earino

> library(MASS)                  # load the MASS package 
> height.response = na.omit(survey$Height)
> n = length(height.response) 
> s = sd(height.response)        # sample standard deviation 
> SE = s/sqrt(n); SE             # standard error estimate 
[1] 0.6811677
> 
> print(paste("Standard Error:", SE))
[1] "Standard Error: 0.68116773214787"
> 

earino

> system.time({ caret.model <- train(carat ~ depth + table + price + x + y + z, data=diamonds, distribution="gaussian", method="gbm", trControl = trainControl(method="none", number=1), tuneLength=1, verbose=FALSE)})
   user  system elapsed 
  1.108   0.060   1.188 
> system.time({ model <- gbm(carat ~ depth + table + price + x + y + z, data=diamonds, distribution="gaussian")})
   user  system elapsed 
  0.818   0.026   0.856 

earino

> install.packages("dplyr")
also installing the dependency ‘DBI’

trying URL 'https://cran.rstudio.com/bin/macosx/mavericks/contrib/3.3/DBI_0.5-1.tgz'
Content type 'application/x-gzip' length 353669 bytes (345 KB)
==================================================
downloaded 345 KB

trying URL 'https://cran.rstudio.com/bin/macosx/mavericks/contrib/3.3/dplyr_0.5.0.tgz'
Content type 'application/x-gzip' length 4841443 bytes (4.6 MB)

earino

> class(hash_table)
[1] "hash"
attr(,"package")
[1] "hash"
> str(hash_table)
Formal class 'hash' [package "hash"] with 1 slot
  ..@ .xData:<environment: 0x24f72ec8> 
> object_size(hash_table)
type: 17
Error: Unimplemented type

earino

if (! "old_library" %in% ls()) {
  old_library <- library
}

logging_library <- function(...) {
  cat(as.character(substitute(...)), 
      sep="\n",
      file="library_log.txt", 
      append=TRUE)
  

earino

MERGE INTO Inventory AS I
USING Changes AS C
ON I.Part = C.Part
WHEN MATCHED AND
 I.Action = 'Mod'
 THEN UPDATE
 SET Qty = I.Qty + C.Qty
WHEN NOT MATCHED AND
 I.Action = 'New'
 THEN INSERT (Part, Qty)

earino

library(ggplot2)
library(gridExtra)

cs_100.1x <- data.frame(state=c("Enrolled", 
                                "Active", 
                                "Completed a Quiz", 
                                "Installed the VM",
                                "Completed Lab 1",
                                "Completed Lab 2",
                                "Completed Lab 3",

earino

library(dplyr)
library(magrittr)
library(ggmap)
library(readr)
library(animation)
library(lubridate)

parking <- read_csv("csvs/parking.csv")

parking %<>% mutate(wday=wday(Date.Time), 

earino

p <- ggplot(data.frame(x=c(2,4,8,16), y=c(1, 1.84, 3.7, 7.22)), aes(x=x, y=y)) + 
  ggtitle("Scaling of Spark Decision Trees") +
  xlab("Machines") + 
  ylab("Speedup") + 
  
  geom_line(aes(color="actual")) + 
  geom_point() + 
  geom_text(aes(label=y), vjust=.5, hjust=-.15) +
  
  geom_line(aes(y=2*y, color="implied")) + 

earino

library(randomForest)

Set.seed(12345)

genr_data <- function(n,p) { 
  X <- matrix(rnorm(n*p),n,p)
  y <- as.factor(apply(X,1, function(x) 
    ifelse(sum(x^2)>qchisq(0.5,p),"+","-")))
  ## Hastie etal 10.2