cddesja

[internal] Wed Dec 21 08:22:34 2022:
(:message "Running language server: (/Library/Frameworks/Python.framework/Versions/3.10/bin/pyright-langserver --stdio)")
[client-request] (id:1) Wed Dec 21 08:22:34 2022:
(:jsonrpc "2.0" :id 1 :method "initialize" :params
	  (:processId 11322 :rootPath "/Users/cdesjardins/Dropbox/chris/programming/python/python_data_science_handbook/" :rootUri "file:///Users/cdesjardins/Dropbox/chris/programming/python/python_data_science_handbook" :initializationOptions #s(hash-table size 1 test eql rehash-size 1.5 rehash-threshold 0.8125 data
																																  ())
		      :capabilities
		      (:workspace
		       (:applyEdit t :executeCommand
				   (:dynamicRegistration :json-false)

cddesja

#' @param xbar sample mean
#' @param s sample standard deviation
#' @param n sample size
#' @param mu0 null hypothesis value
#' @param ha alternative hypothesis. takes on the value of "less than", "greater than", "not equal to"
#' @example 
#' single.mean.test(xbar = 1.91, s = 1.22, n = 305, mu0 = 2.47, ha = "not equal to")
single.mean.test <- function(xbar, s, n, mu0, ha = "not equal to"){
  t.stat <- (xbar - mu0) / (s / sqrt(n))
  cat("The t-statistic is equal to:", t.stat, "\n")

cddesja

# modified version of StatBin2 inherits from StatBin, except for an
# additional 2nd last line in compute_group() function
StatBin2 <- ggproto(
  "StatBin2", 
  StatBin,
  compute_group = function (data, scales, binwidth = NULL, bins = NULL, 
                            center = NULL, boundary = NULL, 
                            closed = c("right", "left"), pad = FALSE, 
                            breaks = NULL, origin = NULL, right = NULL, 
                            drop = NULL, width = NULL) {

cddesja

vadj <- .03
hadj <- .015
grid.newpage()
vp <- viewport(width=0.85,height=0.85)
pushViewport(vp)
grid.lines(x = c(0, 1),
           y = c(0, 0),
           gp = gpar(fill = "black"),
           arrow = arrow(angle = 20, type = "closed"))
## participants

cddesja

covid <- read.csv("https://data.cdc.gov/api/views/y5bj-9g5w/rows.csv?accessType=DOWNLOAD&bom=true&format=true%20target=")
names(covid)[1] <- "Jurisdiction"

library(dplyr)
library(ggplot2)

ct <- covid %>%
  group_by(Week, Year) %>% 
  filter(Type == "Unweighted", Jurisdiction != "United States") %>%
  summarize(totl = sum(Number.of.Deaths))

cddesja

---
title: "RR Laura Le"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

<iframe id="inlineFrameExample"

cddesja

mtcars$vs.f <- ifelse(mtcars$vs == 0, "0", "1")
mtcars.0 <- subset(mtcars, vs.f == "0")
mtcars.1 <- subset(mtcars, vs.f == "1")
coef(lm(mpg ~ cyl * vs.f, data = mtcars)) # association between 1 should be strong
coef(lm(mpg ~ cyl, data = mtcars.0)) # association between 0 smaller
coef(lm(mpg ~ cyl, data = mtcars.1)) # association between 1 larger
cor(mtcars.0$mpg, mtcars.0$cyl)
cor(mtcars.1$mpg, mtcars.1$cyl)

cddesja

cddesja

# untidyverse
# this one is sooooooo hard to type
an.agg <- aggregate(bmi ~ an_j + months,
                    FUN = function(x) c(m = mean(x), n = n(x)),
                    data = an.l)

# tidyverse
# this one makes my fingers sing
bmi %>%
  group_by(an_j) %>%

cddesja

cleanNAs <- function(x){
    if(sum(is.na(x)) == length(x)) {
        x <- NA
    } else
        x <- x[!is.na(x)]
    x
}

dat <- read.csv("testing.csv", header = TRUE)
dat$clean <- apply(dat, 1, cleanNAs)