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.drop(columns=['ts_code', 'yield'] + 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

股票板块数据

获取数据

股票板块数据在同花顺软件中最全，同样可以在爱问财上查到，但问题是非会员只能导出100条数据，因此必须写爬虫脚本下载所有股票板块数据

http://www.iwencai.com/unifiedwap/result?querytype=&issugs&sign=1618471686432&w=a股市值>0元

然而使用以下python爬虫脚本也被拦截了，可能有反爬虫机制

import time

import requests
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.support.select import Select

import pandas as pd

url = 'http://www.iwencai.com/unifiedwap/result?querytype=&issugs&sign=1618471686432&w=a%E8%82%A1%E5%B8%82%E5%80%BC%3E0%E5%85%83'

chrome_options = webdriver.ChromeOptions()
driver = webdriver.Chrome(chrome_options=chrome_options)

driver.get(url)
# /html/body/p[1]/a

df = pd.DataFrame(columns=['ts_code', 'sector'])

i = 1
while True:
    try:
        ts_code = driver.find_element_by_xpath(
            '//*[@id="iwc-table-container"]/div[4]/div[1]/div[2]/table/tbody/tr[%d]/td[4]/div' % i).text
        sector = driver.find_element_by_xpath(
            '//*[@id="iwc-table-container"]/div[4]/div[1]/div[2]/table/tbody/tr[%d]/td[9]/div' % i).text
        df.append(ts_code, sector)
        i += 1
    except:
        break

i = 1
while True:
    page = driver.find_element_by_xpath('//*[@id="iwcTableWrapper"]/div[2]/div[1]/ul/li[9]/a')
    if page.text == '下页':
        page.click()
        break

print(df)

只好一页页将数据复制到文本，然后数据处理，数据源见./data/sector.txt

由于行业是按照大-中-小类进行区分的（例如：信息服务-传媒-营销服务），因此每只股票有三个行业数据

file =  open('data/sector.txt', encoding='utf-8')
df = pd.DataFrame(columns=['ts_code', 'name', 'sector1', 'sector2', 'sector3'])

i = 1  # 股票index
j = 0  # 行数 
lines = file.readlines()
while j<len(lines):
    if lines[j].strip() == str(i):
        ts_code = lines[j+1].strip()
        name = lines[j+2].strip()
        sector1, sector2, sector3 = lines[j+3].strip().split('-')
        print(ts_code, name, sector1, sector2, sector3)
        df = df.append({'ts_code':ts_code, 'name':name, 'sector1':sector1, 'sector2':sector2, 'sector3':sector3}, ignore_index=True)
        j+=3
        i+=1
    j +=1

600891 退市秋林 综合 综合 综合Ⅲ
002071 长城退 信息服务 传媒 营销服务
600701 退市工新 综合 综合 综合Ⅲ
603157 *ST拉夏 纺织服装 服装家纺 女装
...
300362 天翔环境 机械设备 专用设备 环保设备
600485 *ST信威 信息设备 通信设备 通信配套服务
600614 *ST鹏起 有色金属 新材料 金属新材料Ⅲ
600634 *ST富控 信息服务 传媒 其他传媒
002260 *ST德奥 家用电器 白色家电 小家电
002359 *ST北讯 信息设备 通信设备 通信配套服务
002711 *ST欧浦 交通运输 物流 物流Ⅲ

df

	ts_code	name	sector1	sector2	sector3
0	600891	退市秋林	综合	综合	综合Ⅲ
1	002071	长城退	信息服务	传媒	营销服务
2	600701	退市工新	综合	综合	综合Ⅲ
3	603157	*ST拉夏	纺织服装	服装家纺	女装
4	688215	瑞晟智能	机械设备	专用设备	其它专用机械
...	...	...	...	...	...
4254	600614	*ST鹏起	有色金属	新材料	金属新材料Ⅲ
4255	600634	*ST富控	信息服务	传媒	其他传媒
4256	002260	*ST德奥	家用电器	白色家电	小家电
4257	002359	*ST北讯	信息设备	通信设备	通信配套服务
4258	002711	*ST欧浦	交通运输	物流	物流Ⅲ

4259 rows × 5 columns

print(len(set(df['sector1'])), len(set(df['sector2'])), len(set(df['sector3'])))

24 66 200

板块可视化

class Tree:
    def __init__(self, list_):
        self.name = list_[0]
        self.children = set()
        self.value=1
        if isinstance(list_, list) and len(list_) > 1:
            self.children.add(Tree(list_[1:]))
    
    def print(self, tab):
        print('\t'*tab+self.name)
        for child in self.children:
            child.print(tab+1)

    def get_child(self, name):
        for child in self.children:
            if child.name == name:
                return child
        return None
            
    def update(self, list_):
        # 输入该节点后面的数组
        # print(list_)
        if isinstance(list_, list):
            if len(list_) == 0 :
                self.value+=1   # 计数+1
                return
            
            child = self.get_child(list_[0])
            if child:
                child.update(list_[1:])
            else:
                self.children.add(Tree(list_))
                
                
    def to_json(self):
        if len(self.children)>0:
            s = '{"name":"%s","children":[' % (self.name) 
            children = ','.join([child.to_json() for child in self.children])
            return s + children + ']}'
        return '{"name":"%s","value":%d}' % (self.name, self.value)

base = Tree(['base'])
for index, row in df.iterrows():
    list_ = list(row)[2:]
    print(index, list_)  # 输出每行的索引值

    base.update(list_)

0 ['综合', '综合', '综合Ⅲ']
1 ['信息服务', '传媒', '营销服务']
2 ['综合', '综合', '综合Ⅲ']
3 ['纺织服装', '服装家纺', '女装']
4 ['机械设备', '专用设备', '其它专用机械']
5 ['机械设备', '专用设备', '其它专用机械']
6 ['医药生物', '医疗器械服务', '医疗器械Ⅲ']
7 ['公用事业', '环保工程', '环保工程及服务']
8 ['医药生物', '医疗器械服务', '医疗器械Ⅲ']
9 ['有色金属', '新材料', '金属新材料Ⅲ']
10 ['公用事业', '环保工程', '环保工程及服务']
11 ['交运设备', '汽车零部件', '汽车零部件Ⅲ']
12 ['化工', '化学制品', '其他化学制品']
13 ['信息设备', '通信设备', '通信传输设备']
14 ['信息服务', '计算机应用', '软件开发及服务']
15 ['信息设备', '通信设备', '通信传输设备']
16 ['化工', '化学制品', '涂料油漆油墨制造']
17 ['机械设备', '专用设备', '其它专用机械']
18 ['机械设备', '专用设备', '环保设备']
19 ['公用事业', '环保工程', '环保工程及服务']
20 ['机械设备', '专用设备', '其它专用机械']
21 ['机械设备', '仪器仪表', '仪器仪表']
22 ['信息服务', '计算机应用', '软件开发及服务']
23 ['机械设备', '通用设备', '机床工具']
24 ['机械设备', '专用设备', '其它专用机械']
25 ['电子', '电子制造', '电子零部件制造']
26 ['化工', '化学制品', '其他化学制品']
27 ['机械设备', '专用设备', '环保设备']
28 ['化工', '化工合成材料', '涤纶']
...
4253 ['信息设备', '通信设备', '通信配套服务']
4254 ['有色金属', '新材料', '金属新材料Ⅲ']
4255 ['信息服务', '传媒', '其他传媒']
4256 ['家用电器', '白色家电', '小家电']
4257 ['信息设备', '通信设备', '通信配套服务']
4258 ['交通运输', '物流', '物流Ⅲ']

base.print(0)

base
	轻工制造
		造纸
			造纸Ⅲ
		包装印刷
			包装印刷Ⅲ
		家用轻工
			其他家用轻工
			珠宝首饰
			文娱用品
			家具
	交运设备
		汽车零部件
			汽车零部件Ⅲ
		非汽车交运
			其他交运设备
			铁路设备
		汽车整车
			商用载客车
			乘用车
			商用载货车
		交运设备服务
			汽车服务
	...

base.to_json()

'{"name":"base","children":[{"name":"轻工制造","children":[{"name":"造纸","children":[{"name":"造纸Ⅲ","value":24}]},{"name":"包装印刷","children":[{"name":"包装印刷Ⅲ","value":40}]},{"name":"家用轻工","children":[{"name":"其他家用轻工","value":17},{"name":"珠宝首饰","value":12},{"name":"文娱用品","value":12},{"name":"家具","value":30}]}]},{"name":"交运设备","children":[{"name":"汽车零部件","children":[{"name":"汽车零部件Ⅲ","value":150}]},{"name":"非汽车交运","children":[{"name":"其他交运设备","value":11},{"name":"铁路设备","value":22}]},{"name":"汽车整车","children":[{"name":"商用载客车","value":6},{"name":"乘用车","value":10},{"name":"商用载货车","value":7}]},{"name":"交运设备服务","children":[{"name":"汽车服务","value":13}]}]},{"name":"农林牧渔","children":[{"name":"农产品加工","children":[{"name":"果蔬加工","value":4},{"name":"其他农产品加工","value":9},{"name":"饲料Ⅲ","value":16},{"name":"粮油加工","value":4}]},{"name":"农业服务","children":[{"name":"动物保健","value":11},{"name":"农业综合Ⅲ","value":1}]},{"name":"种植业与林业","children":[{"name":"种子生产","value":8},{"name":"粮食种植","value":5},{"name":"林业Ⅲ","value":4},{"name":"其他种植业","value":5}]},{"name":"养殖业","children":[{"name":"水产养殖","value":7},{"name":"畜禽养殖","value":14},{"name":"海洋捕捞","value":2}]}]},{"name":"家用电器","children":[{"name":"白色家电","children":[{"name":"洗衣机","value":1},{"name":"冰箱","value":5},{"name":"其他白色家电","value":20},{"name":"小家电","value":29},{"name":"空调","value":3}]},{"name":"视听器材","children":[{"name":"其它视听器材","value":5},{"name":"彩电","value":6}]}]},{"name":"餐饮旅游","children":[{"name":"酒店及餐饮","children":[{"name":"酒店Ⅲ","value":5},{"name":"餐饮Ⅲ","value":4}]},{"name":"景点及旅游","children":[{"name":"自然景点","value":9},{"name":"人工景点","value":4},{"name":"旅游综合Ⅲ","value":12}]}]},{"name":"信息设备","children":[{"name":"计算机设备","children":[{"name":"计算机设备Ⅲ","value":51}]},{"name":"通信设备","children":[{"name":"终端设备","value":35},{"name":"通信传输设备","value":45},{"name":"通信配套服务","value":29}]}]},{"name":"黑色金属","children":[{"name":"钢铁","children":[{"name":"普钢","value":22},{"name":"特钢","value":14}]}]},{"name":"商业贸易","children":[{"name":"贸易","children":[{"name":"贸易Ⅲ","value":29}]},{"name":"零售","children":[{"name":"商业物业经营","value":15},{"name":"专业连锁","value":14},{"name":"百货零售","value":50}]}]},{"name":"房地产","children":[{"name":"园区开发","children":[{"name":"园区开发Ⅲ","value":11}]},{"name":"房地产开发","children":[{"name":"房地产开发Ⅲ","value":114}]}]},{"name":"有色金属","children":[{"name":"有色冶炼加工","children":[{"name":"铅锌","value":14},{"name":"铝","value":25},{"name":"黄金","value":11},{"name":"铜","value":14},{"name":"小金属","value":28}]},{"name":"新材料","children":[{"name":"非金属新材料","value":16},{"name":"金属新材料Ⅲ","value":18},{"name":"磁性材料","value":11}]}]},{"name":"化工","children":[{"name":"化工合成材料","children":[{"name":"其他橡胶制品","value":8},{"name":"其他塑料制品","value":23},{"name":"改性塑料","value":12},{"name":"氨纶","value":1},{"name":"维纶","value":1},{"name":"轮胎","value":9},{"name":"合成革","value":3},{"name":"粘胶","value":3},{"name":"涤纶","value":14},{"name":"炭黑","value":4},{"name":"其他纤维","value":6}]},{"name":"化工新材料","children":[{"name":"聚氨酯","value":11},{"name":"玻纤","value":7}]},{"name":"基础化学","children":[{"name":"石油加工","value":15},{"name":"纯碱","value":6},{"name":"无机盐","value":8},{"name":"其他化学原料","value":9},{"name":"氯碱","value":16},{"name":"石油贸易","value":4}]},{"name":"化学制品","children":[{"name":"复合肥","value":8},{"name":"氟化工及制冷剂","value":5},{"name":"钾肥","value":4},{"name":"涂料油漆油墨制造","value":17},{"name":"其他化学制品","value":122},{"name":"民爆用品","value":13},{"name":"磷化工及磷酸盐","value":4},{"name":"磷肥","value":2},{"name":"农药","value":25},{"name":"纺织化学用品","value":9},{"name":"氮肥","value":5},{"name":"日用化学产品","value":12}]}]},{"name":"建筑材料","children":[{"name":"建筑装饰","children":[{"name":"装饰园林","value":41},{"name":"专业工程","value":30},{"name":"基础建设","value":36},{"name":"房屋建设","value":20}]},{"name":"建筑材料","children":[{"name":"水泥制造","value":18},{"name":"管材","value":10},{"name":"玻璃制造","value":7},{"name":"耐火材料","value":5},{"name":"其他建材","value":31}]}]},{"name":"采掘","children":[{"name":"采掘服务","children":[{"name":"油气钻采服务","value":14},{"name":"其他采掘服务","value":1}]},{"name":"煤炭开采加工","children":[{"name":"焦炭加工","value":7},{"name":"煤炭开采Ⅲ","value":28}]},{"name":"石油矿业开采","children":[{"name":"石油开采Ⅲ","value":5},{"name":"其他采掘Ⅲ","value":7}]}]},{"name":"金融服务","children":[{"name":"银行","children":[{"name":"银行Ⅲ","value":38}]},{"name":"证券","children":[{"name":"证券Ⅲ","value":48}]},{"name":"保险及其他","children":[{"name":"多元金融","value":31},{"name":"保险Ⅲ","value":7}]}]},{"name":"信息服务","children":[{"name":"通信服务","children":[{"name":"通信运营Ⅲ","value":6},{"name":"有线电视网络","value":11},{"name":"互联网信息服务","value":17},{"name":"其他网络服务","value":1}]},{"name":"传媒","children":[{"name":"平面媒体","value":22},{"name":"营销服务","value":38},{"name":"其他传媒","value":62},{"name":"影视动漫","value":23}]},{"name":"计算机应用","children":[{"name":"软件开发及服务","value":221}]}]},{"name":"医药生物","children":[{"name":"医疗器械服务","children":[{"name":"医疗服务Ⅲ","value":28},{"name":"医疗器械Ⅲ","value":89}]},{"name":"医药商业","children":[{"name":"医药商业Ⅲ","value":26}]},{"name":"中药","children":[{"name":"中药Ⅲ","value":68}]},{"name":"化学制药","children":[{"name":"化学制剂","value":88},{"name":"化学原料药","value":36}]},{"name":"生物制品","children":[{"name":"生物制品Ⅲ","value":45}]}]},{"name":"国防军工","children":[{"name":"国防军工","children":[{"name":"航空装备","value":36},{"name":"航天装备","value":16},{"name":"地面兵装","value":19},{"name":"船舶制造","value":11}]}]},{"name":"综合","children":[{"name":"综合","children":[{"name":"综合Ⅲ","value":33}]}]},{"name":"电子","children":[{"name":"光学光电子","children":[{"name":"LED","value":33},{"name":"显示器件Ⅲ","value":37},{"name":"光学元件","value":16}]},{"name":"其他电子","children":[{"name":"其他电子Ⅲ","value":33}]},{"name":"半导体及元件","children":[{"name":"印制电路板","value":31},{"name":"集成电路","value":48},{"name":"分立器件","value":9},{"name":"被动元件","value":13},{"name":"半导体材料","value":14}]},{"name":"电子制造","children":[{"name":"电子系统组装","value":16},{"name":"电子零部件制造","value":65}]}]},{"name":"机械设备","children":[{"name":"通用设备","children":[{"name":"制冷空调设备","value":8},{"name":"机械基础件","value":43},{"name":"磨具磨料","value":13},{"name":"金属制品","value":22},{"name":"内燃机","value":6},{"name":"机床工具","value":16},{"name":"其它通用机械","value":40}]},{"name":"仪器仪表","children":[{"name":"仪器仪表","value":42}]},{"name":"电气设备","children":[{"name":"电源设备","value":93},{"name":"电气自控设备","value":49},{"name":"输变电设备","value":44},{"name":"电机","value":18},{"name":"其他电力设备","value":31}]},{"name":"专用设备","children":[{"name":"重型机械","value":8},{"name":"工程机械","value":12},{"name":"其它专用机械","value":109},{"name":"环保设备","value":18},{"name":"印刷包装机械","value":9},{"name":"纺织服装设备","value":9},{"name":"农用机械","value":3},{"name":"冶金矿采化工设备","value":32},{"name":"楼宇设备","value":11}]}]},{"name":"食品饮料","children":[{"name":"饮料制造","children":[{"name":"其他酒类","value":3},{"name":"软饮料","value":9},{"name":"葡萄酒","value":4},{"name":"啤酒","value":7},{"name":"白酒","value":18},{"name":"黄酒","value":3}]},{"name":"食品加工制造","children":[{"name":"调味发酵品","value":12},{"name":"乳品","value":15},{"name":"食品综合","value":37},{"name":"肉制品","value":7}]}]},{"name":"纺织服装","children":[{"name":"纺织制造","children":[{"name":"其他纺织","value":13},{"name":"辅料","value":3},{"name":"丝绸","value":1},{"name":"印染","value":3},{"name":"毛纺","value":4},{"name":"棉纺","value":8}]},{"name":"服装家纺","children":[{"name":"男装","value":11},{"name":"其他服装","value":19},{"name":"休闲服装","value":6},{"name":"女装","value":9},{"name":"家纺","value":5},{"name":"鞋帽","value":8}]}]},{"name":"公用事业","children":[{"name":"环保工程","children":[{"name":"环保工程及服务","value":79}]},{"name":"电力","children":[{"name":"水电","value":21},{"name":"热电","value":8},{"name":"火电","value":25},{"name":"燃机发电","value":1},{"name":"新能源发电","value":20}]},{"name":"燃气水务","children":[{"name":"水务Ⅲ","value":23},{"name":"燃气Ⅲ","value":25}]}]},{"name":"交通运输","children":[{"name":"港口航运","children":[{"name":"港口Ⅲ","value":18},{"name":"航运Ⅲ","value":11}]},{"name":"公路铁路运输","children":[{"name":"铁路运输Ⅲ","value":5},{"name":"高速公路Ⅲ","value":21}]},{"name":"机场航运","children":[{"name":"机场Ⅲ","value":4},{"name":"航空运输Ⅲ","value":8}]},{"name":"公交","children":[{"name":"公交Ⅲ","value":9}]},{"name":"物流","children":[{"name":"物流Ⅲ","value":46}]}]}]}'

行业环形图

行业气泡图

关键的问题是如何选择板块？选择一级还是二级、三级板块，有以下几种方案：

分为24个大板块，每天训练24个模型去拟合数据
（1的基础上）将相似的板块进行聚合，每天训练的模型更少些
将板块作为一个属性，是则为1，否则为0，相当于扩展自变量的因子的维度，24个大板块相当于24个因子
（3的基础上）对板块因子进行PCA降维处理，低维数据进行训练

数据连接与处理

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

sectors = set(df["sector1"])
for sector in sectors:
    df[sector] = 0
    df.loc[df["sector1"]==sector, sector] = 1

def get_value(target):
    try:
        return int(target)
    except:
        print(target)
        return 0
    
ts_codes = set(X["ts_code"])
for ts_code in ts_codes:
    target = df.loc[df["ts_code"]==ts_code[:-3], sectors]
    if target.empty:
        print(ts_code)
    
    for sector in sectors:
        X[sector] = 0
        X.loc[X["ts_code"]==ts_code, sector] = get_value(target[sector])
    # X.loc[X["ts_code"]==ts_code, sectors] = target

600401.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000939.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600317.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600074.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000662.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600747.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002509.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600677.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600978.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002018.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002477.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000022.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000043.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
300104.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000979.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600086.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600680.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600175.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
300090.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002070.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600270.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002220.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
300156.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
601558.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600687.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600069.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600240.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002604.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002143.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
600247.SH
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
300028.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000418.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
000018.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
002680.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)
300216.SZ
Series([], Name: 农林牧渔, dtype: int64)
Series([], Name: 电子, dtype: int64)
Series([], Name: 信息设备, dtype: int64)
Series([], Name: 机械设备, dtype: int64)
Series([], Name: 国防军工, dtype: int64)
Series([], Name: 轻工制造, dtype: int64)
Series([], Name: 黑色金属, dtype: int64)
Series([], Name: 纺织服装, dtype: int64)
Series([], Name: 交运设备, dtype: int64)
Series([], Name: 家用电器, dtype: int64)
Series([], Name: 建筑材料, dtype: int64)
Series([], Name: 医药生物, dtype: int64)
Series([], Name: 食品饮料, dtype: int64)
Series([], Name: 有色金属, dtype: int64)
Series([], Name: 交通运输, dtype: int64)
Series([], Name: 商业贸易, dtype: int64)
Series([], Name: 公用事业, dtype: int64)
Series([], Name: 信息服务, dtype: int64)
Series([], Name: 餐饮旅游, dtype: int64)
Series([], Name: 房地产, dtype: int64)
Series([], Name: 金融服务, dtype: int64)
Series([], Name: 综合, dtype: int64)
Series([], Name: 化工, dtype: int64)
Series([], Name: 采掘, dtype: int64)

数据中有35支股票没有出现在爱问财的数据中。默认这些股票不属于任何板块

注意：这种写法是无效的：

X.loc[X["ts_code"]=='000001.SZ', sectors] = df.loc[df["ts_code"]=='000001', sectors]

X不会做任何改变

for sector in sectors:
    X[sector] = 0
    X.loc[X["ts_code"]=='000001.SZ',sector] = int(df.loc[df["ts_code"]=='000001', sector])

	ts_code	trade_date	size	beta	betad	idvol	total_vol	idskew	skew	coskew	...	交通运输	商业贸易	公用事业	信息服务	餐饮旅游	房地产	金融服务	综合	化工	采掘
0	000001.SZ	2013-01-04	4.601898	-2.105874	-0.460532	-0.907805	-0.897914	-0.579302	-0.055647	0.660801	...	0	0	0	0	0	0	1	0	0	0
1	000001.SZ	2013-01-07	4.601898	-2.105874	-0.488850	-0.907805	-0.892487	-0.675182	0.521760	0.888520	...	0	0	0	0	0	0	1	0	0	0
2	000001.SZ	2013-01-08	4.601898	-2.105874	-0.558443	-0.907805	-0.888240	-0.666963	0.092729	0.688570	...	0	0	0	0	0	0	1	0	0	0
3	000001.SZ	2013-01-09	4.601898	-2.105874	-0.576943	-0.907580	-0.887551	-0.670033	0.191668	1.119817	...	0	0	0	0	0	0	1	0	0	0
4	000001.SZ	2013-01-10	4.601898	-2.105874	-0.650214	-0.907805	-0.887770	-0.630891	0.327425	0.369202	...	0	0	0	0	0	0	1	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
560391	603993.SH	2013-12-25	2.407300	1.397118	1.071666	-0.561467	-0.430017	0.055492	-0.358272	-1.371213	...	0	0	0	0	0	0	0	0	0	0
560392	603993.SH	2013-12-26	2.426591	1.274875	1.085033	-0.550457	-0.448470	0.031905	-0.356828	-1.252903	...	0	0	0	0	0	0	0	0	0	0
560393	603993.SH	2013-12-27	2.436236	1.231414	1.098576	-0.548650	-0.450277	0.033331	-0.368329	-1.304196	...	0	0	0	0	0	0	0	0	0	0
560394	603993.SH	2013-12-30	2.431414	0.897085	0.367304	-0.559399	-0.550522	0.068427	0.074625	0.796905	...	0	0	0	0	0	0	0	0	0	0
560395	603993.SH	2013-12-31	2.450705	0.884423	0.384394	-0.560569	-0.551959	0.066667	0.062694	0.748050	...	0	0	0	0	0	0	0	0	0	0

560396 rows × 82 columns

线性模型拟合

from sklearn.linear_model import LinearRegression  

def linear_train(date, state, remove_factors=[]):
    # 划分数据集
    x_train, x_test, y_train, y_test = get_split_by_trade_date(date, state, remove_factors)

    # 模型训练
    model = LinearRegression()
    model.fit(x_train, y_train)

    # 模型预测
    y_pred = model.predict(x_test)
    return prediction(y_pred, y_test.to_numpy(), False)

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

2013-01-04 MSE: 4.233149119757009
2013-01-07 MSE: 3.765677211651225
2013-01-08 MSE: 3.4496176815266173
2013-01-09 MSE: 3.068827201517634
2013-01-10 MSE: 2.789189244289307
2013-01-11 MSE: 3.3056939061431247
2013-01-14 MSE: 2.059142660732336
2013-01-15 MSE: 3.506532343260073
2013-01-16 MSE: 4.037359051833488
2013-01-17 MSE: 3.9657480024956437
2013-01-18 MSE: 2.7456243715579705
2013-01-21 MSE: 3.9639451374066477
2013-01-22 MSE: 4.696021911955441
2013-01-23 MSE: 3.271815201025333
2013-01-24 MSE: 3.2762607438263935
2013-01-25 MSE: 3.413405016175515
2013-01-28 MSE: 2.038492921330912
2013-01-29 MSE: 2.7472204461658425
2013-01-30 MSE: 4.121155234915772
2013-01-31 MSE: 4.110195290302369
2013-02-01 MSE: 3.0280501413678467
2013-02-04 MSE: 4.737991615104639
2013-02-05 MSE: 2.7806242824073384
2013-02-06 MSE: 2.933524939016097
2013-02-07 MSE: 2.415583414993018
2013-02-08 MSE: 3.158600609601366
2013-02-18 MSE: 3.823094766830703
2013-02-19 MSE: 3.222739841573955
2013-02-20 MSE: 2.4266976869629913
2013-02-21 MSE: 3.241538806526292
2013-02-22 MSE: 3.937492914297564
2013-02-25 MSE: 3.2798575396259046
2013-02-26 MSE: 3.7650947283476945
2013-02-27 MSE: 3.471622839868235
2013-02-28 MSE: 2.1371208081873876
2013-03-01 MSE: 2.7658244342428238
2013-03-04 MSE: 2.6361531263650835
2013-03-05 MSE: 2.9958892745990062
2013-03-06 MSE: 4.481021693640189
2013-03-07 MSE: 4.822288356600674
2013-03-08 MSE: 3.5779421262276463
2013-03-11 MSE: 3.041267008351154
2013-03-12 MSE: 3.111247846306445
2013-03-13 MSE: 4.273110959382038
2013-03-14 MSE: 3.7886908586679584
2013-03-15 MSE: 2.932585485849109
2013-03-18 MSE: 4.489750307308804
2013-03-19 MSE: 3.6925775186220062
2013-03-20 MSE: 2.0060153413259254
2013-03-21 MSE: 2.4285325373465336
2013-03-22 MSE: 3.020214755611072
2013-03-25 MSE: 3.4375872122643014
2013-03-26 MSE: 4.036144410739386
2013-03-27 MSE: 3.5957413044513062
2013-03-28 MSE: 4.321783920951984
2013-03-29 MSE: 4.104021432196576
2013-04-01 MSE: 4.849461000907146
2013-04-02 MSE: 4.019269380716311
2013-04-03 MSE: 4.479763507918225
2013-04-08 MSE: 4.51786955552098
2013-04-09 MSE: 3.7650801211278213
2013-04-10 MSE: 2.9046348542995153
2013-04-11 MSE: 2.374659270043006
2013-04-12 MSE: 2.973298176459734
2013-04-15 MSE: 3.213400029176791
2013-04-16 MSE: 2.817429386063684
2013-04-17 MSE: 2.0840493098217023
2013-04-18 MSE: 2.8437795980422704
2013-04-19 MSE: 1.350328235612305
2013-04-22 MSE: 4.087438080456455
2013-04-23 MSE: 2.7795787682078
2013-04-24 MSE: 2.802137078281935
2013-04-25 MSE: 4.831222090434173
2013-04-26 MSE: 4.969919353179857
2013-05-02 MSE: 5.358749819487833
2013-05-03 MSE: 2.7539675692904098
2013-05-06 MSE: 2.8874126737620123
2013-05-07 MSE: 2.789969708106165
2013-05-08 MSE: 2.5691218031474627
2013-05-09 MSE: 4.393084863811518
2013-05-10 MSE: 4.400310527349369
2013-05-13 MSE: 4.459728342061221
2013-05-14 MSE: 3.2590902212831705
2013-05-15 MSE: 2.6077348629212476
2013-05-16 MSE: 3.697974475298041
2013-05-17 MSE: 3.8192945103199207
2013-05-20 MSE: 4.156145125590054
2013-05-21 MSE: 3.953007174287386
2013-05-22 MSE: 4.4239810562267925
2013-05-23 MSE: 3.612128639119359
2013-05-24 MSE: 2.9838380734459458
2013-05-27 MSE: 4.192319184935701
2013-05-28 MSE: 4.626544938247421
2013-05-29 MSE: 2.5532821307329288
2013-05-30 MSE: 3.4203337673897294
2013-05-31 MSE: 3.448878515814778
2013-06-03 MSE: 4.5809459304962346
2013-06-04 MSE: 4.625395692262719
2013-06-05 MSE: 3.4336501194208964
2013-06-06 MSE: 3.894629121499346
2013-06-07 MSE: 4.005813735146131
2013-06-13 MSE: 5.564732828022497
2013-06-14 MSE: 2.5426563326962803
2013-06-17 MSE: 3.6278617751583044
2013-06-18 MSE: 2.8791330750550626
2013-06-19 MSE: 4.141212370233479
2013-06-20 MSE: 4.23632372565977
2013-06-21 MSE: 4.381645076227327
2013-06-24 MSE: 4.33879827452921
2013-06-25 MSE: 6.0159505248383205
2013-06-26 MSE: 2.9607400116022693
2013-06-27 MSE: 6.427276209850155
2013-06-28 MSE: 5.7671160656784854
2013-07-01 MSE: 3.302081616249283
2013-07-02 MSE: 3.290393855083631
2013-07-03 MSE: 3.563095138407353
2013-07-04 MSE: 4.660403659773305
2013-07-05 MSE: 3.6318683572012858
2013-07-08 MSE: 7.382121445111651
2013-07-09 MSE: 4.07522624817326
2013-07-10 MSE: 2.8273313736756633
2013-07-11 MSE: 2.7000364120769786
2013-07-12 MSE: 3.4234850937578143
2013-07-15 MSE: 2.43755851731777
2013-07-16 MSE: 3.3827156229133837
2013-07-17 MSE: 4.538581451411062
2013-07-18 MSE: 4.234914168591637
2013-07-19 MSE: 4.543846163134974
2013-07-22 MSE: 4.269227941890534
2013-07-23 MSE: 2.413499434716021
2013-07-24 MSE: 3.316392156050778
2013-07-25 MSE: 5.396755743292973
2013-07-26 MSE: 4.001926214325805
2013-07-29 MSE: 5.296081872695881
2013-07-30 MSE: 5.364006636804321
2013-07-31 MSE: 3.8064407160424887
2013-08-01 MSE: 2.043246592295615
2013-08-02 MSE: 3.0316492485237276
2013-08-05 MSE: 4.527401329974437
2013-08-06 MSE: 2.697230289938463
2013-08-07 MSE: 4.820917658580198
2013-08-08 MSE: 2.9016963024309725
2013-08-09 MSE: 3.649301259215888
2013-08-12 MSE: 3.3607365966183615
2013-08-13 MSE: 2.8291585572951115
2013-08-14 MSE: 4.2916649497765205
2013-08-15 MSE: 4.616664609465791
2013-08-16 MSE: 4.60572339620524
2013-08-19 MSE: 2.7766295502044063
2013-08-20 MSE: 4.160053739887854
2013-08-21 MSE: 2.834054446079977
2013-08-22 MSE: 3.154189700172675
2013-08-23 MSE: 3.558497134245014
2013-08-26 MSE: 2.5853251169554454
2013-08-27 MSE: 2.415294948605447
2013-08-28 MSE: 6.2617093242942214
2013-08-29 MSE: 5.30545854116128
2013-08-30 MSE: 7.011650208925846
2013-09-02 MSE: 6.913114356410606
2013-09-03 MSE: 3.223077687988044
2013-09-04 MSE: 3.814289207628556
2013-09-05 MSE: 4.314335945596142
2013-09-06 MSE: 4.218242547076395
2013-09-09 MSE: 3.4871565897771646
2013-09-10 MSE: 3.659806006044634
2013-09-11 MSE: 5.12185703947661
2013-09-12 MSE: 4.274821378745957
2013-09-13 MSE: 4.503586499033016
2013-09-16 MSE: 4.41409097119314
2013-09-17 MSE: 4.41192648501019
2013-09-18 MSE: 3.0839119292834622
2013-09-23 MSE: 2.586642283587254
2013-09-24 MSE: 4.689580279213385
2013-09-25 MSE: 5.349169445472196
2013-09-26 MSE: 5.0724975134987265
2013-09-27 MSE: 4.233912416656712
2013-09-30 MSE: 2.723929991958699
2013-10-08 MSE: 4.0931705579703594
2013-10-09 MSE: 3.067280628796464
2013-10-10 MSE: 4.798676190590043
2013-10-11 MSE: 4.370473906649151
2013-10-14 MSE: 6.532665645238672
2013-10-15 MSE: 5.126258386406606
2013-10-16 MSE: 6.5366040036631095
2013-10-17 MSE: 5.401247164668516
2013-10-18 MSE: 3.459260258922997
2013-10-21 MSE: 3.882062689892246
2013-10-22 MSE: 5.39203763210748
2013-10-23 MSE: 6.949522148193933
2013-10-24 MSE: 5.0625580309168505
2013-10-25 MSE: 4.426176509031411
2013-10-28 MSE: 4.8429311792630285
2013-10-29 MSE: 7.87569468311234
2013-10-30 MSE: 2.8912662302315786
2013-10-31 MSE: 4.520749351515384
2013-11-01 MSE: 3.6438731099043387
2013-11-04 MSE: 2.824448780446585
2013-11-05 MSE: 2.579901234515332
2013-11-06 MSE: 3.4496069785069787
2013-11-07 MSE: 4.567857347610637
2013-11-08 MSE: 3.5054683550929946
2013-11-11 MSE: 3.762921363667453
2013-11-12 MSE: 3.222817408254517
2013-11-13 MSE: 3.0939445914620376
2013-11-14 MSE: 3.904504098637324
2013-11-15 MSE: 2.221987122258216
2013-11-18 MSE: 2.4621745755670137
2013-11-19 MSE: 3.4546202047751966
2013-11-20 MSE: 2.8702270822146563
2013-11-21 MSE: 4.601241372604193
2013-11-22 MSE: 3.9420579341014803
2013-11-25 MSE: 4.340438864844637
2013-11-26 MSE: 5.034977625645904
2013-11-27 MSE: 2.6851922241359456
2013-11-28 MSE: 3.668922833602741
2013-11-29 MSE: 3.1511151967069972
2013-12-02 MSE: 5.394492990503025
2013-12-03 MSE: 3.205033695411768
2013-12-04 MSE: 4.151696135699822
2013-12-05 MSE: 4.873751817599435
2013-12-06 MSE: 3.4406548332789657
2013-12-09 MSE: 2.7827530310204494
2013-12-10 MSE: 4.745005360166235
2013-12-11 MSE: 3.0279985444267323
2013-12-12 MSE: 2.3961344429322864
2013-12-13 MSE: 2.5811793563159853
2013-12-16 MSE: 4.259799705859606
2013-12-17 MSE: 3.805055687468061
2013-12-18 MSE: 3.1660685284874646
2013-12-19 MSE: 3.0726052304280276
2013-12-20 MSE: 4.0278925095002736
2013-12-23 MSE: 5.010445408876366
2013-12-24 MSE: 3.132583381475857
2013-12-25 MSE: 2.516287642720609
2013-12-26 MSE: 3.9884286170051846
2013-12-27 MSE: 2.3235935806538777
2013-12-30 MSE: 3.531944554815911
2013-12-31 MSE: 2.7713966170475244

np.array(linear_err1).mean()

3.78887025746859

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

2013-01-04 MSE: 4.714241687822045
2013-01-07 MSE: 3.3429756891258307
2013-01-08 MSE: 3.5075558541831016
2013-01-09 MSE: 3.93699579746151
2013-01-10 MSE: 2.871703786213785
2013-01-11 MSE: 3.8723146520862763
2013-01-14 MSE: 2.4599288305708162
2013-01-15 MSE: 3.1970965178943405
2013-01-16 MSE: 4.369260719325849
2013-01-17 MSE: 4.142062734296863
2013-01-18 MSE: 2.619619591174828
2013-01-21 MSE: 4.224760423610597
2013-01-22 MSE: 4.559992355734214
2013-01-23 MSE: 3.104492569958322
2013-01-24 MSE: 4.1560621821626755
2013-01-25 MSE: 3.488351647888481
2013-01-28 MSE: 1.912375577580364
2013-01-29 MSE: 2.7806886373405764
2013-01-30 MSE: 3.8632578334072116
2013-01-31 MSE: 4.109820846646647
2013-02-01 MSE: 3.52373355365379
2013-02-04 MSE: 4.825257186916256
2013-02-05 MSE: 3.1457701549250583
2013-02-06 MSE: 2.6549539015317944
2013-02-07 MSE: 2.2884696652105307
2013-02-08 MSE: 2.5271787610807763
2013-02-18 MSE: 3.587340825846199
2013-02-19 MSE: 4.0579761467815345
2013-02-20 MSE: 1.9203731394028662
2013-02-21 MSE: 3.1103371596178673
2013-02-22 MSE: 3.763901025808841
2013-02-25 MSE: 3.2829571876009975
2013-02-26 MSE: 3.2371084697388532
2013-02-27 MSE: 3.1266223245275193
2013-02-28 MSE: 2.2841653360811396
2013-03-01 MSE: 2.8906956901694736
2013-03-04 MSE: 2.876933762711643
2013-03-05 MSE: 2.9460658539315325
2013-03-06 MSE: 4.034678655028863
2013-03-07 MSE: 5.217587805248312
2013-03-08 MSE: 4.109122812091744
2013-03-11 MSE: 3.2672171292626864
2013-03-12 MSE: 4.506231429161551
2013-03-13 MSE: 4.215445084328837
2013-03-14 MSE: 3.149596383868343
2013-03-15 MSE: 3.076120722389792
2013-03-18 MSE: 4.371060883857852
2013-03-19 MSE: 3.690122435233914
2013-03-20 MSE: 1.9675025824578845
2013-03-21 MSE: 2.8420217783802086
2013-03-22 MSE: 3.184712082754817
2013-03-25 MSE: 3.44528231641185
2013-03-26 MSE: 4.31943969795425
2013-03-27 MSE: 3.0188969244955963
2013-03-28 MSE: 3.967438235874507
2013-03-29 MSE: 3.8492352855002543
2013-04-01 MSE: 4.498558912624707
2013-04-02 MSE: 4.3036253459489755
2013-04-03 MSE: 4.4743932915226745
2013-04-08 MSE: 4.934443821128527
2013-04-09 MSE: 2.668581562927411
2013-04-10 MSE: 3.482195733261146
2013-04-11 MSE: 2.641691624902714
2013-04-12 MSE: 4.0275470362502475
2013-04-15 MSE: 4.595867202454955
2013-04-16 MSE: 2.499912139285393
2013-04-17 MSE: 1.9283883846408867
2013-04-18 MSE: 2.756526580496624
2013-04-19 MSE: 1.5761991302921383
2013-04-22 MSE: 3.9641577593272794
2013-04-23 MSE: 3.114761966145212
2013-04-24 MSE: 3.1251847598882088
2013-04-25 MSE: 5.060825098560124
2013-04-26 MSE: 4.000880661934135
2013-05-02 MSE: 4.481126841670108
2013-05-03 MSE: 2.2061078375081338
2013-05-06 MSE: 3.331344455708478
2013-05-07 MSE: 3.290483687363775
2013-05-08 MSE: 3.2456075315526243
2013-05-09 MSE: 4.438253776318789
2013-05-10 MSE: 4.134200643230964
2013-05-13 MSE: 3.0406836782108915
2013-05-14 MSE: 3.9797403512464413
2013-05-15 MSE: 3.464937479304122
2013-05-16 MSE: 3.2682299296804427
2013-05-17 MSE: 2.865827940375785
2013-05-20 MSE: 4.2720991977119676
2013-05-21 MSE: 3.5621247398853226
2013-05-22 MSE: 4.962969685704769
2013-05-23 MSE: 3.577393392102211
2013-05-24 MSE: 3.0559639120420212
2013-05-27 MSE: 3.8094746222225315
2013-05-28 MSE: 4.096135194040803
2013-05-29 MSE: 3.613190273357069
2013-05-30 MSE: 3.3932362132115625
2013-05-31 MSE: 3.5876328422473405
2013-06-03 MSE: 4.49711744141313
2013-06-04 MSE: 4.038744022210944
2013-06-05 MSE: 2.7620654155923923
2013-06-06 MSE: 3.9577626141912026
2013-06-07 MSE: 4.670758721055154
2013-06-13 MSE: 5.7313180037948
2013-06-14 MSE: 2.565822096620124
2013-06-17 MSE: 3.639136326665408
2013-06-18 MSE: 3.6392618802391556
2013-06-19 MSE: 4.160416485354079
2013-06-20 MSE: 4.113633767920121
2013-06-21 MSE: 4.585187473945124
2013-06-24 MSE: 3.665059411876752
2013-06-25 MSE: 6.026637819731102
2013-06-26 MSE: 3.169919879131445
2013-06-27 MSE: 6.25259444635197
2013-06-28 MSE: 4.61216528800944
2013-07-01 MSE: 3.930970559933143
2013-07-02 MSE: 3.63298451999474
2013-07-03 MSE: 4.684378340885755
2013-07-04 MSE: 4.760513101674036
2013-07-05 MSE: 3.6992563000797967
2013-07-08 MSE: 6.80451032082084
2013-07-09 MSE: 4.018516355917407
2013-07-10 MSE: 3.180630978334622
2013-07-11 MSE: 2.226395214401114
2013-07-12 MSE: 3.2551070485871705
2013-07-15 MSE: 3.0094093955866006
2013-07-16 MSE: 3.535662034426115
2013-07-17 MSE: 4.383703593323584
2013-07-18 MSE: 4.66086049879628
2013-07-19 MSE: 6.472856417000104
2013-07-22 MSE: 3.519219693662694
2013-07-23 MSE: 3.0646391548849827
2013-07-24 MSE: 4.035498649186635
2013-07-25 MSE: 6.135367745004208
2013-07-26 MSE: 4.765124240825765
2013-07-29 MSE: 4.774757275760481
2013-07-30 MSE: 4.778286245567786
2013-07-31 MSE: 3.8422540931014493
2013-08-01 MSE: 2.5057151978460377
2013-08-02 MSE: 3.9724496104159837
2013-08-05 MSE: 3.327616540405284
2013-08-06 MSE: 3.586186501526803
2013-08-07 MSE: 4.029794208471441
2013-08-08 MSE: 3.970943499163649
2013-08-09 MSE: 4.571791923065786
2013-08-12 MSE: 3.7574953553972246
2013-08-13 MSE: 3.5072339685106404
2013-08-14 MSE: 3.660106260305817
2013-08-15 MSE: 4.297355304956393
2013-08-16 MSE: 4.2086139496073445
2013-08-19 MSE: 2.6491763631764544
2013-08-20 MSE: 4.12626028093997
2013-08-21 MSE: 3.3510513751959263
2013-08-22 MSE: 4.088389679286453
2013-08-23 MSE: 5.515541502683463
2013-08-26 MSE: 2.971786813949549
2013-08-27 MSE: 3.2587962451024155
2013-08-28 MSE: 5.55265866685738
2013-08-29 MSE: 4.92857963477561
2013-08-30 MSE: 6.623311126011407
2013-09-02 MSE: 6.220717739214578
2013-09-03 MSE: 3.3759140839724178
2013-09-04 MSE: 4.363501480881079
2013-09-05 MSE: 5.419832576600191
2013-09-06 MSE: 4.507746327421906
2013-09-09 MSE: 3.509319895205948
2013-09-10 MSE: 3.984551773162988
2013-09-11 MSE: 5.872703712067808
2013-09-12 MSE: 3.8064716014854234
2013-09-13 MSE: 3.694156556042076
2013-09-16 MSE: 4.349521663093377
2013-09-17 MSE: 4.329202134070377
2013-09-18 MSE: 3.8150209646778395
2013-09-23 MSE: 3.2947234284769062
2013-09-24 MSE: 5.3558271410681835
2013-09-25 MSE: 4.687730403214136
2013-09-26 MSE: 5.264454581470839
2013-09-27 MSE: 4.422890372768799
2013-09-30 MSE: 3.4669406193415453
2013-10-08 MSE: 4.232338196101863
2013-10-09 MSE: 3.3381632384767874
2013-10-10 MSE: 6.41529400793711
2013-10-11 MSE: 4.411331378810725
2013-10-14 MSE: 5.638910976515932
2013-10-15 MSE: 5.609434498904636
2013-10-16 MSE: 6.620902972515307
2013-10-17 MSE: 6.02756166586827
2013-10-18 MSE: 3.5564838668179797
2013-10-21 MSE: 3.2508693968301476
2013-10-22 MSE: 5.693673527767772
2013-10-23 MSE: 5.80277906986296
2013-10-24 MSE: 4.55207199945145
2013-10-25 MSE: 5.744207285191015
2013-10-28 MSE: 6.788729918523151
2013-10-29 MSE: 7.514678209439663
2013-10-30 MSE: 3.4873224975055446
2013-10-31 MSE: 4.837370202319121
2013-11-01 MSE: 4.609045751892083
2013-11-04 MSE: 3.0862762595599826
2013-11-05 MSE: 2.416338988456892
2013-11-06 MSE: 2.9869293290522965
2013-11-07 MSE: 4.210115357181893
2013-11-08 MSE: 4.821781807557171
2013-11-11 MSE: 3.375679262735163
2013-11-12 MSE: 3.589221050779068
2013-11-13 MSE: 3.8461175756862533
2013-11-14 MSE: 3.382464033130963
2013-11-15 MSE: 2.596291617812035
2013-11-18 MSE: 2.7460035536039005
2013-11-19 MSE: 3.441222276443585
2013-11-20 MSE: 3.4900629656819953
2013-11-21 MSE: 3.261781446237586
2013-11-22 MSE: 4.181428719548602
2013-11-25 MSE: 4.194086975815692
2013-11-26 MSE: 3.7156595597409905
2013-11-27 MSE: 2.6477025728792825
2013-11-28 MSE: 3.519351465342494
2013-11-29 MSE: 2.895051839625232
2013-12-02 MSE: 5.877806882829327
2013-12-03 MSE: 3.3536089843369465
2013-12-04 MSE: 3.9499634091548685
2013-12-05 MSE: 4.587543360427792
2013-12-06 MSE: 3.812024542307605
2013-12-09 MSE: 3.0634862852681253
2013-12-10 MSE: 3.427182775394523
2013-12-11 MSE: 3.024689195282004
2013-12-12 MSE: 3.1203755622268865
2013-12-13 MSE: 2.982218345892254
2013-12-16 MSE: 4.032710233624234
2013-12-17 MSE: 3.735353803095791
2013-12-18 MSE: 2.8204051319212575
2013-12-19 MSE: 3.4517745578424854
2013-12-20 MSE: 3.5085221625577083
2013-12-23 MSE: 4.774772589704875
2013-12-24 MSE: 2.6371119559935514
2013-12-25 MSE: 2.664203832423157
2013-12-26 MSE: 3.9927150539641936
2013-12-27 MSE: 2.7500419643567877
2013-12-30 MSE: 3.807790786048106
2013-12-31 MSE: 2.9325070406859304

np.array(linear_err).mean()

3.7449913993792343

XGBoost拟合

def XGBoost_train(date, state=0, remove_factors=[]):
    # 划分数据集
    x_train, x_test, y_train, y_test = get_split_by_trade_date(date, state, remove_factors)

    # 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)
#     model.fit(x_train, y_train)

    # 模型预测
    y_pred = model.predict(x_test)
    return prediction(y_pred, y_test.to_numpy(), False)

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

2013-01-04 [0]	validation_0-rmse:2.56848
[1]	validation_0-rmse:2.52235
[2]	validation_0-rmse:2.47978
[3]	validation_0-rmse:2.43784
[4]	validation_0-rmse:2.40057
[5]	validation_0-rmse:2.36513
[6]	validation_0-rmse:2.33334
[7]	validation_0-rmse:2.30656
[8]	validation_0-rmse:2.28056
[9]	validation_0-rmse:2.25651
[10]	validation_0-rmse:2.23218
[11]	validation_0-rmse:2.21197
[12]	validation_0-rmse:2.19228
[13]	validation_0-rmse:2.17478
[14]	validation_0-rmse:2.15741
[15]	validation_0-rmse:2.14363
[16]	validation_0-rmse:2.13360
[17]	validation_0-rmse:2.12239
[18]	validation_0-rmse:2.10958
[19]	validation_0-rmse:2.09868
[20]	validation_0-rmse:2.09215
[21]	validation_0-rmse:2.08159
[22]	validation_0-rmse:2.07230
[23]	validation_0-rmse:2.06811
[24]	validation_0-rmse:2.06149
[25]	validation_0-rmse:2.05740
[26]	validation_0-rmse:2.05028
[27]	validation_0-rmse:2.04503
[28]	validation_0-rmse:2.04330
[29]	validation_0-rmse:2.04106
[30]	validation_0-rmse:2.03689
[31]	validation_0-rmse:2.03408
[32]	validation_0-rmse:2.02734
[33]	validation_0-rmse:2.02452
[34]	validation_0-rmse:2.02438
[35]	validation_0-rmse:2.02195
[36]	validation_0-rmse:2.02012
[37]	validation_0-rmse:2.01802
[38]	validation_0-rmse:2.01616
[39]	validation_0-rmse:2.01570
[40]	validation_0-rmse:2.01596
[41]	validation_0-rmse:2.01382
[42]	validation_0-rmse:2.01271
[43]	validation_0-rmse:2.01090
[44]	validation_0-rmse:2.01122
[45]	validation_0-rmse:2.01176
[46]	validation_0-rmse:2.01217
[47]	validation_0-rmse:2.01200
[48]	validation_0-rmse:2.01246
MSE: 4.043701422169699
2013-01-07 [0]	validation_0-rmse:1.99874
[1]	validation_0-rmse:1.97426
[2]	validation_0-rmse:1.95156
[3]	validation_0-rmse:1.92742
[4]	validation_0-rmse:1.90586
[5]	validation_0-rmse:1.88719
[6]	validation_0-rmse:1.87028
[7]	validation_0-rmse:1.85556
[8]	validation_0-rmse:1.84201
[9]	validation_0-rmse:1.82659
[10]	validation_0-rmse:1.81608
[11]	validation_0-rmse:1.80621
[12]	validation_0-rmse:1.79789
[13]	validation_0-rmse:1.78847
[14]	validation_0-rmse:1.78118
[15]	validation_0-rmse:1.77545
[16]	validation_0-rmse:1.76642
[17]	validation_0-rmse:1.76131
[18]	validation_0-rmse:1.75679
[19]	validation_0-rmse:1.75162
[20]	validation_0-rmse:1.74631
[21]	validation_0-rmse:1.74223
[22]	validation_0-rmse:1.73720
[23]	validation_0-rmse:1.73612
[24]	validation_0-rmse:1.73261
[25]	validation_0-rmse:1.72950
[26]	validation_0-rmse:1.72523
[27]	validation_0-rmse:1.72382
[28]	validation_0-rmse:1.72132
[29]	validation_0-rmse:1.71970
[30]	validation_0-rmse:1.71946
[31]	validation_0-rmse:1.71758
[32]	validation_0-rmse:1.71511
[33]	validation_0-rmse:1.71291
[34]	validation_0-rmse:1.71421
[35]	validation_0-rmse:1.71435
[36]	validation_0-rmse:1.71477
[37]	validation_0-rmse:1.71442
MSE: 2.934072467892393
2013-01-08 [0]	validation_0-rmse:1.96706
[1]	validation_0-rmse:1.94691
[2]	validation_0-rmse:1.92959
[3]	validation_0-rmse:1.91298
[4]	validation_0-rmse:1.89873
[5]	validation_0-rmse:1.88706
[6]	validation_0-rmse:1.87619
[7]	validation_0-rmse:1.86504
[8]	validation_0-rmse:1.85498
[9]	validation_0-rmse:1.84633
[10]	validation_0-rmse:1.83743
[11]	validation_0-rmse:1.83190
[12]	validation_0-rmse:1.82379
[13]	validation_0-rmse:1.81638
[14]	validation_0-rmse:1.81161
[15]	validation_0-rmse:1.80480
[16]	validation_0-rmse:1.80104
[17]	validation_0-rmse:1.79357
[18]	validation_0-rmse:1.79111
[19]	validation_0-rmse:1.78826
[20]	validation_0-rmse:1.78736
[21]	validation_0-rmse:1.78634
[22]	validation_0-rmse:1.78656
[23]	validation_0-rmse:1.78628
[24]	validation_0-rmse:1.78526
[25]	validation_0-rmse:1.78255
[26]	validation_0-rmse:1.78361
[27]	validation_0-rmse:1.77885
[28]	validation_0-rmse:1.77839
[29]	validation_0-rmse:1.77725
[30]	validation_0-rmse:1.77748
[31]	validation_0-rmse:1.77767
[32]	validation_0-rmse:1.77630
[33]	validation_0-rmse:1.77577
[34]	validation_0-rmse:1.77650
[35]	validation_0-rmse:1.77555
[36]	validation_0-rmse:1.77697
[37]	validation_0-rmse:1.77848
[38]	validation_0-rmse:1.78016
[39]	validation_0-rmse:1.77981
MSE: 3.152590821316556
2013-01-09 [0]	validation_0-rmse:1.64638
[1]	validation_0-rmse:1.63337
[2]	validation_0-rmse:1.62441
[3]	validation_0-rmse:1.61556
[4]	validation_0-rmse:1.60933
[5]	validation_0-rmse:1.60533
[6]	validation_0-rmse:1.59930
[7]	validation_0-rmse:1.59527
[8]	validation_0-rmse:1.59248
[9]	validation_0-rmse:1.58785
[10]	validation_0-rmse:1.58646
[11]	validation_0-rmse:1.58252
[12]	validation_0-rmse:1.58251
[13]	validation_0-rmse:1.58053
[14]	validation_0-rmse:1.57870
[15]	validation_0-rmse:1.57725
[16]	validation_0-rmse:1.57553
[17]	validation_0-rmse:1.57286
[18]	validation_0-rmse:1.57214
[19]	validation_0-rmse:1.57441
[20]	validation_0-rmse:1.57561
[21]	validation_0-rmse:1.57799
[22]	validation_0-rmse:1.57877
MSE: 2.471627922631097
...
2013-12-27 [0]	validation_0-rmse:2.18770
[1]	validation_0-rmse:2.13401
[2]	validation_0-rmse:2.08843
[3]	validation_0-rmse:2.04272
[4]	validation_0-rmse:1.99790
[5]	validation_0-rmse:1.95592
[6]	validation_0-rmse:1.92223
[7]	validation_0-rmse:1.88873
[8]	validation_0-rmse:1.85935
[9]	validation_0-rmse:1.82728
[10]	validation_0-rmse:1.80221
[11]	validation_0-rmse:1.77814
[12]	validation_0-rmse:1.75729
[13]	validation_0-rmse:1.73386
[14]	validation_0-rmse:1.71258
[15]	validation_0-rmse:1.69569
[16]	validation_0-rmse:1.67526
[17]	validation_0-rmse:1.65927
[18]	validation_0-rmse:1.64267
[19]	validation_0-rmse:1.63168
[20]	validation_0-rmse:1.62000
[21]	validation_0-rmse:1.60894
[22]	validation_0-rmse:1.59791
[23]	validation_0-rmse:1.59057
[24]	validation_0-rmse:1.58224
[25]	validation_0-rmse:1.57563
[26]	validation_0-rmse:1.57127
[27]	validation_0-rmse:1.56269
[28]	validation_0-rmse:1.55863
[29]	validation_0-rmse:1.55280
[30]	validation_0-rmse:1.54832
[31]	validation_0-rmse:1.54345
[32]	validation_0-rmse:1.53834
[33]	validation_0-rmse:1.53456
[34]	validation_0-rmse:1.53139
[35]	validation_0-rmse:1.52860
[36]	validation_0-rmse:1.52747
[37]	validation_0-rmse:1.52691
[38]	validation_0-rmse:1.52489
[39]	validation_0-rmse:1.52249
[40]	validation_0-rmse:1.51897
[41]	validation_0-rmse:1.51873
[42]	validation_0-rmse:1.51678
[43]	validation_0-rmse:1.51384
[44]	validation_0-rmse:1.51071
[45]	validation_0-rmse:1.51055
[46]	validation_0-rmse:1.50841
[47]	validation_0-rmse:1.50696
[48]	validation_0-rmse:1.50620
[49]	validation_0-rmse:1.50604
[50]	validation_0-rmse:1.50563
[51]	validation_0-rmse:1.50306
[52]	validation_0-rmse:1.50113
[53]	validation_0-rmse:1.50196
[54]	validation_0-rmse:1.50047
[55]	validation_0-rmse:1.50170
[56]	validation_0-rmse:1.50211
[57]	validation_0-rmse:1.50307
[58]	validation_0-rmse:1.50269
[59]	validation_0-rmse:1.50007
[60]	validation_0-rmse:1.50035
[61]	validation_0-rmse:1.49963
[62]	validation_0-rmse:1.49882
[63]	validation_0-rmse:1.50058
[64]	validation_0-rmse:1.50046
[65]	validation_0-rmse:1.50086
[66]	validation_0-rmse:1.49926
[67]	validation_0-rmse:1.49730
[68]	validation_0-rmse:1.49653
[69]	validation_0-rmse:1.49547
[70]	validation_0-rmse:1.49487
[71]	validation_0-rmse:1.49513
[72]	validation_0-rmse:1.49564
[73]	validation_0-rmse:1.49589
[74]	validation_0-rmse:1.49511
[75]	validation_0-rmse:1.49396
[76]	validation_0-rmse:1.49421
[77]	validation_0-rmse:1.49427
[78]	validation_0-rmse:1.49518
[79]	validation_0-rmse:1.49595
MSE: 2.231910076582099
2013-12-30 [0]	validation_0-rmse:1.93906
[1]	validation_0-rmse:1.93359
[2]	validation_0-rmse:1.92819
[3]	validation_0-rmse:1.92651
[4]	validation_0-rmse:1.92279
[5]	validation_0-rmse:1.91881
[6]	validation_0-rmse:1.91686
[7]	validation_0-rmse:1.91041
[8]	validation_0-rmse:1.91220
[9]	validation_0-rmse:1.90896
[10]	validation_0-rmse:1.90735
[11]	validation_0-rmse:1.90522
[12]	validation_0-rmse:1.90449
[13]	validation_0-rmse:1.90569
[14]	validation_0-rmse:1.90641
[15]	validation_0-rmse:1.90621
[16]	validation_0-rmse:1.90516
[17]	validation_0-rmse:1.90327
[18]	validation_0-rmse:1.90342
[19]	validation_0-rmse:1.90315
[20]	validation_0-rmse:1.90352
[21]	validation_0-rmse:1.90459
[22]	validation_0-rmse:1.90443
[23]	validation_0-rmse:1.89994
[24]	validation_0-rmse:1.89822
[25]	validation_0-rmse:1.90061
[26]	validation_0-rmse:1.90302
[27]	validation_0-rmse:1.90303
[28]	validation_0-rmse:1.90350
[29]	validation_0-rmse:1.90689
MSE: 3.6032332875160864
2013-12-31 [0]	validation_0-rmse:1.83542
[1]	validation_0-rmse:1.82147
[2]	validation_0-rmse:1.80914
[3]	validation_0-rmse:1.79377
[4]	validation_0-rmse:1.78160
[5]	validation_0-rmse:1.77186
[6]	validation_0-rmse:1.76250
[7]	validation_0-rmse:1.75562
[8]	validation_0-rmse:1.74869
[9]	validation_0-rmse:1.74666
[10]	validation_0-rmse:1.74312
[11]	validation_0-rmse:1.74120
[12]	validation_0-rmse:1.73566
[13]	validation_0-rmse:1.73385
[14]	validation_0-rmse:1.73097
[15]	validation_0-rmse:1.72780
[16]	validation_0-rmse:1.72685
[17]	validation_0-rmse:1.72226
[18]	validation_0-rmse:1.72152
[19]	validation_0-rmse:1.71858
[20]	validation_0-rmse:1.71410
[21]	validation_0-rmse:1.71197
[22]	validation_0-rmse:1.71016
[23]	validation_0-rmse:1.70847
[24]	validation_0-rmse:1.70468
[25]	validation_0-rmse:1.70422
[26]	validation_0-rmse:1.70064
[27]	validation_0-rmse:1.69980
[28]	validation_0-rmse:1.69591
[29]	validation_0-rmse:1.69645
[30]	validation_0-rmse:1.69711
[31]	validation_0-rmse:1.69528
[32]	validation_0-rmse:1.69525
[33]	validation_0-rmse:1.69382
[34]	validation_0-rmse:1.69191
[35]	validation_0-rmse:1.69289
[36]	validation_0-rmse:1.69030
[37]	validation_0-rmse:1.69106
[38]	validation_0-rmse:1.68965
[39]	validation_0-rmse:1.68950
[40]	validation_0-rmse:1.69076
[41]	validation_0-rmse:1.69101
[42]	validation_0-rmse:1.69115
[43]	validation_0-rmse:1.69064
[44]	validation_0-rmse:1.68908
[45]	validation_0-rmse:1.69075
[46]	validation_0-rmse:1.69156
[47]	validation_0-rmse:1.69101
[48]	validation_0-rmse:1.69182
[49]	validation_0-rmse:1.69143
MSE: 2.8529854946568176

np.array(XGBoost_err1).mean()

3.7986009350913554

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

2013-01-04 [0]	validation_0-rmse:2.44318
[1]	validation_0-rmse:2.40152
[2]	validation_0-rmse:2.36182
[3]	validation_0-rmse:2.33011
[4]	validation_0-rmse:2.29835
[5]	validation_0-rmse:2.26878
[6]	validation_0-rmse:2.24580
[7]	validation_0-rmse:2.21818
[8]	validation_0-rmse:2.19798
[9]	validation_0-rmse:2.18198
[10]	validation_0-rmse:2.16001
[11]	validation_0-rmse:2.13964
[12]	validation_0-rmse:2.12171
[13]	validation_0-rmse:2.10896
[14]	validation_0-rmse:2.09479
[15]	validation_0-rmse:2.08295
[16]	validation_0-rmse:2.07276
[17]	validation_0-rmse:2.05876
[18]	validation_0-rmse:2.05218
[19]	validation_0-rmse:2.04452
[20]	validation_0-rmse:2.03878
[21]	validation_0-rmse:2.02923
[22]	validation_0-rmse:2.02653
[23]	validation_0-rmse:2.02442
[24]	validation_0-rmse:2.01944
[25]	validation_0-rmse:2.01919
[26]	validation_0-rmse:2.01373
[27]	validation_0-rmse:2.01374
[28]	validation_0-rmse:2.01153
[29]	validation_0-rmse:2.01001
[30]	validation_0-rmse:2.00388
[31]	validation_0-rmse:2.00178
[32]	validation_0-rmse:1.99756
[33]	validation_0-rmse:1.99374
[34]	validation_0-rmse:1.99449
[35]	validation_0-rmse:1.99203
[36]	validation_0-rmse:1.99206
[37]	validation_0-rmse:1.98968
[38]	validation_0-rmse:1.98934
[39]	validation_0-rmse:1.98827
[40]	validation_0-rmse:1.98593
[41]	validation_0-rmse:1.98631
[42]	validation_0-rmse:1.98598
[43]	validation_0-rmse:1.98562
[44]	validation_0-rmse:1.98390
[45]	validation_0-rmse:1.98224
[46]	validation_0-rmse:1.98291
[47]	validation_0-rmse:1.98148
[48]	validation_0-rmse:1.98168
[49]	validation_0-rmse:1.98083
[50]	validation_0-rmse:1.98047
[51]	validation_0-rmse:1.97901
[52]	validation_0-rmse:1.97997
[53]	validation_0-rmse:1.98024
[54]	validation_0-rmse:1.98122
[55]	validation_0-rmse:1.97757
[56]	validation_0-rmse:1.97720
[57]	validation_0-rmse:1.97802
[58]	validation_0-rmse:1.97489
[59]	validation_0-rmse:1.97369
[60]	validation_0-rmse:1.97213
[61]	validation_0-rmse:1.97182
[62]	validation_0-rmse:1.97214
[63]	validation_0-rmse:1.96714
[64]	validation_0-rmse:1.96568
[65]	validation_0-rmse:1.96631
[66]	validation_0-rmse:1.96698
[67]	validation_0-rmse:1.96879
[68]	validation_0-rmse:1.96831
MSE: 3.8639077725769915
...
2013-12-19 [0]	validation_0-rmse:2.26243
[1]	validation_0-rmse:2.21521
[2]	validation_0-rmse:2.16818
[3]	validation_0-rmse:2.13110
[4]	validation_0-rmse:2.10142
[5]	validation_0-rmse:2.07255
[6]	validation_0-rmse:2.04726
[7]	validation_0-rmse:2.02428
[8]	validation_0-rmse:2.00001
[9]	validation_0-rmse:1.98182
[10]	validation_0-rmse:1.96493
[11]	validation_0-rmse:1.94950
[12]	validation_0-rmse:1.93532
[13]	validation_0-rmse:1.92592
[14]	validation_0-rmse:1.91825
[15]	validation_0-rmse:1.91094
[16]	validation_0-rmse:1.90156
[17]	validation_0-rmse:1.89696
[18]	validation_0-rmse:1.88729
[19]	validation_0-rmse:1.88177
[20]	validation_0-rmse:1.87716
[21]	validation_0-rmse:1.87606
[22]	validation_0-rmse:1.87312
[23]	validation_0-rmse:1.86895
[24]	validation_0-rmse:1.86818
[25]	validation_0-rmse:1.86642
[26]	validation_0-rmse:1.86499
[27]	validation_0-rmse:1.86304
[28]	validation_0-rmse:1.86375
[29]	validation_0-rmse:1.86171
[30]	validation_0-rmse:1.85841
[31]	validation_0-rmse:1.85742
[32]	validation_0-rmse:1.85925
[33]	validation_0-rmse:1.85906
[34]	validation_0-rmse:1.85931
[35]	validation_0-rmse:1.85881
[36]	validation_0-rmse:1.85957
MSE: 3.4500033654207676
2013-12-20 [0]	validation_0-rmse:2.47451
[1]	validation_0-rmse:2.41299
[2]	validation_0-rmse:2.35223
[3]	validation_0-rmse:2.30003
[4]	validation_0-rmse:2.25076
[5]	validation_0-rmse:2.20463
[6]	validation_0-rmse:2.16373
[7]	validation_0-rmse:2.12599
[8]	validation_0-rmse:2.08803
[9]	validation_0-rmse:2.05551
[10]	validation_0-rmse:2.02426
[11]	validation_0-rmse:1.99819
[12]	validation_0-rmse:1.97611
[13]	validation_0-rmse:1.95361
[14]	validation_0-rmse:1.93586
[15]	validation_0-rmse:1.91759
[16]	validation_0-rmse:1.90058
[17]	validation_0-rmse:1.88260
[18]	validation_0-rmse:1.87033
[19]	validation_0-rmse:1.85998
[20]	validation_0-rmse:1.85078
[21]	validation_0-rmse:1.83849
[22]	validation_0-rmse:1.82773
[23]	validation_0-rmse:1.81902
[24]	validation_0-rmse:1.80712
[25]	validation_0-rmse:1.79882
[26]	validation_0-rmse:1.78942
[27]	validation_0-rmse:1.78279
[28]	validation_0-rmse:1.78059
[29]	validation_0-rmse:1.77651
[30]	validation_0-rmse:1.77353
[31]	validation_0-rmse:1.77047
[32]	validation_0-rmse:1.76449
[33]	validation_0-rmse:1.76270
[34]	validation_0-rmse:1.76295
[35]	validation_0-rmse:1.76020
[36]	validation_0-rmse:1.76174
[37]	validation_0-rmse:1.75878
[38]	validation_0-rmse:1.75704
[39]	validation_0-rmse:1.75256
[40]	validation_0-rmse:1.74974
[41]	validation_0-rmse:1.75367
[42]	validation_0-rmse:1.75073
[43]	validation_0-rmse:1.75055
[44]	validation_0-rmse:1.75148
MSE: 3.0616037032709182
2013-12-23 [0]	validation_0-rmse:2.19096
[1]	validation_0-rmse:2.15799
[2]	validation_0-rmse:2.13766
[3]	validation_0-rmse:2.11095
[4]	validation_0-rmse:2.09422
[5]	validation_0-rmse:2.07719
[6]	validation_0-rmse:2.06015
[7]	validation_0-rmse:2.04105
[8]	validation_0-rmse:2.02886
[9]	validation_0-rmse:2.00590
[10]	validation_0-rmse:1.99288
[11]	validation_0-rmse:1.97951
[12]	validation_0-rmse:1.97051
[13]	validation_0-rmse:1.96038
[14]	validation_0-rmse:1.95441
[15]	validation_0-rmse:1.94419
[16]	validation_0-rmse:1.93340
[17]	validation_0-rmse:1.92519
[18]	validation_0-rmse:1.92493
[19]	validation_0-rmse:1.92629
[20]	validation_0-rmse:1.91814
[21]	validation_0-rmse:1.91162
[22]	validation_0-rmse:1.90251
[23]	validation_0-rmse:1.89891
[24]	validation_0-rmse:1.89797
[25]	validation_0-rmse:1.89129
[26]	validation_0-rmse:1.89099
[27]	validation_0-rmse:1.88508
[28]	validation_0-rmse:1.88524
[29]	validation_0-rmse:1.88439
[30]	validation_0-rmse:1.88111
[31]	validation_0-rmse:1.87681
[32]	validation_0-rmse:1.87535
[33]	validation_0-rmse:1.87511
[34]	validation_0-rmse:1.87151
[35]	validation_0-rmse:1.86807
[36]	validation_0-rmse:1.86496
[37]	validation_0-rmse:1.86261
[38]	validation_0-rmse:1.86176
[39]	validation_0-rmse:1.85970
[40]	validation_0-rmse:1.85800
[41]	validation_0-rmse:1.85780
[42]	validation_0-rmse:1.85563
[43]	validation_0-rmse:1.85476
[44]	validation_0-rmse:1.85429
[45]	validation_0-rmse:1.85237
[46]	validation_0-rmse:1.85089
[47]	validation_0-rmse:1.84792
[48]	validation_0-rmse:1.84632
[49]	validation_0-rmse:1.84676
[50]	validation_0-rmse:1.84632
[51]	validation_0-rmse:1.84358
[52]	validation_0-rmse:1.84450
[53]	validation_0-rmse:1.84214
[54]	validation_0-rmse:1.84020
[55]	validation_0-rmse:1.83810
[56]	validation_0-rmse:1.83788
[57]	validation_0-rmse:1.83696
[58]	validation_0-rmse:1.83744
[59]	validation_0-rmse:1.83755
[60]	validation_0-rmse:1.83521
[61]	validation_0-rmse:1.83413
[62]	validation_0-rmse:1.83360
[63]	validation_0-rmse:1.83058
[64]	validation_0-rmse:1.83137
[65]	validation_0-rmse:1.82970
[66]	validation_0-rmse:1.83006
[67]	validation_0-rmse:1.82821
[68]	validation_0-rmse:1.82967
[69]	validation_0-rmse:1.83033
[70]	validation_0-rmse:1.82932
[71]	validation_0-rmse:1.83010
MSE: 3.342357195049782
2013-12-24 [0]	validation_0-rmse:1.52366
[1]	validation_0-rmse:1.51772
[2]	validation_0-rmse:1.51573
[3]	validation_0-rmse:1.51314
[4]	validation_0-rmse:1.51032
[5]	validation_0-rmse:1.50672
[6]	validation_0-rmse:1.50524
[7]	validation_0-rmse:1.50372
[8]	validation_0-rmse:1.50623
[9]	validation_0-rmse:1.50457
[10]	validation_0-rmse:1.50544
[11]	validation_0-rmse:1.50565
[12]	validation_0-rmse:1.50577
MSE: 2.2611714617370846
2013-12-25 [0]	validation_0-rmse:2.13223
[1]	validation_0-rmse:2.09703
[2]	validation_0-rmse:2.06964
[3]	validation_0-rmse:2.04013
[4]	validation_0-rmse:2.01116
[5]	validation_0-rmse:1.98585
[6]	validation_0-rmse:1.96014
[7]	validation_0-rmse:1.94057
[8]	validation_0-rmse:1.92415
[9]	validation_0-rmse:1.90737
[10]	validation_0-rmse:1.88513
[11]	validation_0-rmse:1.87699
[12]	validation_0-rmse:1.86223
[13]	validation_0-rmse:1.84667
[14]	validation_0-rmse:1.83660
[15]	validation_0-rmse:1.82961
[16]	validation_0-rmse:1.81544
[17]	validation_0-rmse:1.80491
[18]	validation_0-rmse:1.79681
[19]	validation_0-rmse:1.78916
[20]	validation_0-rmse:1.78440
[21]	validation_0-rmse:1.77992
[22]	validation_0-rmse:1.77654
[23]	validation_0-rmse:1.77384
[24]	validation_0-rmse:1.76925
[25]	validation_0-rmse:1.76814
[26]	validation_0-rmse:1.76457
[27]	validation_0-rmse:1.75864
[28]	validation_0-rmse:1.75386
[29]	validation_0-rmse:1.75237
[30]	validation_0-rmse:1.75161
[31]	validation_0-rmse:1.74903
[32]	validation_0-rmse:1.74869
[33]	validation_0-rmse:1.74699
[34]	validation_0-rmse:1.74521
[35]	validation_0-rmse:1.74545
[36]	validation_0-rmse:1.74429
[37]	validation_0-rmse:1.74220
[38]	validation_0-rmse:1.74411
[39]	validation_0-rmse:1.74329
[40]	validation_0-rmse:1.74453
[41]	validation_0-rmse:1.74384
MSE: 3.0352565772030533
2013-12-26 [0]	validation_0-rmse:3.02065
[1]	validation_0-rmse:2.93822
[2]	validation_0-rmse:2.86038
[3]	validation_0-rmse:2.78871
[4]	validation_0-rmse:2.72547
[5]	validation_0-rmse:2.66673
[6]	validation_0-rmse:2.61010
[7]	validation_0-rmse:2.56228
[8]	validation_0-rmse:2.51891
[9]	validation_0-rmse:2.47300
[10]	validation_0-rmse:2.43732
[11]	validation_0-rmse:2.40228
[12]	validation_0-rmse:2.37311
[13]	validation_0-rmse:2.34763
[14]	validation_0-rmse:2.32642
[15]	validation_0-rmse:2.30218
[16]	validation_0-rmse:2.27991
[17]	validation_0-rmse:2.25759
[18]	validation_0-rmse:2.24096
[19]	validation_0-rmse:2.22678
[20]	validation_0-rmse:2.21118
[21]	validation_0-rmse:2.19811
[22]	validation_0-rmse:2.18625
[23]	validation_0-rmse:2.17402
[24]	validation_0-rmse:2.15913
[25]	validation_0-rmse:2.14800
[26]	validation_0-rmse:2.13788
[27]	validation_0-rmse:2.13257
[28]	validation_0-rmse:2.12622
[29]	validation_0-rmse:2.12211
[30]	validation_0-rmse:2.11635
[31]	validation_0-rmse:2.11009
[32]	validation_0-rmse:2.10359
[33]	validation_0-rmse:2.09910
[34]	validation_0-rmse:2.09040
[35]	validation_0-rmse:2.08964
[36]	validation_0-rmse:2.08759
[37]	validation_0-rmse:2.08388
[38]	validation_0-rmse:2.08449
[39]	validation_0-rmse:2.08467
[40]	validation_0-rmse:2.08118
[41]	validation_0-rmse:2.08052
[42]	validation_0-rmse:2.07834
[43]	validation_0-rmse:2.07500
[44]	validation_0-rmse:2.07553
[45]	validation_0-rmse:2.07539
[46]	validation_0-rmse:2.06966
[47]	validation_0-rmse:2.06999
[48]	validation_0-rmse:2.06838
[49]	validation_0-rmse:2.06802
[50]	validation_0-rmse:2.06689
[51]	validation_0-rmse:2.06770
[52]	validation_0-rmse:2.06357
[53]	validation_0-rmse:2.06444
[54]	validation_0-rmse:2.06464
[55]	validation_0-rmse:2.06644
[56]	validation_0-rmse:2.06554
MSE: 4.258306415731426
2013-12-27 [0]	validation_0-rmse:2.11966
[1]	validation_0-rmse:2.07567
[2]	validation_0-rmse:2.03479
[3]	validation_0-rmse:1.99587
[4]	validation_0-rmse:1.96147
[5]	validation_0-rmse:1.93318
[6]	validation_0-rmse:1.90681
[7]	validation_0-rmse:1.87941
[8]	validation_0-rmse:1.86288
[9]	validation_0-rmse:1.83793
[10]	validation_0-rmse:1.82391
[11]	validation_0-rmse:1.80607
[12]	validation_0-rmse:1.79382
[13]	validation_0-rmse:1.77725
[14]	validation_0-rmse:1.76884
[15]	validation_0-rmse:1.75784
[16]	validation_0-rmse:1.74474
[17]	validation_0-rmse:1.73570
[18]	validation_0-rmse:1.73032
[19]	validation_0-rmse:1.72180
[20]	validation_0-rmse:1.71586
[21]	validation_0-rmse:1.70818
[22]	validation_0-rmse:1.70502
[23]	validation_0-rmse:1.70502
[24]	validation_0-rmse:1.70111
[25]	validation_0-rmse:1.69988
[26]	validation_0-rmse:1.69690
[27]	validation_0-rmse:1.69549
[28]	validation_0-rmse:1.69344
[29]	validation_0-rmse:1.68966
[30]	validation_0-rmse:1.68670
[31]	validation_0-rmse:1.68488
[32]	validation_0-rmse:1.68365
[33]	validation_0-rmse:1.68428
[34]	validation_0-rmse:1.68444
[35]	validation_0-rmse:1.68463
[36]	validation_0-rmse:1.68649
[37]	validation_0-rmse:1.68718
MSE: 2.834690871313615
2013-12-30 [0]	validation_0-rmse:1.88700
[1]	validation_0-rmse:1.88286
[2]	validation_0-rmse:1.88379
[3]	validation_0-rmse:1.88394
[4]	validation_0-rmse:1.89196
[5]	validation_0-rmse:1.89199
[6]	validation_0-rmse:1.88985
MSE: 3.54516857664672
2013-12-31 [0]	validation_0-rmse:1.59974
[1]	validation_0-rmse:1.59088
[2]	validation_0-rmse:1.58136
[3]	validation_0-rmse:1.57059
[4]	validation_0-rmse:1.56463
[5]	validation_0-rmse:1.55896
[6]	validation_0-rmse:1.55437
[7]	validation_0-rmse:1.55505
[8]	validation_0-rmse:1.55019
[9]	validation_0-rmse:1.54865
[10]	validation_0-rmse:1.55050
[11]	validation_0-rmse:1.54665
[12]	validation_0-rmse:1.54876
[13]	validation_0-rmse:1.54673
[14]	validation_0-rmse:1.54645
[15]	validation_0-rmse:1.54309
[16]	validation_0-rmse:1.54613
[17]	validation_0-rmse:1.54592
[18]	validation_0-rmse:1.54819
[19]	validation_0-rmse:1.54660
MSE: 2.3811128419799914

np.array(XGBoost_err2).mean()

3.7204174628478524

2013年全年MSE平均值	原始模型	去除低重要性因子	加入板块数据
Linear使用平均值	3.9213	3.9034	3.7450
Linear去除缺失值	3.8005	3.8178	3.7889
XGBoost未去除缺失值	3.8883	3.9095	3.7986
XGBoost去除缺失值	3.7419	3.7494	3.7204

欣喜地看到，MSE有了显著的降低，尤其对于使用平均值/未去除缺失值数据。

毕设（六）板块可视化与板块因子

股票板块数据

获取数据

板块可视化

行业环形图

行业气泡图

数据连接与处理

线性模型拟合

XGBoost拟合

多因子模型及策略指数

毕设（五）去除低重要性因子

Nihilight

Nihilight