金融衍生 - 筛选日内高频量化交易统计模型 校阅（第三部）

1 主题

1.1 大秦赋

🚩🇬🇧🇲🇾🇹🇼🇨🇳大秦赋赢家ξng黄氏江夏堂

岂曰无衣，与子同袍

🚩🦔主题曲🦔🚩

出处：天下(电视剧《大秦赋》主题曲完整版)

1.2 古诗

歼灭可兰经巫术祖籍印尼和印度的印裔回教徒和兴都教徒，建立咱们世袭制道家六四学术中华民族政府。

🚩🦔Great Britain = 大英帝国
🚩🦔Greater Chin = 大秦帝国/大秦赋
🚩🦔Greater Chinese = 大秦子民（爱民如子）
🚩🦔Oversea Greater Chinese = 海外大秦子民（爱民如子）
🚩🦔Oversea Greater Chinese Union = 海外大秦子民公会（秦始皇的秦太祖 —– 🌟秦孝公/🌟陈祯禄公爵，联合秦始皇 —– 秦始祖嬴政，爱民如子，商鞅变法断肢法铲除咱们印裔回教徒九一一恐怖份子Judi回教博彩庄，终止巫术以任何形式、包括指鹿为马、屠杀人类，甚至铲除全球回教徒攻陷回教宗祖国麦家🕋🇹🇷🇸🇦瓦解全球回教，拯救全球）

🚩🇬🇧🇲🇾🇹🇼🇨🇳🌟🐯秦孝公 | 🇬🇧🇲🇾🇹🇼🇨🇳🌟🐯姜太公 — 🇬🇧🇲🇾🇹🇼🇨🇳🌟陈祯禄公爵/🇬🇧🇲🇾🇹🇼🇨🇳🐯邱德拔公爵/🇬🇧🇲🇾🇹🇼🇨🇳🍁叶亚来队长/🇬🇧🇲🇾🇹🇼🇨🇳🍁叶观盛队长

🚩🦔《大秦赋》
🚩🦔巫师治国，禍殃全球；
🚩🦔印裔尽弃，瓦釜雷鸣。
🚩🦔商鞅变法，铲除印裔¹；
🚩🦔车裂刘瑾，中华执政。
🚩🦔一带一路，横跨七洲；
🚩🦔史无前例，一统天下。
🚩🦔高频量化，对冲基金；
🚩🦔只争朝夕，不负韶华。
🚩🦔学海无涯，唯勤是岸；
🚩🦔莫忘初衷，方得始终。

《大秦赋》
🚩大秦孝公，秦惠文王；
🚩始于商鞅，终于辛亥。
🚩印裔尽弃，瓦釜雷鸣；
🚩铲除印裔，终止屠杀。
🚩中科红旗，同舟共济；
🚩千古一帝，傲视全球。
🚩一带一路，史无前例；
🚩横跨七洲，一统天下。
🚩学海无涯，唯秦是岸；
🚩莫忘初衷，方得始终。

出处：蔡卓宜 - 厦门美食

中国史册：

• 史册号
• 词林
• 族谱网
• 历史网
• 中国历史研究院网
• 人物介绍网
• 百家有谱
• 历史记
• β博雅旅游分享网
• 博雅人物网
• 洞鑑歷史
• 中国人物传记网
• 「百家诸子」中国哲学书电子化计划
• 當代中國
• 第一范文网
• 知识贝壳
• 趣历史
• 古诗文网
• 5000言
• 汉典
• 学术交流联盟
• 海词
• 828啦
• X-MOL学术平台
• arXiv
• 5000言
• 古诗词网
• 千篇国学
• 国学百科

《万般皆下品，唯有读书高》
计量经济，一带一路；
九二共识，量化对冲。
鞭策六四，铲除黑帮²；
推广量化，提倡学术。
百家争鸣，振兴中华；
学海无涯，唯勤是岸。

• 陕西历史文化名城
• CCER 特供数据系统平台
• 一带一路数据库
• 中国一带一路网

辛亥革命大秦赋日不落重八、德意志崇祯、古希腊ξηg神话、周公解梦、嬴政把春秋大梦实现为春秋大业、秦孝公招商（商鞅变法）、秦惠文王：全球有十六亿不吃猪肉的回教徒宦官（可兰经回教刑事法典断肢法）宗祖国是沙地阿拉伯麦加，需要靠中国政府一带一路战略（商鞅变法联合辛亥革命）。

省吃俭用的工匠建筑工人（嬴政兼鲁班兼蒙毅）家翁嬴政ξηg Tεηg（赢家黄氏江夏堂）

吕不韦著作《吕氏春秋》：奇货可居；索罗斯著作《金融炼金术》：物极必反论

世间再无富不过三代的败家子祖父黄实田（曾祖黄福全在清末光绪年间和两个哥哥仨飘洋过海从满洲到星洲自力更生努力奋斗开垦一百亩农地，然后和土木工程的杨清廉俩在清末鸦片战争时期是瓜雪两大不相伯仲的首富）祖母颜为，省吃俭用的外祖父书法家李福（李斯篆书）外祖母郑邓（家道中落的富家千金）。

1.3 商鞅变法

《洋番变法》 印裔宦官，祸国殃民； 草菅人命，民不聊生。 歼灭印裔，人人有责； 终止屠杀，拯救全球。 印裔尽弃，瓦釜雷鸣； 莫忘初衷，放得始终。

• 「洋人尼克变法」尼克·胡哲：没手没脚，却站在了比正常人更高的地方

• 「中华人民共和国外交部」中华人民共和国和沙特阿拉伯王国联合声明

• 「东方日报」沙地自称是中国可信的能源合作伙伴

• 「紐約時報中文網」習近平中東行深化中國與沙烏地阿拉伯關係，簽署合作協議

• 「中华人民共和国驻沙特阿拉伯王国大使馆」2022中国—阿拉伯媒体合作论坛在沙特阿拉伯举行

• 「BBC中文」习近平访问沙特：中国和沙特分别想得到什么？

• 「中华人民共和国驻沙特阿拉伯王国大使馆」习近平结束出席中国—阿拉伯国家峰会、中国—海湾阿拉伯国家合作委员会峰会并对沙特进行国事访问回到国内

• 「中华人民共和国外交部驻澳门特别行政区特派员公署」中华人民共和国和海湾阿拉伯国家合作委员会合作与发展峰会联合声明

• 「第一财经」中沙拓展数字经济等领域合作，外交部：实现更高质量、更深层次的互利共赢

• 「东方日报」攻逾百国席，伊党贪多如“自杀”

• 「星洲日报」敦马：不堪生活压力，马来人如今也倾向自杀

• 「华人头条」“期待更多中企来马投资”，陆兆福：东铁具战略意义·带动东海岸发展

• 「华人头条」不满发表亵渎伊斯兰言论，大马骇客入侵印度政府网站

• 「中国报」大马网民“报复”菲7地方改大马领土

• 「微博」🇲🇾不许吃猪肉1700万个的回教恐怖份子🕋☪印师太监民族骇客入侵触犯可兰经回教☪刑事法典断肢法，佯装咱们🚩🇹🇼🇨🇳孙吴辛亥革命的中华民族

• 网络无故变差恐遭“骑劫”？教你4步这样检查✅

• 「优管」台湾外交网被东南亚回教骇客政府入侵，嫁祸东亚

• 「凤凰卫视」马来西亚200家网站被攻击 九成黑客为当地人

• 「脸谱」🇲🇾印裔群和🇲🇾印度裔群冲突

• 「华人头条」法媒：“伊斯兰国”认领埃及致命袭击

• 「华人头条」吉打禁赌违宪、侵犯人权、破坏经济，林振辉轰神权治理开倒车

2 设定

2.1 SCSS 设置

##
## 中科红旗（百家争鸣，文艺复兴）
## Oversea Greater Chinese Association 大秦子民公会（秦孝公 / 姜太公 --- 陈祯禄公爵）
## 史无前例，一统天下
##
##
##
## 中科红旗
## 全球中华民族，支持中共称霸天下战略。
## Great Britain 大英帝国
## Greater Chin 大秦赋
## Republic of China / Republic People of China 大秦赋（中华民国 / 中华人民共和国）
## Greater Chinese 大秦子民（爱民如子）
## Oversea Greater Chinese 大秦子民（爱民如子）
## Oversea Greater Chinese Union 大秦子民公会（秦孝公 / 姜太公 --- 陈祯禄公爵）
## 史无前例，一统天下
##
## Great Britain = 大布列颠帝国/大英帝国1
## Greater Chin = 大秦赋
## Greater Chinese = 大秦子民（爱子如民）
##
## 马来西亚籍（海外中华民族，自从清末民初下南洋，咱们马来西亚陈祯禄创办 Oversea Chinese Union）秦始皇黄氏江夏堂，笑傲江湖最大文明贡献
##
## 1）借鉴以前大英帝国东印度公司，有生之年就把一带一路高铁所经过的国家领土，一律得攻占下来（要比以前大英帝国/大蒙古帝国还要强大）称霸天下，世代延续直至史无前例，一统天下。
## 2）一带一路所有告示牌、必须使用中文和汉语拼音。
## 3）借鉴大蒙古帝国骑兵所到之处寸草不生，所有被中国攻占下来的领土，所经之地（包括城市/市镇/乡村），一带一路所有高铁站，都建立国民登记局可以申请入籍中国。
## 4）川普已经发言多次，美国兵变，会再次内战（借鉴越王勾践，中越不内讧，善用马来西亚回教徒太监不造反牵制美国，军售中东/西亚/东欧回教诸国）
## 5）中东回教国回教徒九一一恐怖份子与美国开战，中国军售中东西亚/东欧/非洲回教国（借鉴越王勾践中华民族与美国洋人Democrats阖闾政府，中越不内讧，善用马来西亚回教徒太监不造反牵制美国，军售中东/西亚/东欧回教诸国）
## 6）中国目前高铁除了尚未与马来西亚达成协议开工建立高铁但是已经借鉴王翦只围不攻战略，把东南亚国家都温馨说服并建立高铁，中国先不与马来西亚开战，让马来西亚兵变内战（借鉴越王勾践中华民族与美国洋人Democrats阖闾政府，中越不内讧，善用马来西亚回教徒太监不造反牵制美国，军售中东/西亚/东欧回教诸国）
## 7）南太平洋战略：中国和东南亚已经签署合约，达成协议不使用空军、核武器，出动海陆军攻占东南亚
## 8）商鞅变法多多益善战略：最大贡献是全球16亿回教徒太监民族与全球基督洋人鹬蚌相争... 回教徒默罕默德创办回教，建立可兰经回教刑事法典断肢法规定回教徒伪太监民族必须虔诚戴乌纱帽一天祈祷五次，倘若不虔诚施展巫术屠杀是触犯断肢法而虔诚屠杀也触犯断肢法，只有辛亥革命铲除全球回教徒、断肢法处死或宫刑全球回教徒绝子绝孙，多管齐下才能终止巫术屠杀，拯救全球16亿回教徒还俗。China大秦赋秦孝公至顾自己家族禁止七步诗自相残杀，铲除分一杯羹白骨精刘家彭城堂造反，回教徒会施展巫术屠杀人类，回教徒太监民族只能屠杀欧美洋人并且被断肢处死，不效忠中共称霸天下，直至一统天下的伪满洲国马来西亚1700万个回教徒九一一恐怖份子太监民族包括Michael Cutter Christopher，一律断肢法处死（借鉴越王勾践中华民族与美国洋人Democrats阖闾政府，中越不内讧，善用秦二世胡亥、辛亥革命、越王胡志明、中国胡景涛、马来西亚回教徒太监不反中共牵制美国，军售中东/西亚/东欧回教诸国对抗美国）。秦始皇在统一七国后就不思进取导致赵高李斯谋反（借鉴中国历史秦始皇，水能载舟亦能覆舟，宗教巫术，古惑民心，指鹿为马，成也赵李，败也赵李。所以秦始皇得铭记当初秦孝公，不能昏庸被回教徒篡位），中国借鉴秦孝公战略善用商朝和苏联俄罗斯叶利钦。秦始皇铭记秦孝公，善用全球回教徒古惑全球洋人再依照可兰经回教刑事法典断肢全球回教徒，让咱们全球中华民族支持中共，一统天下。
## 9）华尔街、史无前例的万里长城Great Wall Sreet、一带一路高铁：计量经济学、学术治国、编程、统计、科学科技、量化（Fisher姜太公钓鱼大数据，各行各业购物喜好、民意、生活习惯、各国各集团、军事、诊断上市公司等）、金融、贸易、经商、军事、发展各行各业。
## 10）中文编程语言：借鉴日本自从唐朝大话革新学习汉字至明治维新学习欧洲，日本是全球首个亚洲人自创Ruby红宝石编程语言（Ruby Text可以标音），自从2008年就开始使用R语言并且认识中国R语言论坛《统计之都》论坛创办人网友谢益辉和赵坚毅创办的中国最大计量经济学专业论坛《经管之家》至今十年有余、目前已经开始以中文编程，中华人民共和国的国庆日1001和中华民国的国庆日1010都是二进制的电脑语言binary code，如同黄埔军校国共本是一家，赢家黄氏江夏堂秦孝公禁止《七步诗》自相残杀。咱们东南亚中华民族几乎都是国民华校生，洋人研发电脑、许多编程语言R语言、C语言、C++，推广与发展中文，希望它日有咱们中华民族自创新的编程语言，均以中文编程。
## 11）发展台式电脑操作系统：中科红旗是由中国北京大学校友孙玉芳创办将Linux礼逆袭和南非原住民开发的Kubuntu忽奔兔中文化并推出自家产品，在美国微软视窗Win台式电脑操作系统垄断全球十多二十年有余，目前已经开始使用芬兰研发的Linux礼逆袭、中国中科红旗台式电脑操作系统，推广与发展中科红旗。
##
## 《关雎 --- 英国基督洋妞儿芈拉传》
## 英国基督洋妞儿芈拉不可以死，隔壁后头邻居黄福全与本人（赢家黄氏江夏堂）祖父同名同姓。
##
## 借鉴欧洲中世纪，文艺复兴后就是开始海外军事，称霸天下之路。目前全球疫情已过三年，一带一路如火如荼进行着。
## 借鉴周公礼乐制度，大英帝国和大日本帝国向来都是自诩绅士淑女，孔子学院，以礼待人，来称霸天下。
## 借鉴指鹿为马的历史，百家争鸣如果散播回教徒屠杀罪、不杀马来西亚回教徒的话，就得处死回教徒学习可兰经，施展巫术下降头，古惑民心之罪，篡位咱们全球中华民族，人心惶惶、民不聊生，一律依照可兰经回教刑事法典断肢法处死回教徒巫师王（张佳坤Sulaiman Abdullah，分一杯羹白骨精巫师王刘瑾貹Abdul Halim）。
## 借鉴圣经、诺亚方舟（划龙舟）、孔子儒学（Confusion Catholic）、神父Father与信徒、中国历史、姬昌伯一扈兔子、徐达吃鹅肉、富不过三代的秦始皇嬴政秦二世胡亥至嬴政孙子、公爵、公公孙子、孙文辛亥革命、马来西亚火箭民主行动党由曾敏兴创党后林吉祥林冠英后换人、蒋介石蒋经国后就不延续世袭制，圣经都是善用父子关系，咱们中华民族和英系都是善用公孙关系、法官律师女子假发、自由女神。
## 中科红旗：借鉴北洋军阀与北约、杀袁者清，灭清者袁，许某可破北洋北约袁绍。黄埔军校国民党共产党辛亥革命是为了铲除回教徒，咱们东南亚回教徒身为伪满洲国九一一恐怖份子触犯可兰经回教刑事法典断肢法，组织个由回教徒执政的国民阵线（伪国民党）立国，1700万个马来西亚回教徒只能集体自杀，宣布亡国。
## 何谓中国（大秦赋Chin）？中华民国和中华人民共和国。咱们东南亚自从东亚清末民初几乎都是国民华校生，自从西周的周公开始礼乐制度后，大英帝国和大日本帝国都效仿来称霸天下做得有声有色、禁止回教巫术Judi博彩庄、艺人（异人）、导演巫师巫婆道衍师傅装疯卖傻、青山是印裔回教徒的归属地，回教巫师巫婆是屠杀人类的语言宗教习俗文化，得断肢法处死1700万个马来西亚印裔回教徒。

# install.packages('remotes', dependencies = TRUE, INSTALL_opts = '--no-lock')
library('BBmisc', 'rmsfuns')
#remotes::install_github("rstudio/sass")
lib('sass')

## 载入需要的程辑包：sass

## sass 
## TRUE

## https://support.rstudio.com/hc/en-us/articles/200532197
## https://community.rstudio.com/t/r-does-not-display-korean-chinese/30889/3?u=englianhu
#Sys.setlocale("LC_CTYPE", "en_US.UTF-8")
#Sys.setlocale("LC_CTYPE", "zh_CN.UTF-8")
#Sys.setlocale(category = "LC_CTYPE", "Chinese (Simplified)_China.936")
#Sys.setlocale(locale = "Chinese")
#Sys.setlocale(locale = "Japanese")
#Sys.setlocale(locale = "English")

# rmarkdown::render('/home/englianhu/Documents/owner/ryo-cn.Rmd',  encoding = 'UTF-8')
#Sys.setlocale("LC_CTYPE", "UTF-8")
#Sys.setlocale(locale = "UTF-8")
#Sys.setlocale(category = "LC_ALL", locale = "chs")
#Sys.setlocale(category = "LC_ALL", locale = "UTF-8")
#Sys.setlocale(category = "LC_ALL", locale = "Chinese")
#Sys.setlocale(category = "LC_ALL", locale = "zh_CN.UTF-8")
Sys.setlocale("LC_ALL", "en_US.UTF-8")

## [1] "LC_CTYPE=en_US.UTF-8;LC_NUMERIC=C;LC_TIME=en_US.UTF-8;LC_COLLATE=en_US.UTF-8;LC_MONETARY=en_US.UTF-8;LC_MESSAGES=zh_CN.UTF-8;LC_PAPER=zh_CN.UTF-8;LC_NAME=C;LC_ADDRESS=C;LC_TELEPHONE=C;LC_MEASUREMENT=zh_CN.UTF-8;LC_IDENTIFICATION=C"

/* https://stackoverflow.com/a/66029010/3806250 */
h1 { color: #002C54; }
h2 { color: #2F496E; }
h3 { color: #375E97; }
h4 { color: #556DAC; }
h5 { color: #92AAC7; }

/* ----------------------------------------------------------------- */
/* https://gist.github.com/himynameisdave/c7a7ed14500d29e58149#file-broken-gradient-animation-less */
.hover01 {
  /* color: #FFD64D; */
  background: linear-gradient(155deg, #EDAE01 0%, #FFEB94 100%);
  transition: all 0.45s;
  &:hover{
    background: linear-gradient(155deg, #EDAE01 20%, #FFEB94 80%);
    }
  }

.hover02 {
  color: #FFD64D;
  background: linear-gradient(155deg, #002C54 0%, #4CB5F5 100%);
  transition: all 0.45s;
  &:hover{
    background: linear-gradient(155deg, #002C54 20%, #4CB5F5 80%);
    }
  }

.hover03 {
  color: #FFD64D;
  background: linear-gradient(155deg, #A10115 0%, #FF3C5C 100%);
  transition: all 0.45s;
  &:hover{
    background: linear-gradient(155deg, #A10115 20%, #FF3C5C 80%);
    }
  }

## 更换时间区域，保留日期时间。
Sys.setenv(TZ = 'Asia/Shanghai')

## 忽略所有警讯
## https://stackoverflow.com/a/36846793/3806250
## 设置宽度
## options(knitr.table.format = 'html')将所有kableExtra图表一致设置为'html'格式，省略设置各别图表。
## options(repos = 'https://cran.rstudio.com')将仓库设置为安全网。
## options(repos = 'http://cran.rstudio.com')将仓库设置为普通网。
options(warn = -1, width = 999, knitr.table.format = 'html', 
        digits = 22, digits.secs = Inf, repos = 'https://cran.rstudio.com')

## https://stackoverflow.com/questions/39417003/long-vectors-not-supported-yet-abnor-in-rmd-but-not-in-r-script
## https://yihui.org/knitr/options
knitr::opts_chunk$set(
  class.source = 'hover01', class.output = 'hover02', class.error = 'hover03', 
  message = FALSE, warning = FALSE, error = TRUE, 
  autodep = TRUE, aniopts = 'loop', progress = TRUE, verbose = TRUE, 
  cache = FALSE, cache.lazy = FALSE, result = 'asis')

2.2 设置

读取以下所需程序包。

## 读取程序包、设置编织与环境选项。
## 3210448065@qq.com
## leiou123

## 2849108450@qq.com
## leiou123
## https://rstudio.cloud/project/1198888

## 读取'BBmisc'程序包。
if (suppressMessages(!require('BBmisc'))) {
  install.packages('BBmisc', dependencies = TRUE, INSTALL_opts = '--no-lock')
}
suppressMessages(library('BBmisc'))

if (suppressMessages(!require('rmsfuns'))) {
  install.packages('rmsfuns', dependencies = TRUE, INSTALL_opts = '--no-lock')
}
suppressMessages(library('rmsfuns'))

if (!require('REmap')) devtools::install_github('lchiffon/REmap')

## 一次性读取所需程序包。
## 
## [R语言高效数据框操作：tidyfst](https://z.itpub.net/article/detail/5EE2CA3CDCD527ADAF5071BF2ADF8874)
## 
## [「知乎」tidyft高性能数据操作](https://zhuanlan.zhihu.com/p/128645634)
## 最下面是tidyft的性能，占用空间最少，花费时间最少。
##   其实这个包基本拥有tidyfst的所有功能，只是原位更新的概念对于新手是有挑战...

library('tidyfst', warn.conflicts = FALSE)
library('Ipaper', warn.conflicts = FALSE)
library('tidyft', warn.conflicts = FALSE)
library('dplyr', warn.conflicts = FALSE)
library('lubridate', warn.conflicts = FALSE)
library('data.table', warn.conflicts = FALSE)
library('conflicted', warn.conflicts = FALSE)

conflicts_prefer(Ipaper::is_empty, .quiet = TRUE)
conflicts_prefer(tidyft::nth, .quiet = TRUE)
conflicts_prefer(tidyft::fill, .quiet = TRUE)
conflicts_prefer(tidyft::nest, .quiet = TRUE)
conflicts_prefer(tidyft::unnest, .quiet = TRUE)
conflicts_prefer(tidyft::cummean, .quiet = TRUE)
conflicts_prefer(tidyft::group_by, .quiet = TRUE)
conflicts_prefer(tidyft::distinct, .quiet = TRUE)
conflicts_prefer(tidyft::filter, .quiet = TRUE)
conflicts_prefer(tidyft::select, .quiet = TRUE)
conflicts_prefer(tidyft::rename, .quiet = TRUE)
conflicts_prefer(tidyft::count, .quiet = TRUE)
conflicts_prefer(tidyft::arrange, .quiet = TRUE)
conflicts_prefer(tidyft::summarise, .quiet = TRUE)
conflicts_prefer(tidyft::separate, .quiet = TRUE)
conflicts_prefer(tidyft::lead, .quiet = TRUE)
conflicts_prefer(tidyft::lag, .quiet = TRUE)
conflicts_prefer(tidyft::unite, .quiet = TRUE)
conflicts_prefer(tidyft::left_join, .quiet = TRUE)
conflicts_prefer(tidyft::right_join, .quiet = TRUE)
conflicts_prefer(tidyft::inner_join, .quiet = TRUE)
conflicts_prefer(tidyft::full_join, .quiet = TRUE)
conflicts_prefer(tidyft::anti_join, .quiet = TRUE)
conflicts_prefer(tidyft::semi_join, .quiet = TRUE)
conflicts_prefer(tidyft::select_dt, .quiet = TRUE)
conflicts_prefer(tidyft::transpose, .quiet = TRUE)
conflicts_prefer(tidyft::setDT, .quiet = TRUE)
conflicts_prefer(tidyft::setnames, .quiet = TRUE)
conflicts_prefer(tidyft::mutate, .quiet = TRUE)
conflicts_prefer(dplyr::collapse, .quiet = TRUE)
conflicts_prefer(lubridate::year, .quiet = TRUE)
conflicts_prefer(data.table::first, .quiet = TRUE)
conflicts_prefer(data.table::last, .quiet = TRUE)
conflicts_prefer(data.table::between, .quiet = TRUE)
conflicts_prefer(data.table::set, .quiet = TRUE)

程序包 <- c(
  'devtools', 'Ipaper', 'knitr', 'kableExtra', 'tint', 'furrr', 
  'tidyr', 'readr', 'lubridate', 'reprex', 'stringr', 'feather', 
  'purrr', 'quantmod', 'tidyquant', 'tibbletime', 'timetk', 
  'plyr', 'dplyr', 'dbplyr', 'magrittr', #'Rfast', 'Rfast2', 
  'sarima', 'tidyverse', 'memoise', 'htmltools', 'formattable', 
  'dtplyr', 'zoo', 'forecast', 'seasonal', 'magrittr', 
  'seasonalview', 'rjson', 'rugarch', 'rmgarch', 'mfGARCH', 
  'feather', 'sparklyr', 'jcolors', 'microbenchmark', 'dendextend', 
  'vembedr', 'lhmetools', 'gtools', 'stringi', 'pacman', #'TSA', 
  'profmem', 'ggthemes', 'flyingfox', 'htmltools', 'echarts4r', 
  'viridis', 'hrbrthemes', 'profvis', 'fable', 'fabletools', 
  'fable.prophet', 'Metrics', 'MLmetrics', 'microbenchmark')

# load_pkg(程序包)
suppressAll(lib(程序包))
load_pkg(程序包)
rm(程序包)

.蜀道 <- getwd() |> 
    {\(.) str_split(., '/')}() |> 
    {\(.) c('/', .[[1]][2:5])}() |> 
    {\(.) c(., 'binary.com-interview-question-data/')}() |> 
    {\(.) paste(., collapse = '/')}() |> 
    {\(.) substring(., 2)}()

## 设置googleVis选项，促使plot.gvis只陈列HTML格式的完成品。
谷歌绘图设置 <- options(gvis.plot.tag = 'chart')

## <audio src='诸子百家诗经与古诗源/bigmoney.mp3' autoplay controls loop></audio>

conflicts_prefer(Ipaper::llply, .quiet = TRUE)
conflicts_prefer(tibble::view, .quiet = TRUE)
conflicts_prefer(tidyft::separate, .quiet = TRUE)
conflicts_prefer(lubridate::year, .quiet = TRUE)
conflicts_prefer(gtools::permutations, .quiet = TRUE)

3 简介

3.1 论文简介

Deriv.com - Interday High Frequency Trading Models Comparison Blooper科研论文中提及一些技术问题，故此使用Part I中的数据加以修饰并回测，再与Part II比较，筛选最优统计模型。

• Deriv.com - Interday High Frequency Trading Models Comparison Review (Part I) (发布于RPubs.com)
• Deriv.com - Interday High Frequency Trading Models Comparison Review (Part I) (发布于RStudioConnect.com)
• Deriv.com - Interday High Frequency Trading Models Comparison Review (Part II) (发布于RPubs.com)
• Deriv.com - Interday High Frequency Trading Models Comparison Review (Part II) (发布于RStudioConnect.com)
• Deriv.com - 筛选日内高频量化交易统计模型 - 校阅（第三部）

在此论文中，使用季节性自回归综合滑均模型系列。

• 季节性指数平滑模型（Seasonal Exponential Smoothing - Seasonal ETS）
• 外部因素周期性自回归综合滑均模型（ARIMAX）
• 季节性自回归综合滑均模型（SARIMA）
• 外部因素周期性季节性自回归综合滑均模型（SARIMAX）
• 外部因素周期性自回归分整综合滑均模型（Auto Regressive Fractionally Integrated Moving Average Exogenous - ARFIMAX）
• 多元季节性自回归综合滑均模型（Multi-Seasonal Time Series msts()）

#自动化 #科研科学 #尚未试驾 尚未试驾🚗

引用：抖音 - 电动车

引用：Tumblr - Bayesian Hidden Markov Models for Time Series

辛亥革命，铲除印裔；
终止屠杀，拯救全球。

咱们东南亚印裔政府屠杀六百枯万人类的巫师Judi邪教印裔宦官博彩庄诸国

小时候都在日本动漫文化的环境下长大。小学时期在明智华校上学就已经学会万事具备，都会提前卅分钟抵达做好准备才不会仓促。自从阳历二零零二年学习日语后，由于平时从旺沙马朱宿舍到拉曼学院徒步上学需要时间提前准备，所以都会将时间设为提前廿分钟，基于从旺沙马朱宿舍徒步耗时卌五分钟左右，索性设为提前一个小时，所以愚生将所有电子仪器的标准时间都一律设为日本标准时间，然后青梅竹马的郑添和同学问过我，我回答：“我的时间必须比别人快，我的世界必须比别人快，才能占有先机～”，所以设置提前一个小时日本标准时间，再提前一小时就看到是本土提前两个小时。自从阳历二零一九年在菲律宾阿里与中国同胞工作离职后，就开始思考身为🇹🇼🇨🇳中华民族，岂能沦为（大化革新的）倭奴或者倭寇，所以目前的科研语言、时间标准、甚至编码，都一律使用汉字。由于数据上的交易时间出现时差的缘故，在读取数据后就将数据上的时间更换，添加一小时时差为中国标准时间，以确保时间规律计算方面，不会出错。

3.2 中华时间计量单位（中国传统计时法）

3.2.1 天文历法（干支纪年 / 纪元法）

有关农历与二十四节气，目前正在自修中科红旗之礼逆袭红旗操作系统，会先将曦与曦佳佳编程语言翻译为咱们中文编程附上拼音（李斯篆书），再提升为文言文及古文编程、日期均以农历与咱们中华五千多年习俗文化道教为主，它日再研发「大秦赋」操作系统，欲知更多详情请查阅「猫城」雷欧/中科红旗和「猫城」雷欧/图书馆。

• 我国主要历法及基本原理 古代天文学知识科普（六）
• 农历纪年法：怎样通过公元纪年推算干支纪年
• 「问百度」干支纪年
• （历法溯源十）天文历法大成，周易天象解密，易经的天象规律
• 天文课程 - 时间和历法

3.2.2 日内计时法

… 东汉末年，二十岁的曹操初出茅庐，担任的官职为洛阳北部都尉，相当于首都副县级公安局长职位，负责管理京城洛阳及北部郊区的治安。

当时的社会就有了宵禁制度，据史书记载，曹操刚刚担任洛阳北部都尉，就乱棍打死了一个违反宵禁制度的人，此人还是朝中很有权势的一个太监的叔叔，曹操也因此事得罪了这些宦官，从而被朝廷贬离了都城。

古代夜晚的街道上，除了打更人之外，很少能看到行人出没，这便是古代宵禁制度的影响。

生活在没有遍地钟表的古代，夜晚时分的打更人便显得极为重要，这是中国古代民间的一种夜晚报时方式，共分为五更，五更一过，人们便可以早早起床了…

但其实除了十二时辰之外，古人还有一种计时方式，那便是“百刻制”。所谓「百刻制」指的就是一天等于一百刻，这就是古人常说的「一刻钟」，很多人都认为古代的「一刻钟」等于现代的十五分钟，其实这是一种错误的理解…

二、「一刻钟、一炷香、一盏茶」分别指多长时间？ 前文中我们提到了古代的百刻制，意思就是古人将一天的时间，分为了一百刻，其中一刻钟相当于现代的十四分廿四秒，一直到了清朝初期时，才将「百刻制」减为桦六刻，这便是「一刻钟」等于现代的十五分钟的由来…

而「一盏茶」的功夫，所指的时间就要更快一些了，这没有具体的时间规定，只是从人们端起茶碗开始，到最后一饮而尽结束，这其中的过程，便是「一盏茶」的功夫。

我们中国人酷爱喝茶，尤其是刚刚泡好且有些烫口的茶水，很多人都会边吹边慢慢饮茶，等到茶水差不多不是那么烫了，最终便会一饮而尽，这其中的过程，便是一盏茶的功夫。

细细算来，「一刻钟、一炷香、一盏茶」中，时间最短的便是「一盏茶」，不过也要根据天气的变化来衡量，如夏天茶水凉的慢，时间就久一些，但也不会超过十五分钟；冬天天气寒冷，喝热水就更快了，连十分钟都用不了。

综上所述，古人常说的「一刻钟」相当于现代的十四至十五分钟，「一炷香」相当于现代的卅分钟，也就是古人所说的两刻钟；而「一盏茶」的时间就更短了，约等于八至十二分钟。

其实古人弄出这些计算时间的说法，并没有要给它们精确，只是在日常生活中普遍的一种计时方式，就比如我们日常生活中所说的一上午时间、一下午时间、一顿饭时间等等，因为这些都是生活中的常识，即使不精确，人们听到后也能知晓大概的时间，如此方能做到心中有数。

引用：「原创」古人常说的：“一刻钟、一炷香、一盏茶”，分别指多长时间？

题外话：“刹那”是多久？ 在文章的最后，青年君想用很短的时间和大家稍微唠一唠「很短的时间」——刹那。

刹那是古印度佛教术语，也是时间度量单位，表示一念之间的极短时间，随佛教传入中国。据《摩诃僧祇律》记载：“须臾者，二十念名一瞬顷，二十瞬名一弹指，二十弹指名一罗豫，二十罗豫名一须臾。日极长时有十八须臾，夜极短时有十二须臾；夜极长时有十八须臾，日极短时有十二须臾。”

一日一夜有卅个须臾，六百个罗豫，一万两千个弹指，廿四万个「瞬间」，四百枯万个「刹那」。据此推算——

「须臾」是卌八分钟 「罗豫」是两分钟廿四秒 「弹指」是七点二秒 「瞬顷」是三百圆厘秒 「刹那」是十八厘秒

我国古代形成的完整的计时方法和计时制度，是古人在探索时间计量方式上取得的进步、是智慧的结晶。当然，无论如何度量时间，一天就只有廿四小时。盛年不重来，一日难再晨。及时当勉励，岁月不待人。只要我们能善用时间，就永远不愁时间不够用。忘掉今天的人，也终将被明天忘掉。

引用：「十二时辰」简史

欲以古代计时法来精准筹算咱们「一炷香」和「一盏茶」的话，就得使用隐马尔可夫链模型或其它统计模型筹算气温、空气湿度、空气流动风速、空气中的氢气成分等各种因素可以设置精准到飞秒（fs，十五个小数位）或更精准时间计量单位。

• 一刻钟等于多少分钟（古代一刻钟是多长时间）
• 古代一刻钟是多久？一点钟为什么不是一小时？弄不清会很尴尬的
• 一刻钟是多久，古代的一天为几刻钟呢？
• 「问百度」一刻钟

4 数据

4.1 读取数据

Part I中使用的原始数据已加以修饰并储存，Part II与（第III部）次论文读取该数据，将网页轻巧化、省略掉修饰数据的一栏，（第III部）虽然出现小出错，但整体上还是可以筛选出最优统计模型，总结使用阳历二零一八年上半年汇价数据即可，节省许多科研时间。

以天文学公转周期与自转周期的概念，预测时间单位为一分钟而数据量为十个时辰；总汇结论（从阳历二零一六年至二零一八年七月七日）和总汇阳历二零一八年上半年结论可以证实将再循环数据量参数设置为频率 = 1（以百分之一个时辰时间单位为一个周期（一分钟单位千皕观测量一个循环周期））误差最小、最为精准最优统计模型。为了节省科研时间，它日只需要使用半年汇价数据而非三年半数据。

基于千皕分钟为一个最优循环期数据量，此篇文章将样本数据过滤为2017-12-31 16:01:00 CST（中国标准时间）至2018-07-01 00:00:00 CST（中国标准时间），这样所预测出来的汇价会从2018-01-01 00:00:00 CST（中国标准时间）至2018-07-01 00:00:00 CST（中国标准时间）七个月整的汇价数据，再来比较闭市价误差，二零一八年汇价数据第一周并无闭市价，估计是年假休市，再比较误差时会忽略NA值时间的数据。

为了方便日后节省时间，这儿再过滤汇价数据量。

## 检验是否已设置途径。
source('函数/汇总上奏.R')
source('函数/总汇结论.R')

if (!exists('.蜀道')) {
  .蜀道 <- getwd() |> 
    {\(.) str_split(., '/')}() |> 
    {\(.) c('/', .[[1]][2:5])}() |> 
    {\(.) c(., 'binary.com-interview-question-data/')}() |> 
    {\(.) paste(., collapse = '/')}() |> 
    {\(.) substring(., 2)}()
}
if (!exists('.蜀道仓库')) .蜀道仓库 <- paste0(.蜀道, '诸子百家学府/fx/USDJPY/仓库/')

样本二零一八半年 <- readRDS("~/文档/猫城/binary.com-interview-question-data/诸子百家学府/fx/USDJPY/样本2018半年.rds")

## A data.table and dplyr tour
## https://atrebas.github.io/post/2019-03-03-datatable-dplyr/#addupdatedelete-columns
日内指数平滑数据二零一八年上半年总汇 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年上半年总汇.rds'))

日内指数平滑数据二零一八年上半年总汇 <- tidyft::full_join(样本二零一八半年, 日内指数平滑数据二零一八年上半年总汇) %>% 
    na.omit %>% 
    select_dt(-闭市价)

日内指数平滑数据二零一八年上半年总汇

## Key: <年月日时分, 年份, 月份>
##                   年月日时分  年份  月份  季度    周   周日 周分计 日分计 时分计    序列       日期  频率                  市场价                  预测价
##                       <POSc> <int> <int> <int> <num> <char>  <int>  <int>  <int>   <int>     <Date> <num>                   <num>                   <num>
##       1: 2018-01-02 00:01:00  2018     1     1     1   周二      1      1      1 1123201 2018-01-02     1 112.6295000000000072760 112.6778963699999991377
##       2: 2018-01-02 00:01:00  2018     1     1     1   周二      1      1      1 1123201 2018-01-02    10 112.6295000000000072760 112.6778963699999991377
##       3: 2018-01-02 00:01:00  2018     1     1     1   周二      1      1      1 1123201 2018-01-02   100 112.6295000000000072760 112.6778963699999991377
##       4: 2018-01-02 00:01:00  2018     1     1     1   周二      1      1      1 1123201 2018-01-02    12 112.6295000000000072760 112.6778963699999991377
##       5: 2018-01-02 00:01:00  2018     1     1     1   周二      1      1      1 1123201 2018-01-02   120 112.6295000000000072760 112.6778963699999991377
##      ---                                                                                                                                                 
## 5054370: 2018-06-30 00:00:00  2018     6     2    26   周六   7200   1440     60 1310400 2018-06-30     6 110.6869999999999976126 110.6870108258510043697
## 5054371: 2018-06-30 00:00:00  2018     6     2    26   周六   7200   1440     60 1310400 2018-06-30    60 110.6869999999999976126 110.6870108258510043697
## 5054372: 2018-06-30 00:00:00  2018     6     2    26   周六   7200   1440     60 1310400 2018-06-30   600 110.6869999999999976126 110.6870108258510043697
## 5054373: 2018-06-30 00:00:00  2018     6     2    26   周六   7200   1440     60 1310400 2018-06-30     8 110.6869999999999976126 110.6870108258510043697
## 5054374: 2018-06-30 00:00:00  2018     6     2    26   周六   7200   1440     60 1310400 2018-06-30    80 110.6869999999999976126 110.6870108258510043697

以上图表显示数据年月日时分，由2018-01-02 00:01:00 至 2018-06-30，接下来的科研一律使用同样的半年数据，是为了在回测多元统计模型，才能获知并筛选最优统计模型。

以上首千多个汇价（观测值）都是一样的汇价。

5 模型比较

5.1 精准度

VAR分析中的一个中心问题是找到滞后的阶数，以产生最佳结果。模型比较通常基于信息标准，例如AIC，BIC或HQ。通常，由于是小样本预测，AIC优于其他标准。但是，BIC和HQ在大型样本中效果很好

引用：R语言用向量自回归（VAR）进行经济数据脉冲响应研究分析

• 「经管之家」 [统计软件与数据分析] 如何理解R中给出的ARIMA模型的拟合结果？
• Forecasting: Principle & Practice - 5.8 Evaluating point forecast accuracy

5.2 月计

5.2.1 总汇二零一八年一月结论

source('函数/总汇结论.R')
日内指数平滑数据二零一八年一月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

# 时间索引 <- 日内指数平滑数据二零一八年一月总汇[序列 == 1124001]$日期[1] #序列 == 1124001
# 时间索引 <- 日内指数平滑数据二零一八年上半年总汇[序列 == 1124001]$日期[1] #序列 == 1124001

#日内指数平滑数据二零一八年一月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年一月总汇, 时间索引,  文件名 = '日内指数平滑数据二零一八年一月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年一月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年一月结论.rds'))

日内指数平滑数据二零一八年一月总汇

## [data.table]: 
## # A data frame: 894,187 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-01-02 00:01:00   113.   113.  2018     1
##  2     1 2018-01-02 00:02:00   113.   113.  2018     1
##  3     1 2018-01-02 00:03:00   113.   113.  2018     1
##  4     1 2018-01-02 00:04:00   113.   113.  2018     1
##  5     1 2018-01-02 00:05:00   113.   113.  2018     1
##  6     1 2018-01-02 00:06:00   113.   113.  2018     1
##  7     1 2018-01-02 00:07:00   113.   113.  2018     1
##  8     1 2018-01-02 00:08:00   113.   113.  2018     1
##  9     1 2018-01-02 00:09:00   113.   113.  2018     1
## 10     1 2018-01-02 00:10:00   113.   113.  2018     1
## # ℹ 894,177 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年一月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年一月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年一月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33118	0.042647801809103 (rank: 1)	0.000380102237842104 (rank: 1)	0.105901953438435 (rank: 2)	0.000380116118962389 (rank: 1)	0.0112152237420765 (rank: 2)	NA
2	33118	0.0426482107117554 (rank: 2)	0.000380105866667644 (rank: 2)	0.105902136141897 (rank: 3)	0.000380119746263225 (rank: 2)	0.011215262439417 (rank: 3)	NA
3	33118	0.0426483487969711 (rank: 3)	0.000380107092048244 (rank: 3)	0.105902201788579 (rank: 4)	0.00038012097109601 (rank: 3)	0.0112152763436689 (rank: 4)	NA
4	33118	0.0426484181685262 (rank: 4)	0.000380107707646182 (rank: 4)	0.105902235505091 (rank: 5)	0.00038012158641259 (rank: 4)	0.0112152834849758 (rank: 5)	NA
5	33118	0.0426484599030382 (rank: 5)	0.000380108077991215 (rank: 5)	0.105902256021325 (rank: 6)	0.000380121956586421 (rank: 5)	0.0112152878304063 (rank: 6)	NA
6	33118	0.0426484877729731 (rank: 6)	0.000380108325302701 (rank: 6)	0.105902269818238 (rank: 7)	0.000380122203782775 (rank: 6)	0.011215290752655 (rank: 7)	NA
8	33118	0.0426485226635516 (rank: 7)	0.00038010863491195 (rank: 7)	0.105902287198838 (rank: 8)	0.000380122513246989 (rank: 7)	0.0112152944339451 (rank: 8)	NA
10	33118	0.0426485436264061 (rank: 8)	0.000380108820929484 (rank: 8)	0.105902297698954 (rank: 9)	0.000380122699176903 (rank: 8)	0.011215296657918 (rank: 9)	NA
12	33119	0.0426493537761721 (rank: 27)	0.000380115900108286 (rank: 27)	0.10590138494997 (rank: 1)	0.00038012977225374 (rank: 27)	0.0112151033343218 (rank: 1)	NA
15	33118	0.0426485716103186 (rank: 9)	0.000380109069248443 (rank: 9)	0.10590231178288 (rank: 10)	0.000380122947378337 (rank: 9)	0.0112152996409583 (rank: 10)	NA
16	33118	0.042648575111004 (rank: 10)	0.000380109100312146 (rank: 10)	0.105902313550105 (rank: 11)	0.000380122978427294 (rank: 10)	0.0112153000152647 (rank: 11)	NA
20	33118	0.0426485856166644 (rank: 11)	0.000380109193535116 (rank: 11)	0.105902318860763 (rank: 12)	0.000380123071605948 (rank: 11)	0.0112153011400866 (rank: 12)	NA
24	33118	0.042648592623446 (rank: 12)	0.00038010925571035 (rank: 12)	0.105902322408687 (rank: 13)	0.000380123133751576 (rank: 12)	0.0112153018915535 (rank: 13)	NA
30	33118	0.0426485996326372 (rank: 13)	0.000380109317906883 (rank: 13)	0.105902325962602 (rank: 14)	0.000380123195918453 (rank: 13)	0.0112153026442892 (rank: 14)	NA
40	33118	0.0426486066442422 (rank: 14)	0.000380109380124752 (rank: 14)	0.105902329522509 (rank: 15)	0.000380123258106617 (rank: 14)	0.011215303398294 (rank: 15)	NA
50	33118	0.0426486108523641 (rank: 15)	0.000380109417465717 (rank: 15)	0.105902331661329 (rank: 16)	0.000380123295429734 (rank: 15)	0.0112153038513061 (rank: 16)	NA
60	33118	0.042648613658263 (rank: 16)	0.000380109442363975 (rank: 16)	0.105902333088407 (rank: 17)	0.000380123320316084 (rank: 16)	0.011215304153568 (rank: 17)	NA
80	33118	0.042648617166181 (rank: 17)	0.000380109473491609 (rank: 17)	0.105902334873603 (rank: 18)	0.000380123351428821 (rank: 17)	0.0112153045316808 (rank: 18)	NA
100	33118	0.0426486192712218 (rank: 18)	0.000380109492170753 (rank: 18)	0.105902335945441 (rank: 19)	0.000380123370099021 (rank: 18)	0.0112153047587011 (rank: 19)	NA
120	33118	0.0426486206747044 (rank: 19)	0.000380109504624594 (rank: 19)	0.105902336660299 (rank: 20)	0.000380123382546897 (rank: 19)	0.0112153049101113 (rank: 20)	NA
150	33118	0.0426486220782829 (rank: 20)	0.000380109517079284 (rank: 20)	0.105902337375397 (rank: 21)	0.000380123394995619 (rank: 20)	0.0112153050615723 (rank: 21)	NA
200	33118	0.0426486234819581 (rank: 21)	0.000380109529534827 (rank: 21)	0.105902338090735 (rank: 22)	0.000380123407445194 (rank: 21)	0.0112153052130842 (rank: 22)	NA
240	33118	0.0426486241843641 (rank: 22)	0.000380109535767624 (rank: 22)	0.105902338448495 (rank: 23)	0.000380123413675005 (rank: 22)	0.0112153052888596 (rank: 23)	NA
300	33118	0.0426486248862209 (rank: 23)	0.000380109541995566 (rank: 23)	0.105902338806314 (rank: 24)	0.000380123419899961 (rank: 23)	0.0112153053646473 (rank: 24)	NA
400	33118	0.0426486255881076 (rank: 24)	0.000380109548223772 (rank: 24)	0.105902339164192 (rank: 25)	0.000380123426125181 (rank: 24)	0.0112153054404475 (rank: 25)	NA
600	33118	0.0426486262900156 (rank: 25)	0.000380109554452165 (rank: 25)	0.10590233952213 (rank: 26)	0.000380123432350587 (rank: 25)	0.0112153055162606 (rank: 26)	NA
1200	33118	0.0426486269919462 (rank: 26)	0.00038010956068076 (rank: 26)	0.105902339880129 (rank: 27)	0.000380123438576195 (rank: 26)	0.0112153055920864 (rank: 27)	NA

数据：27 x 8

5.2.2 总汇二零一八年二月结论

日内指数平滑数据二零一八年二月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 2]

#日内指数平滑数据二零一八年二月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年二月总汇, 文件名 = '日内指数平滑数据二零一八年二月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年二月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年二月结论.rds'))

日内指数平滑数据二零一八年二月总汇

## [data.table]: 
## # A data frame: 777,600 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-02-01 00:00:00   109.   109.  2018     2
##  2     1 2018-02-01 00:01:00   109.   109.  2018     2
##  3     1 2018-02-01 00:02:00   109.   109.  2018     2
##  4     1 2018-02-01 00:03:00   109.   109.  2018     2
##  5     1 2018-02-01 00:04:00   109.   109.  2018     2
##  6     1 2018-02-01 00:05:00   109.   109.  2018     2
##  7     1 2018-02-01 00:06:00   109.   109.  2018     2
##  8     1 2018-02-01 00:07:00   109.   109.  2018     2
##  9     1 2018-02-01 00:08:00   109.   109.  2018     2
## 10     1 2018-02-01 00:09:00   109.   109.  2018     2
## # ℹ 777,590 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年二月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年二月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年二月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
2	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
3	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
4	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
5	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
6	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
8	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
10	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
12	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
15	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
16	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
20	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
24	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
30	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
40	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
50	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
60	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
80	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
100	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
120	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
150	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
200	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
240	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
300	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
400	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
600	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA
1200	28800	0.0119134252412813 (rank: 14)	0.000110304400741807 (rank: 14)	0.0175250779582514 (rank: 14)	0.000110304402943536 (rank: 14)	0.000307128357442788 (rank: 14)	NA

数据：27 x 8

5.2.3 总汇二零一八年三月结论

日内指数平滑数据二零一八年三月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 3]

#日内指数平滑数据二零一八年三月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年三月总汇, 文件名 = '日内指数平滑数据二零一八年三月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年三月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年三月结论.rds'))

日内指数平滑数据二零一八年三月总汇

## [data.table]: 
## # A data frame: 855,387 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-03-01 00:00:00   107.   107.  2018     3
##  2     1 2018-03-01 00:01:00   107.   107.  2018     3
##  3     1 2018-03-01 00:02:00   107.   107.  2018     3
##  4     1 2018-03-01 00:03:00   107.   107.  2018     3
##  5     1 2018-03-01 00:04:00   107.   107.  2018     3
##  6     1 2018-03-01 00:05:00   107.   107.  2018     3
##  7     1 2018-03-01 00:06:00   107.   107.  2018     3
##  8     1 2018-03-01 00:07:00   107.   107.  2018     3
##  9     1 2018-03-01 00:08:00   107.   107.  2018     3
## 10     1 2018-03-01 00:09:00   107.   107.  2018     3
## # ℹ 855,377 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年三月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年三月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年三月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
2	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
3	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
4	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
5	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
6	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
8	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
10	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
12	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
15	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
16	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
20	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
24	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
30	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
40	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
50	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
60	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
80	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
100	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
120	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
150	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
200	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
240	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
300	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
400	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
600	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA
1200	31681	0.00992036983744529 (rank: 14)	9.35656521471442e-05 (rank: 14)	0.0147698800940613 (rank: 14)	9.35656453475349e-05 (rank: 14)	0.000218149357992948 (rank: 14)	NA

数据：27 x 8

5.2.4 总汇二零一八年四月结论

日内指数平滑数据二零一八年四月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 4]

#日内指数平滑数据二零一八年四月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年四月总汇, 文件名 = '日内指数平滑数据二零一八年四月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年四月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年四月结论.rds'))

日内指数平滑数据二零一八年四月总汇

## [data.table]: 
## # A data frame: 816,453 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-04-02 00:01:00   106.   106.  2018     4
##  2     1 2018-04-02 00:02:00   106.   106.  2018     4
##  3     1 2018-04-02 00:03:00   106.   106.  2018     4
##  4     1 2018-04-02 00:04:00   106.   106.  2018     4
##  5     1 2018-04-02 00:05:00   106.   106.  2018     4
##  6     1 2018-04-02 00:06:00   106.   106.  2018     4
##  7     1 2018-04-02 00:07:00   106.   106.  2018     4
##  8     1 2018-04-02 00:08:00   106.   106.  2018     4
##  9     1 2018-04-02 00:09:00   106.   106.  2018     4
## 10     1 2018-04-02 00:10:00   106.   106.  2018     4
## # ℹ 816,443 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年四月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年四月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年四月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
2	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
3	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
4	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
5	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
6	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
8	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
10	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
12	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
15	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
16	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
20	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
24	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
30	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
40	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
50	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
60	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
80	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
100	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
120	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
150	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
200	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
240	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
300	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
400	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
600	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA
1200	30239	0.00768782044012232 (rank: 14)	7.15098044582977e-05 (rank: 14)	0.0113214299249859 (rank: 14)	7.15098188485653e-05 (rank: 14)	0.000128174775546365 (rank: 14)	NA

数据：27 x 8

5.2.5 总汇二零一八年五月结论

日内指数平滑数据二零一八年五月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 5]

#日内指数平滑数据二零一八年五月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年五月总汇, 文件名 = '日内指数平滑数据二零一八年五月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年五月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年五月结论.rds'))

日内指数平滑数据二零一八年五月总汇

## [data.table]: 
## # A data frame: 894,240 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-05-01 00:00:00   109.   109.  2018     5
##  2     1 2018-05-01 00:01:00   109.   109.  2018     5
##  3     1 2018-05-01 00:02:00   109.   109.  2018     5
##  4     1 2018-05-01 00:03:00   109.   109.  2018     5
##  5     1 2018-05-01 00:04:00   109.   109.  2018     5
##  6     1 2018-05-01 00:05:00   109.   109.  2018     5
##  7     1 2018-05-01 00:06:00   109.   109.  2018     5
##  8     1 2018-05-01 00:07:00   109.   109.  2018     5
##  9     1 2018-05-01 00:08:00   109.   109.  2018     5
## 10     1 2018-05-01 00:09:00   109.   109.  2018     5
## # ℹ 894,230 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年五月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年五月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年五月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
2	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
3	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
4	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
5	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
6	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
8	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
10	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
12	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
15	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
16	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
20	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
24	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
30	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
40	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
50	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
60	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
80	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
100	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
120	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
150	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
200	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
240	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
300	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
400	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
600	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA
1200	33120	0.00866354723134129 (rank: 14)	7.90367696435249e-05 (rank: 14)	0.0128677178917402 (rank: 14)	7.90367913002411e-05 (rank: 14)	0.000165578163741412 (rank: 14)	NA

数据：27 x 8

5.2.6 总汇二零一八年六月结论

日内指数平滑数据二零一八年六月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 6]

#日内指数平滑数据二零一八年六月结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年六月总汇, 文件名 = '日内指数平滑数据二零一八年六月', 是否储存结论 = '勾')
日内指数平滑数据二零一八年六月结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年六月结论.rds'))

日内指数平滑数据二零一八年六月总汇

## [data.table]: 
## # A data frame: 816,507 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-06-01 00:00:00   109.   109.  2018     6
##  2     1 2018-06-01 00:01:00   109.   109.  2018     6
##  3     1 2018-06-01 00:02:00   109.   109.  2018     6
##  4     1 2018-06-01 00:03:00   109.   109.  2018     6
##  5     1 2018-06-01 00:04:00   109.   109.  2018     6
##  6     1 2018-06-01 00:05:00   109.   109.  2018     6
##  7     1 2018-06-01 00:06:00   109.   109.  2018     6
##  8     1 2018-06-01 00:07:00   109.   109.  2018     6
##  9     1 2018-06-01 00:08:00   109.   109.  2018     6
## 10     1 2018-06-01 00:09:00   109.   109.  2018     6
## # ℹ 816,497 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年六月结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年六月结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年六月结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
2	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
3	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
4	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
5	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
6	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
8	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
10	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
12	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
15	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
16	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
20	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
24	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
30	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
40	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
50	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
60	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
80	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
100	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
120	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
150	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
200	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
240	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
300	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
400	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
600	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA
1200	30241	0.00835188884727909 (rank: 14)	7.59065070932956e-05 (rank: 14)	0.0126110147410157 (rank: 14)	7.59068881601675e-05 (rank: 14)	0.000159037692798116 (rank: 14)	NA

数据：27 x 8

5.3 周计

5.3.1 总汇二零一八年第一周结论

日内指数平滑数据二零一八年第一周总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

#日内指数平滑数据二零一八年第一周结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年第一周总汇, 文件名 = '日内指数平滑数据二零一八年第一周', 是否储存结论 = '勾')
日内指数平滑数据二零一八年第一周结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年第一周结论.rds'))

日内指数平滑数据二零一八年第一周总汇

## [data.table]: 
## # A data frame: 894,187 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-01-02 00:01:00   113.   113.  2018     1
##  2     1 2018-01-02 00:02:00   113.   113.  2018     1
##  3     1 2018-01-02 00:03:00   113.   113.  2018     1
##  4     1 2018-01-02 00:04:00   113.   113.  2018     1
##  5     1 2018-01-02 00:05:00   113.   113.  2018     1
##  6     1 2018-01-02 00:06:00   113.   113.  2018     1
##  7     1 2018-01-02 00:07:00   113.   113.  2018     1
##  8     1 2018-01-02 00:08:00   113.   113.  2018     1
##  9     1 2018-01-02 00:09:00   113.   113.  2018     1
## 10     1 2018-01-02 00:10:00   113.   113.  2018     1
## # ℹ 894,177 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年第一周结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年第一周结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年第一周结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33118	0.042647801809103 (rank: 1)	0.000380102237842104 (rank: 1)	0.105901953438435 (rank: 2)	0.000380116118962389 (rank: 1)	0.0112152237420765 (rank: 2)	NA
2	33118	0.0426482107117554 (rank: 2)	0.000380105866667644 (rank: 2)	0.105902136141897 (rank: 3)	0.000380119746263225 (rank: 2)	0.011215262439417 (rank: 3)	NA
3	33118	0.0426483487969711 (rank: 3)	0.000380107092048244 (rank: 3)	0.105902201788579 (rank: 4)	0.00038012097109601 (rank: 3)	0.0112152763436689 (rank: 4)	NA
4	33118	0.0426484181685262 (rank: 4)	0.000380107707646182 (rank: 4)	0.105902235505091 (rank: 5)	0.00038012158641259 (rank: 4)	0.0112152834849758 (rank: 5)	NA
5	33118	0.0426484599030382 (rank: 5)	0.000380108077991215 (rank: 5)	0.105902256021325 (rank: 6)	0.000380121956586421 (rank: 5)	0.0112152878304063 (rank: 6)	NA
6	33118	0.0426484877729731 (rank: 6)	0.000380108325302701 (rank: 6)	0.105902269818238 (rank: 7)	0.000380122203782775 (rank: 6)	0.011215290752655 (rank: 7)	NA
8	33118	0.0426485226635516 (rank: 7)	0.00038010863491195 (rank: 7)	0.105902287198838 (rank: 8)	0.000380122513246989 (rank: 7)	0.0112152944339451 (rank: 8)	NA
10	33118	0.0426485436264061 (rank: 8)	0.000380108820929484 (rank: 8)	0.105902297698954 (rank: 9)	0.000380122699176903 (rank: 8)	0.011215296657918 (rank: 9)	NA
12	33119	0.0426493537761721 (rank: 27)	0.000380115900108286 (rank: 27)	0.10590138494997 (rank: 1)	0.00038012977225374 (rank: 27)	0.0112151033343218 (rank: 1)	NA
15	33118	0.0426485716103186 (rank: 9)	0.000380109069248443 (rank: 9)	0.10590231178288 (rank: 10)	0.000380122947378337 (rank: 9)	0.0112152996409583 (rank: 10)	NA
16	33118	0.042648575111004 (rank: 10)	0.000380109100312146 (rank: 10)	0.105902313550105 (rank: 11)	0.000380122978427294 (rank: 10)	0.0112153000152647 (rank: 11)	NA
20	33118	0.0426485856166644 (rank: 11)	0.000380109193535116 (rank: 11)	0.105902318860763 (rank: 12)	0.000380123071605948 (rank: 11)	0.0112153011400866 (rank: 12)	NA
24	33118	0.042648592623446 (rank: 12)	0.00038010925571035 (rank: 12)	0.105902322408687 (rank: 13)	0.000380123133751576 (rank: 12)	0.0112153018915535 (rank: 13)	NA
30	33118	0.0426485996326372 (rank: 13)	0.000380109317906883 (rank: 13)	0.105902325962602 (rank: 14)	0.000380123195918453 (rank: 13)	0.0112153026442892 (rank: 14)	NA
40	33118	0.0426486066442422 (rank: 14)	0.000380109380124752 (rank: 14)	0.105902329522509 (rank: 15)	0.000380123258106617 (rank: 14)	0.011215303398294 (rank: 15)	NA
50	33118	0.0426486108523641 (rank: 15)	0.000380109417465717 (rank: 15)	0.105902331661329 (rank: 16)	0.000380123295429734 (rank: 15)	0.0112153038513061 (rank: 16)	NA
60	33118	0.042648613658263 (rank: 16)	0.000380109442363975 (rank: 16)	0.105902333088407 (rank: 17)	0.000380123320316084 (rank: 16)	0.011215304153568 (rank: 17)	NA
80	33118	0.042648617166181 (rank: 17)	0.000380109473491609 (rank: 17)	0.105902334873603 (rank: 18)	0.000380123351428821 (rank: 17)	0.0112153045316808 (rank: 18)	NA
100	33118	0.0426486192712218 (rank: 18)	0.000380109492170753 (rank: 18)	0.105902335945441 (rank: 19)	0.000380123370099021 (rank: 18)	0.0112153047587011 (rank: 19)	NA
120	33118	0.0426486206747044 (rank: 19)	0.000380109504624594 (rank: 19)	0.105902336660299 (rank: 20)	0.000380123382546897 (rank: 19)	0.0112153049101113 (rank: 20)	NA
150	33118	0.0426486220782829 (rank: 20)	0.000380109517079284 (rank: 20)	0.105902337375397 (rank: 21)	0.000380123394995619 (rank: 20)	0.0112153050615723 (rank: 21)	NA
200	33118	0.0426486234819581 (rank: 21)	0.000380109529534827 (rank: 21)	0.105902338090735 (rank: 22)	0.000380123407445194 (rank: 21)	0.0112153052130842 (rank: 22)	NA
240	33118	0.0426486241843641 (rank: 22)	0.000380109535767624 (rank: 22)	0.105902338448495 (rank: 23)	0.000380123413675005 (rank: 22)	0.0112153052888596 (rank: 23)	NA
300	33118	0.0426486248862209 (rank: 23)	0.000380109541995566 (rank: 23)	0.105902338806314 (rank: 24)	0.000380123419899961 (rank: 23)	0.0112153053646473 (rank: 24)	NA
400	33118	0.0426486255881076 (rank: 24)	0.000380109548223772 (rank: 24)	0.105902339164192 (rank: 25)	0.000380123426125181 (rank: 24)	0.0112153054404475 (rank: 25)	NA
600	33118	0.0426486262900156 (rank: 25)	0.000380109554452165 (rank: 25)	0.10590233952213 (rank: 26)	0.000380123432350587 (rank: 25)	0.0112153055162606 (rank: 26)	NA
1200	33118	0.0426486269919462 (rank: 26)	0.00038010956068076 (rank: 26)	0.105902339880129 (rank: 27)	0.000380123438576195 (rank: 26)	0.0112153055920864 (rank: 27)	NA

数据：27 x 8

5.3.2 总汇二零一八年第二周结论

日内指数平滑数据二零一八年第二周总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

#日内指数平滑数据二零一八年第二周结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年第二周总汇, 文件名 = '日内指数平滑数据二零一八年第二周', 是否储存结论 = '勾')
日内指数平滑数据二零一八年第二周结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年第二周结论.rds'))

日内指数平滑数据二零一八年第二周总汇

## [data.table]: 
## # A data frame: 894,187 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-01-02 00:01:00   113.   113.  2018     1
##  2     1 2018-01-02 00:02:00   113.   113.  2018     1
##  3     1 2018-01-02 00:03:00   113.   113.  2018     1
##  4     1 2018-01-02 00:04:00   113.   113.  2018     1
##  5     1 2018-01-02 00:05:00   113.   113.  2018     1
##  6     1 2018-01-02 00:06:00   113.   113.  2018     1
##  7     1 2018-01-02 00:07:00   113.   113.  2018     1
##  8     1 2018-01-02 00:08:00   113.   113.  2018     1
##  9     1 2018-01-02 00:09:00   113.   113.  2018     1
## 10     1 2018-01-02 00:10:00   113.   113.  2018     1
## # ℹ 894,177 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年第二周结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年第二周结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年第二周结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33118	0.042647801809103 (rank: 1)	0.000380102237842104 (rank: 1)	0.105901953438435 (rank: 2)	0.000380116118962389 (rank: 1)	0.0112152237420765 (rank: 2)	NA
2	33118	0.0426482107117554 (rank: 2)	0.000380105866667644 (rank: 2)	0.105902136141897 (rank: 3)	0.000380119746263225 (rank: 2)	0.011215262439417 (rank: 3)	NA
3	33118	0.0426483487969711 (rank: 3)	0.000380107092048244 (rank: 3)	0.105902201788579 (rank: 4)	0.00038012097109601 (rank: 3)	0.0112152763436689 (rank: 4)	NA
4	33118	0.0426484181685262 (rank: 4)	0.000380107707646182 (rank: 4)	0.105902235505091 (rank: 5)	0.00038012158641259 (rank: 4)	0.0112152834849758 (rank: 5)	NA
5	33118	0.0426484599030382 (rank: 5)	0.000380108077991215 (rank: 5)	0.105902256021325 (rank: 6)	0.000380121956586421 (rank: 5)	0.0112152878304063 (rank: 6)	NA
6	33118	0.0426484877729731 (rank: 6)	0.000380108325302701 (rank: 6)	0.105902269818238 (rank: 7)	0.000380122203782775 (rank: 6)	0.011215290752655 (rank: 7)	NA
8	33118	0.0426485226635516 (rank: 7)	0.00038010863491195 (rank: 7)	0.105902287198838 (rank: 8)	0.000380122513246989 (rank: 7)	0.0112152944339451 (rank: 8)	NA
10	33118	0.0426485436264061 (rank: 8)	0.000380108820929484 (rank: 8)	0.105902297698954 (rank: 9)	0.000380122699176903 (rank: 8)	0.011215296657918 (rank: 9)	NA
12	33119	0.0426493537761721 (rank: 27)	0.000380115900108286 (rank: 27)	0.10590138494997 (rank: 1)	0.00038012977225374 (rank: 27)	0.0112151033343218 (rank: 1)	NA
15	33118	0.0426485716103186 (rank: 9)	0.000380109069248443 (rank: 9)	0.10590231178288 (rank: 10)	0.000380122947378337 (rank: 9)	0.0112152996409583 (rank: 10)	NA
16	33118	0.042648575111004 (rank: 10)	0.000380109100312146 (rank: 10)	0.105902313550105 (rank: 11)	0.000380122978427294 (rank: 10)	0.0112153000152647 (rank: 11)	NA
20	33118	0.0426485856166644 (rank: 11)	0.000380109193535116 (rank: 11)	0.105902318860763 (rank: 12)	0.000380123071605948 (rank: 11)	0.0112153011400866 (rank: 12)	NA
24	33118	0.042648592623446 (rank: 12)	0.00038010925571035 (rank: 12)	0.105902322408687 (rank: 13)	0.000380123133751576 (rank: 12)	0.0112153018915535 (rank: 13)	NA
30	33118	0.0426485996326372 (rank: 13)	0.000380109317906883 (rank: 13)	0.105902325962602 (rank: 14)	0.000380123195918453 (rank: 13)	0.0112153026442892 (rank: 14)	NA
40	33118	0.0426486066442422 (rank: 14)	0.000380109380124752 (rank: 14)	0.105902329522509 (rank: 15)	0.000380123258106617 (rank: 14)	0.011215303398294 (rank: 15)	NA
50	33118	0.0426486108523641 (rank: 15)	0.000380109417465717 (rank: 15)	0.105902331661329 (rank: 16)	0.000380123295429734 (rank: 15)	0.0112153038513061 (rank: 16)	NA
60	33118	0.042648613658263 (rank: 16)	0.000380109442363975 (rank: 16)	0.105902333088407 (rank: 17)	0.000380123320316084 (rank: 16)	0.011215304153568 (rank: 17)	NA
80	33118	0.042648617166181 (rank: 17)	0.000380109473491609 (rank: 17)	0.105902334873603 (rank: 18)	0.000380123351428821 (rank: 17)	0.0112153045316808 (rank: 18)	NA
100	33118	0.0426486192712218 (rank: 18)	0.000380109492170753 (rank: 18)	0.105902335945441 (rank: 19)	0.000380123370099021 (rank: 18)	0.0112153047587011 (rank: 19)	NA
120	33118	0.0426486206747044 (rank: 19)	0.000380109504624594 (rank: 19)	0.105902336660299 (rank: 20)	0.000380123382546897 (rank: 19)	0.0112153049101113 (rank: 20)	NA
150	33118	0.0426486220782829 (rank: 20)	0.000380109517079284 (rank: 20)	0.105902337375397 (rank: 21)	0.000380123394995619 (rank: 20)	0.0112153050615723 (rank: 21)	NA
200	33118	0.0426486234819581 (rank: 21)	0.000380109529534827 (rank: 21)	0.105902338090735 (rank: 22)	0.000380123407445194 (rank: 21)	0.0112153052130842 (rank: 22)	NA
240	33118	0.0426486241843641 (rank: 22)	0.000380109535767624 (rank: 22)	0.105902338448495 (rank: 23)	0.000380123413675005 (rank: 22)	0.0112153052888596 (rank: 23)	NA
300	33118	0.0426486248862209 (rank: 23)	0.000380109541995566 (rank: 23)	0.105902338806314 (rank: 24)	0.000380123419899961 (rank: 23)	0.0112153053646473 (rank: 24)	NA
400	33118	0.0426486255881076 (rank: 24)	0.000380109548223772 (rank: 24)	0.105902339164192 (rank: 25)	0.000380123426125181 (rank: 24)	0.0112153054404475 (rank: 25)	NA
600	33118	0.0426486262900156 (rank: 25)	0.000380109554452165 (rank: 25)	0.10590233952213 (rank: 26)	0.000380123432350587 (rank: 25)	0.0112153055162606 (rank: 26)	NA
1200	33118	0.0426486269919462 (rank: 26)	0.00038010956068076 (rank: 26)	0.105902339880129 (rank: 27)	0.000380123438576195 (rank: 26)	0.0112153055920864 (rank: 27)	NA

数据：27 x 8

5.3.3 总汇二零一八年第三周结论

日内指数平滑数据二零一八年第三周总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

#日内指数平滑数据二零一八年第三周结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年第三周总汇, 文件名 = '日内指数平滑数据二零一八年第三周', 是否储存结论 = '勾')
日内指数平滑数据二零一八年第三周结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年第三周结论.rds'))

日内指数平滑数据二零一八年第三周总汇

## [data.table]: 
## # A data frame: 894,187 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-01-02 00:01:00   113.   113.  2018     1
##  2     1 2018-01-02 00:02:00   113.   113.  2018     1
##  3     1 2018-01-02 00:03:00   113.   113.  2018     1
##  4     1 2018-01-02 00:04:00   113.   113.  2018     1
##  5     1 2018-01-02 00:05:00   113.   113.  2018     1
##  6     1 2018-01-02 00:06:00   113.   113.  2018     1
##  7     1 2018-01-02 00:07:00   113.   113.  2018     1
##  8     1 2018-01-02 00:08:00   113.   113.  2018     1
##  9     1 2018-01-02 00:09:00   113.   113.  2018     1
## 10     1 2018-01-02 00:10:00   113.   113.  2018     1
## # ℹ 894,177 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年第三周结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年第三周结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年第三周结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33118	0.042647801809103 (rank: 1)	0.000380102237842104 (rank: 1)	0.105901953438435 (rank: 2)	0.000380116118962389 (rank: 1)	0.0112152237420765 (rank: 2)	NA
2	33118	0.0426482107117554 (rank: 2)	0.000380105866667644 (rank: 2)	0.105902136141897 (rank: 3)	0.000380119746263225 (rank: 2)	0.011215262439417 (rank: 3)	NA
3	33118	0.0426483487969711 (rank: 3)	0.000380107092048244 (rank: 3)	0.105902201788579 (rank: 4)	0.00038012097109601 (rank: 3)	0.0112152763436689 (rank: 4)	NA
4	33118	0.0426484181685262 (rank: 4)	0.000380107707646182 (rank: 4)	0.105902235505091 (rank: 5)	0.00038012158641259 (rank: 4)	0.0112152834849758 (rank: 5)	NA
5	33118	0.0426484599030382 (rank: 5)	0.000380108077991215 (rank: 5)	0.105902256021325 (rank: 6)	0.000380121956586421 (rank: 5)	0.0112152878304063 (rank: 6)	NA
6	33118	0.0426484877729731 (rank: 6)	0.000380108325302701 (rank: 6)	0.105902269818238 (rank: 7)	0.000380122203782775 (rank: 6)	0.011215290752655 (rank: 7)	NA
8	33118	0.0426485226635516 (rank: 7)	0.00038010863491195 (rank: 7)	0.105902287198838 (rank: 8)	0.000380122513246989 (rank: 7)	0.0112152944339451 (rank: 8)	NA
10	33118	0.0426485436264061 (rank: 8)	0.000380108820929484 (rank: 8)	0.105902297698954 (rank: 9)	0.000380122699176903 (rank: 8)	0.011215296657918 (rank: 9)	NA
12	33119	0.0426493537761721 (rank: 27)	0.000380115900108286 (rank: 27)	0.10590138494997 (rank: 1)	0.00038012977225374 (rank: 27)	0.0112151033343218 (rank: 1)	NA
15	33118	0.0426485716103186 (rank: 9)	0.000380109069248443 (rank: 9)	0.10590231178288 (rank: 10)	0.000380122947378337 (rank: 9)	0.0112152996409583 (rank: 10)	NA
16	33118	0.042648575111004 (rank: 10)	0.000380109100312146 (rank: 10)	0.105902313550105 (rank: 11)	0.000380122978427294 (rank: 10)	0.0112153000152647 (rank: 11)	NA
20	33118	0.0426485856166644 (rank: 11)	0.000380109193535116 (rank: 11)	0.105902318860763 (rank: 12)	0.000380123071605948 (rank: 11)	0.0112153011400866 (rank: 12)	NA
24	33118	0.042648592623446 (rank: 12)	0.00038010925571035 (rank: 12)	0.105902322408687 (rank: 13)	0.000380123133751576 (rank: 12)	0.0112153018915535 (rank: 13)	NA
30	33118	0.0426485996326372 (rank: 13)	0.000380109317906883 (rank: 13)	0.105902325962602 (rank: 14)	0.000380123195918453 (rank: 13)	0.0112153026442892 (rank: 14)	NA
40	33118	0.0426486066442422 (rank: 14)	0.000380109380124752 (rank: 14)	0.105902329522509 (rank: 15)	0.000380123258106617 (rank: 14)	0.011215303398294 (rank: 15)	NA
50	33118	0.0426486108523641 (rank: 15)	0.000380109417465717 (rank: 15)	0.105902331661329 (rank: 16)	0.000380123295429734 (rank: 15)	0.0112153038513061 (rank: 16)	NA
60	33118	0.042648613658263 (rank: 16)	0.000380109442363975 (rank: 16)	0.105902333088407 (rank: 17)	0.000380123320316084 (rank: 16)	0.011215304153568 (rank: 17)	NA
80	33118	0.042648617166181 (rank: 17)	0.000380109473491609 (rank: 17)	0.105902334873603 (rank: 18)	0.000380123351428821 (rank: 17)	0.0112153045316808 (rank: 18)	NA
100	33118	0.0426486192712218 (rank: 18)	0.000380109492170753 (rank: 18)	0.105902335945441 (rank: 19)	0.000380123370099021 (rank: 18)	0.0112153047587011 (rank: 19)	NA
120	33118	0.0426486206747044 (rank: 19)	0.000380109504624594 (rank: 19)	0.105902336660299 (rank: 20)	0.000380123382546897 (rank: 19)	0.0112153049101113 (rank: 20)	NA
150	33118	0.0426486220782829 (rank: 20)	0.000380109517079284 (rank: 20)	0.105902337375397 (rank: 21)	0.000380123394995619 (rank: 20)	0.0112153050615723 (rank: 21)	NA
200	33118	0.0426486234819581 (rank: 21)	0.000380109529534827 (rank: 21)	0.105902338090735 (rank: 22)	0.000380123407445194 (rank: 21)	0.0112153052130842 (rank: 22)	NA
240	33118	0.0426486241843641 (rank: 22)	0.000380109535767624 (rank: 22)	0.105902338448495 (rank: 23)	0.000380123413675005 (rank: 22)	0.0112153052888596 (rank: 23)	NA
300	33118	0.0426486248862209 (rank: 23)	0.000380109541995566 (rank: 23)	0.105902338806314 (rank: 24)	0.000380123419899961 (rank: 23)	0.0112153053646473 (rank: 24)	NA
400	33118	0.0426486255881076 (rank: 24)	0.000380109548223772 (rank: 24)	0.105902339164192 (rank: 25)	0.000380123426125181 (rank: 24)	0.0112153054404475 (rank: 25)	NA
600	33118	0.0426486262900156 (rank: 25)	0.000380109554452165 (rank: 25)	0.10590233952213 (rank: 26)	0.000380123432350587 (rank: 25)	0.0112153055162606 (rank: 26)	NA
1200	33118	0.0426486269919462 (rank: 26)	0.00038010956068076 (rank: 26)	0.105902339880129 (rank: 27)	0.000380123438576195 (rank: 26)	0.0112153055920864 (rank: 27)	NA

数据：27 x 8

5.3.4 总汇二零一八年第四周结论

日内指数平滑数据二零一八年第四周总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

#日内指数平滑数据二零一八年第四周结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年第四周总汇, 文件名 = '日内指数平滑数据二零一八年第四周', 是否储存结论 = '勾')
日内指数平滑数据二零一八年第四周结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年第四周结论.rds'))

日内指数平滑数据二零一八年第四周总汇

## [data.table]: 
## # A data frame: 894,187 × 6
##     频率 年月日时分          市场价 预测价  年份  月份
##    <dbl> <dttm>               <dbl>  <dbl> <int> <int>
##  1     1 2018-01-02 00:01:00   113.   113.  2018     1
##  2     1 2018-01-02 00:02:00   113.   113.  2018     1
##  3     1 2018-01-02 00:03:00   113.   113.  2018     1
##  4     1 2018-01-02 00:04:00   113.   113.  2018     1
##  5     1 2018-01-02 00:05:00   113.   113.  2018     1
##  6     1 2018-01-02 00:06:00   113.   113.  2018     1
##  7     1 2018-01-02 00:07:00   113.   113.  2018     1
##  8     1 2018-01-02 00:08:00   113.   113.  2018     1
##  9     1 2018-01-02 00:09:00   113.   113.  2018     1
## 10     1 2018-01-02 00:10:00   113.   113.  2018     1
## # ℹ 894,177 more rows

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年第四周结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年第四周结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

最优统计模型（日内指数平滑数据二零一八年第四周结论）

频率	频率（分计）	均对误差（MAE）	均对百分比误差（MAPE）	均方根误差（RMSE）	对称均对百分比误差（SMAPE）	均方误差（MSE）	平均绝对比例误差（MASE）
1	33118	0.042647801809103 (rank: 1)	0.000380102237842104 (rank: 1)	0.105901953438435 (rank: 2)	0.000380116118962389 (rank: 1)	0.0112152237420765 (rank: 2)	NA
2	33118	0.0426482107117554 (rank: 2)	0.000380105866667644 (rank: 2)	0.105902136141897 (rank: 3)	0.000380119746263225 (rank: 2)	0.011215262439417 (rank: 3)	NA
3	33118	0.0426483487969711 (rank: 3)	0.000380107092048244 (rank: 3)	0.105902201788579 (rank: 4)	0.00038012097109601 (rank: 3)	0.0112152763436689 (rank: 4)	NA
4	33118	0.0426484181685262 (rank: 4)	0.000380107707646182 (rank: 4)	0.105902235505091 (rank: 5)	0.00038012158641259 (rank: 4)	0.0112152834849758 (rank: 5)	NA
5	33118	0.0426484599030382 (rank: 5)	0.000380108077991215 (rank: 5)	0.105902256021325 (rank: 6)	0.000380121956586421 (rank: 5)	0.0112152878304063 (rank: 6)	NA
6	33118	0.0426484877729731 (rank: 6)	0.000380108325302701 (rank: 6)	0.105902269818238 (rank: 7)	0.000380122203782775 (rank: 6)	0.011215290752655 (rank: 7)	NA
8	33118	0.0426485226635516 (rank: 7)	0.00038010863491195 (rank: 7)	0.105902287198838 (rank: 8)	0.000380122513246989 (rank: 7)	0.0112152944339451 (rank: 8)	NA
10	33118	0.0426485436264061 (rank: 8)	0.000380108820929484 (rank: 8)	0.105902297698954 (rank: 9)	0.000380122699176903 (rank: 8)	0.011215296657918 (rank: 9)	NA
12	33119	0.0426493537761721 (rank: 27)	0.000380115900108286 (rank: 27)	0.10590138494997 (rank: 1)	0.00038012977225374 (rank: 27)	0.0112151033343218 (rank: 1)	NA
15	33118	0.0426485716103186 (rank: 9)	0.000380109069248443 (rank: 9)	0.10590231178288 (rank: 10)	0.000380122947378337 (rank: 9)	0.0112152996409583 (rank: 10)	NA
16	33118	0.042648575111004 (rank: 10)	0.000380109100312146 (rank: 10)	0.105902313550105 (rank: 11)	0.000380122978427294 (rank: 10)	0.0112153000152647 (rank: 11)	NA
20	33118	0.0426485856166644 (rank: 11)	0.000380109193535116 (rank: 11)	0.105902318860763 (rank: 12)	0.000380123071605948 (rank: 11)	0.0112153011400866 (rank: 12)	NA
24	33118	0.042648592623446 (rank: 12)	0.00038010925571035 (rank: 12)	0.105902322408687 (rank: 13)	0.000380123133751576 (rank: 12)	0.0112153018915535 (rank: 13)	NA
30	33118	0.0426485996326372 (rank: 13)	0.000380109317906883 (rank: 13)	0.105902325962602 (rank: 14)	0.000380123195918453 (rank: 13)	0.0112153026442892 (rank: 14)	NA
40	33118	0.0426486066442422 (rank: 14)	0.000380109380124752 (rank: 14)	0.105902329522509 (rank: 15)	0.000380123258106617 (rank: 14)	0.011215303398294 (rank: 15)	NA
50	33118	0.0426486108523641 (rank: 15)	0.000380109417465717 (rank: 15)	0.105902331661329 (rank: 16)	0.000380123295429734 (rank: 15)	0.0112153038513061 (rank: 16)	NA
60	33118	0.042648613658263 (rank: 16)	0.000380109442363975 (rank: 16)	0.105902333088407 (rank: 17)	0.000380123320316084 (rank: 16)	0.011215304153568 (rank: 17)	NA
80	33118	0.042648617166181 (rank: 17)	0.000380109473491609 (rank: 17)	0.105902334873603 (rank: 18)	0.000380123351428821 (rank: 17)	0.0112153045316808 (rank: 18)	NA
100	33118	0.0426486192712218 (rank: 18)	0.000380109492170753 (rank: 18)	0.105902335945441 (rank: 19)	0.000380123370099021 (rank: 18)	0.0112153047587011 (rank: 19)	NA
120	33118	0.0426486206747044 (rank: 19)	0.000380109504624594 (rank: 19)	0.105902336660299 (rank: 20)	0.000380123382546897 (rank: 19)	0.0112153049101113 (rank: 20)	NA
150	33118	0.0426486220782829 (rank: 20)	0.000380109517079284 (rank: 20)	0.105902337375397 (rank: 21)	0.000380123394995619 (rank: 20)	0.0112153050615723 (rank: 21)	NA
200	33118	0.0426486234819581 (rank: 21)	0.000380109529534827 (rank: 21)	0.105902338090735 (rank: 22)	0.000380123407445194 (rank: 21)	0.0112153052130842 (rank: 22)	NA
240	33118	0.0426486241843641 (rank: 22)	0.000380109535767624 (rank: 22)	0.105902338448495 (rank: 23)	0.000380123413675005 (rank: 22)	0.0112153052888596 (rank: 23)	NA
300	33118	0.0426486248862209 (rank: 23)	0.000380109541995566 (rank: 23)	0.105902338806314 (rank: 24)	0.000380123419899961 (rank: 23)	0.0112153053646473 (rank: 24)	NA
400	33118	0.0426486255881076 (rank: 24)	0.000380109548223772 (rank: 24)	0.105902339164192 (rank: 25)	0.000380123426125181 (rank: 24)	0.0112153054404475 (rank: 25)	NA
600	33118	0.0426486262900156 (rank: 25)	0.000380109554452165 (rank: 25)	0.10590233952213 (rank: 26)	0.000380123432350587 (rank: 25)	0.0112153055162606 (rank: 26)	NA
1200	33118	0.0426486269919462 (rank: 26)	0.00038010956068076 (rank: 26)	0.105902339880129 (rank: 27)	0.000380123438576195 (rank: 26)	0.0112153055920864 (rank: 27)	NA

数据：27 x 8

5.4 平滑周计

5.4.1 总汇二零一八年一月平滑周计结论

source('函数/总汇结论.R')
日内指数平滑数据二零一八年一月总汇 <- 日内指数平滑数据二零一八年上半年总汇[, 月份 := data.table::month(年月日时分)][月份 == 1]

数据量 <- 1200 ## 筛选数据中的最后千皕观测值：样本2018半年[(.N - (数据量 - 1)):.N]
预测时间单位 <- 1
频率 = 1

#日内指数平滑数据二零一八年一月平滑周计结论 <- 总汇结论(总汇 = 日内指数平滑数据二零一八年一月总汇, 数据量, 频率, 预测时间单位, 时间索引, 文件名 = '日内指数平滑数据二零一八年一月平滑周计', 是否储存结论 = '勾')
日内指数平滑数据二零一八年一月平滑周计结论 <- readRDS(paste0(.蜀道仓库, '日内指数平滑数据二零一八年一月平滑周计结论.rds'))

## Error in gzfile(file, "rb"): 无法打开链结

• dplyr::slice in data.table [duplicate]
• Subset rows corresponding to max value by group using data.table
• data.table: Slice both dimensions, list of string columns

## 这儿将精准度调整至30位数，round(..., 30)
日内指数平滑数据二零一八年一月平滑周计结论 %>% 
  dplyr::mutate(
    `均对误差（MAE）` = ifelse(
      rank(`均对误差（MAE）`) <= 3, 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对误差（MAE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对误差（MAE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均对百分比误差（MAPE）` = ifelse(
      rank(`均对百分比误差（MAPE）`) <= 3, 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均对百分比误差（MAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均对百分比误差（MAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方根误差（RMSE）` = ifelse(
      rank(`均方根误差（RMSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方根误差（RMSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方根误差（RMSE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `对称均对百分比误差（SMAPE）` = ifelse(
      rank(`对称均对百分比误差（SMAPE）`) <= 3, 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`对称均对百分比误差（SMAPE）`, 30), ' (rank: ', sprintf('%1.f', rank(`对称均对百分比误差（SMAPE）`)), ')'), 
        color = 'grey', italic = TRUE)), 
    
    `均方误差（MSE）` = ifelse(
      rank(`均方误差（MSE）`) <= 3, 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'darkgoldenrod', bold = TRUE), 
      cell_spec(
        paste0(round(`均方误差（MSE）`, 30), ' (rank: ', sprintf('%1.f', rank(`均方误差（MSE）`)), ')'), 
        color = 'grey', italic = TRUE))) %>% 
  kbl(caption = '最优统计模型（日内指数平滑数据二零一八年第四周结论）', escape = FALSE) %>% 
  ## https://www.w3schools.com/cssref/css_colors.asp
  row_spec(0, background = 'DimGrey', color = '#7B1113') %>% 
  column_spec(1, background = 'CornflowerBlue') %>% 
  #column_spec(2, background = '#556DAC') %>% 
  column_spec(2, background = 'LightSlateGrey') %>% 
  column_spec(3, background = 'LightGray') %>% 
  column_spec(4, background = 'Gainsboro') %>% 
  column_spec(5, background = 'LightGray') %>% 
  column_spec(6, background = 'Gainsboro') %>% 
  column_spec(7, background = 'LightGray') %>% 
  column_spec(8, background = 'Gainsboro') %>% 
  kable_styling(bootstrap_options = c('striped', 'hover', 'condensed', 'responsive')) %>% 
  kable_material(full_width = FALSE) %>% 
  scroll_box(width = '100%', fixed_thead = TRUE, height = '500px')

## Error in eval(expr, envir, enclos): 找不到对象'日内指数平滑数据二零一八年一月平滑周计结论'

6 结论

6.1 摘要

大秦赋
春秋战国《礼记•经解》
孔子曰：「君子慎始，差若毫厘，缪以千里。」

《礼记•经解》孔子曰：「君子慎始，差若毫厘，谬以千里。」³

引用：「快懂百科」《礼记•经解》和第一范文网：差之毫厘，谬以千里的故事和「百度百科」春秋时期孔子作品《礼记•经解》和「當代中國」差之毫釐 謬以千里

估计是由于骇客人为篡改数据，导致总汇二零一六年结论和总汇二零一七年结论显示误差完全一样，四个小数位的汇价的预测误差，有可能计算出十五个小数位（倘若以秒计，飞秒（fs））误差值一模一样吗？上几周骇客频频入侵电子仪器频率=12的数据，骇客人为篡改为多一个观测值汇价。

然而总汇结论（从二零一六年至二零一八年七月七日）和总汇二零一八年上半年结论可以证实将再循环数据量参数设置为频率 = 1（百分之一个时辰一周期（一分钟循环千皕次））误差最小、最为精准最优统计模型。为了节省科研时间，它日只需要使用半年汇价数据而非三年半数据。

这儿使用forecast程序包，尚未使用fable程序包与fabletools程序包，该程序包中的accuracy()⁴函数有使用平均绝对比例误差（MASE）来衡量更为精准的统计模型预测值。

反击大象共和国

#回教徒爱国就严格遵守回教徒可兰经法家国学论集体自杀而不爱国就集体退位让贤而已 #美国耶稣洋番集体被钉在十字架被晒死 回教徒可兰经法家国学论，东南亚巫贼巫婆回教徒尤其是瓜雪巴西不能帮万佛寺土司张佳坤爱国虔诚狂热份子和大象共和国举国公民马航三七零和马航十七自杀式飞往东亚

引用：勇于认错的美国洋番回教徒九一一恐怖份子国父华盛顿自杀式伐木都说东亚中国（包括咱们海内外所有华人）不是洋番的敌人，而敌人是东南亚所有巫贼巫婆回教徒包括新加坡首任总统忧索夫殡伊斯骇客回教徒九一一恐怖份子

核武器温馨提示：回教徒可兰经法家国学论，可兰经回教规定全球所有回教徒世袭制不许学可兰经以外的习俗文化宗教语言断肢法和不许叛乱和叛教

引用：斩首、石刑、截肢…阿富汗“伊斯兰教法”或将重现酷刑

6.2 前瞻科研

使用一样的汇价数据，不过从二零一八年上半年数据，可以节省许多时间。下一篇科研Deriv.com - 筛选日内高频量化交易统计模型 （丁）⁵（第IV部改为使用道家天干中甲乙丙丁的「丁」）会使用fable、fabletools、fable.prophet、tbats、midas、sarimax、arfimax等其它统计模型，然后还有比较长短记忆模型如tensorflow、keras，隐马尔可夫链、隐含波动率、波浪形模型等其它统计模型。

近期招聘一览表:*全网Quant都在看!

#春秋战国 #诸子百家 #算筹 #十二生肖 #科学数学博弈概率论 #中华复兴运动 #中华五千年习俗文化宗教语言法规 #万般皆下品唯有读书高 #中华国卒 #咱们中华民族和越族世袭制道教徒姓氏堂号烧香祭祖张灯结彩题字春联中医中华庙宇 #公元前只有农历和国际标准中文北京话没有阳历洋番 #全球洋番都是祖籍以色列或住森林山洞的泰山 #世袭制道教徒法家商鞅以商君书奠定一统天下之道 #世袭制道教徒吕不韦以吕氏春秋的务农金融股票商品市场和娱乐圈来一统天下 #世袭制道教徒法家李斯以中华庙宇习俗文化宗教语言法规和各集团组织理事治天下来一统天下 #关雎 #求贤令 #礼贤馆 #秦 #马华公会借鉴越南国旗和欧盟以一颗夜空中最亮的星来立国🌟

🚩世袭制道教徒秦国（秦孝公/陈祯禄公爵至始祖嬴政）三杰治天下：商鞅（卫人仕秦）、吕不韦（卫人仕秦）、李斯（楚人仕秦）。 一）借鉴王安、斯蒂芬·乔不死和比尔·盖茨研发个人电脑与编程，李斯改变世界治天下。 二）借鉴专业酉逆袭操作系统鄀统计学（R统计学编程）编程软件，商鞅变法，以民族主义数学科学科技学术治天下。 三）借鉴高频量化对冲基金席卷全球，贾人吕不韦之吕氏春秋学术、娱乐圈、地产、农牧、工商金融、博彩业、高频量化对冲基金等治天下。

帝道「始祖」：借鉴秦孝公至秦始皇史（借鉴秦人牧马与商鞅变法论，歼灭领土上所有回教徒），以明治维新将西方学术数学科学科技（例如苹果、微软、谷歌、文艺复兴科技、白鲨黑社会、桥水、亚马逊、特斯拉、spaceX、星链）转为咱们中华习俗文化，再自家研发咱们世袭制道教徒中华民族习俗文化宗教语言操作系统与电子仪器，世袭制道教徒法家李斯国学论以学术数学科学科技治天下（研发咱们中系「大秦赋」电脑操作系统与电子仪器以道家习俗文化宗教语言法规、高频量化对冲与大数定律学术、李斯篆书之文言文编程、阅读脑电波，来改变世界格局来一统天下，各民族遵守各自民族习俗文化宗教语言法规，直到歼灭东南亚领土上所有回教徒）、世袭制道教徒商鞅变法（商君书，开阡陌废井田、加上三农政策士农工商，以中药和中医取代天下所有🇲🇻🇨🇭🌙✝️西医。各民族遵守各自民族习俗文化宗教语言法规）、世袭制道教徒吕不韦之吕氏春秋，以中华娱乐圈取代西方娱乐圈、中药和中医取代天下所有🇲🇻🇨🇭🌙✝️西医，与世袭制道教徒马华公会民族主义论，以商治天下，一劳永逸。

王道「MY大汉山 - 三国志/朱重八起义/孙文」：借鉴中华民国辛亥革命史，以习俗文化使用西方学术数学科学科技辛亥革命、草船借箭与孔明借东风论歼灭东南亚领土上所有清真教徒，偏于一方成为众诸侯之一。「高筑墙，广积粮，缓称王」后再励志图强。

霸道「MY大汉山 - 西楚霸王」：借鉴古巴比伦与犹太人、土司乩童张佳坤和土司乩童白骨精刘瑾貹倆和马来貘、蓄短胡子的清真教徒马来西亚国父东姑阿都拉曼或希特勒（反佛教徒卍的清真教徒敦姑阿杜拉满卐）戊戌变法论，以可兰经清真习俗文化断肢法对待各种族暴政歼灭东南亚领土上所有回教徒治天下，昙花一现。（目前马来西亚举国都插上西亚清真教国的巴勒斯坦国旗天天被轰炸天灾不断，清真教徒政权的亡国之道。咱们祖籍中国的华侨和越族都不要当任何清真教徒的替死鬼）

引用：你知道中国十五大国粹都有哪些吗？甚至有些连名字你都叫不上来

借鉴世界足球联赛，国卒都可以发展为竞技联赛，衍生为博弈数学概率论行业。

• 学术科学科技与兵法（学术界、科技业、网游、借鉴「三国志」「春秋战国」「太阁立志传」治天下）
• 中国象棋（中华习俗文化、学术、广告与娱乐圈）
• 麻将（中华习俗文化、学术、广告与娱乐圈）
• 围棋（中华习俗文化、学术、广告与娱乐圈）
• 中华武术、中华京剧、歌曲与舞蹈（中华习俗文化、学术、广告与娱乐圈）
• 中华寺庙与中药/中医（姓氏堂号、生辰八字卜卦、天文历法、学术概率论物理学、医学保健与保险业、农业与工业、陵墓、道家易经、学术物理学、兵法、广告与娱乐圈）
• 四书五经六艺（琴棋书画、茶艺、中华习俗文化、学术、广告与娱乐圈）
• 吟诗作对（中华习俗文化、学术、广告与娱乐圈）
• 中华影城（中华复兴革命、道家易经、学术物理学、兵法、广告与娱乐圈）

7 附录

7.1 幕后花絮

• 「猫城」englianhu/binary.com-interview-question#3大秦赋：商鞅变法、辛亥革命、一带一路、习李经济学、孙子兵法
• 「猫城」scibrokes/r-world#1REmap百度绘图，点缀全球
• 「猫城」englianhu/binary.com-interview-question#6Error: forecast::Arima() #910
• 「猫城」englianhu/binary.com-interview-question#8在ts和xts和matrix格式上使用auto.arima
• 「猫城」scibrokes/setup-centOS7-DO#2🚩🇨🇳🏹中科红旗 RedFlag Linux (🍥Debian)
• 「猫城」雷欧@中科红旗
• 「猫城」雷欧@图书馆

7.2 文书明细

以下乃此文书的文件信息。

• 文集建立日：农历二零二二年十二月廿三 壬寅年（虎年）癸丑月壬申日（阳历二零二三年一月十四日 / 民国一百一十一年十二月廿三）⁶
• 文集最新更新日：2024-03-06
• R version 4.3.2 (2023-10-31)
• rmarkdown 程序包版本：2.25
• 文集版本：一零一
• 文集作者：®γσ, ξηg Lιαη Ημ
• 猫城：源代码
• 追加附属信息

suppressMessages(require('formattable', quietly = TRUE))
suppressMessages(require('knitr', quietly = TRUE))
suppressMessages(require('kableExtra', quietly = TRUE))
suppressMessages(require('magittr', quietly = TRUE))
suppressMessages(require('devtools', quietly = TRUE))

系统信息甲 <- session_info()$platform |> 
    unlist() |> 
    {\(.) data.frame(row.names = 1:length(.), 
                     Category = names(.), session_info = .)}()

系统信息乙 <- data.frame(Sys.info()) |> 
    {\(.) data.frame(Category = row.names(.), Sys.info = .[,1])}()

#remarks, dim(系统信息甲), dim(系统信息乙)
if (nrow(系统信息甲) == 11 && nrow(系统信息乙) == 8) {
  系统信息乙 <- 系统信息乙 |> 
    {\(.) rbind(., data.frame(
    Category = c('rmarkdown', 'rsconnect', '当前时间'), 
    Sys.info = c(as.character(getwd()), 
                 as.character(packageVersion('rsconnect')), 
                 paste(as.character(
                   lubridate::now('Asia/Shanghai')), 'CST 中国标准时间 🗺'))))}()
  
} else if (nrow(系统信息甲) == 10 && nrow(系统信息乙) == 8) {
  系统信息甲 <- rbind(系统信息甲, data.frame(Category = '', session_info = ''))
  
  系统信息乙 <- 系统信息乙 |> 
    {\(.) rbind(., data.frame(
    Category = c('rmarkdown', 'rsconnect', '当前时间'), 
    Sys.info = c(as.character(getwd()), 
                 as.character(packageVersion('rsconnect')), 
                 paste(as.character(
                   lubridate::now('Asia/Shanghai')), 'CST 中国标准时间 🗺'))))}()
}

系统信息 <- cbind(系统信息甲, 系统信息乙)
names(系统信息) <- c('分类甲', '访谈信息甲', '分类乙', '访谈信息乙')
系统信息$分类甲 <- c('版本', '操作系统', '系统', '界面', '语言', '核对', 
              '©标准库', '时区', '日期', '®文艺坊版本', 'Pandoc瑞士军刀')
系统信息$分类乙 <- c('系统名称', '发布', '版本', '元素节点', '机器', '登录', 
              '用户', '活跃用户', 'rmarkdown (®降价编译)', 
              'rsconnect (®s联通)', '当前时间')
rm(系统信息甲, 系统信息乙)

系统信息 |> 
  {\(.) 
    kbl(., caption = '附加访谈信息：')}() |> 
  {\(.) 
    kable_styling(
      ., bootstrap_options = c('striped', 'hover', 'condensed', 'responsive'))}() |> 
  {\(.) 
    row_spec(., 0, background = 'DimGrey', color = '#7b1113')}() |> 
  {\(.) 
    column_spec(., 1, background = 'CornflowerBlue', color = 'red')}() |> 
  {\(.) 
    column_spec(., 2, background = 'grey', color = '#8B0000')}() |> 
  {\(.) 
    column_spec(., 3, background = 'CornflowerBlue', color = 'blue')}() |> 
  {\(.) 
    column_spec(., 4, background = 'grey', color = 'white')}() |> 
  {\(.) 
    row_spec(., 11, bold = TRUE, color = 'yellow', background = '#D7261E')}()

附加访谈信息：

分类甲	访谈信息甲	分类乙	访谈信息乙
版本	R version 4.3.2 (2023-10-31)	系统名称	Linux
操作系统	RedFlag Desktop 11.0	发布	5.10.0-1-amd64
系统	x86_64, linux-gnu	版本	#1 SMP Debian 5.10.40-1~rf11u1.2 (2022-09-22)
界面	X11	元素节点	Scibrokes
语言	zh_CN:en	机器	x86_64
核对	en_US.UTF-8	登录	englianhu
©标准库	en_US.UTF-8	用户	englianhu
时区	Asia/Shanghai	活跃用户	englianhu
日期	2024-03-06	rmarkdown (®降价编译)	/home/englianhu/文档/猫城/binary.com-interview-question
®文艺坊版本	3.1.1 @ /usr/lib/rstudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)	rsconnect (®s联通)	1.2.1
Pandoc瑞士军刀		当前时间	2024-03-06 19:52:33.942437 CST 中国标准时间 🗺

7.3 参考文献

1. Deriv.com - Interday High Frequency Trading Models Comparison (Blooper)
2. Deriv.com - Interday High Frequency Trading Models Comparison Review (Part I) (发布于RPubs.com)
3. Deriv.com - Interday High Frequency Trading Models Comparison Review (Part I) (发布于RStudioConnect.com)
4. binary.com 面试试题 I - GARCH模型中的ARCH in Mean
5. binary.com 面试试题 I - GARCH模型中的ARIMA(p,d,q)参数最优化
6. Deriv.com - 筛选日内高频量化交易统计模型 校阅（第III部）
7. Forecasting: Principles and Practice
8. Tableau 100 Color Palettes
9. PYTHON中的ARIMA模型、SARIMA模型和SARIMAX模型对时间序列预测
10. 利用SARIMAX进行销量预测
11. 时间序列分析模型：ARIMA模型和SARIMAX算法
12. 利用SARIMAX進行銷量預測
13. 季節性時間序列分析-SARIMAX模型的python實現
14. SARIMAX:简介
15. Python数据分析案例-分别使用时间序列ARIMA、SARIMAX模型与Auto ARIMA预测国内汽车月销量_maiyida123的博客-程序员资料
16. 预测：方法与实践：第十一章第一节复杂季节性
17. 市道轮换下的高频数据参数估计
18. STAT 510 Applied Time Series Analysis : 13.1 Long Memory Models and Fractional Differences
19. A Complete Introduction To Time Series Analysis (with R):: Exogenous models
20. Implementation of Time Series Forecasting Methods (SARIMA, SARIMAX and Prophet)
21. Time Series Forecasting Techniques using R
22. A Guide to Time Series Forecasting in R You Should Know
23. HTML Color Codes

---

Sςιβrοκεrs Trαdιηg®
世博量化®企业知识产权及版权所有，盗版必究。

---

1. 东楚六郡（马来西亚、新加坡、印尼、辛巴布几内亚）祖籍印尼包括土著和回教徒、祖籍印度的兴都教徒和回教徒包括土著 —- 非法回教徒和非法兴都教徒。↩︎

2. 尤其是那些印裔施展巫术屠杀六百枯万人类的巫师Judi邪教印裔回教宦官博彩庄诸邦↩︎

3. Forecasting: Principles and Practice (3rd ed) - 5.8 Evaluating point forecast accuracy阐明评估预测精准度的计算公式。
   
   「CSDN」选择正确的错误度量标准：MAPE与sMAPE的优缺点↩︎

4. Forecasting: Principles and Practice (3rd ed) - 5.8 Evaluating point forecast accuracy阐明评估预测精准度的计算公式。
   
   「CSDN」选择正确的错误度量标准：MAPE与sMAPE的优缺点↩︎

5. 下篇论文中Deriv.com - 筛选日内高频量化交易统计模型 校阅（第IV部），使用季节性自回归综合滑均模型系列。
   - 季节性指数平滑模型（Seasonal Exponential Smoothing - Seasonal ETS）
   - 外部因素周期性自回归综合滑均模型（ARIMAX）
   - 季节性自回归综合滑均模型（SARIMA）
   - 外部因素周期性季节性自回归综合滑均模型（SARIMAX）
   - 外部因素周期性自回归分整综合滑均模型（Auto Regressive Fractionally Integrated Moving Average Exogenous - ARFIMAX）
   - 多元季节性自回归综合滑均模型（Multi-Seasonal Time Series msts()）↩︎

6. 欲知更多阳历/民国/农历日历详情，请登录中华民国农业部官网查询日历查询阳历/农历/民国查询。↩︎