mkim0710

solve <- function(n) {
  result <- largeSubtract(largeAdd(sumMultiple(n, 3), sumMultiple(n, 5)), sumMultiple(n, 15))
}

right <- function (string, char){
  substr(string,nchar(string)-(char-1),nchar(string))
}

left <- function (string,char){
  substr(string,1,char)

mkim0710

url_Data <- readLines("https://raw.githubusercontent.com/issactoast/Machine-Learning-with-R/master/Data/house.txt") %>% paste(collapse = "\n")
houseData <- read.table(text = url_Data, header = FALSE, sep = ":")
houseData
for (i in 1:dim(houseData)[2]){
houseData[,i] <- gsub(paste("",i), "", houseData[,i])
}
houseData <- houseData %>% unlist() %>% as.numeric() %>% matrix(ncol = 14)
colnames(houseData) <- c("MEDV", "CRIM", "ZN", "INDUS",
                        "CHAS", "NOX", "RM", "AGE",
                        "DIS", "RAD", "TAX", "PTRATIO",

mkim0710

_contracts = {}


class Contract:
    @classmethod
    def __init_subclass__(cls):
        _contracts[cls.__name__] = cls

    def __set__(self, instance, value):
        self.check(value)

mkim0710

# see blog post here:
# http://gettinggeneticsdone.blogspot.com/2015/01/microbenchmark-package-r-compare-runtime-r-expressions.html

library(dplyr)
library(nycflights13)
flights

# base
aggregate(flights$arr_delay, by=list(flights$carrier), mean, na.rm=TRUE)

mkim0710

function.list_TABLE_NAME.sqlFetch_sqlColumns = function(channel) {
    # source("https://gist.githubusercontent.com/mkim0710/09f4626f80edd8c837b8834ef1685f31/raw/e825646ba318ce55d491ea7a61696c1ec8a2dd1f/library(RODBC)%2520Big%2520Data%2520Management%25202018%2520HW1%2520Grading.r")
    library(RODBC)
    library(tidyverse)
    out = filter(sqlTables(channel), TABLE_TYPE == "TABLE")$TABLE_NAME %>% map(function(x) {
        tmp.list = list()
        tmp.list$sqlFetch = sqlQuery(channel, paste0("SELECT * FROM ", x))
        tmp.list$sqlColumns = sqlColumns(channel, x)
        tmp.list
    })

mkim0710

library(tidyverse)
library(readxl)
Big_Data_Management_Student_List_2018 = read_excel("D:/tmp.files/[[Big Data Management]] Student List 2018.xlsx")[1:44, c("First Name", "Last Name", "CWID")]
vec.new.file.name = Big_Data_Management_Student_List_2018 %>% transmute(new.file.name = paste0(`Last Name`, ", ", `First Name`, " (", CWID, ")")) %>% unlist %>% unname
current.folder = "D:/[[Big Data Management]] 2018/HW1"
original.file.name = "HW1 Gradesheet 2018.xlsx"
new.folder = "D:/[[Big Data Management]] 2018/HW1 Gradesheet 2018"
for (i in 1:length(vec.new.file.name)){
    file.copy(
        overwrite = T

mkim0710

How to Ask for Help using R
========================================================

The key to getting good help with an R problem is to provide a minimally working 
reproducible example (MWRE). Making an MWRE is really easy with R, and it will 
help ensure that those helping you can identify the source of the error, and 
ideally submit to you back the corrected code to fix the error instead of sending
you hunting for code that works. To have an MWRE you need the following items:

- a minimal dataset that produces the error

mkim0710

#@ function.11matching.by.factors() -----
function.11matching.by.factors = function(data, varname4MatchingUpon = "diabetes", varnames4MatchingBy = c("age", "sex"), seed = 1) {
    library(tidyverse)
    if ("RowNum_original" %in% names(data)) {
        warning('"RowNum_original" %in% names(data)')
    } else {
        data$RowNum_original = 1:nrow(data)
    }
    set.seed(seed)
    data$runif = runif(nrow(data))

mkim0710

--#@@ [Research] HCCI MDD annual prevalence 180501.pptm -p128.sql ----
select count(z_patid), count(distinct z_patid)
from hcci.MEMBER_SDDV2_1115
where (
	z_patid in (
		select z_patid
		from hcci.MEMBER_SDDV2_1115
		where (
			gdr in ('1', '2')

mkim0710

ID_207_Group_Project_Version_2_Vertical_July_24_2018_07_34 %>% mutate(
    Q3138rowMeans = rowMeans(.[, c("Q31", "Q32", "Q33", "Q34", "Q35", "Q36", "Q37", "Q38")], na.rm = T)
    , Q3138rowSums = rowSums(.[, c("Q31", "Q32", "Q33", "Q34", "Q35", "Q36", "Q37", "Q38")], na.rm = T)
    , Q4044rowMeans = rowMeans(.[, c("Q40", "Q41", "Q42", "Q43", "Q44")], na.rm = T)
    , Q4044rowSums = rowSums(.[, c("Q40", "Q41", "Q42", "Q43", "Q44")], na.rm = T)
) %>% select(Q31, Q32, Q33, Q34, Q35, Q36, Q37, Q38, matches("Q3138"), Q40, Q41, Q42, Q43, Q44, matches("Q4044")) %>% 
# > ID_207_Group_Project_Version_2_Vertical_July_24_2018_07_34 %>% mutate(
# +     Q3138rowMeans = rowMeans(.[, c("Q31", "Q32", "Q33", "Q34", "Q35", "Q36", "Q37", "Q38")], na.rm = T)
# +     , Q3138rowSums = rowSums(.[, c("Q31", "Q32", "Q33", "Q34", "Q35", "Q36", "Q37", "Q38")], na.rm = T)