2.12006
[10]	validation_0-rmse:2.09587
[11]	validation_0-rmse:2.07339
[12]	validation_0-rmse:2.04927
[13]	validation_0-rmse:2.03210
[14]	validation_0-rmse:2.01497
[15]	validation_0-rmse:2.00233
[16]	validation_0-rmse:1.98758
[17]	validation_0-rmse:1.97418
[18]	validation_0-rmse:1.96359
[19]	validation_0-rmse:1.95194
[20]	validation_0-rmse:1.94411
[21]	validation_0-rmse:1.93538
[22]	validation_0-rmse:1.92844
[23]	validation_0-rmse:1.92259
[24]	validation_0-rmse:1.91411
[25]	validation_0-rmse:1.90856
[26]	validation_0-rmse:1.90620
[27]	validation_0-rmse:1.90025
[28]	validation_0-rmse:1.89549
[29]	validation_0-rmse:1.89190
[30]	validation_0-rmse:1.88803
[31]	validation_0-rmse:1.88336
[32]	validation_0-rmse:1.87740
[33]	validation_0-rmse:1.87631
[34]	validation_0-rmse:1.87285
[35]	validation_0-rmse:1.87090
[36]	validation_0-rmse:1.86915
[37]	validation_0-rmse:1.86485
[38]	validation_0-rmse:1.86454
[39]	validation_0-rmse:1.86267
[40]	validation_0-rmse:1.85725
[41]	validation_0-rmse:1.85345
[42]	validation_0-rmse:1.85321
[43]	validation_0-rmse:1.85299
[44]	validation_0-rmse:1.85393
[45]	validation_0-rmse:1.85441
[46]	validation_0-rmse:1.85222
[47]	validation_0-rmse:1.85128
[48]	validation_0-rmse:1.85197
[49]	validation_0-rmse:1.84963
[50]	validation_0-rmse:1.84854
[51]	validation_0-rmse:1.84855
[52]	validation_0-rmse:1.84776
[53]	validation_0-rmse:1.84315
[54]	validation_0-rmse:1.84244
[55]	validation_0-rmse:1.84082
[56]	validation_0-rmse:1.84197
[57]	validation_0-rmse:1.84060
[58]	validation_0-rmse:1.84109
[59]	validation_0-rmse:1.84236
[60]	validation_0-rmse:1.84235
[61]	validation_0-rmse:1.84354
[62]	validation_0-rmse:1.84242
MSE: 3.387808379507812
...

np.array(XGBoost_err2).mean()

3.7494466498176644

准确率对比

2013年全年MSE平均值	不去除	去除低重要性因子
Linear使用平均值	3.921	3.903
Linear去除缺失值	3.801	3.818
XGBoost未去除缺失值	3.888	3.910
XGBoost去除缺失值	3.742	3.749

选择最佳因子组合

逐个排除因子（预降维）

（使用全年的数据在Linear模型上）对无用特征进行排序过后，考虑逐个排除因子，查看准确率是否有较大的影响：

remove_factors1 = []
output = {}

for j in range(0, 40):
    linear_err = []
    for day in days:
        print(day)
        linear_err.append(linear_train(day, 1, get_trivial(j)))
    
    output[j] = np.array(linear_err).mean()

2013-01-04
x_train.shape=(1185, 56)
y_train.shape =(1185,)
x_test.shape=(297, 56)
y_test.shape=(297,)
MSE: 3.617532364939728
2013-01-07
x_train.shape=(1175, 56)
y_train.shape =(1175,)
x_test.shape=(294, 56)
y_test.shape=(294,)
MSE: 3.767207686481283
...
2013-09-06
x_train.shape=(1262, 54)
y_train.shape =(1262,)
x_test.shape=(316, 54)
y_test.shape=(316,)
MSE: 4.479822455337999
2013-09-09
x_train.shape=(1245, 54)
y_train.shape =(1245,)
x_test.shape=(312, 54)
y_test.shape=(312,)
MSE: 2.6867597216311045
2013-09-10

output

{0: 3.8005630796082426,
 1: 3.800560102538793,
 2: 3.7993222041207915,
 3: 3.796581734282571,
 4: 3.810176307276948,
 5: 3.821326643110776,
 6: 3.8207592247949775,
 7: 3.8226390947166196,
 8: 3.8198824229201382,
 9: 3.8178624023374335,
 10: 3.8164553373810577,
 11: 3.817581805700733,
 12: 3.8162670045691693,
 13: 3.8173551938010513,
 14: 3.8128217050940854,
 15: 3.8171463773589944,
 16: 3.8382788440258135,
 17: 3.8355687130078513,
 18: 3.8323229320104573,
 19: 3.8318099337863303,
 20: 3.827302483819496,
 21: 3.84656562478651,
 22: 3.845318679687666,
 23: 3.8486123394339438,
 24: 3.9034638992606205,
 25: 3.9005512092481425,
 26: 3.90396465347381,
 27: 3.918746734890699,
 28: 3.9180623909064027,
 29: 3.917919924138114,
 30: 3.8968072309036286,
 31: 3.8957130947549037,
 32: 3.8947024917348525,
 33: 3.8949611266433943,
 34: 3.9093928642932676,
 35: 3.924233068042662,
 36: 3.922568663342627,
 37: 3.9293781688167835,
 38: 3.967771645777158,
 39: 4.045240388664313}

plt.plot(list(output.keys()), list(output.values()))

[<matplotlib.lines.Line2D at 0x7f3f48772ee0>]

png

如图所示，在去除20个因子以前，误差变化较小，在去除3个因子时，误差达到最小值。

而去除因子达到35个以上，误差会急剧增大，可能因为去除了有效的因子。

这说明在56个因子中，真正有效的因子数量甚至不到一半，直接去除掉不但提高了模型的可解释性，甚至同时能提升准确性

动态排除因子（后降维）

预降维是在全年排除相同因子采用的，而后降维将对每天的数据进行评估，对于每天的模型去除不重要的因子。

因此，可以预想到，去除的因子数量会更多（接近一半的负排序重要性因子都会被去除），准确性是一定会提升的。

此处采取的策略是：对每天因子重要性进行三次计算，均为负则去除该因子。然后再次回归

def remove_and_fit(date, state=1):
    # 划分数据集
    x_train, x_test, y_train, y_test = get_split_by_trade_date(date, state)

    # 模型训练
    model = LinearRegression()
    model.fit(x_train, y_train)
    
    # 计算排序重要性
    df = pd.DataFrame(index = factors)
    
    for i in range(3):
        perm = PermutationImportance(model, random_state=i).fit(x_test, y_test)
        df[i] = perm.feature_importances_
    
    series = df[df<0].transpose().count()==3
    remove_factors = list(series[series].index)
    print(remove_factors)
    
    return len(remove_factors), linear_train(day, state, remove_factors)  # 这里划分数据集的方式不同

linear_remove = pd.DataFrame(columns = ['removed', 'err'])
for day in days:
    print(day, end = ' ')
    removed, err = remove_and_fit(day)
    linear_remove.loc[day] = {'removed':removed, 'err':err}

2013-01-04 ['beta', 'turn', 'sharechg', 'age', 'lagretn', 'AM', 'DP', 'BVEG', 'INVG', 'CT', 'RD', 'RDsales', 'salecash']
MSE: 3.7858729998590723
2013-01-07 ['beta', 'idvol', 'skew', 'turn', 'std_turn', 'age', 'lagretn', 'AM', 'SG', 'PMG', 'cash', 'RDsales', 'QR', 'saleinv', 'CRG']
MSE: 4.025161449626848
2013-01-08 ['size', 'beta', 'skew', 'coskew', 'turn', 'LM', 'age', 'BM', 'CFP', 'INVG', 'ROA', 'PA', 'salecash']
MSE: 4.162825913159681
2013-01-09 ['size', 'beta', 'idvol', 'skew', 'std_turn', 'retnmax', 'age', 'AM', 'PMG', 'ROA', 'RDsales']
MSE: 2.9702129885547928
2013-01-10 ['beta', 'betad', 'idvol', 'sharechg', 'lagretn', 'AM', 'INVG', 'SgINVg', 'cash', 'cashpr', 'salecash']
MSE: 2.4174113537403037
2013-01-11 ['beta', 'turn', 'age', 'mom6', 'LEV', 'CFP', 'TAXchg', 'cash', 'RDsales', 'CR', 'salecash']
MSE: 3.751365716737459
2013-01-14 ['volumed', 'std_dvol', 'AM', 'OCFP', 'INVchg', 'PMG', 'ROA', 'RD', 'saleinv']
MSE: 2.4185355766852887
2013-01-15 ['beta', 'betad', 'idvol', 'age', 'lagretn', 'INVG', 'PMG', 'cashpr', 'CFdebt']
MSE: 3.370724501216639
2013-01-16 ['idvol', 'turn', 'std_turn', 'volumed', 'EP', 'CFP', 'DP', 'INVchg', 'QRG']
MSE: 4.447045990712184
2013-01-17 ['beta', 'total_vol', 'retnmax', 'illq', 'sharechg', 'age', 'AM', 'LEV', 'INVG', 'SG', 'PMG', 'TAXchg', 'CT', 'cash', 'CR', 'QR', 'salecash']
MSE: 4.082304969198799
2013-01-18 ['turn', 'CFP', 'OCFP', 'PMG', 'ROA']
MSE: 2.1234872477788023
2013-01-21 ['idvol', 'idskew', 'skew', 'std_dvol', 'illq', 'lagretn', 'PMG', 'ROA', 'CR']
MSE: 4.075557103299469
2013-01-22 ['betad', 'skew', 'mom6', 'AM', 'CFP', 'OCFP', 'PA', 'cash', 'RD', 'CR', 'salecash']
MSE: 3.0421280038462126
2013-01-23 ['size', 'betad', 'idskew', 'turn', 'mom6', 'lagretn', 'AM', 'EP', 'LG', 'TAXchg', 'ROA', 'PA', 'RDsales', 'salecash']
MSE: 3.8397380865824173
2013-01-24 ['std_turn', 'age', 'AM', 'INVG', 'PMG', 'ROA']
MSE: 4.3652342753144415
2013-01-25 ['skew', 'LM', 'BM', 'AM', 'INVG', 'INVchg', 'PMG', 'cash', 'salecash', 'CRG']
MSE: 3.649042345177247
2013-01-28 ['beta', 'skew', 'EP', 'CFP', 'BVEG', 'INVchg', 'SG', 'PMG', 'ACCP', 'RD', 'RDsales', 'QR']
MSE: 1.998549925155473
2013-01-29 ['idvol', 'total_vol', 'skew', 'turn', 'illq', 'age', 'AM', 'EP', 'OCFP', 'LG', 'INVchg', 'SgINVg', 'ROA', 'PA', 'cashpr', 'RDsales', 'CR', 'CFdebt', 'salecash', 'CRG']
MSE: 2.9341143357828474
2013-01-30 ['beta', 'idskew', 'retnmax', 'age', 'mom6', 'PA', 'cash']
MSE: 3.37135529969674
2013-01-31 ['beta', 'idvol', 'turn', 'AM', 'INVG', 'SG', 'TAXchg', 'ACC', 'RD']
MSE: 4.029868334639127
2013-02-01 ['size', 'skew', 'coskew', 'turn', 'std_turn', 'LEV', 'BVEG', 'INVG', 'INVchg', 'CT', 'cash', 'CFdebt']
MSE: 2.9752105980905337
2013-02-04 ['lagretn', 'SG', 'PMG', 'RDsales', 'salecash']
MSE: 5.564731556991589
2013-02-05 ['beta', 'age', 'mom6', 'CFP', 'DP', 'AG', 'INVG', 'INVchg', 'cash', 'cashpr', 'QRG']
MSE: 3.015906109352361
2013-02-06 ['AM', 'cash', 'QR']
MSE: 2.2884328731540524
2013-02-07 ['LM', 'CFP', 'OCFP', 'BVEG', 'PA', 'RDsales', 'salecash']
MSE: 2.6887185072823114
2013-02-08 ['idvol', 'skew', 'volumed', 'retnmax', 'ACC', 'cash']
MSE: 2.4370138796593364
2013-02-18 ['illq', 'AM', 'OCFP', 'LG', 'RD', 'CRG']
MSE: 3.0436795852997207
2013-02-19 ['age', 'lagretn', 'AM', 'EP', 'OCFP', 'INVG', 'QR']
MSE: 3.589772885371211
2013-02-20 ['betad', 'turn', 'lagretn', 'AM', 'CT', 'RD', 'RDsales', 'CR']
MSE: 2.376644549747271
2013-02-21 ['idvol', 'sharechg', 'EP', 'CFP', 'DP', 'SP', 'BVEG', 'INVG', 'RDsales']
MSE: 4.382255648644994
2013-02-22 ['skew', 'volumed', 'retnmax', 'LM', 'mom6', 'imom', 'AM', 'CFP', 'PA', 'RD']
MSE: 3.984581871361109
2013-02-25 ['skew', 'volumed', 'mom12', 'EP', 'CFP', 'DP', 'LG', 'cash', 'RD', 'QR', 'CFdebt']
MSE: 2.628439990574723
2013-02-26 ['skew', 'coskew', 'retnmax', 'sharechg', 'age', 'imom', 'lagretn', 'LEV', 'EP', 'DP', 'BVEG', 'INVG', 'cash', 'RDsales', 'salecash', 'CRG']
MSE: 3.617891237938386
2013-02-27 ['size', 'idvol', 'coskew', 'retnmax', 'age', 'lagretn', 'AM', 'LEV', 'SG', 'PMG', 'TAXchg', 'CFdebt']
MSE: 2.9805103770521884
2013-02-28 ['betad', 'volumed', 'imom', 'lagretn', 'DP', 'AG', 'TAXchg', 'cash', 'CFdebt']
MSE: 2.4335964170626463
2013-03-01 ['betad', 'skew', 'turn', 'std_turn', 'volumed', 'illq', 'LM', 'age', 'mom6', 'lagretn', 'EP', 'INVG', 'CFdebt', 'salecash']
MSE: 3.308268260769943
2013-03-04 ['betad', 'skew', 'turn', 'volumed', 'AM', 'LEV', 'SP', 'QR', 'salecash']
MSE: 3.091217982194591
2013-03-05 ['skew', 'turn', 'retnmax', 'lagretn', 'CFP', 'DP', 'INVG', 'CT']
MSE: 3.0806149519588337
2013-03-06 ['idvol', 'turn', 'retnmax', 'age', 'momchg', 'AM', 'RDsales']
MSE: 4.669136460161346
2013-03-07 ['idvol', 'volumed', 'LM', 'AM', 'LEV', 'OCFP', 'INVchg', 'RD', 'salecash']
MSE: 4.602641402312919
2013-03-08 ['turn', 'age', 'AM', 'EP', 'INVchg', 'SG', 'PMG', 'CFdebt', 'salecash']
MSE: 3.559080961750365
2013-03-11 ['idvol', 'skew', 'EP', 'CFP', 'PMG', 'RD', 'QR']
MSE: 3.1585437676637826
2013-03-12 ['skew', 'turn', 'volumed', 'imom', 'AM', 'LEV', 'EP', 'BVEG', 'SgINVg', 'PA', 'CT', 'cash', 'CFdebt']
MSE: 4.33071164653929
2013-03-13 ['skew', 'volumed', 'illq', 'mom6', 'lagretn', 'AM', 'EP', 'OCFP', 'DP', 'TAXchg', 'saleinv', 'QRG']
MSE: 4.228758398689912
2013-03-14 ['total_vol', 'skew', 'retnmax', 'illq', 'mom6', 'AM', 'EP', 'CFP', 'SP', 'RD', 'QRG']
MSE: 2.919961024320269
2013-03-15 ['turn', 'illq', 'LM', 'BM', 'BVEG', 'salecash']
MSE: 3.2026742871048857
2013-03-18 ['LM', 'age', 'imom', 'CFP', 'INVchg', 'CFdebt']
MSE: 4.825258612532052
2013-03-19 ['turn', 'age', 'BM', 'AM', 'LEV', 'EP', 'ACC', 'QRG']
MSE: 4.917209643944105
2013-03-20 ['size', 'beta', 'idvol', 'skew', 'age', 'lagretn', 'CFP', 'SP', 'LG', 'INVG', 'SG', 'ROA', 'CT', 'QRG']
MSE: 2.2047808208664144
2013-03-21 ['beta', 'betad', 'idvol', 'turn', 'AM', 'CFP', 'DP', 'PMG', 'TAXchg', 'ACC', 'PA', 'RDsales', 'CFdebt', 'QRG']
MSE: 2.507678699246893
2013-03-22 ['skew', 'lagretn', 'EP', 'DP', 'INVG', 'PMG', 'ROE', 'saleinv']
MSE: 2.8863295573117242
2013-03-25 ['betad', 'skew', 'turn', 'std_turn', 'volumed', 'lagretn', 'CFP', 'DP', 'INVG', 'SG', 'ROA', 'cashpr']
MSE: 3.316622703962829
2013-03-26 ['skew', 'age', 'mom6', 'AM', 'EP', 'CFP', 'INVG', 'QR']
MSE: 4.50087835556555
2013-03-27 ['skew', 'turn', 'volumed', 'age', 'mom6', 'LEV', 'EP', 'SG', 'SgINVg', 'PMG', 'TAXchg', 'CT', 'RDsales']
MSE: 3.8974965957604497
2013-03-28 ['skew', 'turn', 'volumed', 'LM', 'QR']
MSE: 3.344769615966232
2013-03-29 ['beta', 'turn', 'age', 'mom6', 'EP', 'OCFP', 'LG', 'SG', 'cash', 'RD']
MSE: 3.6517181917715344
2013-04-01 ['betad', 'turn', 'volumed', 'std_dvol', 'retnmax', 'imom', 'lagretn', 'LEV', 'EP', 'INVchg', 'cashpr', 'RD', 'CR', 'QR', 'salecash']
MSE: 3.39461678703113
2013-04-02 ['size', 'idvol', 'age', 'mom6', 'lagretn', 'AM', 'EP', 'SgINVg', 'TAXchg', 'cash', 'salecash', 'saleinv']
MSE: 5.006330832570682
2013-04-03 ['std_turn', 'retnmax', 'illq', 'LM', 'EP', 'CFP', 'OCFP', 'SgINVg', 'PMG', 'ROA', 'RD', 'CR', 'QRG']
MSE: 4.595119149833135
2013-04-08 ['beta', 'illq', 'mom6', 'CFP', 'OCFP', 'INVG', 'cash']
MSE: 4.27367902986036
2013-04-09 ['size', 'idvol', 'retnmax', 'illq', 'EP', 'QRG']
MSE: 4.311125099788795
2013-04-10 ['coskew', 'turn', 'retnmax', 'AM', 'OCFP', 'INVG', 'PMG', 'CT', 'cashpr', 'saleinv', 'CRG', 'QRG']
MSE: 2.943656923181127
2013-04-11 ['beta', 'skew', 'coskew', 'turn', 'std_turn', 'LM', 'sharechg', 'AM', 'EP', 'CFP', 'OCFP', 'PMG', 'ACC', 'ROA', 'CT', 'CFdebt', 'salecash']
MSE: 3.0621524306130676
2013-04-12 ['turn', 'age', 'mom6', 'AM', 'AG', 'LG', 'INVG', 'INVchg', 'RDsales', 'QR', 'CFdebt', 'CRG']
MSE: 2.594489069882756
2013-04-15 ['coskew', 'INVG', 'cash']
MSE: 4.122738534906467
2013-04-16 ['idvol', 'total_vol', 'skew', 'coskew', 'volumed', 'std_dvol', 'retnmax', 'age', 'lagretn', 'SG', 'SgINVg', 'ACCP', 'PA', 'CT', 'RDsales', 'CR', 'salecash']
MSE: 2.9841222620046266
2013-04-17 ['coskew', 'turn', 'retnmax', 'imom', 'AM', 'CFP', 'INVG', 'RD', 'CR']
MSE: 2.4707997412930944
2013-04-18 ['skew', 'AM', 'LEV', 'OCFP', 'PMG', 'cashpr', 'QR', 'salecash', 'QRG']
MSE: 3.1476566645198756
2013-04-19 ['lagretn', 'EP', 'BVEG', 'CT', 'RD', 'RDsales', 'CRG']
MSE: 1.750884841826081
2013-04-22 ['idvol', 'coskew', 'PMG', 'cash', 'RDsales', 'QR']
MSE: 4.292764260288389
2013-04-23 ['size', 'betad', 'idvol', 'skew', 'turn', 'std_dvol', 'AM', 'CFP', 'BVEG', 'RDsales', 'QR']
MSE: 3.1710658821709057
2013-04-24 ['turn', 'retnmax', 'LM', 'momchg', 'BM', 'DP', 'BVEG', 'SG', 'SgINVg', 'ACCP', 'PA', 'cash', 'RD', 'CR', 'QR', 'salecash']
MSE: 3.351606083122748
2013-04-25 ['beta', 'volumed', 'std_dvol', 'retnmax', 'age', 'AM', 'INVchg', 'PMG', 'CT', 'cashpr', 'RD', 'saleinv', 'QRG']
MSE: 4.790360563735561
2013-04-26 ['size', 'turn', 'retnmax', 'illq', 'INVG', 'PA', 'cash', 'RD', 'salecash']
MSE: 4.628211756526541
2013-05-02 ['idvol', 'volumed', 'retnmax', 'sharechg', 'SG', 'PMG', 'CR']
MSE: 5.240087277472901
2013-05-03 ['idvol', 'skew', 'LM', 'EP', 'CFP', 'SP', 'cash']
MSE: 2.5405350578236368
2013-05-06 ['size', 'betad', 'skew', 'coskew', 'turn', 'retnmax', 'illq', 'momchg', 'AM', 'DP', 'SP', 'INVchg', 'SG', 'TAXchg', 'PA', 'cashpr', 'RD', 'RDsales', 'CR', 'CRG']
MSE: 3.0044574721981134
2013-05-07 ['idvol', 'skew', 'illq', 'LM', 'mom6', 'OCFP', 'AG', 'PMG', 'ACC', 'cash', 'CR', 'salecash']
MSE: 2.771803937426694
2013-05-08 ['turn', 'age', 'mom6', 'imom', 'AM', 'EP', 'BVEG', 'SG', 'CT', 'RD', 'QR', 'salecash']
MSE: 2.7455414666450255
2013-05-09 ['beta', 'idvol', 'turn', 'age', 'mom6', 'momchg', 'lagretn', 'CFP', 'SP', 'SgINVg', 'TAXchg', 'ROA', 'PA', 'cashpr', 'RDsales']
MSE: 4.6174483990466335
2013-05-10 ['size', 'betad', 'idvol', 'skew', 'illq', 'age', 'EP', 'CFP', 'DP', 'SP', 'INVG', 'PMG', 'cashpr', 'CFdebt', 'salecash']
MSE: 4.2289625201434475
2013-05-13 ['beta', 'volumed', 'retnmax', 'momchg', 'BVEG', 'INVG', 'INVchg', 'SgINVg', 'ROA', 'RD', 'RDsales']
MSE: 3.2821573771656642
2013-05-14 ['betad', 'turn', 'volumed', 'age', 'momchg', 'AM', 'DP', 'BVEG', 'SG', 'PMG']
MSE: 4.236639304204587
2013-05-15 ['turn', 'LM', 'mom6', 'lagretn', 'EP', 'DP', 'SgINVg', 'cash', 'RD', 'QR', 'salecash', 'QRG']
MSE: 2.308756438792809
2013-05-16 ['retnmax', 'SG', 'RD', 'RDsales', 'salecash']
MSE: 3.66247839778964
2013-05-17 ['idvol', 'total_vol', 'momchg', 'AM', 'CFP', 'AG', 'BVEG', 'INVG', 'INVchg', 'cashpr', 'RD', 'RDsales', 'salecash']
MSE: 3.4005687977375905
2013-05-20 ['idvol', 'turn', 'retnmax', 'INVG', 'SG', 'CRG']
MSE: 4.251271852207275
2013-05-21 ['idvol', 'volumed', 'retnmax', 'age', 'lagretn', 'EP', 'OCFP', 'INVchg', 'PMG', 'ROA', 'PA', 'cashpr', 'CR', 'CFdebt', 'QRG']
MSE: 3.7684960172846664
2013-05-22 ['volumed', 'EP', 'INVchg', 'PMG', 'ACC', 'CT', 'cash', 'RDsales', 'QR']
MSE: 4.730338570373537
2013-05-23 ['skew', 'coskew', 'retnmax', 'age', 'lagretn', 'AM', 'DP', 'SP', 'RD', 'salecash']
MSE: 3.981534716882582
2013-05-24 ['total_vol', 'skew', 'turn', 'lagretn', 'AM', 'CFP', 'LG', 'INVG', 'SG', 'RDsales', 'QR', 'CRG']
MSE: 3.3530280927986165
2013-05-27 ['size', 'idvol', 'volumed', 'mom6', 'imom', 'SG', 'CT', 'RD']
MSE: 4.061919240761789
2013-05-28 ['turn', 'retnmax', 'illq', 'LM', 'age', 'mom6', 'LEV', 'CFP', 'PA', 'CT', 'RD', 'QR', 'CFdebt', 'salecash']
MSE: 5.243846264700614
2013-05-29 ['betad', 'total_vol', 'illq', 'age', 'AM', 'INVG', 'RDsales']
MSE: 2.7711284059099497
2013-05-30 ['size', 'idvol', 'skew', 'turn', 'std_turn', 'volumed', 'lagretn', 'EP', 'INVchg', 'SG', 'ACC', 'ROA', 'CR']
MSE: 3.5887124438798774
2013-05-31 ['beta', 'skew', 'LM', 'mom6', 'CFP', 'INVG', 'RD', 'CFdebt', 'QRG']
MSE: 3.9045752522526107
2013-06-03 ['sharechg', 'AM', 'LEV', 'EP', 'DP', 'SP', 'SgINVg', 'TAXchg', 'PA', 'RD', 'RDsales', 'salecash']
MSE: 4.7864433498877705
2013-06-04 ['total_vol', 'volumed', 'age', 'lagretn', 'BVEG', 'CR']
MSE: 4.2228459858796015
2013-06-05 ['size', 'coskew', 'age', 'momchg', 'AM', 'EP', 'DP', 'LG', 'BVEG', 'PA', 'cash', 'QR']
MSE: 3.1121881665080253
2013-06-06 ['idskew', 'volumed', 'illq', 'mom6', 'momchg', 'SP', 'SG', 'PMG', 'CT', 'RD', 'CR']
MSE: 3.283001630711237
2013-06-07 ['betad', 'idvol', 'skew', 'retnmax', 'AM', 'EP', 'DP', 'BVEG', 'SgINVg', 'TAXchg', 'RD', 'QR', 'salecash']
MSE: 4.962202056166642
2013-06-13 ['retnmax', 'illq', 'LG', 'SG', 'cashpr', 'CR', 'CFdebt', 'salecash']
MSE: 5.353840468483478
2013-06-14 ['coskew', 'illq', 'mom6', 'AM', 'INVG', 'SgINVg', 'PMG', 'ACC', 'salecash', 'CRG']
MSE: 2.5061345638899355
2013-06-17 ['idvol', 'skew', 'coskew', 'turn', 'volumed', 'age', 'momchg', 'SP', 'BVEG', 'INVG', 'SG', 'PA', 'cash', 'CR', 'salecash']
MSE: 3.9994831436523994
2013-06-18 ['idvol', 'idskew', 'coskew', 'retnmax', 'age', 'lagretn', 'DP', 'LG', 'SgINVg', 'ROA', 'PA', 'CT', 'cashpr', 'RDsales']
MSE: 3.723980540254007
2013-06-19 ['beta', 'idvol', 'std_dvol', 'retnmax', 'age', 'lagretn', 'AM', 'OCFP', 'INVchg', 'SG', 'PA', 'cash', 'cashpr', 'RD']
MSE: 4.331620733088984
2013-06-20 ['skew', 'illq', 'sharechg', 'age', 'AM', 'LEV', 'SgINVg', 'CR', 'QR', 'salecash']
MSE: 2.856545736980471
2013-06-21 ['skew', 'volumed', 'age', 'BM', 'AM', 'CFP', 'BVEG', 'INVchg', 'PMG', 'PA', 'RDsales', 'CFdebt']
MSE: 4.2808016622111165
2013-06-24 ['size', 'turn', 'std_turn', 'LM', 'AM', 'CFP', 'DP', 'cashpr', 'CR', 'QRG']
MSE: 4.300456944090253
2013-06-25 ['turn', 'lagretn', 'DP', 'BVEG', 'INVG', 'ROA', 'RD']
MSE: 5.634483683169749
2013-06-26 ['idvol', 'skew', 'volumed', 'retnmax', 'AM', 'DP', 'LG', 'CT', 'QR', 'CFdebt']
MSE: 3.889013796976845
2013-06-27 ['beta', 'betad', 'skew', 'turn', 'std_turn', 'retnmax', 'mom6', 'DP', 'PMG']
MSE: 6.958856578714843
2013-06-28 ['turn', 'lagretn', 'AM', 'BVEG', 'SgINVg', 'cash', 'cashpr']
MSE: 4.021165719370021
2013-07-01 ['betad', 'skew', 'turn', 'age', 'mom6', 'CFP', 'CFdebt', 'salecash', 'saleinv']
MSE: 3.0490661274428366
2013-07-02 ['coskew', 'OCFP', 'AG', 'BVEG', 'INVG', 'PMG', 'CR']
MSE: 3.2681444178466332
2013-07-03 ['idvol', 'skew', 'volumed', 'lagretn', 'AM', 'CFP', 'OCFP', 'BVEG', 'INVchg', 'CR']
MSE: 4.458588490993542
2013-07-04 ['std_dvol', 'illq', 'EP', 'OCFP', 'BVEG', 'INVchg', 'PMG', 'ACCP', 'cash', 'RDsales', 'QR']
MSE: 4.5351058807630364
2013-07-05 ['beta', 'betad', 'lagretn', 'INVG', 'PA', 'RD', 'RDsales']
MSE: 4.107400239809365
2013-07-08 ['turn', 'illq', 'imom', 'AM', 'SP', 'QR', 'salecash']
MSE: 5.079964916060136
2013-07-09 ['skew', 'coskew', 'turn', 'retnmax', 'lagretn', 'EP', 'RDsales']
MSE: 4.48783743996065
2013-07-10 ['beta', 'idvol', 'turn', 'volumed', 'sharechg', 'imom', 'lagretn']
MSE: 2.91120609934653
2013-07-11 ['idskew', 'skew', 'lagretn', 'AG', 'TAXchg', 'CT', 'RDsales', 'QRG']
MSE: 2.476220330100001
2013-07-12 ['skew', 'turn', 'std_turn', 'mom6', 'LEV', 'SG']
MSE: 2.9211273543349447
2013-07-15 ['size', 'turn', 'AM', 'EP', 'CFP', 'OCFP', 'DP', 'BVEG', 'INVchg', 'TAXchg', 'ROE', 'ROA', 'CR', 'QRG']
MSE: 3.4050465131682772
2013-07-16 ['skew', 'std_turn', 'volumed', 'retnmax', 'age', 'SP', 'BVEG', 'INVG', 'INVchg', 'PA', 'RD', 'QR']
MSE: 3.7945392668841373
2013-07-17 ['skew', 'turn', 'LEV', 'EP', 'SgINVg', 'cash', 'RD', 'RDsales', 'salecash']
MSE: 5.203289917919129
2013-07-18 ['total_vol', 'coskew', 'volumed', 'retnmax', 'AM', 'INVchg', 'RDsales', 'CR']
MSE: 4.509474728031157
2013-07-19 ['turn', 'retnmax', 'imom', 'LEV', 'INVG', 'ACC', 'ROA', 'salecash']
MSE: 4.979871792755535
2013-07-22 ['idvol', 'coskew', 'turn', 'age', 'AM', 'CFP', 'cashpr']
MSE: 4.324260298617077
2013-07-23 ['momchg', 'AM', 'SP', 'SG', 'TAXchg', 'ACC', 'cash', 'CR', 'CFdebt', 'CRG']
MSE: 2.955548999586859
2013-07-24 ['size', 'betad', 'idvol', 'turn', 'retnmax', 'imom', 'LEV', 'BVEG', 'SG', 'TAXchg', 'ROA']
MSE: 3.9297805684821476
2013-07-25 ['lagretn', 'AM', 'EP', 'PMG']
MSE: 6.005756235116204
2013-07-26 ['idvol', 'total_vol', 'coskew', 'volumed', 'retnmax', 'CFP', 'BVEG', 'INVchg', 'SG', 'TAXchg', 'RD', 'CR', 'salecash', 'saleinv']
MSE: 3.652047181874535
2013-07-29 ['size', 'idvol', 'turn', 'LEV', 'OCFP', 'SgINVg', 'PA', 'RD', 'CFdebt']
MSE: 4.084588835171696
2013-07-30 ['idvol', 'skew', 'turn', 'volumed', 'age', 'mom6', 'imom', 'lagretn', 'CFP', 'BVEG', 'SG', 'PMG', 'CT', 'cashpr', 'RD', 'QR']
MSE: 5.427820478672383
2013-07-31 ['size', 'idvol', 'skew', 'turn', 'std_turn', 'volumed', 'retnmax', 'LM', 'lagretn', 'OCFP', 'INVG', 'INVchg', 'SgINVg', 'PMG', 'CT', 'CR']
MSE: 4.857858414184512
2013-08-01 ['skew', 'std_turn', 'age', 'EP', 'CFP', 'SG', 'ROA', 'RDsales', 'QR', 'CFdebt']
MSE: 2.013532319730573
2013-08-02 ['turn', 'sharechg', 'BVEG', 'INVG', 'INVchg', 'SG', 'cash', 'RD']
MSE: 3.5316282738391513
2013-08-05 ['skew', 'retnmax', 'illq', 'age', 'AM', 'DP', 'SP', 'ROA', 'cashpr']
MSE: 3.698425872146903
2013-08-06 ['volumed', 'std_dvol', 'retnmax', 'mom6', 'lagretn', 'BVEG', 'INVG', 'TAXchg', 'ACCP', 'ROA', 'PA', 'CT', 'cash', 'cashpr', 'RDsales', 'CFdebt', 'QRG']
MSE: 2.8973094805224786
2013-08-07 ['idvol', 'age', 'lagretn', 'EP', 'CFP', 'INVchg', 'ACCP', 'salecash']
MSE: 3.593317809201272
2013-08-08 ['idvol', 'lagretn', 'AM', 'CFP', 'SG', 'PMG', 'ROA', 'CR', 'salecash']
MSE: 3.351461269519372
2013-08-09 ['coskew', 'mom6', 'OCFP', 'INVG', 'ROA', 'RDsales']
MSE: 4.0261812796161855
2013-08-12 ['betad', 'std_turn', 'EP', 'LG', 'INVchg', 'PMG', 'CT', 'RDsales', 'CR', 'salecash']
MSE: 2.9240852956829206
2013-08-13 ['size', 'idvol', 'retnmax', 'age', 'momchg', 'lagretn', 'AM', 'AG', 'BVEG', 'CRG']
MSE: 2.769309375178218
2013-08-14 ['beta', 'skew', 'std_turn', 'imom', 'lagretn', 'CFP', 'QR']
MSE: 3.1386489115048763
2013-08-15 ['coskew', 'illq', 'age', 'mom6', 'imom', 'OCFP', 'TAXchg', 'CT', 'cash', 'RD', 'CFdebt', 'salecash']
MSE: 3.1872869055781012
2013-08-16 ['sharechg', 'lagretn', 'LEV', 'EP', 'cash']
MSE: 4.331717368162058
2013-08-19 ['idvol', 'retnmax', 'lagretn', 'AM', 'EP', 'OCFP', 'LG', 'INVchg', 'TAXchg', 'ACC', 'ROA', 'saleinv']
MSE: 3.1894871655441053
2013-08-20 ['idvol', 'skew', 'illq', 'age', 'momchg', 'AM', 'EP', 'cash', 'RDsales', 'QR']
MSE: 3.64489260107602
2013-08-21 ['idskew', 'coskew', 'turn', 'sharechg', 'imom', 'EP', 'CFP', 'SG', 'CT', 'RD', 'salecash']
MSE: 3.133218730832844
2013-08-22 ['skew', 'turn', 'DP', 'BVEG', 'INVchg', 'PA', 'cash', 'RD', 'RDsales', 'CR']
MSE: 2.9998075331609875
2013-08-23 ['total_vol', 'age', 'imom', 'LEV', 'EP', 'INVchg', 'CFdebt']
MSE: 4.128531566187385
2013-08-26 ['beta', 'std_turn', 'age', 'momchg', 'AM', 'SG', 'cash', 'CR', 'QR', 'salecash']
MSE: 3.1464418828179266
2013-08-27 ['size', 'beta', 'skew', 'turn', 'std_dvol', 'AM', 'CFP', 'SG', 'PMG', 'CT', 'cashpr', 'RD', 'QR']
MSE: 3.451404811937106
2013-08-28 ['size', 'idvol', 'turn', 'illq', 'LEV', 'EP', 'PMG', 'cash', 'salecash']
MSE: 5.279398156725779
2013-08-29 ['beta', 'idvol', 'skew', 'turn', 'age', 'imom', 'LEV', 'INVchg', 'TAXchg', 'cash', 'RDsales', 'QR']
MSE: 5.070080414799744
2013-08-30 ['size', 'idvol', 'BVEG', 'INVG', 'PMG', 'RD', 'salecash']
MSE: 6.2538219549019525
2013-09-02 ['age', 'mom6', 'TAXchg', 'PA', 'RD', 'salecash']
MSE: 6.5811019041794205
2013-09-03 ['beta', 'skew', 'turn', 'mom6', 'PMG', 'ROA', 'CT', 'RDsales']
MSE: 4.43396936602181
2013-09-04 ['size', 'turn', 'sharechg', 'age', 'LG']
MSE: 4.650476080237525
2013-09-05 ['idvol', 'illq', 'age', 'imom', 'OCFP', 'SP', 'INVG', 'SG', 'TAXchg', 'PA', 'cash', 'RD']
MSE: 4.547262023813774
2013-09-06 ['idskew', 'skew', 'std_dvol', 'mom6', 'CFP', 'ACCP']
MSE: 4.244393336537197
2013-09-09 ['size', 'beta', 'betad', 'idvol', 'volumed', 'age', 'imom', 'DP', 'AG', 'INVG', 'PMG', 'salecash', 'saleinv', 'CRG']
MSE: 4.132922887031511
2013-09-10 ['skew', 'turn', 'std_turn', 'illq', 'AM', 'EP', 'TAXchg', 'RD']
MSE: 4.124117314719291
2013-09-11 ['turn', 'std_turn', 'age', 'mom6', 'BM', 'BVEG', 'SgINVg', 'CR', 'CFdebt']
MSE: 5.6085128303163545
2013-09-12 ['skew', 'illq', 'INVG', 'SG', 'RD']
MSE: 3.4850675051252296
2013-09-13 ['LEV', 'CFP', 'SG', 'SgINVg', 'PA', 'CT', 'cash', 'RDsales', 'CR', 'QRG']
MSE: 4.029990953218458
2013-09-16 ['betad', 'skew', 'turn', 'retnmax', 'imom', 'lagretn', 'EP', 'DP', 'INVG', 'SG', 'ROA', 'QR', 'CFdebt', 'salecash']
MSE: 3.801293360185082
2013-09-17 ['betad', 'illq', 'LEV', 'CFP', 'BVEG', 'cash', 'RDsales', 'salecash']
MSE: 4.813227650270847
2013-09-18 ['betad', 'idvol', 'turn', 'std_turn', 'momchg', 'AM', 'CFP', 'INVchg', 'ACC', 'CT', 'CFdebt', 'salecash', 'saleinv']
MSE: 3.5081704961882854
2013-09-23 ['mom6', 'PMG', 'TAXchg', 'PA', 'cash']
MSE: 2.7720720592228916
2013-09-24 ['total_vol', 'retnmax', 'illq', 'AM', 'SG', 'CT', 'cash', 'RDsales']
MSE: 4.876084895763892
2013-09-25 ['idskew', 'turn', 'std_turn', 'retnmax', 'illq', 'LEV', 'OCFP', 'DP', 'SP', 'CT', 'RD', 'CFdebt', 'salecash']
MSE: 5.0340127061687925
2013-09-26 ['beta', 'idvol', 'turn', 'age', 'SP', 'INVG', 'cashpr', 'QR', 'CRG']
MSE: 5.773339755545188
2013-09-27 ['size', 'idskew', 'turn', 'age', 'LEV', 'INVG', 'ROA', 'CT', 'RD', 'CR']
MSE: 4.931646845338142
2013-09-30 ['total_vol', 'turn', 'retnmax', 'sharechg', 'AM', 'CFP', 'INVchg', 'ROA', 'PA', 'CR']
MSE: 2.853335134669498
2013-10-08 ['idvol', 'retnmax', 'AM', 'OCFP', 'INVG', 'TAXchg', 'CT', 'RDsales', 'CR']
MSE: 3.8198359428496502
2013-10-09 ['turn', 'volumed', 'lagretn', 'CFP', 'LG', 'SG', 'PMG', 'ROA', 'CT', 'RDsales', 'QRG']
MSE: 3.1539746575072862
2013-10-10 ['idvol', 'turn', 'illq', 'age', 'lagretn', 'AG', 'TAXchg', 'cash', 'cashpr', 'RDsales', 'CR', 'CRG']
MSE: 6.029162821566159
2013-10-11 ['beta', 'idskew', 'turn', 'volumed', 'age', 'AM', 'INVchg', 'SG', 'PMG', 'CT', 'RD', 'CR']
MSE: 4.083926097141506
2013-10-14 ['coskew', 'turn', 'CFP', 'DP', 'SG', 'TAXchg', 'ROE', 'salecash']
MSE: 5.358110375884738
2013-10-15 ['beta', 'idvol', 'volumed', 'retnmax', 'LM', 'LEV', 'EP', 'CFP', 'SP', 'LG', 'INVG', 'SG']
MSE: 4.379737994755032
2013-10-16 ['skew', 'turn', 'mom6', 'EP', 'SG', 'PA', 'RDsales', 'CFdebt']
MSE: 5.418096078492006
2013-10-17 ['idvol', 'mom6', 'imom', 'AG', 'PMG', 'TAXchg', 'cash', 'CR', 'CRG']
MSE: 4.744623539638933
2013-10-18 ['turn', 'age', 'AM', 'ROA', 'RD', 'QRG']
MSE: 3.8896567621758504
2013-10-21 ['betad', 'total_vol', 'idskew', 'lagretn', 'AM', 'cash']
MSE: 2.7790111037241867
2013-10-22 ['idvol', 'momchg', 'imom', 'AM', 'EP', 'DP', 'SP', 'INVG', 'INVchg', 'CT', 'cash', 'RD', 'RDsales']
MSE: 6.093988664010849
2013-10-23 ['idvol', 'turn', 'retnmax', 'mom6', 'imom', 'lagretn', 'BM', 'AM', 'LEV', 'EP', 'CFP', 'DP', 'LG', 'BVEG', 'SgINVg', 'TAXchg', 'PA', 'cashpr', 'RD', 'RDsales', 'QR', 'QRG']
MSE: 5.786239798513934
2013-10-24 ['betad', 'idvol', 'skew', 'coskew', 'turn', 'illq', 'mom6', 'imom', 'AM', 'INVG', 'CT', 'RD', 'RDsales']
MSE: 5.030191474831782
2013-10-25 ['idskew', 'std_turn', 'mom6', 'AM', 'CFP', 'OCFP', 'AG', 'BVEG', 'INVG', 'CR', 'salecash', 'QRG']
MSE: 4.639727451186666
2013-10-28 ['skew', 'coskew', 'SP', 'ROA', 'PA', 'RD', 'RDsales', 'CR', 'saleinv']
MSE: 6.330372509834726
2013-10-29 ['skew', 'retnmax', 'sharechg', 'age', 'momchg', 'imom', 'AM', 'LEV', 'CFP', 'AG', 'LG', 'BVEG', 'INVG', 'ROA', 'cashpr', 'RD', 'salecash']
MSE: 7.175615556082851
2013-10-30 ['age', 'momchg', 'lagretn', 'AM', 'INVchg', 'CT', 'cash', 'CR', 'CRG']
MSE: 3.0270851338446665
2013-10-31 ['turn', 'mom6', 'imom', 'AM', 'ACCP', 'PA', 'RD', 'RDsales', 'CR']
MSE: 5.288040276830776
2013-11-01 ['coskew', 'turn', 'age', 'INVchg', 'SG', 'CT', 'cash', 'RD', 'RDsales', 'QR', 'CRG', 'QRG']
MSE: 4.1196453322319
2013-11-04 ['size', 'skew', 'std_turn', 'illq', 'age', 'mom6', 'momchg', 'AM', 'OCFP', 'BVEG', 'cash', 'RDsales', 'CFdebt']
MSE: 3.0966750440768926
2013-11-05 ['total_vol', 'skew', 'std_turn', 'age', 'mom6', 'CFP', 'INVchg', 'SG', 'RDsales', 'salecash', 'CRG']
MSE: 2.662112847030313
2013-11-06 ['idvol', 'turn', 'illq', 'LEV', 'EP', 'OCFP', 'BVEG', 'INVchg', 'cash', 'RD', 'RDsales', 'CR', 'salecash']
MSE: 2.990025202465042
2013-11-07 ['size', 'beta', 'std_turn', 'SG', 'ROA', 'QRG']
MSE: 3.711989594519554
2013-11-08 ['betad', 'idvol', 'skew', 'volumed', 'std_dvol', 'lagretn', 'AM', 'DP', 'INVG', 'PMG', 'CR']
MSE: 4.592895702838832
2013-11-11 ['size', 'turn', 'INVchg', 'ROA', 'CT', 'QR', 'saleinv']
MSE: 4.454780865729851
2013-11-12 ['idvol', 'skew', 'std_dvol', 'CFP', 'OCFP', 'DP', 'SP', 'AG', 'INVchg', 'PMG', 'PA', 'cash', 'cashpr', 'RD', 'QR', 'salecash', 'QRG']
MSE: 3.131677788337437
2013-11-13 ['coskew', 'turn', 'std_turn', 'LM', 'age', 'mom6', 'lagretn', 'LEV', 'CFP', 'OCFP', 'DP', 'BVEG', 'cash', 'RDsales', 'QR']
MSE: 2.767840492935834
2013-11-14 ['turn', 'retnmax', 'age', 'lagretn', 'AM', 'SP', 'AG', 'SG', 'PMG', 'CR', 'QR', 'CRG']
MSE: 3.7624903972143158
2013-11-15 ['idvol', 'coskew', 'turn', 'volumed', 'LM', 'lagretn', 'AM', 'EP', 'LG', 'INVG', 'SG', 'PMG', 'PA', 'CT', 'CR', 'CFdebt', 'QRG']
MSE: 2.234910451900615
2013-11-18 ['std_turn', 'volumed', 'EP', 'DP']
MSE: 3.286022743901893
2013-11-19 ['betad', 'total_vol', 'volumed', 'AM', 'CFP', 'PMG', 'ROA', 'QR', 'CFdebt', 'salecash']
MSE: 3.050946341562079
2013-11-20 ['retnmax', 'LM', 'age', 'ROA', 'cash', 'RD']
MSE: 3.334620743562507
2013-11-21 ['idvol', 'imom', 'AM', 'OCFP', 'BVEG', 'INVchg', 'cashpr', 'RD', 'CR', 'CRG']
MSE: 3.8894040528171714
2013-11-22 ['skew', 'turn', 'age', 'EP', 'cash', 'RDsales']
MSE: 4.045378809032109
2013-11-25 ['size', 'idvol', 'std_turn', 'volumed', 'age', 'mom6', 'CFP', 'OCFP', 'DP', 'PMG', 'TAXchg', 'ROE', 'cashpr', 'RD', 'QR', 'salecash', 'saleinv']
MSE: 4.3597700589470145
2013-11-26 ['beta', 'skew', 'illq', 'LM', 'AM', 'EP', 'PMG', 'RDsales', 'QR']
MSE: 4.716572482662422
2013-11-27 ['illq', 'sharechg', 'age', 'imom', 'SG', 'ROA', 'CR', 'CRG']
MSE: 2.688063586386144
2013-11-28 ['skew', 'illq', 'age', 'imom', 'SgINVg']
MSE: 2.995623491216169
2013-11-29 ['beta', 'imom', 'lagretn', 'AM', 'CFP', 'INVG', 'CFdebt', 'salecash']
MSE: 3.071047354868936
2013-12-02 ['idvol', 'retnmax', 'lagretn', 'AM', 'TAXchg', 'CT', 'RDsales', 'CFdebt', 'salecash']
MSE: 5.16301029674257
2013-12-03 ['beta', 'skew', 'lagretn', 'AM', 'INVG', 'SgINVg', 'ROA', 'CR', 'CRG', 'QRG']
MSE: 3.6562350393532226
2013-12-04 ['turn', 'std_turn', 'mom6', 'INVG', 'INVchg', 'SgINVg', 'cash', 'CR']
MSE: 3.429245762918336
2013-12-05 ['EP', 'CFP', 'SG', 'CFdebt', 'salecash']
MSE: 3.2732258037626787
2013-12-06 ['idskew', 'coskew', 'volumed', 'age', 'AM', 'LEV', 'EP', 'INVG', 'PMG', 'ROA', 'cash', 'RD', 'QR', 'CFdebt']
MSE: 3.0892243267207697
2013-12-09 ['beta', 'coskew', 'illq', 'age', 'INVchg', 'ACCP', 'cash', 'cashpr', 'QRG']
MSE: 2.909975588127043
2013-12-10 ['coskew', 'turn', 'imom', 'lagretn', 'EP', 'CFP', 'DP', 'PMG', 'CT', 'RD', 'QR', 'CFdebt']
MSE: 3.429970656413309
2013-12-11 ['idvol', 'skew', 'LM', 'AM', 'LG', 'SgINVg', 'RD', 'RDsales', 'QR']
MSE: 3.899990774640407
2013-12-12 ['size', 'beta', 'idvol', 'age', 'AM', 'CFP', 'OCFP', 'INVG', 'INVchg', 'SG', 'CR', 'CRG']
MSE: 3.2466069131941597
2013-12-13 ['retnmax', 'LM', 'sharechg', 'mom6', 'lagretn', 'AM', 'LEV', 'EP', 'CFP', 'DP', 'SP', 'BVEG', 'INVG', 'ACC', 'salecash', 'saleinv', 'QRG']
MSE: 2.7994189887519934
2013-12-16 ['size', 'idskew', 'turn', 'LM', 'AM', 'EP', 'CFP', 'BVEG', 'SG', 'PMG', 'RDsales']
MSE: 4.5553817848811144
2013-12-17 ['beta', 'turn', 'std_turn', 'volumed', 'retnmax', 'mom6', 'AM', 'SG', 'PMG', 'RD']
MSE: 3.5561130332117106
2013-12-18 ['turn', 'lagretn', 'LEV', 'PA', 'CT', 'CR', 'salecash']
MSE: 2.474691764611882
2013-12-19 ['size', 'idvol', 'skew', 'coskew', 'turn', 'LM', 'BM', 'LG', 'INVchg', 'SG', 'PMG', 'CT', 'CR']
MSE: 2.5083141184554707
2013-12-20 ['betad', 'idvol', 'skew', 'coskew', 'std_turn', 'LEV', 'OCFP', 'TAXchg', 'CT', 'RD', 'salecash']
MSE: 3.7529575553876904
2013-12-23 ['turn', 'retnmax', 'AM', 'LEV', 'CFP', 'DP', 'CR']
MSE: 5.605109218355425
2013-12-24 ['coskew', 'turn', 'age', 'SG', 'QR', 'salecash']
MSE: 2.609969578928021
2013-12-25 ['mom6', 'lagretn', 'INVG', 'TAXchg', 'cash', 'CFdebt', 'salecash']
MSE: 2.9110866706614567
2013-12-26 ['idvol', 'skew', 'turn', 'sharechg', 'AM', 'PMG', 'ACCP', 'CT', 'RDsales', 'CR', 'salecash']
MSE: 4.76824086903283
2013-12-27 ['lagretn', 'LEV', 'INVG', 'RDsales', 'CFdebt']
MSE: 2.4008224944342778
2013-12-30 ['skew', 'turn', 'retnmax', 'mom6', 'momchg', 'INVG', 'CR', 'QRG']
MSE: 3.3727608487381446
2013-12-31 ['volumed', 'mom6', 'lagretn', 'DP', 'INVchg', 'SG', 'TAXchg', 'RD', 'RDsales', 'CFdebt', 'salecash']
MSE: 2.764648018725637

linear_remove['removed'].mean()

10.084033613445378

linear_remove['err'].mean()

3.808543809919859

毕设（五）去除低重要性因子